On Fri, Apr 25, 2025 at 1:27 AM Vlastimil Babka <vba...@suse.cz> wrote:
>
> Extend the sheaf infrastructure for more efficient kfree_rcu() handling.
> For caches with sheaves, on each cpu maintain a rcu_free sheaf in
> addition to main and spare sheaves.
>
> kfree_rcu() operations will try to put objects on this sheaf. Once full,
> the sheaf is detached and submitted to call_rcu() with a handler that
> will try to put it in the barn, or flush to slab pages using bulk free,
> when the barn is full. Then a new empty sheaf must be obtained to put
> more objects there.
>
> It's possible that no free sheaves are available to use for a new
> rcu_free sheaf, and the allocation in kfree_rcu() context can only use
> GFP_NOWAIT and thus may fail. In that case, fall back to the existing
> kfree_rcu() implementation.
>
> Expected advantages:
> - batching the kfree_rcu() operations, that could eventually replace the
> existing batching
> - sheaves can be reused for allocations via barn instead of being
> flushed to slabs, which is more efficient
> - this includes cases where only some cpus are allowed to process rcu
> callbacks (Android)
>
> Possible disadvantage:
> - objects might be waiting for more than their grace period (it is
> determined by the last object freed into the sheaf), increasing memory
> usage - but the existing batching does that too.
>
> Only implement this for CONFIG_KVFREE_RCU_BATCHED as the tiny
> implementation favors smaller memory footprint over performance.
>
> Add CONFIG_SLUB_STATS counters free_rcu_sheaf and free_rcu_sheaf_fail to
> count how many kfree_rcu() used the rcu_free sheaf successfully and how
> many had to fall back to the existing implementation.
>
> Signed-off-by: Vlastimil Babka <vba...@suse.cz>
> ---
> mm/slab.h | 3 +
> mm/slab_common.c | 24 ++++++++
> mm/slub.c | 183
> ++++++++++++++++++++++++++++++++++++++++++++++++++++++-
> 3 files changed, 208 insertions(+), 2 deletions(-)
>
> diff --git a/mm/slab.h b/mm/slab.h
> index
> 1980330c2fcb4a4613a7e4f7efc78b349993fd89..ddf1e4bcba734dccbf67e83bdbab3ca7272f540e
> 100644
> --- a/mm/slab.h
> +++ b/mm/slab.h
> @@ -459,6 +459,9 @@ static inline bool is_kmalloc_normal(struct kmem_cache *s)
> return !(s->flags &
> (SLAB_CACHE_DMA|SLAB_ACCOUNT|SLAB_RECLAIM_ACCOUNT));
> }
>
> +bool __kfree_rcu_sheaf(struct kmem_cache *s, void *obj);
> +
> +/* Legal flag mask for kmem_cache_create(), for various configurations */
> #define SLAB_CORE_FLAGS (SLAB_HWCACHE_ALIGN | SLAB_CACHE_DMA | \
> SLAB_CACHE_DMA32 | SLAB_PANIC | \
> SLAB_TYPESAFE_BY_RCU | SLAB_DEBUG_OBJECTS | \
> diff --git a/mm/slab_common.c b/mm/slab_common.c
> index
> 4f295bdd2d42355af6311a799955301005f8a532..6c3b90f03cb79b57f426824450f576a977d85c53
> 100644
> --- a/mm/slab_common.c
> +++ b/mm/slab_common.c
> @@ -1608,6 +1608,27 @@ static void kfree_rcu_work(struct work_struct *work)
> kvfree_rcu_list(head);
> }
>
> +static bool kfree_rcu_sheaf(void *obj)
> +{
> + struct kmem_cache *s;
> + struct folio *folio;
> + struct slab *slab;
> +
> + if (is_vmalloc_addr(obj))
> + return false;
> +
> + folio = virt_to_folio(obj);
> + if (unlikely(!folio_test_slab(folio)))
> + return false;
> +
> + slab = folio_slab(folio);
> + s = slab->slab_cache;
> + if (s->cpu_sheaves)
> + return __kfree_rcu_sheaf(s, obj);
> +
> + return false;
> +}
> +
> static bool
> need_offload_krc(struct kfree_rcu_cpu *krcp)
> {
> @@ -1952,6 +1973,9 @@ void kvfree_call_rcu(struct rcu_head *head, void *ptr)
> if (!head)
> might_sleep();
>
> + if (kfree_rcu_sheaf(ptr))
> + return;
> +
> // Queue the object but don't yet schedule the batch.
