slab: make percpu sheaves compatible with kmalloc_nolock()/kfree_nolock()

Before we enable percpu sheaves for kmalloc caches, we need to make sure
kmalloc_nolock() and kfree_nolock() will continue working properly and
not spin when not allowed to.

Percpu sheaves themselves use local_trylock() so they are already
compatible. We just need to be careful with the barn->lock spin_lock.
Pass a new allow_spin parameter where necessary to use
spin_trylock_irqsave().

In kmalloc_nolock_noprof() we can now attempt alloc_from_pcs() safely,
for now it will always fail until we enable sheaves for kmalloc caches
next. Similarly in kfree_nolock() we can attempt free_to_pcs().

Reviewed-by: Suren Baghdasaryan <surenb@google.com>
Reviewed-by: Harry Yoo <harry.yoo@oracle.com>
Reviewed-by: Hao Li <hao.li@linux.dev>
Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>

Author: tehcaster

mm/slub.c

@@ -2889,15 +2889,19 @@ static void pcs_destroy(struct kmem_cache *s)
 	s->cpu_sheaves = NULL;
 }
 
-static struct slab_sheaf *barn_get_empty_sheaf(struct node_barn *barn)
+static struct slab_sheaf *barn_get_empty_sheaf(struct node_barn *barn,
+					       bool allow_spin)
 {
 	struct slab_sheaf *empty = NULL;
 	unsigned long flags;
 
 	if (!data_race(barn->nr_empty))
 		return NULL;
 
-	spin_lock_irqsave(&barn->lock, flags);
+	if (likely(allow_spin))
+		spin_lock_irqsave(&barn->lock, flags);
+	else if (!spin_trylock_irqsave(&barn->lock, flags))
+		return NULL;
 
 	if (likely(barn->nr_empty)) {
 		empty = list_first_entry(&barn->sheaves_empty,
@@ -2974,15 +2978,19 @@ static struct slab_sheaf *barn_get_full_or_empty_sheaf(struct node_barn *barn)
  * change.
  */
 static struct slab_sheaf *
-barn_replace_empty_sheaf(struct node_barn *barn, struct slab_sheaf *empty)
+barn_replace_empty_sheaf(struct node_barn *barn, struct slab_sheaf *empty,
+			 bool allow_spin)
 {
 	struct slab_sheaf *full = NULL;
 	unsigned long flags;
 
 	if (!data_race(barn->nr_full))
 		return NULL;
 
-	spin_lock_irqsave(&barn->lock, flags);
+	if (likely(allow_spin))
+		spin_lock_irqsave(&barn->lock, flags);
+	else if (!spin_trylock_irqsave(&barn->lock, flags))
+		return NULL;
 
 	if (likely(barn->nr_full)) {
 		full = list_first_entry(&barn->sheaves_full, struct slab_sheaf,
@@ -3003,7 +3011,8 @@ barn_replace_empty_sheaf(struct node_barn *barn, struct slab_sheaf *empty)
  * barn. But if there are too many full sheaves, reject this with -E2BIG.
  */
 static struct slab_sheaf *
-barn_replace_full_sheaf(struct node_barn *barn, struct slab_sheaf *full)
+barn_replace_full_sheaf(struct node_barn *barn, struct slab_sheaf *full,
+			bool allow_spin)
 {
 	struct slab_sheaf *empty;
 	unsigned long flags;
@@ -3014,7 +3023,10 @@ barn_replace_full_sheaf(struct node_barn *barn, struct slab_sheaf *full)
 	if (!data_race(barn->nr_empty))
 		return ERR_PTR(-ENOMEM);
 
-	spin_lock_irqsave(&barn->lock, flags);
+	if (likely(allow_spin))
+		spin_lock_irqsave(&barn->lock, flags);
+	else if (!spin_trylock_irqsave(&barn->lock, flags))
+		return ERR_PTR(-EBUSY);
 
 	if (likely(barn->nr_empty)) {
 		empty = list_first_entry(&barn->sheaves_empty, struct slab_sheaf,
@@ -5008,7 +5020,8 @@ __pcs_replace_empty_main(struct kmem_cache *s, struct slub_percpu_sheaves *pcs,
 		return NULL;
 	}
 
