Merge tag 'slab-for-6.18' of git://git.kernel.org/pub/scm/linux/kernel/git/vbabka/slab

Pull slab updates from Vlastimil Babka:

 - A new layer for caching objects for allocation and free via percpu
   arrays called sheaves.

   The aim is to combine the good parts of SLAB (lower-overhead and
   simpler percpu caching, compared to SLUB) without the past issues
   with arrays for freeing remote NUMA node objects and their flushing.

   It also allows more efficient kfree_rcu(), and cheaper object
   preallocations for cases where the exact number of objects is
   unknown, but an upper bound is.

   Currently VMAs and maple nodes are using this new caching, with a
   plan to enable it for all caches and remove the complex SLUB fastpath
   based on cpu (partial) slabs and this_cpu_cmpxchg_double().
   (Vlastimil Babka, with Liam Howlett and Pedro Falcato for the maple
   tree changes)

 - Re-entrant kmalloc_nolock(), which allows opportunistic allocations
   from NMI and tracing/kprobe contexts.

   Building on prior page allocator and memcg changes, it will result in
   removing BPF-specific caches on top of slab (Alexei Starovoitov)

 - Various fixes and cleanups. (Kuan-Wei Chiu, Matthew Wilcox, Suren
   Baghdasaryan, Ye Liu)

* tag 'slab-for-6.18' of git://git.kernel.org/pub/scm/linux/kernel/git/vbabka/slab: (40 commits)
  slab: Introduce kmalloc_nolock() and kfree_nolock().
  slab: Reuse first bit for OBJEXTS_ALLOC_FAIL
  slab: Make slub local_(try)lock more precise for LOCKDEP
  mm: Introduce alloc_frozen_pages_nolock()
  mm: Allow GFP_ACCOUNT to be used in alloc_pages_nolock().
  locking/local_lock: Introduce local_lock_is_locked().
  maple_tree: Convert forking to use the sheaf interface
  maple_tree: Add single node allocation support to maple state
  maple_tree: Prefilled sheaf conversion and testing
  tools/testing: Add support for prefilled slab sheafs
  maple_tree: Replace mt_free_one() with kfree()
  maple_tree: Use kfree_rcu in ma_free_rcu
  testing/radix-tree/maple: Hack around kfree_rcu not existing
  tools/testing: include maple-shim.c in maple.c
  maple_tree: use percpu sheaves for maple_node_cache
  mm, vma: use percpu sheaves for vm_area_struct cache
  tools/testing: Add support for changes to slab for sheaves
  slab: allow NUMA restricted allocations to use percpu sheaves
  tools/testing/vma: Implement vm_refcnt reset
  slab: skip percpu sheaves for remote object freeing
  ...

1 files changed, 100 insertions, 20 deletions

diff --git a/tools/testing/shared/linux.c b/tools/testing/shared/linux.c
index 0f97fb0d19e1..8c7257155958 100644
--- a/tools/testing/shared/linux.c
+++ b/tools/testing/shared/linux.c
@@ -16,21 +16,6 @@ int nr_allocated;
 int preempt_count;
 int test_verbose;
 
-struct kmem_cache {
-	pthread_mutex_t lock;
-	unsigned int size;
-	unsigned int align;
-	int nr_objs;
-	void *objs;
-	void (*ctor)(void *);
-	unsigned int non_kernel;
-	unsigned long nr_allocated;
-	unsigned long nr_tallocated;
-	bool exec_callback;
-	void (*callback)(void *);
-	void *private;
-};
-
 void kmem_cache_set_callback(struct kmem_cache *cachep, void (*callback)(void *))
 {
 	cachep->callback = callback;
@@ -79,7 +64,8 @@ void *kmem_cache_alloc_lru(struct kmem_cache *cachep, struct list_lru *lru,
 
 	if (!(gfp & __GFP_DIRECT_RECLAIM)) {
 		if (!cachep->non_kernel) {
-			cachep->exec_callback = true;
+			if (cachep->callback)
+				cachep->exec_callback = true;
 			return NULL;
 		}
 
@@ -152,6 +138,12 @@ void kmem_cache_free_bulk(struct kmem_cache *cachep, size_t size, void **list)
 	if (kmalloc_verbose)
 		pr_debug("Bulk free %p[0-%zu]\n", list, size - 1);
 