> if (debug_rcu_head_queue(ptr)) {
> // Probable double kfree_rcu(), just leak.
> diff --git a/mm/slub.c b/mm/slub.c
> index
> ae3e80ad9926ca15601eef2f2aa016ca059498f8..6f31a27b5d47fa6621fa8af6d6842564077d4b60
> 100644
> --- a/mm/slub.c
> +++ b/mm/slub.c
> @@ -350,6 +350,8 @@ enum stat_item {
> ALLOC_FASTPATH, /* Allocation from cpu slab */
> ALLOC_SLOWPATH, /* Allocation by getting a new cpu slab */
> FREE_PCS, /* Free to percpu sheaf */
> + FREE_RCU_SHEAF, /* Free to rcu_free sheaf */
> + FREE_RCU_SHEAF_FAIL, /* Failed to free to a rcu_free sheaf */
> FREE_FASTPATH, /* Free to cpu slab */
> FREE_SLOWPATH, /* Freeing not to cpu slab */
> FREE_FROZEN, /* Freeing to frozen slab */
> @@ -444,6 +446,7 @@ struct slab_sheaf {
> struct rcu_head rcu_head;
> struct list_head barn_list;
> };
> + struct kmem_cache *cache;
> unsigned int size;
> void *objects[];
> };
> @@ -452,6 +455,7 @@ struct slub_percpu_sheaves {
> local_trylock_t lock;
> struct slab_sheaf *main; /* never NULL when unlocked */
> struct slab_sheaf *spare; /* empty or full, may be NULL */
> + struct slab_sheaf *rcu_free; /* for batching kfree_rcu() */
> struct node_barn *barn;
> };
>
> @@ -2507,6 +2511,8 @@ static struct slab_sheaf *alloc_empty_sheaf(struct
> kmem_cache *s, gfp_t gfp)
> if (unlikely(!sheaf))
> return NULL;
>
> + sheaf->cache = s;
> +
> stat(s, SHEAF_ALLOC);
>
> return sheaf;
> @@ -2631,6 +2637,24 @@ static void sheaf_flush_unused(struct kmem_cache *s,
> struct slab_sheaf *sheaf)
> sheaf->size = 0;
> }
>
> +static void __rcu_free_sheaf_prepare(struct kmem_cache *s,
> + struct slab_sheaf *sheaf);
I think you could safely move __rcu_free_sheaf_prepare() here and
avoid the above forward declaration.
> +
> +static void rcu_free_sheaf_nobarn(struct rcu_head *head)
> +{
> + struct slab_sheaf *sheaf;
> + struct kmem_cache *s;
> +
> + sheaf = container_of(head, struct slab_sheaf, rcu_head);
> + s = sheaf->cache;
> +
> + __rcu_free_sheaf_prepare(s, sheaf);
> +
> + sheaf_flush_unused(s, sheaf);
> +
> + free_empty_sheaf(s, sheaf);
> +}
> +
> /*
> * Caller needs to make sure migration is disabled in order to fully flush
> * single cpu's sheaves
> @@ -2643,7 +2667,7 @@ static void sheaf_flush_unused(struct kmem_cache *s,
> struct slab_sheaf *sheaf)
> static void pcs_flush_all(struct kmem_cache *s)
> {
> struct slub_percpu_sheaves *pcs;
> - struct slab_sheaf *spare;
> + struct slab_sheaf *spare, *rcu_free;
>
> local_lock(&s->cpu_sheaves->lock);
> pcs = this_cpu_ptr(s->cpu_sheaves);
> @@ -2651,6 +2675,9 @@ static void pcs_flush_all(struct kmem_cache *s)
> spare = pcs->spare;
> pcs->spare = NULL;
>
> + rcu_free = pcs->rcu_free;
> + pcs->rcu_free = NULL;
> +
> local_unlock(&s->cpu_sheaves->lock);
>
> if (spare) {
> @@ -2658,6 +2685,9 @@ static void pcs_flush_all(struct kmem_cache *s)