-	full = barn_replace_empty_sheaf(barn, pcs->main);
+	full = barn_replace_empty_sheaf(barn, pcs->main,
+					gfpflags_allow_spinning(gfp));
 
 	if (full) {
 		stat(s, BARN_GET);
@@ -5025,7 +5038,7 @@ __pcs_replace_empty_main(struct kmem_cache *s, struct slub_percpu_sheaves *pcs,
 			empty = pcs->spare;
 			pcs->spare = NULL;
 		} else {
-			empty = barn_get_empty_sheaf(barn);
+			empty = barn_get_empty_sheaf(barn, true);
 		}
 	}
 
@@ -5165,7 +5178,8 @@ void *alloc_from_pcs(struct kmem_cache *s, gfp_t gfp, int node)
 }
 
 static __fastpath_inline
-unsigned int alloc_from_pcs_bulk(struct kmem_cache *s, size_t size, void **p)
+unsigned int alloc_from_pcs_bulk(struct kmem_cache *s, gfp_t gfp, size_t size,
+				 void **p)
 {
 	struct slub_percpu_sheaves *pcs;
 	struct slab_sheaf *main;
@@ -5199,7 +5213,8 @@ unsigned int alloc_from_pcs_bulk(struct kmem_cache *s, size_t size, void **p)
 			return allocated;
 		}
 
-		full = barn_replace_empty_sheaf(barn, pcs->main);
+		full = barn_replace_empty_sheaf(barn, pcs->main,
+						gfpflags_allow_spinning(gfp));
 
 		if (full) {
 			stat(s, BARN_GET);
@@ -5700,7 +5715,7 @@ void *kmalloc_nolock_noprof(size_t size, gfp_t gfp_flags, int node)
 	gfp_t alloc_gfp = __GFP_NOWARN | __GFP_NOMEMALLOC | gfp_flags;
 	struct kmem_cache *s;
 	bool can_retry = true;
-	void *ret = ERR_PTR(-EBUSY);
+	void *ret;
 
 	VM_WARN_ON_ONCE(gfp_flags & ~(__GFP_ACCOUNT | __GFP_ZERO |
 				      __GFP_NO_OBJ_EXT));
@@ -5731,6 +5746,12 @@ void *kmalloc_nolock_noprof(size_t size, gfp_t gfp_flags, int node)
 		 */
 		return NULL;
 
+	ret = alloc_from_pcs(s, alloc_gfp, node);
+	if (ret)
+		goto success;
+
+	ret = ERR_PTR(-EBUSY);
+
 	/*
 	 * Do not call slab_alloc_node(), since trylock mode isn't
 	 * compatible with slab_pre_alloc_hook/should_failslab and
@@ -5767,6 +5788,7 @@ void *kmalloc_nolock_noprof(size_t size, gfp_t gfp_flags, int node)
 		ret = NULL;
 	}
 
+success:
 	maybe_wipe_obj_freeptr(s, ret);
 	slab_post_alloc_hook(s, NULL, alloc_gfp, 1, &ret,
 			     slab_want_init_on_alloc(alloc_gfp, s), size);
@@ -6087,7 +6109,8 @@ static void __pcs_install_empty_sheaf(struct kmem_cache *s,
  * unlocked.
  */
 static struct slub_percpu_sheaves *
-__pcs_replace_full_main(struct kmem_cache *s, struct slub_percpu_sheaves *pcs)
+__pcs_replace_full_main(struct kmem_cache *s, struct slub_percpu_sheaves *pcs,
+			bool allow_spin)
 {
 	struct slab_sheaf *empty;
 	struct node_barn *barn;
@@ -6111,7 +6134,7 @@ __pcs_replace_full_main(struct kmem_cache *s, struct slub_percpu_sheaves *pcs)
 	put_fail = false;
 
 	if (!pcs->spare) {
-		empty = barn_get_empty_sheaf(barn);
+		empty = barn_get_empty_sheaf(barn, allow_spin);
 		if (empty) {
 			pcs->spare = pcs->main;
 			pcs->main = empty;
@@ -6125,15 +6148,16 @@ __pcs_replace_full_main(struct kmem_cache *s, struct slub_percpu_sheaves *pcs)
 		return pcs;
 	}
 
-	empty = barn_replace_full_sheaf(barn, pcs->main);
+	empty = barn_replace_full_sheaf(barn, pcs->main, allow_spin);
 
 	if (!IS_ERR(empty)) {
 		stat(s, BARN_PUT);
 		pcs->main = empty;
 		return pcs;
 	}
 
