+ radix-tree-test-suite-add-support-for-slab-bulk-apis.patch added to mm-unstable branch

[Andrew Morton <akpm@linux-foundation.org>]

The patch titled
     Subject: radix tree test suite: add support for slab bulk APIs
has been added to the -mm mm-unstable branch.  Its filename is
     radix-tree-test-suite-add-support-for-slab-bulk-apis.patch

This patch will shortly appear at
     https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/radix-tree-test-suite-add-support-for-slab-bulk-apis.patch

This patch will later appear in the mm-unstable branch at
    git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Before you just go and hit "reply", please:
   a) Consider who else should be cc'ed
   b) Prefer to cc a suitable mailing list as well
   c) Ideally: find the original patch on the mailing list and do a
      reply-to-all to that, adding suitable additional cc's

*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***

The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days

------------------------------------------------------
From: "Liam R. Howlett" <Liam.Howlett@Oracle.com>
Subject: radix tree test suite: add support for slab bulk APIs
Date: Mon, 22 Aug 2022 15:02:29 +0000

Add support for kmem_cache_free_bulk() and kmem_cache_alloc_bulk() to the
radix tree test suite.

Link: https://lkml.kernel.org/r/20220822150128.1562046-6-Liam.Howlett@oracle.com
Signed-off-by: Liam R. Howlett <Liam.Howlett@Oracle.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: David Howells <dhowells@redhat.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: SeongJae Park <sj@kernel.org>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Will Deacon <will@kernel.org>
Cc: Yu Zhao <yuzhao@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 tools/include/linux/slab.h       |    4 
 tools/testing/radix-tree/linux.c |  118 ++++++++++++++++++++++++++++-
 2 files changed, 120 insertions(+), 2 deletions(-)

--- a/tools/include/linux/slab.h~radix-tree-test-suite-add-support-for-slab-bulk-apis
+++ a/tools/include/linux/slab.h
@@ -41,4 +41,8 @@ struct kmem_cache *kmem_cache_create(con
 			unsigned int align, unsigned int flags,
 			void (*ctor)(void *));
 
+void kmem_cache_free_bulk(struct kmem_cache *cachep, size_t size, void **list);
+int kmem_cache_alloc_bulk(struct kmem_cache *cachep, gfp_t gfp, size_t size,
+			  void **list);
+
 #endif		/* _TOOLS_SLAB_H */
--- a/tools/testing/radix-tree/linux.c~radix-tree-test-suite-add-support-for-slab-bulk-apis
+++ a/tools/testing/radix-tree/linux.c
@@ -93,14 +93,13 @@ void *kmem_cache_alloc_lru(struct kmem_c
 	return p;
 }
 
-void kmem_cache_free(struct kmem_cache *cachep, void *objp)
+void kmem_cache_free_locked(struct kmem_cache *cachep, void *objp)
 {
 	assert(objp);
 	uatomic_dec(&nr_allocated);
 	uatomic_dec(&cachep->nr_allocated);
 	if (kmalloc_verbose)
 		printf("Freeing %p to slab\n", objp);
-	pthread_mutex_lock(&cachep->lock);
 	if (cachep->nr_objs > 10 || cachep->align) {
 		memset(objp, POISON_FREE, cachep->size);
 		free(objp);
@@ -110,9 +109,80 @@ void kmem_cache_free(struct kmem_cache *
 		node->parent = cachep->objs;
 		cachep->objs = node;
 	}
+}
+
+void kmem_cache_free(struct kmem_cache *cachep, void *objp)
+{
+	pthread_mutex_lock(&cachep->lock);
+	kmem_cache_free_locked(cachep, objp);
+	pthread_mutex_unlock(&cachep->lock);
+}
+
+void kmem_cache_free_bulk(struct kmem_cache *cachep, size_t size, void **list)
+{
+	if (kmalloc_verbose)
+		pr_debug("Bulk free %p[0-%lu]\n", list, size - 1);
+
+	pthread_mutex_lock(&cachep->lock);
+	for (int i = 0; i < size; i++)
+		kmem_cache_free_locked(cachep, list[i]);
 	pthread_mutex_unlock(&cachep->lock);
 }
 
