1
linux/fs/bcachefs/btree_key_cache.c

814 lines
22 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
#include "bcachefs.h"
#include "btree_cache.h"
#include "btree_iter.h"
#include "btree_key_cache.h"
#include "btree_locking.h"
#include "btree_update.h"
#include "errcode.h"
#include "error.h"
#include "journal.h"
#include "journal_reclaim.h"
#include "trace.h"
#include <linux/sched/mm.h>
static inline bool btree_uses_pcpu_readers(enum btree_id id)
{
return id == BTREE_ID_subvolumes;
}
static struct kmem_cache *bch2_key_cache;
static int bch2_btree_key_cache_cmp_fn(struct rhashtable_compare_arg *arg,
const void *obj)
{
const struct bkey_cached *ck = obj;
const struct bkey_cached_key *key = arg->key;
return ck->key.btree_id != key->btree_id ||
!bpos_eq(ck->key.pos, key->pos);
}
static const struct rhashtable_params bch2_btree_key_cache_params = {
.head_offset = offsetof(struct bkey_cached, hash),
.key_offset = offsetof(struct bkey_cached, key),
.key_len = sizeof(struct bkey_cached_key),
.obj_cmpfn = bch2_btree_key_cache_cmp_fn,
.automatic_shrinking = true,
};
static inline void btree_path_cached_set(struct btree_trans *trans, struct btree_path *path,
struct bkey_cached *ck,
enum btree_node_locked_type lock_held)
{
path->l[0].lock_seq = six_lock_seq(&ck->c.lock);
path->l[0].b = (void *) ck;
mark_btree_node_locked(trans, path, 0, lock_held);
}
__flatten
inline struct bkey_cached *
bch2_btree_key_cache_find(struct bch_fs *c, enum btree_id btree_id, struct bpos pos)
{
struct bkey_cached_key key = {
.btree_id = btree_id,
.pos = pos,
};
return rhashtable_lookup_fast(&c->btree_key_cache.table, &key,
bch2_btree_key_cache_params);
}
static bool bkey_cached_lock_for_evict(struct bkey_cached *ck)
{
if (!six_trylock_intent(&ck->c.lock))
return false;
if (test_bit(BKEY_CACHED_DIRTY, &ck->flags)) {
six_unlock_intent(&ck->c.lock);
return false;
}
if (!six_trylock_write(&ck->c.lock)) {
six_unlock_intent(&ck->c.lock);
return false;
}
return true;
}
static bool bkey_cached_evict(struct btree_key_cache *c,
struct bkey_cached *ck)
{
bool ret = !rhashtable_remove_fast(&c->table, &ck->hash,
bch2_btree_key_cache_params);
if (ret) {
memset(&ck->key, ~0, sizeof(ck->key));
atomic_long_dec(&c->nr_keys);
}
return ret;
}
static void __bkey_cached_free(struct rcu_pending *pending, struct rcu_head *rcu)
{
struct bch_fs *c = container_of(pending->srcu, struct bch_fs, btree_trans_barrier);
struct bkey_cached *ck = container_of(rcu, struct bkey_cached, rcu);
this_cpu_dec(*c->btree_key_cache.nr_pending);
kmem_cache_free(bch2_key_cache, ck);
}
static void bkey_cached_free(struct btree_key_cache *bc,
struct bkey_cached *ck)
{
kfree(ck->k);
ck->k = NULL;
ck->u64s = 0;
six_unlock_write(&ck->c.lock);
six_unlock_intent(&ck->c.lock);
bool pcpu_readers = ck->c.lock.readers != NULL;
rcu_pending_enqueue(&bc->pending[pcpu_readers], &ck->rcu);
this_cpu_inc(*bc->nr_pending);
}
static struct bkey_cached *__bkey_cached_alloc(unsigned key_u64s, gfp_t gfp)
{
gfp |= __GFP_ACCOUNT|__GFP_RECLAIMABLE;
struct bkey_cached *ck = kmem_cache_zalloc(bch2_key_cache, gfp);
if (unlikely(!ck))
return NULL;
ck->k = kmalloc(key_u64s * sizeof(u64), gfp);
if (unlikely(!ck->k)) {
kmem_cache_free(bch2_key_cache, ck);
return NULL;
}
ck->u64s = key_u64s;
return ck;
}
static struct bkey_cached *
bkey_cached_alloc(struct btree_trans *trans, struct btree_path *path, unsigned key_u64s)
{
struct bch_fs *c = trans->c;
struct btree_key_cache *bc = &c->btree_key_cache;
bool pcpu_readers = btree_uses_pcpu_readers(path->btree_id);
int ret;
struct bkey_cached *ck = container_of_or_null(
rcu_pending_dequeue(&bc->pending[pcpu_readers]),
struct bkey_cached, rcu);
if (ck)
goto lock;
ck = allocate_dropping_locks(trans, ret,
__bkey_cached_alloc(key_u64s, _gfp));
if (ret) {
if (ck)
kfree(ck->k);
kmem_cache_free(bch2_key_cache, ck);
return ERR_PTR(ret);
}
if (ck) {
bch2_btree_lock_init(&ck->c, pcpu_readers ? SIX_LOCK_INIT_PCPU : 0);
ck->c.cached = true;
goto lock;
}
ck = container_of_or_null(rcu_pending_dequeue_from_all(&bc->pending[pcpu_readers]),
struct bkey_cached, rcu);
if (ck)
goto lock;
lock:
six_lock_intent(&ck->c.lock, NULL, NULL);
six_lock_write(&ck->c.lock, NULL, NULL);
return ck;
}
static struct bkey_cached *
bkey_cached_reuse(struct btree_key_cache *c)
{
struct bucket_table *tbl;
struct rhash_head *pos;
struct bkey_cached *ck;
unsigned i;
rcu_read_lock();
tbl = rht_dereference_rcu(c->table.tbl, &c->table);
for (i = 0; i < tbl->size; i++)
rht_for_each_entry_rcu(ck, pos, tbl, i, hash) {
if (!test_bit(BKEY_CACHED_DIRTY, &ck->flags) &&
bkey_cached_lock_for_evict(ck)) {
if (bkey_cached_evict(c, ck))
goto out;
six_unlock_write(&ck->c.lock);
six_unlock_intent(&ck->c.lock);
}
}
ck = NULL;
out:
rcu_read_unlock();
return ck;
}
static int btree_key_cache_create(struct btree_trans *trans, struct btree_path *path,
struct bkey_s_c k)
{
struct bch_fs *c = trans->c;
struct btree_key_cache *bc = &c->btree_key_cache;
/*
* bch2_varint_decode can read past the end of the buffer by at
* most 7 bytes (it won't be used):
*/
unsigned key_u64s = k.k->u64s + 1;
/*
* Allocate some extra space so that the transaction commit path is less
* likely to have to reallocate, since that requires a transaction
* restart:
*/
key_u64s = min(256U, (key_u64s * 3) / 2);
key_u64s = roundup_pow_of_two(key_u64s);
struct bkey_cached *ck = bkey_cached_alloc(trans, path, key_u64s);
int ret = PTR_ERR_OR_ZERO(ck);
if (ret)
return ret;
if (unlikely(!ck)) {
ck = bkey_cached_reuse(bc);
if (unlikely(!ck)) {
bch_err(c, "error allocating memory for key cache item, btree %s",
bch2_btree_id_str(path->btree_id));
return -BCH_ERR_ENOMEM_btree_key_cache_create;
}
}
ck->c.level = 0;
ck->c.btree_id = path->btree_id;
ck->key.btree_id = path->btree_id;
ck->key.pos = path->pos;
ck->flags = 1U << BKEY_CACHED_ACCESSED;
if (unlikely(key_u64s > ck->u64s)) {
mark_btree_node_locked_noreset(path, 0, BTREE_NODE_UNLOCKED);
struct bkey_i *new_k = allocate_dropping_locks(trans, ret,
kmalloc(key_u64s * sizeof(u64), _gfp));
if (unlikely(!new_k)) {
bch_err(trans->c, "error allocating memory for key cache key, btree %s u64s %u",
bch2_btree_id_str(ck->key.btree_id), key_u64s);
ret = -BCH_ERR_ENOMEM_btree_key_cache_fill;
} else if (ret) {
kfree(new_k);
goto err;
}
kfree(ck->k);
ck->k = new_k;
ck->u64s = key_u64s;
}
bkey_reassemble(ck->k, k);
ret = rhashtable_lookup_insert_fast(&bc->table, &ck->hash, bch2_btree_key_cache_params);
if (unlikely(ret)) /* raced with another fill? */
goto err;
atomic_long_inc(&bc->nr_keys);
six_unlock_write(&ck->c.lock);
enum six_lock_type lock_want = __btree_lock_want(path, 0);
if (lock_want == SIX_LOCK_read)
six_lock_downgrade(&ck->c.lock);
btree_path_cached_set(trans, path, ck, (enum btree_node_locked_type) lock_want);
path->uptodate = BTREE_ITER_UPTODATE;
return 0;
err:
bkey_cached_free(bc, ck);
mark_btree_node_locked_noreset(path, 0, BTREE_NODE_UNLOCKED);
return ret;
}
static noinline int btree_key_cache_fill(struct btree_trans *trans,
struct btree_path *ck_path,
unsigned flags)
{
if (flags & BTREE_ITER_cached_nofill) {
ck_path->uptodate = BTREE_ITER_UPTODATE;
return 0;
}
struct bch_fs *c = trans->c;
struct btree_iter iter;
struct bkey_s_c k;
int ret;
bch2_trans_iter_init(trans, &iter, ck_path->btree_id, ck_path->pos,
BTREE_ITER_key_cache_fill|
BTREE_ITER_cached_nofill);
iter.flags &= ~BTREE_ITER_with_journal;
k = bch2_btree_iter_peek_slot(&iter);
ret = bkey_err(k);
if (ret)
goto err;
/* Recheck after btree lookup, before allocating: */
ret = bch2_btree_key_cache_find(c, ck_path->btree_id, ck_path->pos) ? -EEXIST : 0;
if (unlikely(ret))
goto out;
ret = btree_key_cache_create(trans, ck_path, k);
if (ret)
goto err;
out:
/* We're not likely to need this iterator again: */
bch2_set_btree_iter_dontneed(&iter);
err:
bch2_trans_iter_exit(trans, &iter);
return ret;
}
static inline int btree_path_traverse_cached_fast(struct btree_trans *trans,
struct btree_path *path)
{
struct bch_fs *c = trans->c;
struct bkey_cached *ck;
retry:
ck = bch2_btree_key_cache_find(c, path->btree_id, path->pos);
if (!ck)
return -ENOENT;
enum six_lock_type lock_want = __btree_lock_want(path, 0);
int ret = btree_node_lock(trans, path, (void *) ck, 0, lock_want, _THIS_IP_);
if (ret)
return ret;
if (ck->key.btree_id != path->btree_id ||
!bpos_eq(ck->key.pos, path->pos)) {
six_unlock_type(&ck->c.lock, lock_want);
goto retry;
}
if (!test_bit(BKEY_CACHED_ACCESSED, &ck->flags))
set_bit(BKEY_CACHED_ACCESSED, &ck->flags);
btree_path_cached_set(trans, path, ck, (enum btree_node_locked_type) lock_want);
path->uptodate = BTREE_ITER_UPTODATE;
return 0;
}
int bch2_btree_path_traverse_cached(struct btree_trans *trans, struct btree_path *path,
unsigned flags)
{
EBUG_ON(path->level);
path->l[1].b = NULL;
int ret;
do {
ret = btree_path_traverse_cached_fast(trans, path);
if (unlikely(ret == -ENOENT))
ret = btree_key_cache_fill(trans, path, flags);
} while (ret == -EEXIST);
if (unlikely(ret)) {
path->uptodate = BTREE_ITER_NEED_TRAVERSE;
if (!bch2_err_matches(ret, BCH_ERR_transaction_restart)) {
btree_node_unlock(trans, path, 0);
path->l[0].b = ERR_PTR(ret);
}
}
return ret;
}
static int btree_key_cache_flush_pos(struct btree_trans *trans,
struct bkey_cached_key key,
u64 journal_seq,
unsigned commit_flags,
bool evict)
{
struct bch_fs *c = trans->c;
struct journal *j = &c->journal;
struct btree_iter c_iter, b_iter;
struct bkey_cached *ck = NULL;
int ret;
bch2_trans_iter_init(trans, &b_iter, key.btree_id, key.pos,
BTREE_ITER_slots|
BTREE_ITER_intent|
BTREE_ITER_all_snapshots);
bch2_trans_iter_init(trans, &c_iter, key.btree_id, key.pos,
BTREE_ITER_cached|
BTREE_ITER_intent);
b_iter.flags &= ~BTREE_ITER_with_key_cache;
ret = bch2_btree_iter_traverse(&c_iter);
if (ret)
goto out;
ck = (void *) btree_iter_path(trans, &c_iter)->l[0].b;
if (!ck)
goto out;
if (!test_bit(BKEY_CACHED_DIRTY, &ck->flags)) {
if (evict)
goto evict;
goto out;
}
if (journal_seq && ck->journal.seq != journal_seq)
goto out;
trans->journal_res.seq = ck->journal.seq;
/*
* If we're at the end of the journal, we really want to free up space
* in the journal right away - we don't want to pin that old journal
* sequence number with a new btree node write, we want to re-journal
* the update
*/
if (ck->journal.seq == journal_last_seq(j))
commit_flags |= BCH_WATERMARK_reclaim;
if (ck->journal.seq != journal_last_seq(j) ||
!test_bit(JOURNAL_space_low, &c->journal.flags))
commit_flags |= BCH_TRANS_COMMIT_no_journal_res;
ret = bch2_btree_iter_traverse(&b_iter) ?:
bch2_trans_update(trans, &b_iter, ck->k,
BTREE_UPDATE_key_cache_reclaim|
BTREE_UPDATE_internal_snapshot_node|
BTREE_TRIGGER_norun) ?:
bch2_trans_commit(trans, NULL, NULL,
BCH_TRANS_COMMIT_no_check_rw|
BCH_TRANS_COMMIT_no_enospc|
commit_flags);
bch2_fs_fatal_err_on(ret &&
!bch2_err_matches(ret, BCH_ERR_transaction_restart) &&
!bch2_err_matches(ret, BCH_ERR_journal_reclaim_would_deadlock) &&
!bch2_journal_error(j), c,
"flushing key cache: %s", bch2_err_str(ret));
if (ret)
goto out;
bch2_journal_pin_drop(j, &ck->journal);
struct btree_path *path = btree_iter_path(trans, &c_iter);
BUG_ON(!btree_node_locked(path, 0));
if (!evict) {
if (test_bit(BKEY_CACHED_DIRTY, &ck->flags)) {
clear_bit(BKEY_CACHED_DIRTY, &ck->flags);
atomic_long_dec(&c->btree_key_cache.nr_dirty);
}
} else {
struct btree_path *path2;
unsigned i;
evict:
trans_for_each_path(trans, path2, i)
if (path2 != path)
__bch2_btree_path_unlock(trans, path2);
bch2_btree_node_lock_write_nofail(trans, path, &ck->c);
if (test_bit(BKEY_CACHED_DIRTY, &ck->flags)) {
clear_bit(BKEY_CACHED_DIRTY, &ck->flags);
atomic_long_dec(&c->btree_key_cache.nr_dirty);
}
mark_btree_node_locked_noreset(path, 0, BTREE_NODE_UNLOCKED);
if (bkey_cached_evict(&c->btree_key_cache, ck)) {
bkey_cached_free(&c->btree_key_cache, ck);
} else {
six_unlock_write(&ck->c.lock);
six_unlock_intent(&ck->c.lock);
}
}
out:
bch2_trans_iter_exit(trans, &b_iter);
bch2_trans_iter_exit(trans, &c_iter);
return ret;
}
int bch2_btree_key_cache_journal_flush(struct journal *j,
struct journal_entry_pin *pin, u64 seq)
{
struct bch_fs *c = container_of(j, struct bch_fs, journal);
struct bkey_cached *ck =
container_of(pin, struct bkey_cached, journal);
struct bkey_cached_key key;
struct btree_trans *trans = bch2_trans_get(c);
int srcu_idx = srcu_read_lock(&c->btree_trans_barrier);
int ret = 0;
btree_node_lock_nopath_nofail(trans, &ck->c, SIX_LOCK_read);
key = ck->key;
if (ck->journal.seq != seq ||
!test_bit(BKEY_CACHED_DIRTY, &ck->flags)) {
six_unlock_read(&ck->c.lock);
goto unlock;
}
if (ck->seq != seq) {
bch2_journal_pin_update(&c->journal, ck->seq, &ck->journal,
bch2_btree_key_cache_journal_flush);
six_unlock_read(&ck->c.lock);
goto unlock;
}
six_unlock_read(&ck->c.lock);
ret = lockrestart_do(trans,
btree_key_cache_flush_pos(trans, key, seq,
BCH_TRANS_COMMIT_journal_reclaim, false));
unlock:
srcu_read_unlock(&c->btree_trans_barrier, srcu_idx);
bch2_trans_put(trans);
return ret;
}
bool bch2_btree_insert_key_cached(struct btree_trans *trans,
unsigned flags,
bcachefs: don't bump key cache journal seq on nojournal commits fstest generic/388 occasionally reproduces corruptions where an inode has extents beyond i_size. This is a deliberate crash and recovery test, and the post crash+recovery characteristics are usually the same: the inode exists on disk in an early (i.e. just allocated) state based on the journal sequence number associated with the inode. Subsequent inode updates exist in the journal at higher sequence numbers, but the inode hadn't been written back before the associated crash and the post-crash recovery processes a set of journal sequence numbers that doesn't include updates to the inode. In fact, the sequence with the most recent inode key update always happens to be the sequence just before the front of the journal processed by recovery. This last bit is a significant hint that the problem relates to an on-disk journal update of the front of the journal. The root cause of this problem is basically that the inode is updated (multiple times) in-core and in the key cache, each time bumping the key cache sequence number used to control the cache flush. The cache flush skips one or more times, bumping the associated key cache journal pin to the key cache seq value. This has a side effect of holding the inode in memory a bit longer than normal, which helps exacerbate this problem, but is also unsafe in certain cases where the key cache seq may have been updated by a transaction commit that didn't journal the associated key. For example, consider an inode that has been allocated, updated several times in the key cache, journaled, but not yet written back. At this stage, everything should be consistent if the fs happens to crash because the latest update has been journal. Now consider a key update via bch2_extent_update_i_size_sectors() that uses the BTREE_UPDATE_NOJOURNAL flag. While this update may not change inode state, it can have the side effect of bumping ck->seq in bch2_btree_insert_key_cached(). In turn, if a subsequent key cache flush skips due to seq not matching the former, the ck->journal pin is updated to ck->seq even though the most recent key update was not journaled. If this pin happens to reside at the front (tail) of the journal, this means a subsequent journal write can update last_seq to a value beyond that which includes the most recent update to the inode. If this occurs and the fs happens to crash before the inode happens to flush, recovery will see the latest last_seq, fail to recover the inode and leave the inode in the inconsistent state described above. To avoid this problem, skip the key cache seq update on NOJOURNAL commits, except on initial pin add. Pass the insert entry directly to bch2_btree_insert_key_cached() to make the associated flag available and be consistent with btree_insert_key_leaf(). Signed-off-by: Brian Foster <bfoster@redhat.com> Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
2023-03-02 07:03:37 -07:00
struct btree_insert_entry *insert_entry)
{
struct bch_fs *c = trans->c;
struct bkey_cached *ck = (void *) (trans->paths + insert_entry->path)->l[0].b;
bcachefs: don't bump key cache journal seq on nojournal commits fstest generic/388 occasionally reproduces corruptions where an inode has extents beyond i_size. This is a deliberate crash and recovery test, and the post crash+recovery characteristics are usually the same: the inode exists on disk in an early (i.e. just allocated) state based on the journal sequence number associated with the inode. Subsequent inode updates exist in the journal at higher sequence numbers, but the inode hadn't been written back before the associated crash and the post-crash recovery processes a set of journal sequence numbers that doesn't include updates to the inode. In fact, the sequence with the most recent inode key update always happens to be the sequence just before the front of the journal processed by recovery. This last bit is a significant hint that the problem relates to an on-disk journal update of the front of the journal. The root cause of this problem is basically that the inode is updated (multiple times) in-core and in the key cache, each time bumping the key cache sequence number used to control the cache flush. The cache flush skips one or more times, bumping the associated key cache journal pin to the key cache seq value. This has a side effect of holding the inode in memory a bit longer than normal, which helps exacerbate this problem, but is also unsafe in certain cases where the key cache seq may have been updated by a transaction commit that didn't journal the associated key. For example, consider an inode that has been allocated, updated several times in the key cache, journaled, but not yet written back. At this stage, everything should be consistent if the fs happens to crash because the latest update has been journal. Now consider a key update via bch2_extent_update_i_size_sectors() that uses the BTREE_UPDATE_NOJOURNAL flag. While this update may not change inode state, it can have the side effect of bumping ck->seq in bch2_btree_insert_key_cached(). In turn, if a subsequent key cache flush skips due to seq not matching the former, the ck->journal pin is updated to ck->seq even though the most recent key update was not journaled. If this pin happens to reside at the front (tail) of the journal, this means a subsequent journal write can update last_seq to a value beyond that which includes the most recent update to the inode. If this occurs and the fs happens to crash before the inode happens to flush, recovery will see the latest last_seq, fail to recover the inode and leave the inode in the inconsistent state described above. To avoid this problem, skip the key cache seq update on NOJOURNAL commits, except on initial pin add. Pass the insert entry directly to bch2_btree_insert_key_cached() to make the associated flag available and be consistent with btree_insert_key_leaf(). Signed-off-by: Brian Foster <bfoster@redhat.com> Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
2023-03-02 07:03:37 -07:00
struct bkey_i *insert = insert_entry->k;
