mm/slub: allow to set node and align in k[v]realloc

Reimplement k[v]realloc_node() to be able to set node and alignment should
a user need to do so.  In order to do that while retaining the maximal
backward compatibility, add k[v]realloc_node_align() functions and
redefine the rest of API using these new ones.

While doing that, we also keep the number of _noprof variants to a
minimum, which implies some changes to the existing users of older _noprof
functions, that basically being bcachefs.

With that change we also provide the ability for the Rust part of the
kernel to set node and alignment in its K[v]xxx [re]allocations.

Link: https://lkml.kernel.org/r/20250806124147.1724658-1-vitaly.wool@konsulko.se
Signed-off-by: Vitaly Wool <vitaly.wool@konsulko.se>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Alice Ryhl <aliceryhl@google.com>
Cc: Danilo Krummrich <dakr@kernel.org>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Jann Horn <jannh@google.com>
Cc: Kent Overstreet <kent.overstreet@linux.dev>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Uladzislau Rezki (Sony) <urezki@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

fs/bcachefs/darray.c

@@ -21,7 +21,7 @@ int __bch2_darray_resize_noprof(darray_char *d, size_t element_size, size_t new_
 			return -ENOMEM;
 
 		void *data = likely(bytes < INT_MAX)
-			? kvmalloc_noprof(bytes, gfp)
+			? kvmalloc_node_align_noprof(bytes, 1, gfp, NUMA_NO_NODE)
 			: vmalloc_noprof(bytes);
 		if (!data)
 			return -ENOMEM;

fs/bcachefs/util.h

@@ -61,7 +61,7 @@ static inline void *bch2_kvmalloc_noprof(size_t n, gfp_t flags)
 {
 	void *p = unlikely(n >= INT_MAX)
 		? vmalloc_noprof(n)
-		: kvmalloc_noprof(n, flags & ~__GFP_ZERO);
+		: kvmalloc_node_align_noprof(n, 1, flags & ~__GFP_ZERO, NUMA_NO_NODE);
 	if (p && (flags & __GFP_ZERO))
 		memset(p, 0, n);
 	return p;

include/linux/bpfptr.h

@@ -67,7 +67,7 @@ static inline int copy_to_bpfptr_offset(bpfptr_t dst, size_t offset,
 
 static inline void *kvmemdup_bpfptr_noprof(bpfptr_t src, size_t len)
 {
-	void *p = kvmalloc_noprof(len, GFP_USER | __GFP_NOWARN);
+	void *p = kvmalloc_node_align_noprof(len, 1, GFP_USER | __GFP_NOWARN, NUMA_NO_NODE);
 
 	if (!p)
 		return ERR_PTR(-ENOMEM);

include/linux/slab.h

@@ -465,9 +465,13 @@ int kmem_cache_shrink(struct kmem_cache *s);
 /*
  * Common kmalloc functions provided by all allocators
  */
-void * __must_check krealloc_noprof(const void *objp, size_t new_size,
+void * __must_check krealloc_node_align_noprof(const void *objp, size_t new_size,
-				    gfp_t flags) __realloc_size(2);
+					       unsigned long align,
-#define krealloc(...)				alloc_hooks(krealloc_noprof(__VA_ARGS__))
+					       gfp_t flags, int nid) __realloc_size(2);
+#define krealloc_noprof(_o, _s, _f)	krealloc_node_align_noprof(_o, _s, 1, _f, NUMA_NO_NODE)
+#define krealloc_node_align(...)	alloc_hooks(krealloc_node_align_noprof(__VA_ARGS__))
+#define krealloc_node(_o, _s, _f, _n)	krealloc_node_align(_o, _s, 1, _f, _n)
+#define krealloc(...)			krealloc_node(__VA_ARGS__, NUMA_NO_NODE)
 
 void kfree(const void *objp);
 void kfree_sensitive(const void *objp);
@@ -1041,18 +1045,20 @@ static inline __alloc_size(1) void *kzalloc_noprof(size_t size, gfp_t flags)
 #define kzalloc(...)				alloc_hooks(kzalloc_noprof(__VA_ARGS__))
 #define kzalloc_node(_size, _flags, _node)	kmalloc_node(_size, (_flags)|__GFP_ZERO, _node)
 