> free_empty_sheaf(s, spare);
> }
>
> + if (rcu_free)
> + call_rcu(&rcu_free->rcu_head, rcu_free_sheaf_nobarn);
> +
> sheaf_flush_main(s);
> }
>
> @@ -2674,6 +2704,11 @@ static void __pcs_flush_all_cpu(struct kmem_cache *s,
> unsigned int cpu)
> free_empty_sheaf(s, pcs->spare);
> pcs->spare = NULL;
> }
> +
> + if (pcs->rcu_free) {
> + call_rcu(&pcs->rcu_free->rcu_head, rcu_free_sheaf_nobarn);
> + pcs->rcu_free = NULL;
> + }
> }
>
> static void pcs_destroy(struct kmem_cache *s)
> @@ -2699,6 +2734,7 @@ static void pcs_destroy(struct kmem_cache *s)
> */
>
> WARN_ON(pcs->spare);
> + WARN_ON(pcs->rcu_free);
>
> if (!WARN_ON(pcs->main->size)) {
> free_empty_sheaf(s, pcs->main);
> @@ -3755,7 +3791,7 @@ static bool has_pcs_used(int cpu, struct kmem_cache *s)
>
> pcs = per_cpu_ptr(s->cpu_sheaves, cpu);
>
> - return (pcs->spare || pcs->main->size);
> + return (pcs->spare || pcs->rcu_free || pcs->main->size);
> }
>
> static void pcs_flush_all(struct kmem_cache *s);
> @@ -5304,6 +5340,140 @@ bool free_to_pcs(struct kmem_cache *s, void *object)
> return true;
> }
>
> +static void __rcu_free_sheaf_prepare(struct kmem_cache *s,
> + struct slab_sheaf *sheaf)
This function seems to be an almost exact copy of free_to_pcs_bulk()
from your previous patch. Maybe they can be consolidated?
> +{
> + bool init = slab_want_init_on_free(s);
> + void **p = &sheaf->objects[0];
> + unsigned int i = 0;
> +
> + while (i < sheaf->size) {
> + struct slab *slab = virt_to_slab(p[i]);
> +
> + memcg_slab_free_hook(s, slab, p + i, 1);
> + alloc_tagging_slab_free_hook(s, slab, p + i, 1);
> +
> + if (unlikely(!slab_free_hook(s, p[i], init, true))) {
> + p[i] = p[--sheaf->size];
> + continue;
> + }
> +
> + i++;
> + }
> +}
> +
> +static void rcu_free_sheaf(struct rcu_head *head)
> +{
> + struct slab_sheaf *sheaf;
> + struct node_barn *barn;
> + struct kmem_cache *s;
> +
> + sheaf = container_of(head, struct slab_sheaf, rcu_head);
> +
> + s = sheaf->cache;
> +
> + /*
> + * This may reduce the number of objects that the sheaf is no longer
> + * technically full, but it's easier to treat it that way (unless it's
I don't understand the sentence above. Could you please clarify and
maybe reword it?
> + * competely empty), as the code handles it fine, there's just
> slightly
s/competely/completely
> + * worse batching benefit. It only happens due to debugging, which
> + * is a performance hit anyway.
> + */
> + __rcu_free_sheaf_prepare(s, sheaf);
> +
> + barn = get_node(s, numa_mem_id())->barn;
> +
> + /* due to slab_free_hook() */
> + if (unlikely(sheaf->size == 0))
> + goto empty;
> +
> + /*
> + * Checking nr_full/nr_empty outside lock avoids contention in case
> the
> + * barn is at the respective limit. Due to the race we might go over
> the
> + * limit but that should be rare and harmless.