bool kick_reclaim = false;
BUG_ON(insert->k.u64s > ck->u64s);
bkey_copy(ck->k, insert);
if (!test_bit(BKEY_CACHED_DIRTY, &ck->flags)) {
EBUG_ON(test_bit(BCH_FS_clean_shutdown, &c->flags));
set_bit(BKEY_CACHED_DIRTY, &ck->flags);
atomic_long_inc(&c->btree_key_cache.nr_dirty);
if (bch2_nr_btree_keys_need_flush(c))
kick_reclaim = true;
}
bcachefs: don't bump key cache journal seq on nojournal commits fstest generic/388 occasionally reproduces corruptions where an inode has extents beyond i_size. This is a deliberate crash and recovery test, and the post crash+recovery characteristics are usually the same: the inode exists on disk in an early (i.e. just allocated) state based on the journal sequence number associated with the inode. Subsequent inode updates exist in the journal at higher sequence numbers, but the inode hadn't been written back before the associated crash and the post-crash recovery processes a set of journal sequence numbers that doesn't include updates to the inode. In fact, the sequence with the most recent inode key update always happens to be the sequence just before the front of the journal processed by recovery. This last bit is a significant hint that the problem relates to an on-disk journal update of the front of the journal. The root cause of this problem is basically that the inode is updated (multiple times) in-core and in the key cache, each time bumping the key cache sequence number used to control the cache flush. The cache flush skips one or more times, bumping the associated key cache journal pin to the key cache seq value. This has a side effect of holding the inode in memory a bit longer than normal, which helps exacerbate this problem, but is also unsafe in certain cases where the key cache seq may have been updated by a transaction commit that didn't journal the associated key. For example, consider an inode that has been allocated, updated several times in the key cache, journaled, but not yet written back. At this stage, everything should be consistent if the fs happens to crash because the latest update has been journal. Now consider a key update via bch2_extent_update_i_size_sectors() that uses the BTREE_UPDATE_NOJOURNAL flag. While this update may not change inode state, it can have the side effect of bumping ck->seq in bch2_btree_insert_key_cached(). In turn, if a subsequent key cache flush skips due to seq not matching the former, the ck->journal pin is updated to ck->seq even though the most recent key update was not journaled. If this pin happens to reside at the front (tail) of the journal, this means a subsequent journal write can update last_seq to a value beyond that which includes the most recent update to the inode. If this occurs and the fs happens to crash before the inode happens to flush, recovery will see the latest last_seq, fail to recover the inode and leave the inode in the inconsistent state described above. To avoid this problem, skip the key cache seq update on NOJOURNAL commits, except on initial pin add. Pass the insert entry directly to bch2_btree_insert_key_cached() to make the associated flag available and be consistent with btree_insert_key_leaf(). Signed-off-by: Brian Foster <bfoster@redhat.com> Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
2023-03-02 07:03:37 -07:00
/*
* To minimize lock contention, we only add the journal pin here and
* defer pin updates to the flush callback via ->seq. Be careful not to
* update ->seq on nojournal commits because we don't want to update the
* pin to a seq that doesn't include journal updates on disk. Otherwise
* we risk losing the update after a crash.
*
* The only exception is if the pin is not active in the first place. We
* have to add the pin because journal reclaim drives key cache
* flushing. The flush callback will not proceed unless ->seq matches
* the latest pin, so make sure it starts with a consistent value.
*/
if (!(insert_entry->flags & BTREE_UPDATE_nojournal) ||
bcachefs: don't bump key cache journal seq on nojournal commits fstest generic/388 occasionally reproduces corruptions where an inode has extents beyond i_size. This is a deliberate crash and recovery test, and the post crash+recovery characteristics are usually the same: the inode exists on disk in an early (i.e. just allocated) state based on the journal sequence number associated with the inode. Subsequent inode updates exist in the journal at higher sequence numbers, but the inode hadn't been written back before the associated crash and the post-crash recovery processes a set of journal sequence numbers that doesn't include updates to the inode. In fact, the sequence with the most recent inode key update always happens to be the sequence just before the front of the journal processed by recovery. This last bit is a significant hint that the problem relates to an on-disk journal update of the front of the journal. The root cause of this problem is basically that the inode is updated (multiple times) in-core and in the key cache, each time bumping the key cache sequence number used to control the cache flush. The cache flush skips one or more times, bumping the associated key cache journal pin to the key cache seq value. This has a side effect of holding the inode in memory a bit longer than normal, which helps exacerbate this problem, but is also unsafe in certain cases where the key cache seq may have been updated by a transaction commit that didn't journal the associated key. For example, consider an inode that has been allocated, updated several times in the key cache, journaled, but not yet written back. At this stage, everything should be consistent if the fs happens to crash because the latest update has been journal. Now consider a key update via bch2_extent_update_i_size_sectors() that uses the BTREE_UPDATE_NOJOURNAL flag. While this update may not change inode state, it can have the side effect of bumping ck->seq in bch2_btree_insert_key_cached(). In turn, if a subsequent key cache flush skips due to seq not matching the former, the ck->journal pin is updated to ck->seq even though the most recent key update was not journaled. If this pin happens to reside at the front (tail) of the journal, this means a subsequent journal write can update last_seq to a value beyond that which includes the most recent update to the inode. If this occurs and the fs happens to crash before the inode happens to flush, recovery will see the latest last_seq, fail to recover the inode and leave the inode in the inconsistent state described above. To avoid this problem, skip the key cache seq update on NOJOURNAL commits, except on initial pin add. Pass the insert entry directly to bch2_btree_insert_key_cached() to make the associated flag available and be consistent with btree_insert_key_leaf(). Signed-off-by: Brian Foster <bfoster@redhat.com> Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
2023-03-02 07:03:37 -07:00
!journal_pin_active(&ck->journal)) {
ck->seq = trans->journal_res.seq;
}
bch2_journal_pin_add(&c->journal, trans->journal_res.seq,
&ck->journal, bch2_btree_key_cache_journal_flush);
if (kick_reclaim)
journal_reclaim_kick(&c->journal);
return true;
}
void bch2_btree_key_cache_drop(struct btree_trans *trans,
struct btree_path *path)
{
struct bch_fs *c = trans->c;
struct btree_key_cache *bc = &c->btree_key_cache;
struct bkey_cached *ck = (void *) path->l[0].b;
/*
* We just did an update to the btree, bypassing the key cache: the key
* cache key is now stale and must be dropped, even if dirty:
*/
if (test_bit(BKEY_CACHED_DIRTY, &ck->flags)) {
clear_bit(BKEY_CACHED_DIRTY, &ck->flags);
atomic_long_dec(&c->btree_key_cache.nr_dirty);
bch2_journal_pin_drop(&c->journal, &ck->journal);
}
bkey_cached_evict(bc, ck);
bkey_cached_free(bc, ck);
mark_btree_node_locked(trans, path, 0, BTREE_NODE_UNLOCKED);
btree_path_set_dirty(path, BTREE_ITER_NEED_TRAVERSE);
path->should_be_locked = false;
}
static unsigned long bch2_btree_key_cache_scan(struct shrinker *shrink,
struct shrink_control *sc)
{
Many singleton patches against the MM code. The patch series which are included in this merge do the following: - Kemeng Shi has contributed some compation maintenance work in the series "Fixes and cleanups to compaction". - Joel Fernandes has a patchset ("Optimize mremap during mutual alignment within PMD") which fixes an obscure issue with mremap()'s pagetable handling during a subsequent exec(), based upon an implementation which Linus suggested. - More DAMON/DAMOS maintenance and feature work from SeongJae Park i the following patch series: mm/damon: misc fixups for documents, comments and its tracepoint mm/damon: add a tracepoint for damos apply target regions mm/damon: provide pseudo-moving sum based access rate mm/damon: implement DAMOS apply intervals mm/damon/core-test: Fix memory leaks in core-test mm/damon/sysfs-schemes: Do DAMOS tried regions update for only one apply interval - In the series "Do not try to access unaccepted memory" Adrian Hunter provides some fixups for the recently-added "unaccepted memory' feature. To increase the feature's checking coverage. "Plug a few gaps where RAM is exposed without checking if it is unaccepted memory". - In the series "cleanups for lockless slab shrink" Qi Zheng has done some maintenance work which is preparation for the lockless slab shrinking code. - Qi Zheng has redone the earlier (and reverted) attempt to make slab shrinking lockless in the series "use refcount+RCU method to implement lockless slab shrink". - David Hildenbrand contributes some maintenance work for the rmap code in the series "Anon rmap cleanups". - Kefeng Wang does more folio conversions and some maintenance work in the migration code. Series "mm: migrate: more folio conversion and unification". - Matthew Wilcox has fixed an issue in the buffer_head code which was causing long stalls under some heavy memory/IO loads. Some cleanups were added on the way. Series "Add and use bdev_getblk()". - In the series "Use nth_page() in place of direct struct page manipulation" Zi Yan has fixed a potential issue with the direct manipulation of hugetlb page frames. - In the series "mm: hugetlb: Skip initialization of gigantic tail struct pages if freed by HVO" has improved our handling of gigantic pages in the hugetlb vmmemmep optimizaton code. This provides significant boot time improvements when significant amounts of gigantic pages are in use. - Matthew Wilcox has sent the series "Small hugetlb cleanups" - code rationalization and folio conversions in the hugetlb code. - Yin Fengwei has improved mlock()'s handling of large folios in the series "support large folio for mlock" - In the series "Expose swapcache stat for memcg v1" Liu Shixin has added statistics for memcg v1 users which are available (and useful) under memcg v2. - Florent Revest has enhanced the MDWE (Memory-Deny-Write-Executable) prctl so that userspace may direct the kernel to not automatically propagate the denial to child processes. The series is named "MDWE without inheritance". - Kefeng Wang has provided the series "mm: convert numa balancing functions to use a folio" which does what it says. - In the series "mm/ksm: add fork-exec support for prctl" Stefan Roesch makes is possible for a process to propagate KSM treatment across exec(). - Huang Ying has enhanced memory tiering's calculation of memory distances. This is used to permit the dax/kmem driver to use "high bandwidth memory" in addition to Optane Data Center Persistent Memory Modules (DCPMM). The series is named "memory tiering: calculate abstract distance based on ACPI HMAT" - In the series "Smart scanning mode for KSM" Stefan Roesch has optimized KSM by teaching it to retain and use some historical information from previous scans. - Yosry Ahmed has fixed some inconsistencies in memcg statistics in the series "mm: memcg: fix tracking of pending stats updates values". - In the series "Implement IOCTL to get and optionally clear info about PTEs" Peter Xu has added an ioctl to /proc/<pid>/pagemap which permits us to atomically read-then-clear page softdirty state. This is mainly used by CRIU. - Hugh Dickins contributed the series "shmem,tmpfs: general maintenance" - a bunch of relatively minor maintenance tweaks to this code. - Matthew Wilcox has increased the use of the VMA lock over file-backed page faults in the series "Handle more faults under the VMA lock". Some rationalizations of the fault path became possible as a result. - In the series "mm/rmap: convert page_move_anon_rmap() to folio_move_anon_rmap()" David Hildenbrand has implemented some cleanups and folio conversions. - In the series "various improvements to the GUP interface" Lorenzo Stoakes has simplified and improved the GUP interface with an eye to providing groundwork for future improvements. - Andrey Konovalov has sent along the series "kasan: assorted fixes and improvements" which does those things. - Some page allocator maintenance work from Kemeng Shi in the series "Two minor cleanups to break_down_buddy_pages". - In thes series "New selftest for mm" Breno Leitao has developed another MM self test which tickles a race we had between madvise() and page faults. - In the series "Add folio_end_read" Matthew Wilcox provides cleanups and an optimization to the core pagecache code. - Nhat Pham has added memcg accounting for hugetlb memory in the series "hugetlb memcg accounting". - Cleanups and rationalizations to the pagemap code from Lorenzo Stoakes, in the series "Abstract vma_merge() and split_vma()". - Audra Mitchell has fixed issues in the procfs page_owner code's new timestamping feature which was causing some misbehaviours. In the series "Fix page_owner's use of free timestamps". - Lorenzo Stoakes has fixed the handling of new mappings of sealed files in the series "permit write-sealed memfd read-only shared mappings". - Mike Kravetz has optimized the hugetlb vmemmap optimization in the series "Batch hugetlb vmemmap modification operations". - Some buffer_head folio conversions and cleanups from Matthew Wilcox in the series "Finish the create_empty_buffers() transition". - As a page allocator performance optimization Huang Ying has added automatic tuning to the allocator's per-cpu-pages feature, in the series "mm: PCP high auto-tuning". - Roman Gushchin has contributed the patchset "mm: improve performance of accounted kernel memory allocations" which improves their performance by ~30% as measured by a micro-benchmark. - folio conversions from Kefeng Wang in the series "mm: convert page cpupid functions to folios". - Some kmemleak fixups in Liu Shixin's series "Some bugfix about kmemleak". - Qi Zheng has improved our handling of memoryless nodes by keeping them off the allocation fallback list. This is done in the series "handle memoryless nodes more appropriately". - khugepaged conversions from Vishal Moola in the series "Some khugepaged folio conversions". -----BEGIN PGP SIGNATURE----- iHUEABYIAB0WIQTTMBEPP41GrTpTJgfdBJ7gKXxAjgUCZULEMwAKCRDdBJ7gKXxA jhQHAQCYpD3g849x69DmHnHWHm/EHQLvQmRMDeYZI+nx/sCJOwEAw4AKg0Oemv9y FgeUPAD1oasg6CP+INZvCj34waNxwAc= =E+Y4 -----END PGP SIGNATURE----- Merge tag 'mm-stable-2023-11-01-14-33' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Pull MM updates from Andrew Morton: "Many singleton patches against the MM code. The patch series which are included in this merge do the following: - Kemeng Shi has contributed some compation maintenance work in the series 'Fixes and cleanups to compaction' - Joel Fernandes has a patchset ('Optimize mremap during mutual alignment within PMD') which fixes an obscure issue with mremap()'s pagetable handling during a subsequent exec(), based upon an implementation which Linus suggested - More DAMON/DAMOS maintenance and feature work from SeongJae Park i the following patch series: mm/damon: misc fixups for documents, comments and its tracepoint mm/damon: add a tracepoint for damos apply target regions mm/damon: provide pseudo-moving sum based access rate mm/damon: implement DAMOS apply intervals mm/damon/core-test: Fix memory leaks in core-test mm/damon/sysfs-schemes: Do DAMOS tried regions update for only one apply interval - In the series 'Do not try to access unaccepted memory' Adrian Hunter provides some fixups for the recently-added 'unaccepted memory' feature. To increase the feature's checking coverage. 