On 07.03.2023 09:55, Qi Zheng wrote:
> The shrinker_rwsem is a global read-write lock in
> shrinkers subsystem, which protects most operations
> such as slab shrink, registration and unregistration
> of shrinkers, etc. This can easily cause problems in
> the following cases.
>
> 1) When the memory pressure is high and there are many
> filesystems mounted or unmounted at the same time,
> slab shrink will be affected (down_read_trylock()
> failed).
>
> Such as the real workload mentioned by Kirill Tkhai:
>
> ```
> One of the real workloads from my experience is start
> of an overcommitted node containing many starting
> containers after node crash (or many resuming containers
> after reboot for kernel update). In these cases memory
> pressure is huge, and the node goes round in long reclaim.
> ```
>
> 2) If a shrinker is blocked (such as the case mentioned
> in [1]) and a writer comes in (such as mount a fs),
> then this writer will be blocked and cause all
> subsequent shrinker-related operations to be blocked.
>
> Even if there is no competitor when shrinking slab, there
> may still be a problem. If we have a long shrinker list
> and we do not reclaim enough memory with each shrinker,
> then the down_read_trylock() may be called with high
> frequency. Because of the poor multicore scalability of
> atomic operations, this can lead to a significant drop
> in IPC (instructions per cycle).
>
> So many times in history ([2],[3],[4],[5]), some people
> wanted to replace shrinker_rwsem trylock with SRCU in
> the slab shrink, but all these patches were abandoned
> because SRCU was not unconditionally enabled.
>
> But now, since commit 1cd0bd06093c ("rcu: Remove CONFIG_SRCU"),
> the SRCU is unconditionally enabled. So it's time to use
> SRCU to protect readers who previously held shrinker_rwsem.
>
> This commit uses SRCU to make global slab shrink lockless,
> the memcg slab shrink is handled in the subsequent patch.
>
> [1]. https://lore.kernel.org/lkml/20191129214541.3110-1-ptikhomirov@xxxxxxxxxxxxx/
> [2]. https://lore.kernel.org/all/1437080113.3596.2.camel@xxxxxxxxxxxx/
> [3]. https://lore.kernel.org/lkml/1510609063-3327-1-git-send-email-penguin-kernel@xxxxxxxxxxxxxxxxxxx/
> [4]. https://lore.kernel.org/lkml/153365347929.19074.12509495712735843805.stgit@localhost.localdomain/
> [5]. https://lore.kernel.org/lkml/20210927074823.5825-1-sultan@xxxxxxxxxxxxxxx/
>
> Signed-off-by: Qi Zheng <zhengqi.arch@xxxxxxxxxxxxx>
Acked-by: Kirill Tkhai <tkhai@xxxxx>
> ---
> mm/vmscan.c | 27 +++++++++++----------------
> 1 file changed, 11 insertions(+), 16 deletions(-)
>
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index 2dcc01682026..8515ac40bcaf 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -202,6 +202,7 @@ static void set_task_reclaim_state(struct task_struct *task,
>
> LIST_HEAD(shrinker_list);
> DECLARE_RWSEM(shrinker_rwsem);
> +DEFINE_SRCU(shrinker_srcu);
>
> #ifdef CONFIG_MEMCG
> static int shrinker_nr_max;
> @@ -706,7 +707,7 @@ void free_prealloced_shrinker(struct shrinker *shrinker)
> void register_shrinker_prepared(struct shrinker *shrinker)
> {
> down_write(&shrinker_rwsem);
> - list_add_tail(&shrinker->list, &shrinker_list);
> + list_add_tail_rcu(&shrinker->list, &shrinker_list);
> shrinker->flags |= SHRINKER_REGISTERED;
> shrinker_debugfs_add(shrinker);
> up_write(&shrinker_rwsem);
> @@ -760,13 +761,15 @@ void unregister_shrinker(struct shrinker *shrinker)
> return;
>
> down_write(&shrinker_rwsem);
> - list_del(&shrinker->list);
> + list_del_rcu(&shrinker->list);
> shrinker->flags &= ~SHRINKER_REGISTERED;
> if (shrinker->flags & SHRINKER_MEMCG_AWARE)
> unregister_memcg_shrinker(shrinker);
> debugfs_entry = shrinker_debugfs_remove(shrinker);
> up_write(&shrinker_rwsem);
>
> + synchronize_srcu(&shrinker_srcu);
> +
> debugfs_remove_recursive(debugfs_entry);
>
> kfree(shrinker->nr_deferred);
> @@ -786,6 +789,7 @@ void synchronize_shrinkers(void)
> {
> down_write(&shrinker_rwsem);
> up_write(&shrinker_rwsem);
> + synchronize_srcu(&shrinker_srcu);
> }
> EXPORT_SYMBOL(synchronize_shrinkers);
>
> @@ -996,6 +1000,7 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid,
> {
> unsigned long ret, freed = 0;
> struct shrinker *shrinker;
> + int srcu_idx;
>
> /*
> * The root memcg might be allocated even though memcg is disabled
> @@ -1007,10 +1012,10 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid,
> if (!mem_cgroup_disabled() && !mem_cgroup_is_root(memcg))
> return shrink_slab_memcg(gfp_mask, nid, memcg, priority);
>
> - if (!down_read_trylock(&shrinker_rwsem))
> - goto out;
> + srcu_idx = srcu_read_lock(&shrinker_srcu);
>
> - list_for_each_entry(shrinker, &shrinker_list, list) {
> + list_for_each_entry_srcu(shrinker, &shrinker_list, list,
> + srcu_read_lock_held(&shrinker_srcu)) {
> struct shrink_control sc = {
> .gfp_mask = gfp_mask,
> .nid = nid,
> @@ -1021,19 +1026,9 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid,
> if (ret == SHRINK_EMPTY)
> ret = 0;
> freed += ret;
> - /*
> - * Bail out if someone want to register a new shrinker to
> - * prevent the registration from being stalled for long periods
> - * by parallel ongoing shrinking.
> - */
> - if (rwsem_is_contended(&shrinker_rwsem)) {
> - freed = freed ? : 1;
> - break;
> - }
> }
>
> - up_read(&shrinker_rwsem);
> -out:
> + srcu_read_unlock(&shrinker_srcu, srcu_idx);
> cond_resched();
> return freed;
> }
