| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <b295680c-a9f3-4328-9c76-3c59b22df55e@linux.dev>
Date: Wed, 25 Oct 2023 10:18:16 +0800
From: Chengming Zhou <chengming.zhou@...ux.dev>
To: cl@...ux.com, penberg@...nel.org
Cc: rientjes@...gle.com, iamjoonsoo.kim@....com,
akpm@...ux-foundation.org, vbabka@...e.cz,
roman.gushchin@...ux.dev, 42.hyeyoo@...il.com, linux-mm@...ck.org,
linux-kernel@...r.kernel.org,
Chengming Zhou <zhouchengming@...edance.com>
Subject: Re: [RFC PATCH v3 6/7] slub: Delay freezing of partial slabs
On 2023/10/24 17:33, chengming.zhou@...ux.dev wrote:
> From: Chengming Zhou <zhouchengming@...edance.com>
>
> Now we will freeze slabs when moving them out of node partial list to
> cpu partial list, this method needs two cmpxchg_double operations:
>
> 1. freeze slab (acquire_slab()) under the node list_lock
> 2. get_freelist() when pick used in ___slab_alloc()
>
> Actually we don't need to freeze when moving slabs out of node partial
> list, we can delay freezing to when use slab freelist in ___slab_alloc(),
> so we can save one cmpxchg_double().
>
> And there are other good points:
> - The moving of slabs between node partial list and cpu partial list
> becomes simpler, since we don't need to freeze or unfreeze at all.
>
> - The node list_lock contention would be less, since we don't need to
> freeze any slab under the node list_lock.
>
> We can achieve this because there is no concurrent path would manipulate
> the partial slab list except the __slab_free() path, which is serialized
> now.
>
> Since the slab returned by get_partial() interfaces is not frozen anymore
> and no freelist in the partial_context, so we need to use the introduced
> freeze_slab() to freeze it and get its freelist.
>
> Similarly, the slabs on the CPU partial list are not frozen anymore,
> we need to freeze_slab() on it before use.
>
> Signed-off-by: Chengming Zhou <zhouchengming@...edance.com>
> ---
> mm/slub.c | 111 +++++++++++-------------------------------------------
> 1 file changed, 21 insertions(+), 90 deletions(-)
>
> diff --git a/mm/slub.c b/mm/slub.c
> index 5b428648021f..486d44421432 100644
> --- a/mm/slub.c
> +++ b/mm/slub.c
> @@ -2215,51 +2215,6 @@ static void *alloc_single_from_new_slab(struct kmem_cache *s,
> return object;
> }
>
> -/*
> - * Remove slab from the partial list, freeze it and
> - * return the pointer to the freelist.
> - *
> - * Returns a list of objects or NULL if it fails.
> - */
> -static inline void *acquire_slab(struct kmem_cache *s,
> - struct kmem_cache_node *n, struct slab *slab,
> - int mode)
> -{
> - void *freelist;
> - unsigned long counters;
> - struct slab new;
> -
> - lockdep_assert_held(&n->list_lock);
> -
> - /*
> - * Zap the freelist and set the frozen bit.
> - * The old freelist is the list of objects for the
> - * per cpu allocation list.
> - */
> - freelist = slab->freelist;
> - counters = slab->counters;
> - new.counters = counters;
> - if (mode) {
> - new.inuse = slab->objects;
> - new.freelist = NULL;
> - } else {
> - new.freelist = freelist;
> - }
> -
> - VM_BUG_ON(new.frozen);
> - new.frozen = 1;
> -
> - if (!__slab_update_freelist(s, slab,
> - freelist, counters,
> - new.freelist, new.counters,
> - "acquire_slab"))
> - return NULL;
> -
> - remove_partial(n, slab);
> - WARN_ON(!freelist);
> - return freelist;
> -}
> -
> #ifdef CONFIG_SLUB_CPU_PARTIAL
> static void put_cpu_partial(struct kmem_cache *s, struct slab *slab, int drain);
> #else
> @@ -2276,7 +2231,6 @@ static struct slab *get_partial_node(struct kmem_cache *s,
> struct partial_context *pc)
> {
> struct slab *slab, *slab2, *partial = NULL;
> - void *object = NULL;
> unsigned long flags;
> unsigned int partial_slabs = 0;
>
> @@ -2295,7 +2249,7 @@ static struct slab *get_partial_node(struct kmem_cache *s,
> continue;
>
> if (IS_ENABLED(CONFIG_SLUB_TINY) || kmem_cache_debug(s)) {
> - object = alloc_single_from_partial(s, n, slab,
> + void *object = alloc_single_from_partial(s, n, slab,
> pc->orig_size);
> if (object) {
> partial = slab;
> @@ -2305,13 +2259,10 @@ static struct slab *get_partial_node(struct kmem_cache *s,
> continue;
> }
>
> - object = acquire_slab(s, n, slab, object == NULL);