'Plug a few gaps where RAM is exposed without checking if it is unaccepted memory' - In the series 'cleanups for lockless slab shrink' Qi Zheng has done some maintenance work which is preparation for the lockless slab shrinking code - Qi Zheng has redone the earlier (and reverted) attempt to make slab shrinking lockless in the series 'use refcount+RCU method to implement lockless slab shrink' - David Hildenbrand contributes some maintenance work for the rmap code in the series 'Anon rmap cleanups' - Kefeng Wang does more folio conversions and some maintenance work in the migration code. Series 'mm: migrate: more folio conversion and unification' - Matthew Wilcox has fixed an issue in the buffer_head code which was causing long stalls under some heavy memory/IO loads. Some cleanups were added on the way. Series 'Add and use bdev_getblk()' - In the series 'Use nth_page() in place of direct struct page manipulation' Zi Yan has fixed a potential issue with the direct manipulation of hugetlb page frames - In the series 'mm: hugetlb: Skip initialization of gigantic tail struct pages if freed by HVO' has improved our handling of gigantic pages in the hugetlb vmmemmep optimizaton code. This provides significant boot time improvements when significant amounts of gigantic pages are in use - Matthew Wilcox has sent the series 'Small hugetlb cleanups' - code rationalization and folio conversions in the hugetlb code - Yin Fengwei has improved mlock()'s handling of large folios in the series 'support large folio for mlock' - In the series 'Expose swapcache stat for memcg v1' Liu Shixin has added statistics for memcg v1 users which are available (and useful) under memcg v2 - Florent Revest has enhanced the MDWE (Memory-Deny-Write-Executable) prctl so that userspace may direct the kernel to not automatically propagate the denial to child processes. The series is named 'MDWE without inheritance' - Kefeng Wang has provided the series 'mm: convert numa balancing functions to use a folio' which does what it says - In the series 'mm/ksm: add fork-exec support for prctl' Stefan Roesch makes is possible for a process to propagate KSM treatment across exec() - Huang Ying has enhanced memory tiering's calculation of memory distances. This is used to permit the dax/kmem driver to use 'high bandwidth memory' in addition to Optane Data Center Persistent Memory Modules (DCPMM). The series is named 'memory tiering: calculate abstract distance based on ACPI HMAT' - In the series 'Smart scanning mode for KSM' Stefan Roesch has optimized KSM by teaching it to retain and use some historical information from previous scans - Yosry Ahmed has fixed some inconsistencies in memcg statistics in the series 'mm: memcg: fix tracking of pending stats updates values' - In the series 'Implement IOCTL to get and optionally clear info about PTEs' Peter Xu has added an ioctl to /proc/<pid>/pagemap which permits us to atomically read-then-clear page softdirty state. This is mainly used by CRIU - Hugh Dickins contributed the series 'shmem,tmpfs: general maintenance', a bunch of relatively minor maintenance tweaks to this code - Matthew Wilcox has increased the use of the VMA lock over file-backed page faults in the series 'Handle more faults under the VMA lock'. Some rationalizations of the fault path became possible as a result - In the series 'mm/rmap: convert page_move_anon_rmap() to folio_move_anon_rmap()' David Hildenbrand has implemented some cleanups and folio conversions - In the series 'various improvements to the GUP interface' Lorenzo Stoakes has simplified and improved the GUP interface with an eye to providing groundwork for future improvements - Andrey Konovalov has sent along the series 'kasan: assorted fixes and improvements' which does those things - Some page allocator maintenance work from Kemeng Shi in the series 'Two minor cleanups to break_down_buddy_pages' - In thes series 'New selftest for mm' Breno Leitao has developed another MM self test which tickles a race we had between madvise() and page faults - In the series 'Add folio_end_read' Matthew Wilcox provides cleanups and an optimization to the core pagecache code - Nhat Pham has added memcg accounting for hugetlb memory in the series 'hugetlb memcg accounting' - Cleanups and rationalizations to the pagemap code from Lorenzo Stoakes, in the series 'Abstract vma_merge() and split_vma()' - Audra Mitchell has fixed issues in the procfs page_owner code's new timestamping feature which was causing some misbehaviours. In the series 'Fix page_owner's use of free timestamps' - Lorenzo Stoakes has fixed the handling of new mappings of sealed files in the series 'permit write-sealed memfd read-only shared mappings' - Mike Kravetz has optimized the hugetlb vmemmap optimization in the series 'Batch hugetlb vmemmap modification operations' - Some buffer_head folio conversions and cleanups from Matthew Wilcox in the series 'Finish the create_empty_buffers() transition' - As a page allocator performance optimization Huang Ying has added automatic tuning to the allocator's per-cpu-pages feature, in the series 'mm: PCP high auto-tuning' - Roman Gushchin has contributed the patchset 'mm: improve performance of accounted kernel memory allocations' which improves their performance by ~30% as measured by a micro-benchmark - folio conversions from Kefeng Wang in the series 'mm: convert page cpupid functions to folios' - Some kmemleak fixups in Liu Shixin's series 'Some bugfix about kmemleak' - Qi Zheng has improved our handling of memoryless nodes by keeping them off the allocation fallback list. This is done in the series 'handle memoryless nodes more appropriately' - khugepaged conversions from Vishal Moola in the series 'Some khugepaged folio conversions'" [ bcachefs conflicts with the dynamically allocated shrinkers have been resolved as per Stephen Rothwell in https://lore.kernel.org/all/20230913093553.4290421e@canb.auug.org.au/ with help from Qi Zheng. The clone3 test filtering conflict was half-arsed by yours truly ] * tag 'mm-stable-2023-11-01-14-33' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (406 commits) mm/damon/sysfs: update monitoring target regions for online input commit mm/damon/sysfs: remove requested targets when online-commit inputs selftests: add a sanity check for zswap Documentation: maple_tree: fix word spelling error mm/vmalloc: fix the unchecked dereference warning in vread_iter() zswap: export compression failure stats Documentation: ubsan: drop "the" from article title mempolicy: migration attempt to match interleave nodes mempolicy: mmap_lock is not needed while migrating folios mempolicy: alloc_pages_mpol() for NUMA policy without vma mm: add page_rmappable_folio() wrapper mempolicy: remove confusing MPOL_MF_LAZY dead code mempolicy: mpol_shared_policy_init() without pseudo-vma mempolicy trivia: use pgoff_t in shared mempolicy tree mempolicy trivia: slightly more consistent naming mempolicy trivia: delete those ancient pr_debug()s mempolicy: fix migrate_pages(2) syscall return nr_failed kernfs: drop shared NUMA mempolicy hooks hugetlbfs: drop shared NUMA mempolicy pretence mm/damon/sysfs-test: add a unit test for damon_sysfs_set_targets() ...
2023-11-02 22:38:47 -07:00
struct bch_fs *c = shrink->private_data;
struct btree_key_cache *bc = &c->btree_key_cache;
struct bucket_table *tbl;
struct bkey_cached *ck;
size_t scanned = 0, freed = 0, nr = sc->nr_to_scan;
unsigned iter, start;
int srcu_idx;
srcu_idx = srcu_read_lock(&c->btree_trans_barrier);
rcu_read_lock();
tbl = rht_dereference_rcu(bc->table.tbl, &bc->table);
/*
* Scanning is expensive while a rehash is in progress - most elements
* will be on the new hashtable, if it's in progress
*
* A rehash could still start while we're scanning - that's ok, we'll
* still see most elements.
*/
if (unlikely(tbl->nest)) {
rcu_read_unlock();
srcu_read_unlock(&c->btree_trans_barrier, srcu_idx);
return SHRINK_STOP;
}
iter = bc->shrink_iter;
if (iter >= tbl->size)
iter = 0;
start = iter;
do {
struct rhash_head *pos, *next;
pos = rht_ptr_rcu(&tbl->buckets[iter]);
while (!rht_is_a_nulls(pos)) {
next = rht_dereference_bucket_rcu(pos->next, tbl, iter);
ck = container_of(pos, struct bkey_cached, hash);
if (test_bit(BKEY_CACHED_DIRTY, &ck->flags)) {
bc->skipped_dirty++;
} else if (test_bit(BKEY_CACHED_ACCESSED, &ck->flags)) {
clear_bit(BKEY_CACHED_ACCESSED, &ck->flags);
bc->skipped_accessed++;
} else if (!bkey_cached_lock_for_evict(ck)) {
bc->skipped_lock_fail++;
} else if (bkey_cached_evict(bc, ck)) {
bkey_cached_free(bc, ck);
bc->freed++;
freed++;
} else {
six_unlock_write(&ck->c.lock);
six_unlock_intent(&ck->c.lock);
}
scanned++;
if (scanned >= nr)
goto out;
pos = next;
}
iter++;
if (iter >= tbl->size)
iter = 0;
} while (scanned < nr && iter != start);
out:
bc->shrink_iter = iter;
rcu_read_unlock();
srcu_read_unlock(&c->btree_trans_barrier, srcu_idx);
return freed;
}
static unsigned long bch2_btree_key_cache_count(struct shrinker *shrink,
struct shrink_control *sc)
{
Many singleton patches against the MM code. The patch series which are included in this merge do the following: - Kemeng Shi has contributed some compation maintenance work in the series "Fixes and cleanups to compaction". - Joel Fernandes has a patchset ("Optimize mremap during mutual alignment within PMD") which fixes an obscure issue with mremap()'s pagetable handling during a subsequent exec(), based upon an implementation which Linus suggested. - More DAMON/DAMOS maintenance and feature work from SeongJae Park i the following patch series: mm/damon: misc fixups for documents, comments and its tracepoint mm/damon: add a tracepoint for damos apply target regions mm/damon: provide pseudo-moving sum based access rate mm/damon: implement DAMOS apply intervals mm/damon/core-test: Fix memory leaks in core-test mm/damon/sysfs-schemes: Do DAMOS tried regions update for only one apply interval - In the series "Do not try to access unaccepted memory" Adrian Hunter provides some fixups for the recently-added "unaccepted memory' feature. To increase the feature's checking coverage. "Plug a few gaps where RAM is exposed without checking if it is unaccepted memory". - In the series "cleanups for lockless slab shrink" Qi Zheng has done some maintenance work which is preparation for the lockless slab shrinking code. - Qi Zheng has redone the earlier (and reverted) attempt to make slab shrinking lockless in the series "use refcount+RCU method to implement lockless slab shrink". - David Hildenbrand contributes some maintenance work for the rmap code in the series "Anon rmap cleanups". - Kefeng Wang does more folio conversions and some maintenance work in the migration code. Series "mm: migrate: more folio conversion and unification". - Matthew Wilcox has fixed an issue in the buffer_head code which was causing long stalls under some heavy memory/IO loads. Some cleanups were added on the way. Series "Add and use bdev_getblk()". - In the series "Use nth_page() in place of direct struct page manipulation" Zi Yan has fixed a potential issue with the direct manipulation of hugetlb page frames. - In the series "mm: hugetlb: Skip initialization of gigantic tail struct pages if freed by HVO" has improved our handling of gigantic pages in the hugetlb vmmemmep optimizaton code. This provides significant boot time improvements when significant amounts of gigantic pages are in use. - Matthew Wilcox has sent the series "Small hugetlb cleanups" - code rationalization and folio conversions in the hugetlb code. - Yin Fengwei has improved mlock()'s handling of large folios in the series "support large folio for mlock" - In the series "Expose swapcache stat for memcg v1" Liu Shixin has added statistics for memcg v1 users which are available (and useful) under memcg v2. - Florent Revest has enhanced the MDWE (Memory-Deny-Write-Executable) prctl so that userspace may direct the kernel to not automatically propagate the denial to child processes. The series is named "MDWE without inheritance". - Kefeng Wang has provided the series "mm: convert numa balancing functions to use a folio" which does what it says. - In the series "mm/ksm: add fork-exec support for prctl" Stefan Roesch makes is possible for a process to propagate KSM treatment across exec(). - Huang Ying has enhanced memory tiering's calculation of memory distances. This is used to permit the dax/kmem driver to use "high bandwidth memory" in addition to Optane Data Center Persistent Memory Modules (DCPMM). The series is named "memory tiering: calculate abstract distance based on ACPI HMAT" - In the series "Smart scanning mode for KSM" Stefan Roesch has optimized KSM by teaching it to retain and use some historical information from previous scans. - Yosry Ahmed has fixed some inconsistencies in memcg statistics in the series "mm: memcg: fix tracking of pending stats updates values". - In the series "Implement IOCTL to get and optionally clear info about PTEs" Peter Xu has added an ioctl to /proc/<pid>/pagemap which permits us to atomically read-then-clear page softdirty state. This is mainly used by CRIU. - Hugh Dickins contributed the series "shmem,tmpfs: general maintenance" - a bunch of relatively minor maintenance tweaks to this code. - Matthew Wilcox has increased the use of the VMA lock over file-backed page faults in the series "Handle more faults under the VMA lock". Some rationalizations of the fault path became possible as a result. - In the series "mm/rmap: convert page_move_anon_rmap() to folio_move_anon_rmap()" David Hildenbrand has implemented some cleanups and folio conversions. - In the series "various improvements to the GUP interface" Lorenzo Stoakes has simplified and improved the GUP interface with an eye to providing groundwork for future improvements. - Andrey Konovalov has sent along the series "kasan: assorted fixes and improvements" which does those things. - Some page allocator maintenance work from Kemeng Shi in the series "Two minor cleanups to break_down_buddy_pages". - In thes series "New selftest for mm" Breno Leitao has developed another MM self test which tickles a race we had between madvise() and page faults. - In the series "Add folio_end_read" Matthew Wilcox provides cleanups and an optimization to the core pagecache code. - Nhat Pham has added memcg accounting for hugetlb memory in the series "hugetlb memcg accounting". - Cleanups and rationalizations to the pagemap code from Lorenzo Stoakes, in the series "Abstract vma_merge() and split_vma()". - Audra Mitchell has fixed issues in the procfs page_owner code's new timestamping feature which was causing some misbehaviours. In the series "Fix page_owner's use of free timestamps". - Lorenzo Stoakes has fixed the handling of new mappings of sealed files in the series "permit write-sealed memfd read-only shared mappings". - Mike Kravetz has optimized the hugetlb vmemmap optimization in the series "Batch hugetlb vmemmap modification operations". - Some buffer_head folio conversions and cleanups from Matthew Wilcox in the series "Finish the create_empty_buffers() transition". - As a page allocator performance optimization Huang Ying has added automatic tuning to the allocator's per-cpu-pages feature, in the series "mm: PCP high auto-tuning". - Roman Gushchin has contributed the patchset "mm: improve performance of accounted kernel memory allocations" which improves their performance by ~30% as measured by a micro-benchmark. - folio conversions from Kefeng Wang in the series "mm: convert page cpupid functions to folios". - Some kmemleak fixups in Liu Shixin's series "Some bugfix about kmemleak". - Qi Zheng has improved our handling of memoryless nodes by keeping them off the allocation fallback list. This is done in the series "handle memoryless nodes more appropriately". - khugepaged conversions from Vishal Moola in the series "Some khugepaged folio conversions". -----BEGIN PGP SIGNATURE----- iHUEABYIAB0WIQTTMBEPP41GrTpTJgfdBJ7gKXxAjgUCZULEMwAKCRDdBJ7gKXxA jhQHAQCYpD3g849x69DmHnHWHm/EHQLvQmRMDeYZI+nx/sCJOwEAw4AKg0Oemv9y FgeUPAD1oasg6CP+INZvCj34waNxwAc= =E+Y4 -----END PGP SIGNATURE----- Merge tag 'mm-stable-2023-11-01-14-33' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Pull MM updates from Andrew Morton: "Many singleton patches against the MM code. The patch series which are included in this merge do the following: - Kemeng Shi has contributed some compation maintenance work in the series 'Fixes and cleanups to compaction' - Joel Fernandes has a patchset ('Optimize mremap during mutual alignment within PMD') which fixes an obscure issue with mremap()'s pagetable handling during a subsequent exec(), based upon an implementation which Linus suggested - More DAMON/DAMOS maintenance and feature work from SeongJae Park i the following patch series: mm/damon: misc fixups for documents, comments and its tracepoint mm/damon: add a tracepoint for damos apply target regions mm/damon: provide pseudo-moving sum based access rate mm/damon: implement DAMOS apply intervals mm/damon/core-test: Fix memory leaks in core-test mm/damon/sysfs-schemes: Do DAMOS tried regions update for only one apply interval - In the series 'Do not try to access unaccepted memory' Adrian Hunter provides some fixups for the recently-added 'unaccepted memory' feature. To increase the feature's checking coverage. 'Plug a few gaps where RAM is exposed without checking if it is unaccepted memory' - In the series 'cleanups for lockless slab shrink' Qi Zheng has done some maintenance work which is preparation for the lockless slab shrinking code - Qi Zheng has redone the earlier (and reverted) attempt to make slab shrinking lockless in the series 'use refcount+RCU method to implement lockless slab shrink' - David Hildenbrand contributes some maintenance work for the rmap code in the series 'Anon rmap cleanups' - Kefeng Wang does more folio conversions and some maintenance work in the migration code. Series 'mm: migrate: more folio conversion and unification' - Matthew Wilcox has fixed an issue in the buffer_head code which was causing long stalls under some heavy memory/IO loads. Some cleanups were added on the way. Series 'Add and use bdev_getblk()' - In the series 'Use nth_page() in place of direct struct page manipulation' Zi Yan has fixed a potential issue with the direct manipulation of hugetlb page frames - In the series 'mm: hugetlb: Skip initialization of gigantic tail struct pages if freed by HVO' has improved our handling of gigantic pages in the hugetlb vmmemmep optimizaton code. This provides significant boot time improvements when significant amounts of gigantic pages are in use - Matthew Wilcox has sent the series 'Small hugetlb cleanups' - code rationalization and folio conversions in the hugetlb code - Yin Fengwei has improved mlock()'s handling of large folios in the series 'support large folio for mlock' - In the series 'Expose swapcache stat for memcg v1' Liu Shixin has added statistics for memcg v1 users which are available (and useful) under memcg v2 - Florent Revest has enhanced the MDWE (Memory-Deny-Write-Executable) prctl so that userspace may direct the kernel to not automatically propagate the denial to child processes. The series is named 'MDWE without inheritance' - Kefeng Wang has provided the series 'mm: convert numa balancing functions to use a folio' which does what it says - In the series 'mm/ksm: add fork-exec support for prctl' Stefan Roesch makes is possible for a process to propagate KSM treatment across exec() - Huang Ying has enhanced memory tiering's calculation of memory distances. This is used to permit the dax/kmem driver to use 'high bandwidth memory' in addition to Optane Data Center Persistent Memory Modules (DCPMM). The series is named 'memory tiering: calculate abstract distance based on ACPI HMAT' - In the series 'Smart scanning mode for KSM' Stefan Roesch has optimized KSM by teaching it to retain and use some historical information from previous scans - Yosry Ahmed has fixed some inconsistencies in memcg statistics in the series 'mm: memcg: fix tracking of pending stats updates values' - In the series 'Implement IOCTL to get and optionally clear info about PTEs' Peter Xu has added an ioctl to /proc/<pid>/pagemap which permits us to atomically read-then-clear page softdirty state. This is mainly used by CRIU - Hugh Dickins contributed the series 'shmem,tmpfs: general maintenance', a bunch of relatively minor maintenance tweaks to this code - Matthew Wilcox has increased the use of the VMA lock over file-backed page faults in the series 'Handle more faults under the VMA lock'. Some rationalizations of the fault path became possible as a result - In the series 'mm/rmap: convert page_move_anon_rmap() to folio_move_anon_rmap()' David Hildenbrand has implemented some cleanups and folio conversions - In the series 'various improvements to the GUP interface' Lorenzo Stoakes has simplified and improved the GUP interface with an eye to providing groundwork for future improvements - Andrey Konovalov has sent along the series 'kasan: assorted fixes and improvements' which does those things - Some page allocator maintenance work from Kemeng Shi in the series 'Two minor cleanups to break_down_buddy_pages' - In thes series 'New selftest for mm' Breno Leitao has developed another MM self test which tickles a race we had between madvise() and page faults - In the series 'Add folio_end_read' Matthew Wilcox provides cleanups and an optimization to the core pagecache code - Nhat Pham has added memcg accounting for hugetlb memory in the series 'hugetlb memcg accounting' - Cleanups and rationalizations to the pagemap code from Lorenzo Stoakes, in the series 'Abstract vma_merge() and split_vma()' - Audra Mitchell has fixed issues in the procfs page_owner code's new timestamping feature which was causing some misbehaviours. In the series 'Fix page_owner's use of free timestamps' - Lorenzo Stoakes has fixed the handling of new mappings of sealed files in the series 'permit write-sealed memfd read-only shared mappings' - Mike Kravetz has optimized the hugetlb vmemmap optimization in the series 'Batch hugetlb vmemmap modification operations' - Some buffer_head folio conversions and cleanups from Matthew Wilcox in the series 'Finish the create_empty_buffers() transition' - As a page allocator performance optimization Huang Ying has added automatic tuning to the allocator's per-cpu-pages feature, in the series 'mm: PCP high auto-tuning' - Roman Gushchin has contributed the patchset 'mm: improve performance of accounted kernel memory allocations' which improves their performance by ~30% as measured by a micro-benchmark - folio conversions from Kefeng Wang in the series 'mm: convert page cpupid functions to folios' - Some kmemleak fixups in Liu Shixin's series 'Some bugfix about kmemleak' - Qi Zheng has improved our handling of memoryless nodes by keeping them off the allocation fallback list. This is done in the series 'handle memoryless nodes more appropriately' - khugepaged conversions from Vishal Moola in the series 'Some khugepaged folio conversions'" [ bcachefs conflicts with the dynamically allocated shrinkers have been resolved as per Stephen Rothwell in https://lore.kernel.org/all/20230913093553.4290421e@canb.auug.org.au/ with help from Qi Zheng. The clone3 test filtering conflict was half-arsed by yours truly ] * tag 'mm-stable-2023-11-01-14-33' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (406 commits) mm/damon/sysfs: update monitoring target regions for online input commit mm/damon/sysfs: remove requested targets when online-commit inputs selftests: add a sanity check for zswap Documentation: maple_tree: fix word spelling error mm/vmalloc: fix the unchecked dereference warning in vread_iter() zswap: export compression failure stats Documentation: ubsan: drop "the" from article title mempolicy: migration attempt to match interleave nodes mempolicy: mmap_lock is not needed while migrating folios mempolicy: alloc_pages_mpol() for NUMA policy without vma mm: add page_rmappable_folio() wrapper mempolicy: remove confusing MPOL_MF_LAZY dead code mempolicy: mpol_shared_policy_init() without pseudo-vma mempolicy trivia: use pgoff_t in shared mempolicy tree mempolicy trivia: slightly more consistent naming mempolicy trivia: delete those ancient pr_debug()s mempolicy: fix migrate_pages(2) syscall return nr_failed kernfs: drop shared NUMA mempolicy hooks hugetlbfs: drop shared NUMA mempolicy pretence mm/damon/sysfs-test: add a unit test for damon_sysfs_set_targets() ...