> + */
> +
> + if (data_race(barn->nr_full) < MAX_FULL_SHEAVES) {
> + stat(s, BARN_PUT);
> + barn_put_full_sheaf(barn, sheaf);
> + return;
> + }
> +
> + stat(s, BARN_PUT_FAIL);
> + sheaf_flush_unused(s, sheaf);
> +
> +empty:
> + if (data_race(barn->nr_empty) < MAX_EMPTY_SHEAVES) {
> + barn_put_empty_sheaf(barn, sheaf);
> + return;
> + }
> +
> + free_empty_sheaf(s, sheaf);
> +}
> +
> +bool __kfree_rcu_sheaf(struct kmem_cache *s, void *obj)
> +{
> + struct slub_percpu_sheaves *pcs;
> + struct slab_sheaf *rcu_sheaf;
> +
> + if (!local_trylock(&s->cpu_sheaves->lock))
> + goto fail;
> +
> + pcs = this_cpu_ptr(s->cpu_sheaves);
> +
> + if (unlikely(!pcs->rcu_free)) {
> +
> + struct slab_sheaf *empty;
> +
> + empty = barn_get_empty_sheaf(pcs->barn);
> +
> + if (empty) {
> + pcs->rcu_free = empty;
> + goto do_free;
> + }
> +
> + local_unlock(&s->cpu_sheaves->lock);
> +
> + empty = alloc_empty_sheaf(s, GFP_NOWAIT);
> +
> + if (!empty)
> + goto fail;
> +
> + if (!local_trylock(&s->cpu_sheaves->lock))
Aren't you leaking `empty` sheaf on this failure?
> + goto fail;
> +
> + pcs = this_cpu_ptr(s->cpu_sheaves);
> +
> + if (unlikely(pcs->rcu_free))
> + barn_put_empty_sheaf(pcs->barn, empty);
> + else
> + pcs->rcu_free = empty;
> + }
> +
> +do_free:
> +
> + rcu_sheaf = pcs->rcu_free;
> +
> + rcu_sheaf->objects[rcu_sheaf->size++] = obj;
> +
> + if (likely(rcu_sheaf->size < s->sheaf_capacity))
> + rcu_sheaf = NULL;
> + else
> + pcs->rcu_free = NULL;
> +
> + local_unlock(&s->cpu_sheaves->lock);
> +
> + if (rcu_sheaf)
> + call_rcu(&rcu_sheaf->rcu_head, rcu_free_sheaf);
> +
> + stat(s, FREE_RCU_SHEAF);
> + return true;
> +
> +fail:
> + stat(s, FREE_RCU_SHEAF_FAIL);
> + return false;
> +}
> +
> /*
> * Bulk free objects to the percpu sheaves.
> * Unlike free_to_pcs() this includes the calls to all necessary hooks
> @@ -6802,6 +6972,11 @@ int __kmem_cache_shutdown(struct kmem_cache *s)
> struct kmem_cache_node *n;
>
> flush_all_cpus_locked(s);
> +
> + /* we might have rcu sheaves in flight */
> + if (s->cpu_sheaves)
> + rcu_barrier();
> +
> /* Attempt to free all objects */
> for_each_kmem_cache_node(s, node, n) {
> if (n->barn)
> @@ -8214,6 +8389,8 @@ STAT_ATTR(ALLOC_PCS, alloc_cpu_sheaf);
> STAT_ATTR(ALLOC_FASTPATH, alloc_fastpath);
> STAT_ATTR(ALLOC_SLOWPATH, alloc_slowpath);
> STAT_ATTR(FREE_PCS, free_cpu_sheaf);
> +STAT_ATTR(FREE_RCU_SHEAF, free_rcu_sheaf);
> +STAT_ATTR(FREE_RCU_SHEAF_FAIL, free_rcu_sheaf_fail);
> STAT_ATTR(FREE_FASTPATH, free_fastpath);
> STAT_ATTR(FREE_SLOWPATH, free_slowpath);
> STAT_ATTR(FREE_FROZEN, free_frozen);
> @@ -8312,6 +8489,8 @@ static struct attribute *slab_attrs[] = {
> &alloc_fastpath_attr.attr,
> &alloc_slowpath_attr.attr,
> &free_cpu_sheaf_attr.attr,
> + &free_rcu_sheaf_attr.attr,
> + &free_rcu_sheaf_fail_attr.attr,
> &free_fastpath_attr.attr,
> &free_slowpath_attr.attr,
> &free_frozen_attr.attr,
>
> --
> 2.49.0
>