> - if (!object)
> - break;
> + remove_partial(n, slab);
>
> if (!partial) {
> partial = slab;
> - pc->object = object;
> stat(s, ALLOC_FROM_PARTIAL);
> } else {
> put_cpu_partial(s, slab, 0);
> @@ -2610,9 +2561,6 @@ static void __unfreeze_partials(struct kmem_cache *s, struct slab *partial_slab)
> unsigned long flags = 0;
>
> while (partial_slab) {
> - struct slab new;
> - struct slab old;
> -
> slab = partial_slab;
> partial_slab = slab->next;
>
> @@ -2625,23 +2573,7 @@ static void __unfreeze_partials(struct kmem_cache *s, struct slab *partial_slab)
> spin_lock_irqsave(&n->list_lock, flags);
> }
>
> - do {
> -
> - old.freelist = slab->freelist;
> - old.counters = slab->counters;
> - VM_BUG_ON(!old.frozen);
> -
> - new.counters = old.counters;
> - new.freelist = old.freelist;
> -
> - new.frozen = 0;
> -
> - } while (!__slab_update_freelist(s, slab,
> - old.freelist, old.counters,
> - new.freelist, new.counters,
> - "unfreezing slab"));
> -
> - if (unlikely(!new.inuse && n->nr_partial >= s->min_partial)) {
> + if (unlikely(!slab->inuse && n->nr_partial >= s->min_partial)) {
> slab->next = slab_to_discard;
> slab_to_discard = slab;
> } else {
> @@ -3148,7 +3080,6 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
> node = NUMA_NO_NODE;
> goto new_slab;
> }
> -redo:
>
> if (unlikely(!node_match(slab, node))) {
> /*
> @@ -3224,7 +3155,7 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
>
> new_slab:
>
> - if (slub_percpu_partial(c)) {
> + while (slub_percpu_partial(c)) {
> local_lock_irqsave(&s->cpu_slab->lock, flags);
> if (unlikely(c->slab)) {
> local_unlock_irqrestore(&s->cpu_slab->lock, flags);
> @@ -3236,11 +3167,20 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
> goto new_objects;
> }
>
> - slab = c->slab = slub_percpu_partial(c);
> + slab = slub_percpu_partial(c);
> slub_set_percpu_partial(c, slab);
> local_unlock_irqrestore(&s->cpu_slab->lock, flags);
> stat(s, CPU_PARTIAL_ALLOC);
> - goto redo;
> +
> + if (unlikely(!node_match(slab, node) ||
> + !pfmemalloc_match(slab, gfpflags))) {
> + slab->next = NULL;
> + __unfreeze_partials(s, slab);
> + continue;
> + }
> +
> + freelist = freeze_slab(s, slab);
> + goto retry_load_slab;
> }
Oops, this while(slub_percpu_partial(c)) loop block should be put in #ifdef CONFIG_SLUB_CPU_PARTIAL,
since the slab->next and __unfreeze_partials() only defined when CONFIG_SLUB_CPU_PARTIAL.
And I should append a cleanup patch to rename all *unfreeze_partials* functions to *put_partials*
since there is no "unfreeze" in these functions anymore.
Will do in the next version.
Thanks.
>
> new_objects:
> @@ -3249,8 +3189,8 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
> pc.orig_size = orig_size;
> slab = get_partial(s, node, &pc);
> if (slab) {
> - freelist = pc.object;
> if (kmem_cache_debug(s)) {
> + freelist = pc.object;
> /*
> * For debug caches here we had to go through
> * alloc_single_from_partial() so just store the
> @@ -3262,6 +3202,7 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
> return freelist;
> }
>
> + freelist = freeze_slab(s, slab);
> goto retry_load_slab;
> }
>
> @@ -3663,18 +3604,8 @@ static void __slab_free(struct kmem_cache *s, struct slab *slab,
> was_frozen = new.frozen;
> new.inuse -= cnt;
> if ((!new.inuse || !prior) && !was_frozen) {
> -
> - if (kmem_cache_has_cpu_partial(s) && !prior) {
> -
> - /*
> - * Slab was on no list before and will be
> - * partially empty
> - * We can defer the list move and instead
> - * freeze it.
> - */
> - new.frozen = 1;
> -
> - } else { /* Needs to be taken off a list */
> + /* Needs to be taken off a list */
> + if (!kmem_cache_has_cpu_partial(s) || prior) {
>
> n = get_node(s, slab_nid(slab));
> /*
> @@ -3704,9 +3635,9 @@ static void __slab_free(struct kmem_cache *s, struct slab *slab,
> * activity can be necessary.
> */
> stat(s, FREE_FROZEN);
> - } else if (new.frozen) {
> + } else if (kmem_cache_has_cpu_partial(s) && !prior) {
> /*
> - * If we just froze the slab then put it onto the
> + * If we started with a full slab then put it onto the
> * per cpu partial list.
> */
> put_cpu_partial(s, slab, 1);
Powered by blists - more mailing lists