2023-11-02 22:38:47 -07:00
struct bch_fs *c = shrink->private_data;
struct btree_key_cache *bc = &c->btree_key_cache;
long nr = atomic_long_read(&bc->nr_keys) -
atomic_long_read(&bc->nr_dirty);
/*
* Avoid hammering our shrinker too much if it's nearly empty - the
* shrinker code doesn't take into account how big our cache is, if it's
* mostly empty but the system is under memory pressure it causes nasty
* lock contention:
*/
nr -= 128;
return max(0L, nr);
}
void bch2_fs_btree_key_cache_exit(struct btree_key_cache *bc)
{
struct bch_fs *c = container_of(bc, struct bch_fs, btree_key_cache);
struct bucket_table *tbl;
struct bkey_cached *ck;
struct rhash_head *pos;
LIST_HEAD(items);
unsigned i;
Many singleton patches against the MM code. The patch series which are included in this merge do the following: - Kemeng Shi has contributed some compation maintenance work in the series "Fixes and cleanups to compaction". - Joel Fernandes has a patchset ("Optimize mremap during mutual alignment within PMD") which fixes an obscure issue with mremap()'s pagetable handling during a subsequent exec(), based upon an implementation which Linus suggested. - More DAMON/DAMOS maintenance and feature work from SeongJae Park i the following patch series: mm/damon: misc fixups for documents, comments and its tracepoint mm/damon: add a tracepoint for damos apply target regions mm/damon: provide pseudo-moving sum based access rate mm/damon: implement DAMOS apply intervals mm/damon/core-test: Fix memory leaks in core-test mm/damon/sysfs-schemes: Do DAMOS tried regions update for only one apply interval - In the series "Do not try to access unaccepted memory" Adrian Hunter provides some fixups for the recently-added "unaccepted memory' feature. To increase the feature's checking coverage. "Plug a few gaps where RAM is exposed without checking if it is unaccepted memory". - In the series "cleanups for lockless slab shrink" Qi Zheng has done some maintenance work which is preparation for the lockless slab shrinking code. - Qi Zheng has redone the earlier (and reverted) attempt to make slab shrinking lockless in the series "use refcount+RCU method to implement lockless slab shrink". - David Hildenbrand contributes some maintenance work for the rmap code in the series "Anon rmap cleanups". - Kefeng Wang does more folio conversions and some maintenance work in the migration code. Series "mm: migrate: more folio conversion and unification". - Matthew Wilcox has fixed an issue in the buffer_head code which was causing long stalls under some heavy memory/IO loads. Some cleanups were added on the way. Series "Add and use bdev_getblk()". - In the series "Use nth_page() in place of direct struct page manipulation" Zi Yan has fixed a potential issue with the direct manipulation of hugetlb page frames. - In the series "mm: hugetlb: Skip initialization of gigantic tail struct pages if freed by HVO" has improved our handling of gigantic pages in the hugetlb vmmemmep optimizaton code. This provides significant boot time improvements when significant amounts of gigantic pages are in use. - Matthew Wilcox has sent the series "Small hugetlb cleanups" - code rationalization and folio conversions in the hugetlb code. - Yin Fengwei has improved mlock()'s handling of large folios in the series "support large folio for mlock" - In the series "Expose swapcache stat for memcg v1" Liu Shixin has added statistics for memcg v1 users which are available (and useful) under memcg v2. - Florent Revest has enhanced the MDWE (Memory-Deny-Write-Executable) prctl so that userspace may direct the kernel to not automatically propagate the denial to child processes. The series is named "MDWE without inheritance". - Kefeng Wang has provided the series "mm: convert numa balancing functions to use a folio" which does what it says. - In the series "mm/ksm: add fork-exec support for prctl" Stefan Roesch makes is possible for a process to propagate KSM treatment across exec(). - Huang Ying has enhanced memory tiering's calculation of memory distances. This is used to permit the dax/kmem driver to use "high bandwidth memory" in addition to Optane Data Center Persistent Memory Modules (DCPMM). The series is named "memory tiering: calculate abstract distance based on ACPI HMAT" - In the series "Smart scanning mode for KSM" Stefan Roesch has optimized KSM by teaching it to retain and use some historical information from previous scans. - Yosry Ahmed has fixed some inconsistencies in memcg statistics in the series "mm: memcg: fix tracking of pending stats updates values". - In the series "Implement IOCTL to get and optionally clear info about PTEs" Peter Xu has added an ioctl to /proc/<pid>/pagemap which permits us to atomically read-then-clear page softdirty state. This is mainly used by CRIU. - Hugh Dickins contributed the series "shmem,tmpfs: general maintenance" - a bunch of relatively minor maintenance tweaks to this code. - Matthew Wilcox has increased the use of the VMA lock over file-backed page faults in the series "Handle more faults under the VMA lock". Some rationalizations of the fault path became possible as a result. - In the series "mm/rmap: convert page_move_anon_rmap() to folio_move_anon_rmap()" David Hildenbrand has implemented some cleanups and folio conversions. - In the series "various improvements to the GUP interface" Lorenzo Stoakes has simplified and improved the GUP interface with an eye to providing groundwork for future improvements. - Andrey Konovalov has sent along the series "kasan: assorted fixes and improvements" which does those things. - Some page allocator maintenance work from Kemeng Shi in the series "Two minor cleanups to break_down_buddy_pages". - In thes series "New selftest for mm" Breno Leitao has developed another MM self test which tickles a race we had between madvise() and page faults. - In the series "Add folio_end_read" Matthew Wilcox provides cleanups and an optimization to the core pagecache code. - Nhat Pham has added memcg accounting for hugetlb memory in the series "hugetlb memcg accounting". - Cleanups and rationalizations to the pagemap code from Lorenzo Stoakes, in the series "Abstract vma_merge() and split_vma()". - Audra Mitchell has fixed issues in the procfs page_owner code's new timestamping feature which was causing some misbehaviours. In the series "Fix page_owner's use of free timestamps". - Lorenzo Stoakes has fixed the handling of new mappings of sealed files in the series "permit write-sealed memfd read-only shared mappings". - Mike Kravetz has optimized the hugetlb vmemmap optimization in the series "Batch hugetlb vmemmap modification operations". - Some buffer_head folio conversions and cleanups from Matthew Wilcox in the series "Finish the create_empty_buffers() transition". - As a page allocator performance optimization Huang Ying has added automatic tuning to the allocator's per-cpu-pages feature, in the series "mm: PCP high auto-tuning". - Roman Gushchin has contributed the patchset "mm: improve performance of accounted kernel memory allocations" which improves their performance by ~30% as measured by a micro-benchmark. - folio conversions from Kefeng Wang in the series "mm: convert page cpupid functions to folios". - Some kmemleak fixups in Liu Shixin's series "Some bugfix about kmemleak". - Qi Zheng has improved our handling of memoryless nodes by keeping them off the allocation fallback list. This is done in the series "handle memoryless nodes more appropriately". - khugepaged conversions from Vishal Moola in the series "Some khugepaged folio conversions". -----BEGIN PGP SIGNATURE----- iHUEABYIAB0WIQTTMBEPP41GrTpTJgfdBJ7gKXxAjgUCZULEMwAKCRDdBJ7gKXxA jhQHAQCYpD3g849x69DmHnHWHm/EHQLvQmRMDeYZI+nx/sCJOwEAw4AKg0Oemv9y FgeUPAD1oasg6CP+INZvCj34waNxwAc= =E+Y4 -----END PGP SIGNATURE----- Merge tag 'mm-stable-2023-11-01-14-33' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Pull MM updates from Andrew Morton: "Many singleton patches against the MM code. The patch series which are included in this merge do the following: - Kemeng Shi has contributed some compation maintenance work in the series 'Fixes and cleanups to compaction' - Joel Fernandes has a patchset ('Optimize mremap during mutual alignment within PMD') which fixes an obscure issue with mremap()'s pagetable handling during a subsequent exec(), based upon an implementation which Linus suggested - More DAMON/DAMOS maintenance and feature work from SeongJae Park i the following patch series: mm/damon: misc fixups for documents, comments and its tracepoint mm/damon: add a tracepoint for damos apply target regions mm/damon: provide pseudo-moving sum based access rate mm/damon: implement DAMOS apply intervals mm/damon/core-test: Fix memory leaks in core-test mm/damon/sysfs-schemes: Do DAMOS tried regions update for only one apply interval - In the series 'Do not try to access unaccepted memory' Adrian Hunter provides some fixups for the recently-added 'unaccepted memory' feature. To increase the feature's checking coverage. 'Plug a few gaps where RAM is exposed without checking if it is unaccepted memory' - In the series 'cleanups for lockless slab shrink' Qi Zheng has done some maintenance work which is preparation for the lockless slab shrinking code - Qi Zheng has redone the earlier (and reverted) attempt to make slab shrinking lockless in the series 'use refcount+RCU method to implement lockless slab shrink' - David Hildenbrand contributes some maintenance work for the rmap code in the series 'Anon rmap cleanups' - Kefeng Wang does more folio conversions and some maintenance work in the migration code. Series 'mm: migrate: more folio conversion and unification' - Matthew Wilcox has fixed an issue in the buffer_head code which was causing long stalls under some heavy memory/IO loads. Some cleanups were added on the way. Series 'Add and use bdev_getblk()' - In the series 'Use nth_page() in place of direct struct page manipulation' Zi Yan has fixed a potential issue with the direct manipulation of hugetlb page frames - In the series 'mm: hugetlb: Skip initialization of gigantic tail struct pages if freed by HVO' has improved our handling of gigantic pages in the hugetlb vmmemmep optimizaton code. This provides significant boot time improvements when significant amounts of gigantic pages are in use - Matthew Wilcox has sent the series 'Small hugetlb cleanups' - code rationalization and folio conversions in the hugetlb code - Yin Fengwei has improved mlock()'s handling of large folios in the series 'support large folio for mlock' - In the series 'Expose swapcache stat for memcg v1' Liu Shixin has added statistics for memcg v1 users which are available (and useful) under memcg v2 - Florent Revest has enhanced the MDWE (Memory-Deny-Write-Executable) prctl so that userspace may direct the kernel to not automatically propagate the denial to child processes. The series is named 'MDWE without inheritance' - Kefeng Wang has provided the series 'mm: convert numa balancing functions to use a folio' which does what it says - In the series 'mm/ksm: add fork-exec support for prctl' Stefan Roesch makes is possible for a process to propagate KSM treatment across exec() - Huang Ying has enhanced memory tiering's calculation of memory distances. This is used to permit the dax/kmem driver to use 'high bandwidth memory' in addition to Optane Data Center Persistent Memory Modules (DCPMM). The series is named 'memory tiering: calculate abstract distance based on ACPI HMAT' - In the series 'Smart scanning mode for KSM' Stefan Roesch has optimized KSM by teaching it to retain and use some historical information from previous scans - Yosry Ahmed has fixed some inconsistencies in memcg statistics in the series 'mm: memcg: fix tracking of pending stats updates values' - In the series 'Implement IOCTL to get and optionally clear info about PTEs' Peter Xu has added an ioctl to /proc/<pid>/pagemap which permits us to atomically read-then-clear page softdirty state. This is mainly used by CRIU - Hugh Dickins contributed the series 'shmem,tmpfs: general maintenance', a bunch of relatively minor maintenance tweaks to this code - Matthew Wilcox has increased the use of the VMA lock over file-backed page faults in the series 'Handle more faults under the VMA lock'. Some rationalizations of the fault path became possible as a result - In the series 'mm/rmap: convert page_move_anon_rmap() to folio_move_anon_rmap()' David Hildenbrand has implemented some cleanups and folio conversions - In the series 'various improvements to the GUP interface' Lorenzo Stoakes has simplified and improved the GUP interface with an eye to providing groundwork for future improvements - Andrey Konovalov has sent along the series 'kasan: assorted fixes and improvements' which does those things - Some page allocator maintenance work from Kemeng Shi in the series 'Two minor cleanups to break_down_buddy_pages' - In thes series 'New selftest for mm' Breno Leitao has developed another MM self test which tickles a race we had between madvise() and page faults - In the series 'Add folio_end_read' Matthew Wilcox provides cleanups and an optimization to the core pagecache code - Nhat Pham has added memcg accounting for hugetlb memory in the series 'hugetlb memcg accounting' - Cleanups and rationalizations to the pagemap code from Lorenzo Stoakes, in the series 'Abstract vma_merge() and split_vma()' - Audra Mitchell has fixed issues in the procfs page_owner code's new timestamping feature which was causing some misbehaviours. In the series 'Fix page_owner's use of free timestamps' - Lorenzo Stoakes has fixed the handling of new mappings of sealed files in the series 'permit write-sealed memfd read-only shared mappings' - Mike Kravetz has optimized the hugetlb vmemmap optimization in the series 'Batch hugetlb vmemmap modification operations' - Some buffer_head folio conversions and cleanups from Matthew Wilcox in the series 'Finish the create_empty_buffers() transition' - As a page allocator performance optimization Huang Ying has added automatic tuning to the allocator's per-cpu-pages feature, in the series 'mm: PCP high auto-tuning' - Roman Gushchin has contributed the patchset 'mm: improve performance of accounted kernel memory allocations' which improves their performance by ~30% as measured by a micro-benchmark - folio conversions from Kefeng Wang in the series 'mm: convert page cpupid functions to folios' - Some kmemleak fixups in Liu Shixin's series 'Some bugfix about kmemleak' - Qi Zheng has improved our handling of memoryless nodes by keeping them off the allocation fallback list. This is done in the series 'handle memoryless nodes more appropriately' - khugepaged conversions from Vishal Moola in the series 'Some khugepaged folio conversions'" [ bcachefs conflicts with the dynamically allocated shrinkers have been resolved as per Stephen Rothwell in https://lore.kernel.org/all/20230913093553.4290421e@canb.auug.org.au/ with help from Qi Zheng. The clone3 test filtering conflict was half-arsed by yours truly ] * tag 'mm-stable-2023-11-01-14-33' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (406 commits) mm/damon/sysfs: update monitoring target regions for online input commit mm/damon/sysfs: remove requested targets when online-commit inputs selftests: add a sanity check for zswap Documentation: maple_tree: fix word spelling error mm/vmalloc: fix the unchecked dereference warning in vread_iter() zswap: export compression failure stats Documentation: ubsan: drop "the" from article title mempolicy: migration attempt to match interleave nodes mempolicy: mmap_lock is not needed while migrating folios mempolicy: alloc_pages_mpol() for NUMA policy without vma mm: add page_rmappable_folio() wrapper mempolicy: remove confusing MPOL_MF_LAZY dead code mempolicy: mpol_shared_policy_init() without pseudo-vma mempolicy trivia: use pgoff_t in shared mempolicy tree mempolicy trivia: slightly more consistent naming mempolicy trivia: delete those ancient pr_debug()s mempolicy: fix migrate_pages(2) syscall return nr_failed kernfs: drop shared NUMA mempolicy hooks hugetlbfs: drop shared NUMA mempolicy pretence mm/damon/sysfs-test: add a unit test for damon_sysfs_set_targets() ...