-	if (PTR_ERR(empty) == -E2BIG) {
+	/* sheaf_flush_unused() doesn't support !allow_spin */
+	if (PTR_ERR(empty) == -E2BIG && allow_spin) {
 		/* Since we got here, spare exists and is full */
 		struct slab_sheaf *to_flush = pcs->spare;
 
@@ -6158,6 +6182,14 @@ __pcs_replace_full_main(struct kmem_cache *s, struct slub_percpu_sheaves *pcs)
 alloc_empty:
 	local_unlock(&s->cpu_sheaves->lock);
 
+	/*
+	 * alloc_empty_sheaf() doesn't support !allow_spin and it's
+	 * easier to fall back to freeing directly without sheaves
+	 * than add the support (and to sheaf_flush_unused() above)
+	 */
+	if (!allow_spin)
+		return NULL;
+
 	empty = alloc_empty_sheaf(s, GFP_NOWAIT);
 	if (empty)
 		goto got_empty;
@@ -6200,7 +6232,7 @@ __pcs_replace_full_main(struct kmem_cache *s, struct slub_percpu_sheaves *pcs)
  * The object is expected to have passed slab_free_hook() already.
  */
 static __fastpath_inline
-bool free_to_pcs(struct kmem_cache *s, void *object)
+bool free_to_pcs(struct kmem_cache *s, void *object, bool allow_spin)
 {
 	struct slub_percpu_sheaves *pcs;
 
@@ -6211,7 +6243,7 @@ bool free_to_pcs(struct kmem_cache *s, void *object)
 
 	if (unlikely(pcs->main->size == s->sheaf_capacity)) {
 
-		pcs = __pcs_replace_full_main(s, pcs);
+		pcs = __pcs_replace_full_main(s, pcs, allow_spin);
 		if (unlikely(!pcs))
 			return false;
 	}
@@ -6336,7 +6368,7 @@ bool __kfree_rcu_sheaf(struct kmem_cache *s, void *obj)
 			goto fail;
 		}
 
-		empty = barn_get_empty_sheaf(barn);
+		empty = barn_get_empty_sheaf(barn, true);
 
 		if (empty) {
 			pcs->rcu_free = empty;
@@ -6456,7 +6488,7 @@ static void free_to_pcs_bulk(struct kmem_cache *s, size_t size, void **p)
 		goto no_empty;
 
 	if (!pcs->spare) {
-		empty = barn_get_empty_sheaf(barn);
+		empty = barn_get_empty_sheaf(barn, true);
 		if (!empty)
 			goto no_empty;
 
@@ -6470,7 +6502,7 @@ static void free_to_pcs_bulk(struct kmem_cache *s, size_t size, void **p)
 		goto do_free;
 	}
 
-	empty = barn_replace_full_sheaf(barn, pcs->main);
+	empty = barn_replace_full_sheaf(barn, pcs->main, true);
 	if (IS_ERR(empty)) {
 		stat(s, BARN_PUT_FAIL);
 		goto no_empty;
@@ -6722,7 +6754,7 @@ void slab_free(struct kmem_cache *s, struct slab *slab, void *object,
 
 	if (likely(!IS_ENABLED(CONFIG_NUMA) || slab_nid(slab) == numa_mem_id())
 	    && likely(!slab_test_pfmemalloc(slab))) {
-		if (likely(free_to_pcs(s, object)))
+		if (likely(free_to_pcs(s, object, true)))
 			return;
 	}
 
@@ -6993,6 +7025,12 @@ void kfree_nolock(const void *object)
 	 * since kasan quarantine takes locks and not supported from NMI.
 	 */
 	kasan_slab_free(s, x, false, false, /* skip quarantine */true);
+
+	if (likely(!IS_ENABLED(CONFIG_NUMA) || slab_nid(slab) == numa_mem_id())) {
+		if (likely(free_to_pcs(s, x, false)))
+			return;
+	}
+
 	do_slab_free(s, slab, x, x, 0, _RET_IP_);
 }
 EXPORT_SYMBOL_GPL(kfree_nolock);
@@ -7545,7 +7583,7 @@ int kmem_cache_alloc_bulk_noprof(struct kmem_cache *s, gfp_t flags, size_t size,
 		size--;
 	}
 
-	i = alloc_from_pcs_bulk(s, size, p);
+	i = alloc_from_pcs_bulk(s, flags, size, p);
 
 	if (i < size) {
 		/*