+	if (cachep->exec_callback) {
+		if (cachep->callback)
+			cachep->callback(cachep->private);
+		cachep->exec_callback = false;
+	}
+
 	pthread_mutex_lock(&cachep->lock);
 	for (int i = 0; i < size; i++)
 		kmem_cache_free_locked(cachep, list[i]);
@@ -219,6 +211,8 @@ int kmem_cache_alloc_bulk(struct kmem_cache *cachep, gfp_t gfp, size_t size,
 		for (i = 0; i < size; i++)
 			__kmem_cache_free_locked(cachep, p[i]);
 		pthread_mutex_unlock(&cachep->lock);
+		if (cachep->callback)
+			cachep->exec_callback = true;
 		return 0;
 	}
 
@@ -234,26 +228,112 @@ int kmem_cache_alloc_bulk(struct kmem_cache *cachep, gfp_t gfp, size_t size,
 }
 
 struct kmem_cache *
-kmem_cache_create(const char *name, unsigned int size, unsigned int align,
-		unsigned int flags, void (*ctor)(void *))
+__kmem_cache_create_args(const char *name, unsigned int size,
+			  struct kmem_cache_args *args,
+			  unsigned int flags)
 {
 	struct kmem_cache *ret = malloc(sizeof(*ret));
 
 	pthread_mutex_init(&ret->lock, NULL);
 	ret->size = size;
-	ret->align = align;
+	ret->align = args->align;
+	ret->sheaf_capacity = args->sheaf_capacity;
 	ret->nr_objs = 0;
 	ret->nr_allocated = 0;
 	ret->nr_tallocated = 0;
 	ret->objs = NULL;
-	ret->ctor = ctor;
+	ret->ctor = args->ctor;
 	ret->non_kernel = 0;
 	ret->exec_callback = false;
 	ret->callback = NULL;
 	ret->private = NULL;
+
 	return ret;
 }
 
+struct slab_sheaf *
+kmem_cache_prefill_sheaf(struct kmem_cache *s, gfp_t gfp, unsigned int size)
+{
+	struct slab_sheaf *sheaf;
+	unsigned int capacity;
+
+	if (s->exec_callback) {
+		if (s->callback)
+			s->callback(s->private);
+		s->exec_callback = false;
+	}
+
+	capacity = max(size, s->sheaf_capacity);
+
+	sheaf = calloc(1, sizeof(*sheaf) + sizeof(void *) * capacity);
+	if (!sheaf)
+		return NULL;
+
+	sheaf->cache = s;
+	sheaf->capacity = capacity;
+	sheaf->size = kmem_cache_alloc_bulk(s, gfp, size, sheaf->objects);
+	if (!sheaf->size) {
+		free(sheaf);
+		return NULL;
+	}
+
+	return sheaf;
+}
+
+int kmem_cache_refill_sheaf(struct kmem_cache *s, gfp_t gfp,
+		 struct slab_sheaf **sheafp, unsigned int size)
+{
+	struct slab_sheaf *sheaf = *sheafp;
+	int refill;
+
+	if (sheaf->size >= size)
+		return 0;
+
+	if (size > sheaf->capacity) {
+		sheaf = kmem_cache_prefill_sheaf(s, gfp, size);
+		if (!sheaf)
+			return -ENOMEM;
+
+		kmem_cache_return_sheaf(s, gfp, *sheafp);
+		*sheafp = sheaf;
+		return 0;
+	}
+
+	refill = kmem_cache_alloc_bulk(s, gfp, size - sheaf->size,
+				       &sheaf->objects[sheaf->size]);
+	if (!refill)
+		return -ENOMEM;
+
+	sheaf->size += refill;
+	return 0;
+}
+
+void kmem_cache_return_sheaf(struct kmem_cache *s, gfp_t gfp,
+		 struct slab_sheaf *sheaf)
+{
+	if (sheaf->size)
+		kmem_cache_free_bulk(s, sheaf->size, &sheaf->objects[0]);
+
+	free(sheaf);
+}
+
+void *
+kmem_cache_alloc_from_sheaf(struct kmem_cache *s, gfp_t gfp,
+		struct slab_sheaf *sheaf)
+{
+	void *obj;
+
+	if (sheaf->size == 0) {
+		printf("Nothing left in sheaf!\n");
+		return NULL;
+	}
+
+	obj = sheaf->objects[--sheaf->size];
+	sheaf->objects[sheaf->size] = NULL;
+
+	return obj;
+}
+
 /*
  * Test the test infrastructure for kem_cache_alloc/free and bulk counterparts.
  */