2023-11-02 22:38:47 -07:00
shrinker_free(bc->shrink);
/*
* The loop is needed to guard against racing with rehash:
*/
while (atomic_long_read(&bc->nr_keys)) {
rcu_read_lock();
tbl = rht_dereference_rcu(bc->table.tbl, &bc->table);
if (tbl) {
if (tbl->nest) {
/* wait for in progress rehash */
rcu_read_unlock();
mutex_lock(&bc->table.mutex);
mutex_unlock(&bc->table.mutex);
rcu_read_lock();
continue;
}
for (i = 0; i < tbl->size; i++)
while (pos = rht_ptr_rcu(&tbl->buckets[i]), !rht_is_a_nulls(pos)) {
ck = container_of(pos, struct bkey_cached, hash);
BUG_ON(!bkey_cached_evict(bc, ck));
kfree(ck->k);
kmem_cache_free(bch2_key_cache, ck);
}
}
rcu_read_unlock();
}
if (atomic_long_read(&bc->nr_dirty) &&
!bch2_journal_error(&c->journal) &&
test_bit(BCH_FS_was_rw, &c->flags))
panic("btree key cache shutdown error: nr_dirty nonzero (%li)\n",
atomic_long_read(&bc->nr_dirty));
if (atomic_long_read(&bc->nr_keys))
panic("btree key cache shutdown error: nr_keys nonzero (%li)\n",
atomic_long_read(&bc->nr_keys));
if (bc->table_init_done)
rhashtable_destroy(&bc->table);
rcu_pending_exit(&bc->pending[0]);
rcu_pending_exit(&bc->pending[1]);
free_percpu(bc->nr_pending);
}
void bch2_fs_btree_key_cache_init_early(struct btree_key_cache *c)
{
}
int bch2_fs_btree_key_cache_init(struct btree_key_cache *bc)
{
struct bch_fs *c = container_of(bc, struct bch_fs, btree_key_cache);
Many singleton patches against the MM code. The patch series which are included in this merge do the following: - Kemeng Shi has contributed some compation maintenance work in the series "Fixes and cleanups to compaction". - Joel Fernandes has a patchset ("Optimize mremap during mutual alignment within PMD") which fixes an obscure issue with mremap()'s pagetable handling during a subsequent exec(), based upon an implementation which Linus suggested. - More DAMON/DAMOS maintenance and feature work from SeongJae Park i the following patch series: mm/damon: misc fixups for documents, comments and its tracepoint mm/damon: add a tracepoint for damos apply target regions mm/damon: provide pseudo-moving sum based access rate mm/damon: implement DAMOS apply intervals mm/damon/core-test: Fix memory leaks in core-test mm/damon/sysfs-schemes: Do DAMOS tried regions update for only one apply interval - In the series "Do not try to access unaccepted memory" Adrian Hunter provides some fixups for the recently-added "unaccepted memory' feature. To increase the feature's checking coverage. "Plug a few gaps where RAM is exposed without checking if it is unaccepted memory". - In the series "cleanups for lockless slab shrink" Qi Zheng has done some maintenance work which is preparation for the lockless slab shrinking code. - Qi Zheng has redone the earlier (and reverted) attempt to make slab shrinking lockless in the series "use refcount+RCU method to implement lockless slab shrink". - David Hildenbrand contributes some maintenance work for the rmap code in the series "Anon rmap cleanups". - Kefeng Wang does more folio conversions and some maintenance work in the migration code. Series "mm: migrate: more folio conversion and unification". - Matthew Wilcox has fixed an issue in the buffer_head code which was causing long stalls under some heavy memory/IO loads. Some cleanups were added on the way. Series "Add and use bdev_getblk()". - In the series "Use nth_page() in place of direct struct page manipulation" Zi Yan has fixed a potential issue with the direct manipulation of hugetlb page frames. - In the series "mm: hugetlb: Skip initialization of gigantic tail struct pages if freed by HVO" has improved our handling of gigantic pages in the hugetlb vmmemmep optimizaton code. This provides significant boot time improvements when significant amounts of gigantic pages are in use. - Matthew Wilcox has sent the series "Small hugetlb cleanups" - code rationalization and folio conversions in the hugetlb code. - Yin Fengwei has improved mlock()'s handling of large folios in the series "support large folio for mlock" - In the series "Expose swapcache stat for memcg v1" Liu Shixin has added statistics for memcg v1 users which are available (and useful) under memcg v2. - Florent Revest has enhanced the MDWE (Memory-Deny-Write-Executable) prctl so that userspace may direct the kernel to not automatically propagate the denial to child processes. The series is named "MDWE without inheritance". - Kefeng Wang has provided the series "mm: convert numa balancing functions to use a folio" which does what it says. - In the series "mm/ksm: add fork-exec support for prctl" Stefan Roesch makes is possible for a process to propagate KSM treatment across exec(). - Huang Ying has enhanced memory tiering's calculation of memory distances. This is used to permit the dax/kmem driver to use "high bandwidth memory" in addition to Optane Data Center Persistent Memory Modules (DCPMM). The series is named "memory tiering: calculate abstract distance based on ACPI HMAT" - In the series "Smart scanning mode for KSM" Stefan Roesch has optimized KSM by teaching it to retain and use some historical information from previous scans. - Yosry Ahmed has fixed some inconsistencies in memcg statistics in the series "mm: memcg: fix tracking of pending stats updates values". - In the series "Implement IOCTL to get and optionally clear info about PTEs" Peter Xu has added an ioctl to /proc/<pid>/pagemap which permits us to atomically read-then-clear page softdirty state. This is mainly used by CRIU. - Hugh Dickins contributed the series "shmem,tmpfs: general maintenance" - a bunch of relatively minor maintenance tweaks to this code. - Matthew Wilcox has increased the use of the VMA lock over file-backed page faults in the series "Handle more faults under the VMA lock". Some rationalizations of the fault path became possible as a result. - In the series "mm/rmap: convert page_move_anon_rmap() to folio_move_anon_rmap()" David Hildenbrand has implemented some cleanups and folio conversions. - In the series "various improvements to the GUP interface" Lorenzo Stoakes has simplified and improved the GUP interface with an eye to providing groundwork for future improvements. - Andrey Konovalov has sent along the series "kasan: assorted fixes and improvements" which does those things. - Some page allocator maintenance work from Kemeng Shi in the series "Two minor cleanups to break_down_buddy_pages". - In thes series "New selftest for mm" Breno Leitao has developed another MM self test which tickles a race we had between madvise() and page faults. - In the series "Add folio_end_read" Matthew Wilcox provides cleanups and an optimization to the core pagecache code. - Nhat Pham has added memcg accounting for hugetlb memory in the series "hugetlb memcg accounting". - Cleanups and rationalizations to the pagemap code from Lorenzo Stoakes, in the series "Abstract vma_merge() and split_vma()". - Audra Mitchell has fixed issues in the procfs page_owner code's new timestamping feature which was causing some misbehaviours. In the series "Fix page_owner's use of free timestamps". - Lorenzo Stoakes has fixed the handling of new mappings of sealed files in the series "permit write-sealed memfd read-only shared mappings". - Mike Kravetz has optimized the hugetlb vmemmap optimization in the series "Batch hugetlb vmemmap modification operations". - Some buffer_head folio conversions and cleanups from Matthew Wilcox in the series "Finish the create_empty_buffers() transition". - As a page allocator performance optimization Huang Ying has added automatic tuning to the allocator's per-cpu-pages feature, in the series "mm: PCP high auto-tuning". - Roman Gushchin has contributed the patchset "mm: improve performance of accounted kernel memory allocations" which improves their performance by ~30% as measured by a micro-benchmark. - folio conversions from Kefeng Wang in the series "mm: convert page cpupid functions to folios". - Some kmemleak fixups in Liu Shixin's series "Some bugfix about kmemleak". - Qi Zheng has improved our handling of memoryless nodes by keeping them off the allocation fallback list. This is done in the series "handle memoryless nodes more appropriately". - khugepaged conversions from Vishal Moola in the series "Some khugepaged folio conversions". -----BEGIN PGP SIGNATURE----- iHUEABYIAB0WIQTTMBEPP41GrTpTJgfdBJ7gKXxAjgUCZULEMwAKCRDdBJ7gKXxA jhQHAQCYpD3g849x69DmHnHWHm/EHQLvQmRMDeYZI+nx/sCJOwEAw4AKg0Oemv9y FgeUPAD1oasg6CP+INZvCj34waNxwAc= =E+Y4 -----END PGP SIGNATURE----- Merge tag 'mm-stable-2023-11-01-14-33' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Pull MM updates from Andrew Morton: "Many singleton patches against the MM code. The patch series which are included in this merge do the following: - Kemeng Shi has contributed some compation maintenance work in the series 'Fixes and cleanups to compaction' - Joel Fernandes has a patchset ('Optimize mremap during mutual alignment within PMD') which fixes an obscure issue with mremap()'s pagetable handling during a subsequent exec(), based upon an implementation which Linus suggested - More DAMON/DAMOS maintenance and feature work from SeongJae Park i the following patch series: mm/damon: misc fixups for documents, comments and its tracepoint mm/damon: add a tracepoint for damos apply target regions mm/damon: provide pseudo-moving sum based access rate mm/damon: implement DAMOS apply intervals mm/damon/core-test: Fix memory leaks in core-test mm/damon/sysfs-schemes: Do DAMOS tried regions update for only one apply interval - In the series 'Do not try to access unaccepted memory' Adrian Hunter provides some fixups for the recently-added 'unaccepted memory' feature. To increase the feature's checking coverage. 'Plug a few gaps where RAM is exposed without checking if it is unaccepted memory' - In the series 'cleanups for lockless slab shrink' Qi Zheng has done some maintenance work which is preparation for the lockless slab shrinking code - Qi Zheng has redone the earlier (and reverted) attempt to make slab shrinking lockless in the series 'use refcount+RCU method to implement lockless slab shrink' - David Hildenbrand contributes some maintenance work for the rmap code in the series 'Anon rmap cleanups' - Kefeng Wang does more folio conversions and some maintenance work in the migration code. Series 'mm: migrate: more folio conversion and unification' - Matthew Wilcox has fixed an issue in the buffer_head code which was causing long stalls under some heavy memory/IO loads. Some cleanups were added on the way. Series 'Add and use bdev_getblk()' - In the series 'Use nth_page() in place of direct struct page manipulation' Zi Yan has fixed a potential issue with the direct manipulation of hugetlb page frames - In the series 'mm: hugetlb: Skip initialization of gigantic tail struct pages if freed by HVO' has improved our handling of gigantic pages in the hugetlb vmmemmep optimizaton code. This provides significant boot time improvements when significant amounts of gigantic pages are in use - Matthew Wilcox has sent the series 'Small hugetlb cleanups' - code rationalization and folio conversions in the hugetlb code - Yin Fengwei has improved mlock()'s handling of large folios in the series 'support large folio for mlock' - In the series 'Expose swapcache stat for memcg v1' Liu Shixin has added statistics for memcg v1 users which are available (and useful) under memcg v2 - Florent Revest has enhanced the MDWE (Memory-Deny-Write-Executable) prctl so that userspace may direct the kernel to not automatically propagate the denial to child processes. The series is named 'MDWE without inheritance' - Kefeng Wang has provided the series 'mm: convert numa balancing functions to use a folio' which does what it says - In the series 'mm/ksm: add fork-exec support for prctl' Stefan Roesch makes is possible for a process to propagate KSM treatment across exec() - Huang Ying has enhanced memory tiering's calculation of memory distances. This is used to permit the dax/kmem driver to use 'high bandwidth memory' in addition to Optane Data Center Persistent Memory Modules (DCPMM). The series is named 'memory tiering: calculate abstract distance based on ACPI HMAT' - In the series 'Smart scanning mode for KSM' Stefan Roesch has optimized KSM by teaching it to retain and use some historical information from previous scans - Yosry Ahmed has fixed some inconsistencies in memcg statistics in the series 'mm: memcg: fix tracking of pending stats updates values' - In the series 'Implement IOCTL to get and optionally clear info about PTEs' Peter Xu has added an ioctl to /proc/<pid>/pagemap which permits us to atomically read-then-clear page softdirty state. This is mainly used by CRIU - Hugh Dickins contributed the series 'shmem,tmpfs: general maintenance', a bunch of relatively minor maintenance tweaks to this code - Matthew Wilcox has increased the use of the VMA lock over file-backed page faults in the series 'Handle more faults under the VMA lock'. Some rationalizations of the fault path became possible as a result - In the series 'mm/rmap: convert page_move_anon_rmap() to folio_move_anon_rmap()' David Hildenbrand has implemented some cleanups and folio conversions - In the series 'various improvements to the GUP interface' Lorenzo Stoakes has simplified and improved the GUP interface with an eye to providing groundwork for future improvements - Andrey Konovalov has sent along the series 'kasan: assorted fixes and improvements' which does those things - Some page allocator maintenance work from Kemeng Shi in the series 'Two minor cleanups to break_down_buddy_pages' - In thes series 'New selftest for mm' Breno Leitao has developed another MM self test which tickles a race we had between madvise() and page faults - In the series 'Add folio_end_read' Matthew Wilcox provides cleanups and an optimization to the core pagecache code - Nhat Pham has added memcg accounting for hugetlb memory in the series 'hugetlb memcg accounting' - Cleanups and rationalizations to the pagemap code from Lorenzo Stoakes, in the series 'Abstract vma_merge() and split_vma()' - Audra Mitchell has fixed issues in the procfs page_owner code's new timestamping feature which was causing some misbehaviours. In the series 'Fix page_owner's use of free timestamps' - Lorenzo Stoakes has fixed the handling of new mappings of sealed files in the series 'permit write-sealed memfd read-only shared mappings' - Mike Kravetz has optimized the hugetlb vmemmap optimization in the series 'Batch hugetlb vmemmap modification operations' - Some buffer_head folio conversions and cleanups from Matthew Wilcox in the series 'Finish the create_empty_buffers() transition' - As a page allocator performance optimization Huang Ying has added automatic tuning to the allocator's per-cpu-pages feature, in the series 'mm: PCP high auto-tuning' - Roman Gushchin has contributed the patchset 'mm: improve performance of accounted kernel memory allocations' which improves their performance by ~30% as measured by a micro-benchmark - folio conversions from Kefeng Wang in the series 'mm: convert page cpupid functions to folios' - Some kmemleak fixups in Liu Shixin's series 'Some bugfix about kmemleak' - Qi Zheng has improved our handling of memoryless nodes by keeping them off the allocation fallback list. This is done in the series 'handle memoryless nodes more appropriately' - khugepaged conversions from Vishal Moola in the series 'Some khugepaged folio conversions'" [ bcachefs conflicts with the dynamically allocated shrinkers have been resolved as per Stephen Rothwell in https://lore.kernel.org/all/20230913093553.4290421e@canb.auug.org.au/ with help from Qi Zheng. The clone3 test filtering conflict was half-arsed by yours truly ] * tag 'mm-stable-2023-11-01-14-33' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (406 commits) mm/damon/sysfs: update monitoring target regions for online input commit mm/damon/sysfs: remove requested targets when online-commit inputs selftests: add a sanity check for zswap Documentation: maple_tree: fix word spelling error mm/vmalloc: fix the unchecked dereference warning in vread_iter() zswap: export compression failure stats Documentation: ubsan: drop "the" from article title mempolicy: migration attempt to match interleave nodes mempolicy: mmap_lock is not needed while migrating folios mempolicy: alloc_pages_mpol() for NUMA policy without vma mm: add page_rmappable_folio() wrapper mempolicy: remove confusing MPOL_MF_LAZY dead code mempolicy: mpol_shared_policy_init() without pseudo-vma mempolicy trivia: use pgoff_t in shared mempolicy tree mempolicy trivia: slightly more consistent naming mempolicy trivia: delete those ancient pr_debug()s mempolicy: fix migrate_pages(2) syscall return nr_failed kernfs: drop shared NUMA mempolicy hooks hugetlbfs: drop shared NUMA mempolicy pretence mm/damon/sysfs-test: add a unit test for damon_sysfs_set_targets() ...
