mm/list_lru: split the lock to per-cgroup scope

Currently, every list_lru has a per-node lock that protects adding,
deletion, isolation, and reparenting of all list_lru_one instances
belonging to this list_lru on this node.  This lock contention is heavy
when multiple cgroups modify the same list_lru.

This lock can be split into per-cgroup scope to reduce contention.

To achieve this, we need a stable list_lru_one for every cgroup.  This
commit adds a lock to each list_lru_one and introduced a helper function
lock_list_lru_of_memcg, making it possible to pin the list_lru of a memcg.
Then reworked the reparenting process.

Reparenting will switch the list_lru_one instances one by one.  By locking
each instance and marking it dead using the nr_items counter, reparenting
ensures that all items in the corresponding cgroup (on-list or not,
because items have a stable cgroup, see below) will see the list_lru_one
switch synchronously.

Objcg reparent is also moved after list_lru reparent so items will have a
stable mem cgroup until all list_lru_one instances are drained.

The only caller that doesn't work the *_obj interfaces are direct calls to
list_lru_{add,del}.  But it's only used by zswap and that's also based on
objcg, so it's fine.

This also changes the bahaviour of the isolation function when LRU_RETRY
or LRU_REMOVED_RETRY is returned, because now releasing the lock could
unblock reparenting and free the list_lru_one, isolation function will
have to return withoug re-lock the lru.

prepare() {
    mkdir /tmp/test-fs
    modprobe brd rd_nr=1 rd_size=33554432
    mkfs.xfs -f /dev/ram0
    mount -t xfs /dev/ram0 /tmp/test-fs
    for i in $(seq 1 512); do
        mkdir "/tmp/test-fs/$i"
        for j in $(seq 1 10240); do
            echo TEST-CONTENT > "/tmp/test-fs/$i/$j"
        done &
    done; wait
}

do_test() {
    read_worker() {
        sleep 1
        tar -cv "$1" &>/dev/null
    }
    read_in_all() {
        cd "/tmp/test-fs" && ls
        for i in $(seq 1 512); do
            (exec sh -c 'echo "$PPID"') > "/sys/fs/cgroup/benchmark/$i/cgroup.procs"
            read_worker "$i" &
        done; wait
    }
    for i in $(seq 1 512); do
        mkdir -p "/sys/fs/cgroup/benchmark/$i"
    done
    echo +memory > /sys/fs/cgroup/benchmark/cgroup.subtree_control
    echo 512M > /sys/fs/cgroup/benchmark/memory.max
    echo 3 > /proc/sys/vm/drop_caches
    time read_in_all
}

Above script simulates compression of small files in multiple cgroups
with memory pressure. Run prepare() then do_test for 6 times:

Before:
real      0m7.762s user      0m11.340s sys       3m11.224s
real      0m8.123s user      0m11.548s sys       3m2.549s
real      0m7.736s user      0m11.515s sys       3m11.171s
real      0m8.539s user      0m11.508s sys       3m7.618s
real      0m7.928s user      0m11.349s sys       3m13.063s
real      0m8.105s user      0m11.128s sys       3m14.313s

After this commit (about ~15% faster):
real      0m6.953s user      0m11.327s sys       2m42.912s
real      0m7.453s user      0m11.343s sys       2m51.942s
real      0m6.916s user      0m11.269s sys       2m43.957s
real      0m6.894s user      0m11.528s sys       2m45.346s
real      0m6.911s user      0m11.095s sys       2m43.168s
real      0m6.773s user      0m11.518s sys       2m40.774s

Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Kairui Song <[email protected]>
Cc: Chengming Zhou <[email protected]>
Cc: Johannes Weiner <[email protected]>
Cc: Matthew Wilcox (Oracle) <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: Muchun Song <[email protected]>
Cc: Qi Zheng <[email protected]>
Cc: Roman Gushchin <[email protected]>
Cc: Shakeel Butt <[email protected]>
Cc: Waiman Long <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>

Author: ryncsn

drivers/android/binder_alloc.c

@@ -1106,7 +1106,6 @@ enum lru_status binder_alloc_free_page(struct list_head *item,
 	mmput_async(mm);
 	__free_page(page_to_free);
 
-	spin_lock(lock);
 	return LRU_REMOVED_RETRY;
 
 err_invalid_vma:

fs/inode.c

@@ -934,7 +934,6 @@ static enum lru_status inode_lru_isolate(struct list_head *item,
 			mm_account_reclaimed_pages(reap);
 		}
 		inode_unpin_lru_isolating(inode);
-		spin_lock(lru_lock);
 		return LRU_RETRY;
 	}
 

fs/xfs/xfs_qm.c

@@ -496,7 +496,6 @@ xfs_qm_dquot_isolate(
 	trace_xfs_dqreclaim_busy(dqp);
 	XFS_STATS_INC(dqp->q_mount, xs_qm_dqreclaim_misses);
 	xfs_dqunlock(dqp);
-	spin_lock(lru_lock);
 	return LRU_RETRY;
 }
 

include/linux/list_lru.h

@@ -32,6 +32,8 @@ struct list_lru_one {
 	struct list_head	list;
 	/* may become negative during memcg reparenting */
 	long			nr_items;
+	/* protects all fields above */
+	spinlock_t		lock;
 };
 
 struct list_lru_memcg {
@@ -41,11 +43,9 @@ struct list_lru_memcg {
 };
 
 struct list_lru_node {
-	/* protects all lists on the node, including per cgroup */
-	spinlock_t		lock;
 	/* global list, used for the root cgroup in cgroup aware lrus */
 	struct list_lru_one	lru;
-	long			nr_items;
+	atomic_long_t		nr_items;
 } ____cacheline_aligned_in_smp;
 
 struct list_lru {