+int kmem_cache_alloc_bulk(struct kmem_cache *cachep, gfp_t gfp, size_t size,
+			  void **p)
+{
+	size_t i;
+
+	if (kmalloc_verbose)
+		pr_debug("Bulk alloc %lu\n", size);
+
+	if (!(gfp & __GFP_DIRECT_RECLAIM)) {
+		if (cachep->non_kernel < size)
+			return 0;
+
+		cachep->non_kernel -= size;
+	}
+
+	pthread_mutex_lock(&cachep->lock);
+	if (cachep->nr_objs >= size) {
+		struct radix_tree_node *node;
+
+		for (i = 0; i < size; i++) {
+			node = cachep->objs;
+			cachep->nr_objs--;
+			cachep->objs = node->parent;
+			p[i] = node;
+			node->parent = NULL;
+		}
+		pthread_mutex_unlock(&cachep->lock);
+	} else {
+		pthread_mutex_unlock(&cachep->lock);
+		for (i = 0; i < size; i++) {
+			if (cachep->align) {
+				posix_memalign(&p[i], cachep->align,
+					       cachep->size * size);
+			} else {
+				p[i] = malloc(cachep->size * size);
+			}
+			if (cachep->ctor)
+				cachep->ctor(p[i]);
+			else if (gfp & __GFP_ZERO)
+				memset(p[i], 0, cachep->size);
+		}
+	}
+
+	for (i = 0; i < size; i++) {
+		uatomic_inc(&nr_allocated);
+		uatomic_inc(&cachep->nr_allocated);
+		uatomic_inc(&cachep->nr_tallocated);
+		if (kmalloc_verbose)
+			printf("Allocating %p from slab\n", p[i]);
+	}
+
+	return size;
+}
+
 struct kmem_cache *
 kmem_cache_create(const char *name, unsigned int size, unsigned int align,
 		unsigned int flags, void (*ctor)(void *))
@@ -130,3 +200,47 @@ kmem_cache_create(const char *name, unsi
 	ret->non_kernel = 0;
 	return ret;
 }
+
+/*
+ * Test the test infrastructure for kem_cache_alloc/free and bulk counterparts.
+ */
+void test_kmem_cache_bulk(void)
+{
+	int i;
+	void *list[12];
+	static struct kmem_cache *test_cache, *test_cache2;
+
+	/*
+	 * Testing the bulk allocators without aligned kmem_cache to force the
+	 * bulk alloc/free to reuse
+	 */
+	test_cache = kmem_cache_create("test_cache", 256, 0, SLAB_PANIC, NULL);
+
+	for (i = 0; i < 5; i++)
+		list[i] = kmem_cache_alloc(test_cache, __GFP_DIRECT_RECLAIM);
+
+	for (i = 0; i < 5; i++)
+		kmem_cache_free(test_cache, list[i]);
+	assert(test_cache->nr_objs == 5);
+
+	kmem_cache_alloc_bulk(test_cache, __GFP_DIRECT_RECLAIM, 5, list);
+	kmem_cache_free_bulk(test_cache, 5, list);
+
+	for (i = 0; i < 12 ; i++)
+		list[i] = kmem_cache_alloc(test_cache, __GFP_DIRECT_RECLAIM);
+
+	for (i = 0; i < 12; i++)
+		kmem_cache_free(test_cache, list[i]);
+
+	/* The last free will not be kept around */
+	assert(test_cache->nr_objs == 11);
+
+	/* Aligned caches will immediately free */
+	test_cache2 = kmem_cache_create("test_cache2", 128, 128, SLAB_PANIC, NULL);
+
+	kmem_cache_alloc_bulk(test_cache2, __GFP_DIRECT_RECLAIM, 10, list);
+	kmem_cache_free_bulk(test_cache2, 10, list);
+	assert(!test_cache2->nr_objs);
+
+
+}
_

Patches currently in -mm which might be from Liam.Howlett@Oracle.com are

maple-tree-add-new-data-structure.patch
radix-tree-test-suite-add-pr_err-define.patch
radix-tree-test-suite-add-kmem_cache_set_non_kernel.patch
radix-tree-test-suite-add-allocation-counts-and-size-to-kmem_cache.patch
radix-tree-test-suite-add-support-for-slab-bulk-apis.patch
radix-tree-test-suite-add-lockdep_is_held-to-header.patch
lib-test_maple_tree-add-testing-for-maple-tree.patch
mm-start-tracking-vmas-with-maple-tree.patch
mm-mmap-use-the-maple-tree-in-find_vma-instead-of-the-rbtree.patch
mm-mmap-use-the-maple-tree-for-find_vma_prev-instead-of-the-rbtree.patch
mm-mmap-use-maple-tree-for-unmapped_area_topdown.patch
kernel-fork-use-maple-tree-for-dup_mmap-during-forking.patch
damon-convert-__damon_va_three_regions-to-use-the-vma-iterator.patch
mm-remove-rb-tree.patch
mmap-change-zeroing-of-maple-tree-in-__vma_adjust.patch
xen-use-vma_lookup-in-privcmd_ioctl_mmap.patch
mm-optimize-find_exact_vma-to-use-vma_lookup.patch
mm-khugepaged-optimize-collapse_pte_mapped_thp-by-using-vma_lookup.patch
mm-mmap-change-do_brk_flags-to-expand-existing-vma-and-add-do_brk_munmap.patch
mm-use-maple-tree-operations-for-find_vma_intersection.patch
mm-mmap-use-advanced-maple-tree-api-for-mmap_region.patch
mm-remove-vmacache.patch
mm-convert-vma_lookup-to-use-mtree_load.patch
mm-mmap-move-mmap_region-below-do_munmap.patch
mm-mmap-reorganize-munmap-to-use-maple-states.patch
mm-mmap-change-do_brk_munmap-to-use-do_mas_align_munmap.patch
arm64-change-elfcore-for_each_mte_vma-to-use-vma-iterator.patch
fs-proc-base-use-maple-tree-iterators-in-place-of-linked-list.patch
userfaultfd-use-maple-tree-iterator-to-iterate-vmas.patch
ipc-shm-use-vma-iterator-instead-of-linked-list.patch
bpf-remove-vma-linked-list.patch
mm-gup-use-maple-tree-navigation-instead-of-linked-list.patch
mm-madvise-use-vma_find-instead-of-vma-linked-list.patch
mm-memcontrol-stop-using-mm-highest_vm_end.patch
mm-mempolicy-use-vma-iterator-maple-state-instead-of-vma-linked-list.patch
mm-mprotect-use-maple-tree-navigation-instead-of-vma-linked-list.patch
mm-mremap-use-vma_find_intersection-instead-of-vma-linked-list.patch
mm-msync-use-vma_find-instead-of-vma-linked-list.patch
mm-oom_kill-use-maple-tree-iterators-instead-of-vma-linked-list.patch
mm-swapfile-use-vma-iterator-instead-of-vma-linked-list.patch
riscv-use-vma-iterator-for-vdso.patch
mm-remove-the-vma-linked-list.patch
mm-mmap-drop-range_has_overlap-function.patch
mm-mmapc-pass-in-mapping-to-__vma_link_file.patch