2023-11-02 22:38:47 -07:00
struct shrinker *shrink;
bc->nr_pending = alloc_percpu(size_t);
if (!bc->nr_pending)
return -BCH_ERR_ENOMEM_fs_btree_cache_init;
if (rcu_pending_init(&bc->pending[0], &c->btree_trans_barrier, __bkey_cached_free) ||
rcu_pending_init(&bc->pending[1], &c->btree_trans_barrier, __bkey_cached_free))
return -BCH_ERR_ENOMEM_fs_btree_cache_init;
if (rhashtable_init(&bc->table, &bch2_btree_key_cache_params))
return -BCH_ERR_ENOMEM_fs_btree_cache_init;
bc->table_init_done = true;
Second bcachefs pull request for 6.7-rc1 Here's the second big bcachefs pull request. This brings your tree up to date with my master branch, which is what existing bcachefs users are currently running. All but the last few patches have been in linux-next, those being small fixes. Test results from my dashboard: https://evilpiepirate.org/~testdashboard/ci?commit=c7046ed0cf9bb33599aa7e72e7b67bba4be42d64 New features: - rebalance_work btree (and metadata version 1.3): the rebalance thread no longer has to scan to find extents that need processing - big scalability improvement. - sb_errors superblock section: this adds counters for each fsck error type, since filesystem creation, along with the date of the most recent error. It'll get us better bug reports (since users do not typically report errors that fsck was able to fix), and I might add telemetry for this in the future. Fixes include: - multiple snapshot deletion fixes - members_v2 fixups - deleted_inodes btree fixes - copygc thread no longer spins when a device is full but has no fragmented buckets (i.e. rebalance needs to move data around instead) - a fix for a memory reclaim issue with the btree key cache: we're now careful not to hold the srcu read lock that blocks key cache reclaim for too long - an early allocator locking fix, from Brian - endianness fixes, from Brian - CONFIG_BCACHEFS_DEBUG_TRANSACTIONS no longer defaults to y, a big performance improvement on multithreaded workloads -----BEGIN PGP SIGNATURE----- iQIzBAABCgAdFiEEKnAFLkS8Qha+jvQrE6szbY3KbnYFAmVH9xYACgkQE6szbY3K bnahLRAAiNRZL73SQ+MW79o4yPqGwt0Eyy/mvoiGpZf1B8uXp0oZ55j2w3l887Uf LeM03mInAYCPdyp/d4vxqIr96j9BODmRRl8sEkkGdJDzokLG+22F0ovOe45KWTxL kBoNdng/O/oeOe/1K7taP3KzBvMx2nOF6oA+xfgyCjECMArAIXek0iocyEUR4Ywd vGKhLNn1k2c+94wacnDYwjjdcLBxoqxsFXlpu6V0BcaY+DX4J3aBaGmj75KEoCI0 VbBOzxrOO4QzJrzW2+hxZZWgGyvReCkBJvqfORfuPxiSbFobTim10MdfZOAMQA1U Xr1FTEpK1wMX0/pPVgZRqaOsttC+yc/SsfPNgSxybgHPbDlMLaakDHjvYssbKOYG urDWSMG5yCsktSLj95SXsvUFKZaZFD72SKBNdgdt/nZjwTHuNQ7IkdrMwIrCQ/PT Ifn50UrR/Ahd8RAd5tyNCPw6U9VfwnxACSNl2KA7ONKpvHb+gSt1JsJTDyz1+gN9 nFVrw1SHKQ6EIV6XhVon/5DEuRTzqoYGWoN08FHEUq9fBlvnVpmbJErCQMplOjz9 OQnAfpJH4YqkpXyjFAjP1V0An+RUn8QvDgXNqC9TyvCYuOliVFuil4y7/c+7oIQU NEoz+jVLenqsGOGAbduI4/Q567COojRgwEvbebSIxSImXuhCNj4= =Lo4N -----END PGP SIGNATURE----- Merge tag 'bcachefs-2023-11-5' of https://evilpiepirate.org/git/bcachefs Pull more bcachefs updates from Kent Overstreet: "Here's the second big bcachefs pull request. This brings your tree up to date with my master branch, which is what existing bcachefs users are currently running. New features: - rebalance_work btree (and metadata version 1.3): the rebalance thread no longer has to scan to find extents that need processing - big scalability improvement. - sb_errors superblock section: this adds counters for each fsck error type, since filesystem creation, along with the date of the most recent error. It'll get us better bug reports (since users do not typically report errors that fsck was able to fix), and I might add telemetry for this in the future. Fixes include: - multiple snapshot deletion fixes - members_v2 fixups - deleted_inodes btree fixes - copygc thread no longer spins when a device is full but has no fragmented buckets (i.e. rebalance needs to move data around instead) - a fix for a memory reclaim issue with the btree key cache: we're now careful not to hold the srcu read lock that blocks key cache reclaim for too long - an early allocator locking fix, from Brian - endianness fixes, from Brian - CONFIG_BCACHEFS_DEBUG_TRANSACTIONS no longer defaults to y, a big performance improvement on multithreaded workloads" * tag 'bcachefs-2023-11-5' of https://evilpiepirate.org/git/bcachefs: (70 commits) bcachefs: Improve stripe checksum error message bcachefs: Simplify, fix bch2_backpointer_get_key() bcachefs: kill thing_it_points_to arg to backpointer_not_found() bcachefs: bch2_ec_read_extent() now takes btree_trans bcachefs: bch2_stripe_to_text() now prints ptr gens bcachefs: Don't iterate over journal entries just for btree roots bcachefs: Break up bch2_journal_write() bcachefs: Replace ERANGE with private error codes bcachefs: bkey_copy() is no longer a macro bcachefs: x-macro-ify inode flags enum bcachefs: Convert bch2_fs_open() to darray bcachefs: Move __bch2_members_v2_get_mut to sb-members.h bcachefs: bch2_prt_datetime() bcachefs: CONFIG_BCACHEFS_DEBUG_TRANSACTIONS no longer defaults to y bcachefs: Add a comment for BTREE_INSERT_NOJOURNAL usage bcachefs: rebalance_work btree is not a snapshots btree bcachefs: Add missing printk newlines bcachefs: Fix recovery when forced to use JSET_NO_FLUSH journal entry bcachefs: .get_parent() should return an error pointer bcachefs: Fix bch2_delete_dead_inodes() ...
2023-11-07 12:38:38 -07:00
shrink = shrinker_alloc(0, "%s-btree_key_cache", c->name);
Many singleton patches against the MM code. The patch series which are included in this merge do the following: - Kemeng Shi has contributed some compation maintenance work in the series "Fixes and cleanups to compaction". - Joel Fernandes has a patchset ("Optimize mremap during mutual alignment within PMD") which fixes an obscure issue with mremap()'s pagetable handling during a subsequent exec(), based upon an implementation which Linus suggested. - More DAMON/DAMOS maintenance and feature work from SeongJae Park i the following patch series: mm/damon: misc fixups for documents, comments and its tracepoint mm/damon: add a tracepoint for damos apply target regions mm/damon: provide pseudo-moving sum based access rate mm/damon: implement DAMOS apply intervals mm/damon/core-test: Fix memory leaks in core-test mm/damon/sysfs-schemes: Do DAMOS tried regions update for only one apply interval - In the series "Do not try to access unaccepted memory" Adrian Hunter provides some fixups for the recently-added "unaccepted memory' feature. To increase the feature's checking coverage. "Plug a few gaps where RAM is exposed without checking if it is unaccepted memory". - In the series "cleanups for lockless slab shrink" Qi Zheng has done some maintenance work which is preparation for the lockless slab shrinking code. - Qi Zheng has redone the earlier (and reverted) attempt to make slab shrinking lockless in the series "use refcount+RCU method to implement lockless slab shrink". - David Hildenbrand contributes some maintenance work for the rmap code in the series "Anon rmap cleanups". - Kefeng Wang does more folio conversions and some maintenance work in the migration code. Series "mm: migrate: more folio conversion and unification". - Matthew Wilcox has fixed an issue in the buffer_head code which was causing long stalls under some heavy memory/IO loads. Some cleanups were added on the way. Series "Add and use bdev_getblk()". - In the series "Use nth_page() in place of direct struct page manipulation" Zi Yan has fixed a potential issue with the direct manipulation of hugetlb page frames. - In the series "mm: hugetlb: Skip initialization of gigantic tail struct pages if freed by HVO" has improved our handling of gigantic pages in the hugetlb vmmemmep optimizaton code. This provides significant boot time improvements when significant amounts of gigantic pages are in use. - Matthew Wilcox has sent the series "Small hugetlb cleanups" - code rationalization and folio conversions in the hugetlb code. - Yin Fengwei has improved mlock()'s handling of large folios in the series "support large folio for mlock" - In the series "Expose swapcache stat for memcg v1" Liu Shixin has added statistics for memcg v1 users which are available (and useful) under memcg v2. - Florent Revest has enhanced the MDWE (Memory-Deny-Write-Executable) prctl so that userspace may direct the kernel to not automatically propagate the denial to child processes. The series is named "MDWE without inheritance". - Kefeng Wang has provided the series "mm: convert numa balancing functions to use a folio" which does what it says. - In the series "mm/ksm: add fork-exec support for prctl" Stefan Roesch makes is possible for a process to propagate KSM treatment across exec(). - Huang Ying has enhanced memory tiering's calculation of memory distances. This is used to permit the dax/kmem driver to use "high bandwidth memory" in addition to Optane Data Center Persistent Memory Modules (DCPMM). The series is named "memory tiering: calculate abstract distance based on ACPI HMAT" - In the series "Smart scanning mode for KSM" Stefan Roesch has optimized KSM by teaching it to retain and use some historical information from previous scans. - Yosry Ahmed has fixed some inconsistencies in memcg statistics in the series "mm: memcg: fix tracking of pending stats updates values". - In the series "Implement IOCTL to get and optionally clear info about PTEs" Peter Xu has added an ioctl to /proc/<pid>/pagemap which permits us to atomically read-then-clear page softdirty state. This is mainly used by CRIU. - Hugh Dickins contributed the series "shmem,tmpfs: general maintenance" - a bunch of relatively minor maintenance tweaks to this code. - Matthew Wilcox has increased the use of the VMA lock over file-backed page faults in the series "Handle more faults under the VMA lock". Some rationalizations of the fault path became possible as a result. - In the series "mm/rmap: convert page_move_anon_rmap() to folio_move_anon_rmap()" David Hildenbrand has implemented some cleanups and folio conversions. - In the series "various improvements to the GUP interface" Lorenzo Stoakes has simplified and improved the GUP interface with an eye to providing groundwork for future improvements. - Andrey Konovalov has sent along the series "kasan: assorted fixes and improvements" which does those things. - Some page allocator maintenance work from Kemeng Shi in the series "Two minor cleanups to break_down_buddy_pages". - In thes series "New selftest for mm" Breno Leitao has developed another MM self test which tickles a race we had between madvise() and page faults. - In the series "Add folio_end_read" Matthew Wilcox provides cleanups and an optimization to the core pagecache code. - Nhat Pham has added memcg accounting for hugetlb memory in the series "hugetlb memcg accounting". - Cleanups and rationalizations to the pagemap code from Lorenzo Stoakes, in the series "Abstract vma_merge() and split_vma()". - Audra Mitchell has fixed issues in the procfs page_owner code's new timestamping feature which was causing some misbehaviours. In the series "Fix page_owner's use of free timestamps". - Lorenzo Stoakes has fixed the handling of new mappings of sealed files in the series "permit write-sealed memfd read-only shared mappings". - Mike Kravetz has optimized the hugetlb vmemmap optimization in the series "Batch hugetlb vmemmap modification operations". - Some buffer_head folio conversions and cleanups from Matthew Wilcox in the series "Finish the create_empty_buffers() transition". - As a page allocator performance optimization Huang Ying has added automatic tuning to the allocator's per-cpu-pages feature, in the series "mm: PCP high auto-tuning". - Roman Gushchin has contributed the patchset "mm: improve performance of accounted kernel memory allocations" which improves their performance by ~30% as measured by a micro-benchmark. - folio conversions from Kefeng Wang in the series "mm: convert page cpupid functions to folios". - Some kmemleak fixups in Liu Shixin's series "Some bugfix about kmemleak". - Qi Zheng has improved our handling of memoryless nodes by keeping them off the allocation fallback list. This is done in the series "handle memoryless nodes more appropriately". - khugepaged conversions from Vishal Moola in the series "Some khugepaged folio conversions". -----BEGIN PGP SIGNATURE----- iHUEABYIAB0WIQTTMBEPP41GrTpTJgfdBJ7gKXxAjgUCZULEMwAKCRDdBJ7gKXxA jhQHAQCYpD3g849x69DmHnHWHm/EHQLvQmRMDeYZI+nx/sCJOwEAw4AKg0Oemv9y FgeUPAD1oasg6CP+INZvCj34waNxwAc= =E+Y4 -----END PGP SIGNATURE----- Merge tag 'mm-stable-2023-11-01-14-33' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Pull MM updates from Andrew Morton: "Many singleton patches against the MM code. The patch series which are included in this merge do the following: - Kemeng Shi has contributed some compation maintenance work in the series 'Fixes and cleanups to compaction' - Joel Fernandes has a patchset ('Optimize mremap during mutual alignment within PMD') which fixes an obscure issue with mremap()'s pagetable handling during a subsequent exec(), based upon an implementation which Linus suggested - More DAMON/DAMOS maintenance and feature work from SeongJae Park i the following patch series: mm/damon: misc fixups for documents, comments and its tracepoint mm/damon: add a tracepoint for damos apply target regions mm/damon: provide pseudo-moving sum based access rate mm/damon: implement DAMOS apply intervals mm/damon/core-test: Fix memory leaks in core-test mm/damon/sysfs-schemes: Do DAMOS tried regions update for only one apply interval - In the series 'Do not try to access unaccepted memory' Adrian Hunter provides some fixups for the recently-added 'unaccepted memory' feature. To increase the feature's checking coverage. 'Plug a few gaps where RAM is exposed without checking if it is unaccepted memory' - In the series 'cleanups for lockless slab shrink' Qi Zheng has done some maintenance work which is preparation for the lockless slab shrinking code - Qi Zheng has redone the earlier (and reverted) attempt to make slab shrinking lockless in the series 'use refcount+RCU method to implement lockless slab shrink' - David Hildenbrand contributes some maintenance work for the rmap code in the series 'Anon rmap cleanups' - Kefeng Wang does more folio conversions and some maintenance work in the migration code. Series 'mm: migrate: more folio conversion and unification' - Matthew Wilcox has fixed an issue in the buffer_head code which was causing long stalls under some heavy memory/IO loads. Some cleanups were added on the way. Series 'Add and use bdev_getblk()' - In the series 'Use nth_page() in place of direct struct page manipulation' Zi Yan has fixed a potential issue with the direct manipulation of hugetlb page frames - In the series 'mm: hugetlb: Skip initialization of gigantic tail struct pages if freed by HVO' has improved our handling of gigantic pages in the hugetlb vmmemmep optimizaton code. This provides significant boot time improvements when significant amounts of gigantic pages are in use - Matthew Wilcox has sent the series 'Small hugetlb cleanups' - code rationalization and folio conversions in the hugetlb code - Yin Fengwei has improved mlock()'s handling of large folios in the series 'support large folio for mlock' - In the series 'Expose swapcache stat for memcg v1' Liu Shixin has added statistics for memcg v1 users which are available (and useful) under memcg v2 - Florent Revest has enhanced the MDWE (Memory-Deny-Write-Executable) prctl so that userspace may direct the kernel to not automatically propagate the denial to child processes. The series is named 'MDWE without inheritance' - Kefeng Wang has provided the series 'mm: convert numa balancing functions to use a folio' which does what it says - In the series 'mm/ksm: add fork-exec support for prctl' Stefan Roesch makes is possible for a process to propagate KSM treatment across exec() - Huang Ying has enhanced memory tiering's calculation of memory distances. This is used to permit the dax/kmem driver to use 'high bandwidth memory' in addition to Optane Data Center Persistent Memory Modules (DCPMM). The series is named 'memory tiering: calculate abstract distance based on ACPI HMAT' - In the series 'Smart scanning mode for KSM' Stefan Roesch has optimized KSM by teaching it to retain and use some historical information from previous scans - Yosry Ahmed has fixed some inconsistencies in memcg statistics in the series 'mm: memcg: fix tracking of pending stats updates values' - In the series 'Implement IOCTL to get and optionally clear info about PTEs' Peter Xu has added an ioctl to /proc/<pid>/pagemap which permits us to atomically read-then-clear page softdirty state. This is mainly used by CRIU - Hugh Dickins contributed the series 'shmem,tmpfs: general maintenance', a bunch of relatively minor maintenance tweaks to this code - Matthew Wilcox has increased the use of the VMA lock over file-backed page faults in the series 'Handle more faults under the VMA lock'. Some rationalizations of the fault path became possible as a result - In the series 'mm/rmap: convert page_move_anon_rmap() to folio_move_anon_rmap()' David Hildenbrand has implemented some cleanups and folio conversions - In the series 'various improvements to the GUP interface' Lorenzo Stoakes has simplified and improved the GUP interface with an eye to providing groundwork for future improvements - Andrey Konovalov has sent along the series 'kasan: assorted fixes and improvements' which does those things - Some page allocator maintenance work from Kemeng Shi in the series 'Two minor cleanups to break_down_buddy_pages' - In thes series 'New selftest for mm' Breno Leitao has developed another MM self test which tickles a race we had between madvise() and page faults - In the series 'Add folio_end_read' Matthew Wilcox provides cleanups and an optimization to the core pagecache code - Nhat Pham has added memcg accounting for hugetlb memory in the series 'hugetlb memcg accounting' - Cleanups and rationalizations to the pagemap code from Lorenzo Stoakes, in the series 'Abstract vma_merge() and split_vma()' - Audra Mitchell has fixed issues in the procfs page_owner code's new timestamping feature which was causing some misbehaviours. In the series 'Fix page_owner's use of free timestamps' - Lorenzo Stoakes has fixed the handling of new mappings of sealed files in the series 'permit write-sealed memfd read-only shared mappings' - Mike Kravetz has optimized the hugetlb vmemmap optimization in the series 'Batch hugetlb vmemmap modification operations' - Some buffer_head folio conversions and cleanups from Matthew Wilcox in the series 'Finish the create_empty_buffers() transition' - As a page allocator performance optimization Huang Ying has added automatic tuning to the allocator's per-cpu-pages feature, in the series 'mm: PCP high auto-tuning' - Roman Gushchin has contributed the patchset 'mm: improve performance of accounted kernel memory allocations' which improves their performance by ~30% as measured by a micro-benchmark - folio conversions from Kefeng Wang in the series 'mm: convert page cpupid functions to folios' - Some kmemleak fixups in Liu Shixin's series 'Some bugfix about kmemleak' - Qi Zheng has improved our handling of memoryless nodes by keeping them off the allocation fallback list. This is done in the series 'handle memoryless nodes more appropriately' - khugepaged conversions from Vishal Moola in the series 'Some khugepaged folio conversions'" [ bcachefs conflicts with the dynamically allocated shrinkers have been resolved as per Stephen Rothwell in https://lore.kernel.org/all/20230913093553.4290421e@canb.auug.org.au/ with help from Qi Zheng. The clone3 test filtering conflict was half-arsed by yours truly ] * tag 'mm-stable-2023-11-01-14-33' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (406 commits) mm/damon/sysfs: update monitoring target regions for online input commit mm/damon/sysfs: remove requested targets when online-commit inputs selftests: add a sanity check for zswap Documentation: maple_tree: fix word spelling error mm/vmalloc: fix the unchecked dereference warning in vread_iter() zswap: export compression failure stats Documentation: ubsan: drop "the" from article title mempolicy: migration attempt to match interleave nodes mempolicy: mmap_lock is not needed while migrating folios mempolicy: alloc_pages_mpol() for NUMA policy without vma mm: add page_rmappable_folio() wrapper mempolicy: remove confusing MPOL_MF_LAZY dead code mempolicy: mpol_shared_policy_init() without pseudo-vma mempolicy trivia: use pgoff_t in shared mempolicy tree mempolicy trivia: slightly more consistent naming mempolicy trivia: delete those ancient pr_debug()s mempolicy: fix migrate_pages(2) syscall return nr_failed kernfs: drop shared NUMA mempolicy hooks hugetlbfs: drop shared NUMA mempolicy pretence mm/damon/sysfs-test: add a unit test for damon_sysfs_set_targets() ...