-void *__kvmalloc_node_noprof(DECL_BUCKET_PARAMS(size, b), gfp_t flags, int node) __alloc_size(1);
+void *__kvmalloc_node_noprof(DECL_BUCKET_PARAMS(size, b), unsigned long align,
-#define kvmalloc_node_noprof(size, flags, node)	\
+			     gfp_t flags, int node) __alloc_size(1);
-	__kvmalloc_node_noprof(PASS_BUCKET_PARAMS(size, NULL), flags, node)
+#define kvmalloc_node_align_noprof(_size, _align, _flags, _node)	\
-#define kvmalloc_node(...)			alloc_hooks(kvmalloc_node_noprof(__VA_ARGS__))
+	__kvmalloc_node_noprof(PASS_BUCKET_PARAMS(_size, NULL), _align, _flags, _node)
-
+#define kvmalloc_node_align(...)		\
-#define kvmalloc(_size, _flags)			kvmalloc_node(_size, _flags, NUMA_NO_NODE)
+	alloc_hooks(kvmalloc_node_align_noprof(__VA_ARGS__))
-#define kvmalloc_noprof(_size, _flags)		kvmalloc_node_noprof(_size, _flags, NUMA_NO_NODE)
+#define kvmalloc_node(_s, _f, _n)		kvmalloc_node_align(_s, 1, _f, _n)
+#define kvmalloc(...)				kvmalloc_node(__VA_ARGS__, NUMA_NO_NODE)
 #define kvzalloc(_size, _flags)			kvmalloc(_size, (_flags)|__GFP_ZERO)
 
 #define kvzalloc_node(_size, _flags, _node)	kvmalloc_node(_size, (_flags)|__GFP_ZERO, _node)
+
 #define kmem_buckets_valloc(_b, _size, _flags)	\
-	alloc_hooks(__kvmalloc_node_noprof(PASS_BUCKET_PARAMS(_size, _b), _flags, NUMA_NO_NODE))
+	alloc_hooks(__kvmalloc_node_noprof(PASS_BUCKET_PARAMS(_size, _b), 1, _flags, NUMA_NO_NODE))
 
 static inline __alloc_size(1, 2) void *
 kvmalloc_array_node_noprof(size_t n, size_t size, gfp_t flags, int node)
@@ -1062,7 +1068,7 @@ kvmalloc_array_node_noprof(size_t n, size_t size, gfp_t flags, int node)
 	if (unlikely(check_mul_overflow(n, size, &bytes)))
 		return NULL;
 
-	return kvmalloc_node_noprof(bytes, flags, node);
+	return kvmalloc_node_align_noprof(bytes, 1, flags, node);
 }
 
 #define kvmalloc_array_noprof(...)		kvmalloc_array_node_noprof(__VA_ARGS__, NUMA_NO_NODE)
@@ -1073,9 +1079,12 @@ kvmalloc_array_node_noprof(size_t n, size_t size, gfp_t flags, int node)
 #define kvcalloc_node(...)			alloc_hooks(kvcalloc_node_noprof(__VA_ARGS__))
 #define kvcalloc(...)				alloc_hooks(kvcalloc_noprof(__VA_ARGS__))
 
-void *kvrealloc_noprof(const void *p, size_t size, gfp_t flags)
+void *kvrealloc_node_align_noprof(const void *p, size_t size, unsigned long align,
-		__realloc_size(2);
+				  gfp_t flags, int nid) __realloc_size(2);
-#define kvrealloc(...)				alloc_hooks(kvrealloc_noprof(__VA_ARGS__))
+#define kvrealloc_node_align(...)		\
+	alloc_hooks(kvrealloc_node_align_noprof(__VA_ARGS__))
+#define kvrealloc_node(_p, _s, _f, _n)		kvrealloc_node_align(_p, _s, 1, _f, _n)
+#define kvrealloc(...)				kvrealloc_node(__VA_ARGS__, NUMA_NO_NODE)
 
 extern void kvfree(const void *addr);
 DEFINE_FREE(kvfree, void *, if (!IS_ERR_OR_NULL(_T)) kvfree(_T))

lib/rhashtable.c

@@ -184,8 +184,8 @@ static struct bucket_table *bucket_table_alloc(struct rhashtable *ht,
 	static struct lock_class_key __key;
 
 	tbl = alloc_hooks_tag(ht->alloc_tag,
-			kvmalloc_node_noprof(struct_size(tbl, buckets, nbuckets),
+			kvmalloc_node_align_noprof(struct_size(tbl, buckets, nbuckets),
-					     gfp|__GFP_ZERO, NUMA_NO_NODE));
+					     1, gfp|__GFP_ZERO, NUMA_NO_NODE));
 
 	size = nbuckets;
 

mm/slub.c

@@ -4881,7 +4881,7 @@ void kfree(const void *object)
 EXPORT_SYMBOL(kfree);
 
 static __always_inline __realloc_size(2) void *
-__do_krealloc(const void *p, size_t new_size, gfp_t flags)
+__do_krealloc(const void *p, size_t new_size, unsigned long align, gfp_t flags, int nid)
 {
 	void *ret;
 	size_t ks = 0;
@@ -4895,6 +4895,16 @@ __do_krealloc(const void *p, size_t new_size, gfp_t flags)
 	if (!kasan_check_byte(p))
 		return NULL;
 