2023-11-02 22:38:47 -07:00
if (!shrink)
return -BCH_ERR_ENOMEM_fs_btree_cache_init;
Many singleton patches against the MM code. The patch series which are included in this merge do the following: - Kemeng Shi has contributed some compation maintenance work in the series "Fixes and cleanups to compaction". - Joel Fernandes has a patchset ("Optimize mremap during mutual alignment within PMD") which fixes an obscure issue with mremap()'s pagetable handling during a subsequent exec(), based upon an implementation which Linus suggested. - More DAMON/DAMOS maintenance and feature work from SeongJae Park i the following patch series: mm/damon: misc fixups for documents, comments and its tracepoint mm/damon: add a tracepoint for damos apply target regions mm/damon: provide pseudo-moving sum based access rate mm/damon: implement DAMOS apply intervals mm/damon/core-test: Fix memory leaks in core-test mm/damon/sysfs-schemes: Do DAMOS tried regions update for only one apply interval - In the series "Do not try to access unaccepted memory" Adrian Hunter provides some fixups for the recently-added "unaccepted memory' feature. To increase the feature's checking coverage. "Plug a few gaps where RAM is exposed without checking if it is unaccepted memory". - In the series "cleanups for lockless slab shrink" Qi Zheng has done some maintenance work which is preparation for the lockless slab shrinking code. - Qi Zheng has redone the earlier (and reverted) attempt to make slab shrinking lockless in the series "use refcount+RCU method to implement lockless slab shrink". - David Hildenbrand contributes some maintenance work for the rmap code in the series "Anon rmap cleanups". - Kefeng Wang does more folio conversions and some maintenance work in the migration code. Series "mm: migrate: more folio conversion and unification". - Matthew Wilcox has fixed an issue in the buffer_head code which was causing long stalls under some heavy memory/IO loads. Some cleanups were added on the way. Series "Add and use bdev_getblk()". - In the series "Use nth_page() in place of direct struct page manipulation" Zi Yan has fixed a potential issue with the direct manipulation of hugetlb page frames. - In the series "mm: hugetlb: Skip initialization of gigantic tail struct pages if freed by HVO" has improved our handling of gigantic pages in the hugetlb vmmemmep optimizaton code. This provides significant boot time improvements when significant amounts of gigantic pages are in use. - Matthew Wilcox has sent the series "Small hugetlb cleanups" - code rationalization and folio conversions in the hugetlb code. - Yin Fengwei has improved mlock()'s handling of large folios in the series "support large folio for mlock" - In the series "Expose swapcache stat for memcg v1" Liu Shixin has added statistics for memcg v1 users which are available (and useful) under memcg v2. - Florent Revest has enhanced the MDWE (Memory-Deny-Write-Executable) prctl so that userspace may direct the kernel to not automatically propagate the denial to child processes. The series is named "MDWE without inheritance". - Kefeng Wang has provided the series "mm: convert numa balancing functions to use a folio" which does what it says. - In the series "mm/ksm: add fork-exec support for prctl" Stefan Roesch makes is possible for a process to propagate KSM treatment across exec(). - Huang Ying has enhanced memory tiering's calculation of memory distances. This is used to permit the dax/kmem driver to use "high bandwidth memory" in addition to Optane Data Center Persistent Memory Modules (DCPMM). The series is named "memory tiering: calculate abstract distance based on ACPI HMAT" - In the series "Smart scanning mode for KSM" Stefan Roesch has optimized KSM by teaching it to retain and use some historical information from previous scans. - Yosry Ahmed has fixed some inconsistencies in memcg statistics in the series "mm: memcg: fix tracking of pending stats updates values". - In the series "Implement IOCTL to get and optionally clear info about PTEs" Peter Xu has added an ioctl to /proc/<pid>/pagemap which permits us to atomically read-then-clear page softdirty state. This is mainly used by CRIU. - Hugh Dickins contributed the series "shmem,tmpfs: general maintenance" - a bunch of relatively minor maintenance tweaks to this code. - Matthew Wilcox has increased the use of the VMA lock over file-backed page faults in the series "Handle more faults under the VMA lock". Some rationalizations of the fault path became possible as a result. - In the series "mm/rmap: convert page_move_anon_rmap() to folio_move_anon_rmap()" David Hildenbrand has implemented some cleanups and folio conversions. - In the series "various improvements to the GUP interface" Lorenzo Stoakes has simplified and improved the GUP interface with an eye to providing groundwork for future improvements. - Andrey Konovalov has sent along the series "kasan: assorted fixes and improvements" which does those things. - Some page allocator maintenance work from Kemeng Shi in the series "Two minor cleanups to break_down_buddy_pages". - In thes series "New selftest for mm" Breno Leitao has developed another MM self test which tickles a race we had between madvise() and page faults. - In the series "Add folio_end_read" Matthew Wilcox provides cleanups and an optimization to the core pagecache code. - Nhat Pham has added memcg accounting for hugetlb memory in the series "hugetlb memcg accounting". - Cleanups and rationalizations to the pagemap code from Lorenzo Stoakes, in the series "Abstract vma_merge() and split_vma()". - Audra Mitchell has fixed issues in the procfs page_owner code's new timestamping feature which was causing some misbehaviours. In the series "Fix page_owner's use of free timestamps". - Lorenzo Stoakes has fixed the handling of new mappings of sealed files in the series "permit write-sealed memfd read-only shared mappings". - Mike Kravetz has optimized the hugetlb vmemmap optimization in the series "Batch hugetlb vmemmap modification operations". - Some buffer_head folio conversions and cleanups from Matthew Wilcox in the series "Finish the create_empty_buffers() transition". - As a page allocator performance optimization Huang Ying has added automatic tuning to the allocator's per-cpu-pages feature, in the series "mm: PCP high auto-tuning". - Roman Gushchin has contributed the patchset "mm: improve performance of accounted kernel memory allocations" which improves their performance by ~30% as measured by a micro-benchmark. - folio conversions from Kefeng Wang in the series "mm: convert page cpupid functions to folios". - Some kmemleak fixups in Liu Shixin's series "Some bugfix about kmemleak". - Qi Zheng has improved our handling of memoryless nodes by keeping them off the allocation fallback list. This is done in the series "handle memoryless nodes more appropriately". - khugepaged conversions from Vishal Moola in the series "Some khugepaged folio conversions". -----BEGIN PGP SIGNATURE----- iHUEABYIAB0WIQTTMBEPP41GrTpTJgfdBJ7gKXxAjgUCZULEMwAKCRDdBJ7gKXxA jhQHAQCYpD3g849x69DmHnHWHm/EHQLvQmRMDeYZI+nx/sCJOwEAw4AKg0Oemv9y FgeUPAD1oasg6CP+INZvCj34waNxwAc= =E+Y4 -----END PGP SIGNATURE----- Merge tag 'mm-stable-2023-11-01-14-33' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Pull MM updates from Andrew Morton: "Many singleton patches against the MM code. The patch series which are included in this merge do the following: - Kemeng Shi has contributed some compation maintenance work in the series 'Fixes and cleanups to compaction' - Joel Fernandes has a patchset ('Optimize mremap during mutual alignment within PMD') which fixes an obscure issue with mremap()'s pagetable handling during a subsequent exec(), based upon an implementation which Linus suggested - More DAMON/DAMOS maintenance and feature work from SeongJae Park i the following patch series: mm/damon: misc fixups for documents, comments and its tracepoint mm/damon: add a tracepoint for damos apply target regions mm/damon: provide pseudo-moving sum based access rate mm/damon: implement DAMOS apply intervals mm/damon/core-test: Fix memory leaks in core-test mm/damon/sysfs-schemes: Do DAMOS tried regions update for only one apply interval - In the series 'Do not try to access unaccepted memory' Adrian Hunter provides some fixups for the recently-added 'unaccepted memory' feature. To increase the feature's checking coverage. 'Plug a few gaps where RAM is exposed without checking if it is unaccepted memory' - In the series 'cleanups for lockless slab shrink' Qi Zheng has done some maintenance work which is preparation for the lockless slab shrinking code - Qi Zheng has redone the earlier (and reverted) attempt to make slab shrinking lockless in the series 'use refcount+RCU method to implement lockless slab shrink' - David Hildenbrand contributes some maintenance work for the rmap code in the series 'Anon rmap cleanups' - Kefeng Wang does more folio conversions and some maintenance work in the migration code. Series 'mm: migrate: more folio conversion and unification' - Matthew Wilcox has fixed an issue in the buffer_head code which was causing long stalls under some heavy memory/IO loads. Some cleanups were added on the way. Series 'Add and use bdev_getblk()' - In the series 'Use nth_page() in place of direct struct page manipulation' Zi Yan has fixed a potential issue with the direct manipulation of hugetlb page frames - In the series 'mm: hugetlb: Skip initialization of gigantic tail struct pages if freed by HVO' has improved our handling of gigantic pages in the hugetlb vmmemmep optimizaton code. This provides significant boot time improvements when significant amounts of gigantic pages are in use - Matthew Wilcox has sent the series 'Small hugetlb cleanups' - code rationalization and folio conversions in the hugetlb code - Yin Fengwei has improved mlock()'s handling of large folios in the series 'support large folio for mlock' - In the series 'Expose swapcache stat for memcg v1' Liu Shixin has added statistics for memcg v1 users which are available (and useful) under memcg v2 - Florent Revest has enhanced the MDWE (Memory-Deny-Write-Executable) prctl so that userspace may direct the kernel to not automatically propagate the denial to child processes. The series is named 'MDWE without inheritance' - Kefeng Wang has provided the series 'mm: convert numa balancing functions to use a folio' which does what it says - In the series 'mm/ksm: add fork-exec support for prctl' Stefan Roesch makes is possible for a process to propagate KSM treatment across exec() - Huang Ying has enhanced memory tiering's calculation of memory distances. This is used to permit the dax/kmem driver to use 'high bandwidth memory' in addition to Optane Data Center Persistent Memory Modules (DCPMM). The series is named 'memory tiering: calculate abstract distance based on ACPI HMAT' - In the series 'Smart scanning mode for KSM' Stefan Roesch has optimized KSM by teaching it to retain and use some historical information from previous scans - Yosry Ahmed has fixed some inconsistencies in memcg statistics in the series 'mm: memcg: fix tracking of pending stats updates values' - In the series 'Implement IOCTL to get and optionally clear info about PTEs' Peter Xu has added an ioctl to /proc/<pid>/pagemap which permits us to atomically read-then-clear page softdirty state. This is mainly used by CRIU - Hugh Dickins contributed the series 'shmem,tmpfs: general maintenance', a bunch of relatively minor maintenance tweaks to this code - Matthew Wilcox has increased the use of the VMA lock over file-backed page faults in the series 'Handle more faults under the VMA lock'. Some rationalizations of the fault path became possible as a result - In the series 'mm/rmap: convert page_move_anon_rmap() to folio_move_anon_rmap()' David Hildenbrand has implemented some cleanups and folio conversions - In the series 'various improvements to the GUP interface' Lorenzo Stoakes has simplified and improved the GUP interface with an eye to providing groundwork for future improvements - Andrey Konovalov has sent along the series 'kasan: assorted fixes and improvements' which does those things - Some page allocator maintenance work from Kemeng Shi in the series 'Two minor cleanups to break_down_buddy_pages' - In thes series 'New selftest for mm' Breno Leitao has developed another MM self test which tickles a race we had between madvise() and page faults - In the series 'Add folio_end_read' Matthew Wilcox provides cleanups and an optimization to the core pagecache code - Nhat Pham has added memcg accounting for hugetlb memory in the series 'hugetlb memcg accounting' - Cleanups and rationalizations to the pagemap code from Lorenzo Stoakes, in the series 'Abstract vma_merge() and split_vma()' - Audra Mitchell has fixed issues in the procfs page_owner code's new timestamping feature which was causing some misbehaviours. In the series 'Fix page_owner's use of free timestamps' - Lorenzo Stoakes has fixed the handling of new mappings of sealed files in the series 'permit write-sealed memfd read-only shared mappings' - Mike Kravetz has optimized the hugetlb vmemmap optimization in the series 'Batch hugetlb vmemmap modification operations' - Some buffer_head folio conversions and cleanups from Matthew Wilcox in the series 'Finish the create_empty_buffers() transition' - As a page allocator performance optimization Huang Ying has added automatic tuning to the allocator's per-cpu-pages feature, in the series 'mm: PCP high auto-tuning' - Roman Gushchin has contributed the patchset 'mm: improve performance of accounted kernel memory allocations' which improves their performance by ~30% as measured by a micro-benchmark - folio conversions from Kefeng Wang in the series 'mm: convert page cpupid functions to folios' - Some kmemleak fixups in Liu Shixin's series 'Some bugfix about kmemleak' - Qi Zheng has improved our handling of memoryless nodes by keeping them off the allocation fallback list. This is done in the series 'handle memoryless nodes more appropriately' - khugepaged conversions from Vishal Moola in the series 'Some khugepaged folio conversions'" [ bcachefs conflicts with the dynamically allocated shrinkers have been resolved as per Stephen Rothwell in https://lore.kernel.org/all/20230913093553.4290421e@canb.auug.org.au/ with help from Qi Zheng. The clone3 test filtering conflict was half-arsed by yours truly ] * tag 'mm-stable-2023-11-01-14-33' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (406 commits) mm/damon/sysfs: update monitoring target regions for online input commit mm/damon/sysfs: remove requested targets when online-commit inputs selftests: add a sanity check for zswap Documentation: maple_tree: fix word spelling error mm/vmalloc: fix the unchecked dereference warning in vread_iter() zswap: export compression failure stats Documentation: ubsan: drop "the" from article title mempolicy: migration attempt to match interleave nodes mempolicy: mmap_lock is not needed while migrating folios mempolicy: alloc_pages_mpol() for NUMA policy without vma mm: add page_rmappable_folio() wrapper mempolicy: remove confusing MPOL_MF_LAZY dead code mempolicy: mpol_shared_policy_init() without pseudo-vma mempolicy trivia: use pgoff_t in shared mempolicy tree mempolicy trivia: slightly more consistent naming mempolicy trivia: delete those ancient pr_debug()s mempolicy: fix migrate_pages(2) syscall return nr_failed kernfs: drop shared NUMA mempolicy hooks hugetlbfs: drop shared NUMA mempolicy pretence mm/damon/sysfs-test: add a unit test for damon_sysfs_set_targets() ...
2023-11-02 22:38:47 -07:00
bc->shrink = shrink;
shrink->count_objects = bch2_btree_key_cache_count;
shrink->scan_objects = bch2_btree_key_cache_scan;
shrink->batch = 1 << 14;
shrink->seeks = 0;
Many singleton patches against the MM code. The patch series which are included in this merge do the following: - Kemeng Shi has contributed some compation maintenance work in the series "Fixes and cleanups to compaction". - Joel Fernandes has a patchset ("Optimize mremap during mutual alignment within PMD") which fixes an obscure issue with mremap()'s pagetable handling during a subsequent exec(), based upon an implementation which Linus suggested. - More DAMON/DAMOS maintenance and feature work from SeongJae Park i the following patch series: mm/damon: misc fixups for documents, comments and its tracepoint mm/damon: add a tracepoint for damos apply target regions mm/damon: provide pseudo-moving sum based access rate mm/damon: implement DAMOS apply intervals mm/damon/core-test: Fix memory leaks in core-test mm/damon/sysfs-schemes: Do DAMOS tried regions update for only one apply interval - In the series "Do not try to access unaccepted memory" Adrian Hunter provides some fixups for the recently-added "unaccepted memory' feature. To increase the feature's checking coverage. "Plug a few gaps where RAM is exposed without checking if it is unaccepted memory". - In the series "cleanups for lockless slab shrink" Qi Zheng has done some maintenance work which is preparation for the lockless slab shrinking code. - Qi Zheng has redone the earlier (and reverted) attempt to make slab shrinking lockless in the series "use refcount+RCU method to implement lockless slab shrink". - David Hildenbrand contributes some maintenance work for the rmap code in the series "Anon rmap cleanups". - Kefeng Wang does more folio conversions and some maintenance work in the migration code. Series "mm: migrate: more folio conversion and unification". - Matthew Wilcox has fixed an issue in the buffer_head code which was causing long stalls under some heavy memory/IO loads. Some cleanups were added on the way. Series "Add and use bdev_getblk()". - In the series "Use nth_page() in place of direct struct page manipulation" Zi Yan has fixed a potential issue with the direct manipulation of hugetlb page frames. - In the series "mm: hugetlb: Skip initialization of gigantic tail struct pages if freed by HVO" has improved our handling of gigantic pages in the hugetlb vmmemmep optimizaton code. This provides significant boot time improvements when significant amounts of gigantic pages are in use. - Matthew Wilcox has sent the series "Small hugetlb cleanups" - code rationalization and folio conversions in the hugetlb code. - Yin Fengwei has improved mlock()'s handling of large folios in the series "support large folio for mlock" - In the series "Expose swapcache stat for memcg v1" Liu Shixin has added statistics for memcg v1 users which are available (and useful) under memcg v2. - Florent Revest has enhanced the MDWE (Memory-Deny-Write-Executable) prctl so that userspace may direct the kernel to not automatically propagate the denial to child processes. The series is named "MDWE without inheritance". - Kefeng Wang has provided the series "mm: convert numa balancing functions to use a folio" which does what it says. - In the series "mm/ksm: add fork-exec support for prctl" Stefan Roesch makes is possible for a process to propagate KSM treatment across exec(). - Huang Ying has enhanced memory tiering's calculation of memory distances. This is used to permit the dax/kmem driver to use "high bandwidth memory" in addition to Optane Data Center Persistent Memory Modules (DCPMM). The series is named "memory tiering: calculate abstract distance based on ACPI HMAT" - In the series "Smart scanning mode for KSM" Stefan Roesch has optimized KSM by teaching it to retain and use some historical information from previous scans. - Yosry Ahmed has fixed some inconsistencies in memcg statistics in the series "mm: memcg: fix tracking of pending stats updates values". - In the series "Implement IOCTL to get and optionally clear info about PTEs" Peter Xu has added an ioctl to /proc/<pid>/pagemap which permits us to atomically read-then-clear page softdirty state. This is mainly used by CRIU. - Hugh Dickins contributed the series "shmem,tmpfs: general maintenance" - a bunch of relatively minor maintenance tweaks to this code. - Matthew Wilcox has increased the use of the VMA lock over file-backed page faults in the series "Handle more faults under the VMA lock". Some rationalizations of the fault path became possible as a result. - In the series "mm/rmap: convert page_move_anon_rmap() to folio_move_anon_rmap()" David Hildenbrand has implemented some cleanups and folio conversions. - In the series "various improvements to the GUP interface" Lorenzo Stoakes has simplified and improved the GUP interface with an eye to providing groundwork for future improvements. - Andrey Konovalov has sent along the series "kasan: assorted fixes and improvements" which does those things. - Some page allocator maintenance work from Kemeng Shi in the series "Two minor cleanups to break_down_buddy_pages". - In thes series "New selftest for mm" Breno Leitao has developed another MM self test which tickles a race we had between madvise() and page faults. - In the series "Add folio_end_read" Matthew Wilcox provides cleanups and an optimization to the core pagecache code. - Nhat Pham has added memcg accounting for hugetlb memory in the series "hugetlb memcg accounting". - Cleanups and rationalizations to the pagemap code from Lorenzo Stoakes, in the series "Abstract vma_merge() and split_vma()". - Audra Mitchell has fixed issues in the procfs page_owner code's new timestamping feature which was causing some misbehaviours. In the series "Fix page_owner's use of free timestamps". - Lorenzo Stoakes has fixed the handling of new mappings of sealed files in the series "permit write-sealed memfd read-only shared mappings". - Mike Kravetz has optimized the hugetlb vmemmap optimization in the series "Batch hugetlb vmemmap modification operations". - Some buffer_head folio conversions and cleanups from Matthew Wilcox in the series "Finish the create_empty_buffers() transition". - As a page allocator performance optimization Huang Ying has added automatic tuning to the allocator's per-cpu-pages feature, in the series "mm: PCP high auto-tuning". - Roman Gushchin has contributed the patchset "mm: improve performance of accounted kernel memory allocations" which improves their performance by ~30% as measured by a micro-benchmark. - folio conversions from Kefeng Wang in the series "mm: convert page cpupid functions to folios". - Some kmemleak fixups in Liu Shixin's series "Some bugfix about kmemleak". - Qi Zheng has improved our handling of memoryless nodes by keeping them off the allocation fallback list. This is done in the series "handle memoryless nodes more appropriately". - khugepaged conversions from Vishal Moola in the series "Some khugepaged folio conversions". -----BEGIN PGP SIGNATURE----- iHUEABYIAB0WIQTTMBEPP41GrTpTJgfdBJ7gKXxAjgUCZULEMwAKCRDdBJ7gKXxA jhQHAQCYpD3g849x69DmHnHWHm/EHQLvQmRMDeYZI+nx/sCJOwEAw4AKg0Oemv9y FgeUPAD1oasg6CP+INZvCj34waNxwAc= =E+Y4 -----END PGP SIGNATURE----- Merge tag 'mm-stable-2023-11-01-14-33' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Pull MM updates from Andrew Morton: "Many singleton patches against the MM code. The patch series which are included in this merge do the following: - Kemeng Shi has contributed some compation maintenance work in the series 'Fixes and cleanups to compaction' - Joel Fernandes has a patchset ('Optimize mremap during mutual alignment within PMD') which fixes an obscure issue with mremap()'s pagetable handling during a subsequent exec(), based upon an implementation which Linus suggested - More DAMON/DAMOS maintenance and feature work from SeongJae Park i the following patch series: mm/damon: misc fixups for documents, comments and its tracepoint mm/damon: add a tracepoint for damos apply target regions mm/damon: provide pseudo-moving sum based access rate mm/damon: implement DAMOS apply intervals mm/damon/core-test: Fix memory leaks in core-test mm/damon/sysfs-schemes: Do DAMOS tried regions update for only one apply interval - In the series 'Do not try to access unaccepted memory' Adrian Hunter provides some fixups for the recently-added 'unaccepted memory' feature. To increase the feature's checking coverage. 'Plug a few gaps where RAM is exposed without checking if it is unaccepted memory' - In the series 'cleanups for lockless slab shrink' Qi Zheng has done some maintenance work which is preparation for the lockless slab shrinking code - Qi Zheng has redone the earlier (and reverted) attempt to make slab shrinking lockless in the series 'use refcount+RCU method to implement lockless slab shrink' - David Hildenbrand contributes some maintenance work for the rmap code in the series 'Anon rmap cleanups' - Kefeng Wang does more folio conversions and some maintenance work in the migration code. Series 'mm: migrate: more folio conversion and unification' - Matthew Wilcox has fixed an issue in the buffer_head code which was causing long stalls under some heavy memory/IO loads. Some cleanups were added on the way. Series 'Add and use bdev_getblk()' - In the series 'Use nth_page() in place of direct struct page manipulation' Zi Yan has fixed a potential issue with the direct manipulation of hugetlb page frames - In the series 'mm: hugetlb: Skip initialization of gigantic tail struct pages if freed by HVO' has improved our handling of gigantic pages in the hugetlb vmmemmep optimizaton code. This provides significant boot time improvements when significant amounts of gigantic pages are in use - Matthew Wilcox has sent the series 'Small hugetlb cleanups' - code rationalization and folio conversions in the hugetlb code - Yin Fengwei has improved mlock()'s handling of large folios in the series 'support large folio for mlock' - In the series 'Expose swapcache stat for memcg v1' Liu Shixin has added statistics for memcg v1 users which are available (and useful) under memcg v2 - Florent Revest has enhanced the MDWE (Memory-Deny-Write-Executable) prctl so that userspace may direct the kernel to not automatically propagate the denial to child processes. The series is named 'MDWE without inheritance' - Kefeng Wang has provided the series 'mm: convert numa balancing functions to use a folio' which does what it says - In the series 'mm/ksm: add fork-exec support for prctl' Stefan Roesch makes is possible for a process to propagate KSM treatment across exec() - Huang Ying has enhanced memory tiering's calculation of memory distances. This is used to permit the dax/kmem driver to use 'high bandwidth memory' in addition to Optane Data Center Persistent Memory Modules (DCPMM). The series is named 'memory tiering: calculate abstract distance based on ACPI HMAT' - In the series 'Smart scanning mode for KSM' Stefan Roesch has optimized KSM by teaching it to retain and use some historical information from previous scans - Yosry Ahmed has fixed some inconsistencies in memcg statistics in the series 'mm: memcg: fix tracking of pending stats updates values' - In the series 'Implement IOCTL to get and optionally clear info about PTEs' Peter Xu has added an ioctl to /proc/<pid>/pagemap which permits us to atomically read-then-clear page softdirty state. This is mainly used by CRIU - Hugh Dickins contributed the series 'shmem,tmpfs: general maintenance', a bunch of relatively minor maintenance tweaks to this code - Matthew Wilcox has increased the use of the VMA lock over file-backed page faults in the series 'Handle more faults under the VMA lock'. Some rationalizations of the fault path became possible as a result - In the series 'mm/rmap: convert page_move_anon_rmap() to folio_move_anon_rmap()' David Hildenbrand has implemented some cleanups and folio conversions - In the series 'various improvements to the GUP interface' Lorenzo Stoakes has simplified and improved the GUP interface with an eye to providing groundwork for future improvements - Andrey Konovalov has sent along the series 'kasan: assorted fixes and improvements' which does those things - Some page allocator maintenance work from Kemeng Shi in the series 'Two minor cleanups to break_down_buddy_pages' - In thes series 'New selftest for mm' Breno Leitao has developed another MM self test which tickles a race we had between madvise() and page faults - In the series 'Add folio_end_read' Matthew Wilcox provides cleanups and an optimization to the core pagecache code - Nhat Pham has added memcg accounting for hugetlb memory in the series 'hugetlb memcg accounting' - Cleanups and rationalizations to the pagemap code from Lorenzo Stoakes, in the series 'Abstract vma_merge() and split_vma()' - Audra Mitchell has fixed issues in the procfs page_owner code's new timestamping feature which was causing some misbehaviours. In the series 'Fix page_owner's use of free timestamps' - Lorenzo Stoakes has fixed the handling of new mappings of sealed files in the series 'permit write-sealed memfd read-only shared mappings' - Mike Kravetz has optimized the hugetlb vmemmap optimization in the series 'Batch hugetlb vmemmap modification operations' - Some buffer_head folio conversions and cleanups from Matthew Wilcox in the series 'Finish the create_empty_buffers() transition' - As a page allocator performance optimization Huang Ying has added automatic tuning to the allocator's per-cpu-pages feature, in the series 'mm: PCP high auto-tuning' - Roman Gushchin has contributed the patchset 'mm: improve performance of accounted kernel memory allocations' which improves their performance by ~30% as measured by a micro-benchmark - folio conversions from Kefeng Wang in the series 'mm: convert page cpupid functions to folios' - Some kmemleak fixups in Liu Shixin's series 'Some bugfix about kmemleak' - Qi Zheng has improved our handling of memoryless nodes by keeping them off the allocation fallback list. This is done in the series 'handle memoryless nodes more appropriately' - khugepaged conversions from Vishal Moola in the series 'Some khugepaged folio conversions'" [ bcachefs conflicts with the dynamically allocated shrinkers have been resolved as per Stephen Rothwell in https://lore.kernel.org/all/20230913093553.4290421e@canb.auug.org.au/ with help from Qi Zheng. The clone3 test filtering conflict was half-arsed by yours truly ] * tag 'mm-stable-2023-11-01-14-33' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (406 commits) mm/damon/sysfs: update monitoring target regions for online input commit mm/damon/sysfs: remove requested targets when online-commit inputs selftests: add a sanity check for zswap Documentation: maple_tree: fix word spelling error mm/vmalloc: fix the unchecked dereference warning in vread_iter() zswap: export compression failure stats Documentation: ubsan: drop "the" from article title mempolicy: migration attempt to match interleave nodes mempolicy: mmap_lock is not needed while migrating folios mempolicy: alloc_pages_mpol() for NUMA policy without vma mm: add page_rmappable_folio() wrapper mempolicy: remove confusing MPOL_MF_LAZY dead code mempolicy: mpol_shared_policy_init() without pseudo-vma mempolicy trivia: use pgoff_t in shared mempolicy tree mempolicy trivia: slightly more consistent naming mempolicy trivia: delete those ancient pr_debug()s mempolicy: fix migrate_pages(2) syscall return nr_failed kernfs: drop shared NUMA mempolicy hooks hugetlbfs: drop shared NUMA mempolicy pretence mm/damon/sysfs-test: add a unit test for damon_sysfs_set_targets() ...
2023-11-02 22:38:47 -07:00
shrink->private_data = c;
shrinker_register(shrink);
return 0;
}
void bch2_btree_key_cache_to_text(struct printbuf *out, struct btree_key_cache *bc)
{
printbuf_tabstop_push(out, 24);
printbuf_tabstop_push(out, 12);
prt_printf(out, "keys:\t%lu\r\n", atomic_long_read(&bc->nr_keys));
prt_printf(out, "dirty:\t%lu\r\n", atomic_long_read(&bc->nr_dirty));
prt_printf(out, "table size:\t%u\r\n", bc->table.tbl->size);
prt_newline(out);
prt_printf(out, "shrinker:\n");
prt_printf(out, "requested_to_free:\t%lu\r\n", bc->requested_to_free);
prt_printf(out, "freed:\t%lu\r\n", bc->freed);
prt_printf(out, "skipped_dirty:\t%lu\r\n", bc->skipped_dirty);
prt_printf(out, "skipped_accessed:\t%lu\r\n", bc->skipped_accessed);
prt_printf(out, "skipped_lock_fail:\t%lu\r\n", bc->skipped_lock_fail);
prt_newline(out);
prt_printf(out, "pending:\t%zu\r\n", per_cpu_sum(bc->nr_pending));
}
void bch2_btree_key_cache_exit(void)
{
kmem_cache_destroy(bch2_key_cache);
}
int __init bch2_btree_key_cache_init(void)
{
bch2_key_cache = KMEM_CACHE(bkey_cached, SLAB_RECLAIM_ACCOUNT);
if (!bch2_key_cache)
return -ENOMEM;
return 0;
}