+	/*
+	 * If reallocation is not necessary (e. g. the new size is less
+	 * than the current allocated size), the current allocation will be
+	 * preserved unless __GFP_THISNODE is set. In the latter case a new
+	 * allocation on the requested node will be attempted.
+	 */
+	if (unlikely(flags & __GFP_THISNODE) && nid != NUMA_NO_NODE &&
+		     nid != page_to_nid(virt_to_page(p)))
+		goto alloc_new;
+
 	if (is_kfence_address(p)) {
 		ks = orig_size = kfence_ksize(p);
 	} else {
@@ -4917,6 +4927,10 @@ __do_krealloc(const void *p, size_t new_size, gfp_t flags)
 	if (new_size > ks)
 		goto alloc_new;
 
+	/* If the old object doesn't satisfy the new alignment, allocate a new one */
+	if (!IS_ALIGNED((unsigned long)p, align))
+		goto alloc_new;
+
 	/* Zero out spare memory. */
 	if (want_init_on_alloc(flags)) {
 		kasan_disable_current();
@@ -4939,7 +4953,7 @@ __do_krealloc(const void *p, size_t new_size, gfp_t flags)
 	return (void *)p;
 
 alloc_new:
-	ret = kmalloc_node_track_caller_noprof(new_size, flags, NUMA_NO_NODE, _RET_IP_);
+	ret = kmalloc_node_track_caller_noprof(new_size, flags, nid, _RET_IP_);
 	if (ret && p) {
 		/* Disable KASAN checks as the object's redzone is accessed. */
 		kasan_disable_current();
@@ -4951,14 +4965,19 @@ __do_krealloc(const void *p, size_t new_size, gfp_t flags)
 }
 
 /**
- * krealloc - reallocate memory. The contents will remain unchanged.
+ * krealloc_node_align - reallocate memory. The contents will remain unchanged.
  * @p: object to reallocate memory for.
  * @new_size: how many bytes of memory are required.
+ * @align: desired alignment.
  * @flags: the type of memory to allocate.
+ * @nid: NUMA node or NUMA_NO_NODE
  *
  * If @p is %NULL, krealloc() behaves exactly like kmalloc().  If @new_size
  * is 0 and @p is not a %NULL pointer, the object pointed to is freed.
  *
+ * Only alignments up to those guaranteed by kmalloc() will be honored. Please see
+ * Documentation/core-api/memory-allocation.rst for more details.
+ *
  * If __GFP_ZERO logic is requested, callers must ensure that, starting with the
  * initial memory allocation, every subsequent call to this API for the same
  * memory allocation is flagged with __GFP_ZERO. Otherwise, it is possible that
@@ -4983,7 +5002,8 @@ __do_krealloc(const void *p, size_t new_size, gfp_t flags)
  *
  * Return: pointer to the allocated memory or %NULL in case of error
  */
-void *krealloc_noprof(const void *p, size_t new_size, gfp_t flags)
+void *krealloc_node_align_noprof(const void *p, size_t new_size, unsigned long align,
+				 gfp_t flags, int nid)
 {
 	void *ret;
 
@@ -4992,13 +5012,13 @@ void *krealloc_noprof(const void *p, size_t new_size, gfp_t flags)
 		return ZERO_SIZE_PTR;
 	}
 
-	ret = __do_krealloc(p, new_size, flags);
+	ret = __do_krealloc(p, new_size, align, flags, nid);
 	if (ret && kasan_reset_tag(p) != kasan_reset_tag(ret))
 		kfree(p);
 
 	return ret;
 }
-EXPORT_SYMBOL(krealloc_noprof);
+EXPORT_SYMBOL(krealloc_node_align_noprof);
 
 static gfp_t kmalloc_gfp_adjust(gfp_t flags, size_t size)
 {
@@ -5029,9 +5049,13 @@ static gfp_t kmalloc_gfp_adjust(gfp_t flags, size_t size)
  * failure, fall back to non-contiguous (vmalloc) allocation.
  * @size: size of the request.
  * @b: which set of kmalloc buckets to allocate from.
+ * @align: desired alignment.
  * @flags: gfp mask for the allocation - must be compatible (superset) with GFP_KERNEL.
  * @node: numa node to allocate from
  *
+ * Only alignments up to those guaranteed by kmalloc() will be honored. Please see
+ * Documentation/core-api/memory-allocation.rst for more details.
+ *
  * Uses kmalloc to get the memory but if the allocation fails then falls back
  * to the vmalloc allocator. Use kvfree for freeing the memory.
  *
@@ -5041,7 +5065,8 @@ static gfp_t kmalloc_gfp_adjust(gfp_t flags, size_t size)
  *
  * Return: pointer to the allocated memory of %NULL in case of failure
  */
-void *__kvmalloc_node_noprof(DECL_BUCKET_PARAMS(size, b), gfp_t flags, int node)
+void *__kvmalloc_node_noprof(DECL_BUCKET_PARAMS(size, b), unsigned long align,
+			     gfp_t flags, int node)
 {
 	void *ret;
 
@@ -5071,7 +5096,7 @@ void *__kvmalloc_node_noprof(DECL_BUCKET_PARAMS(size, b), gfp_t flags, int node)
 	 * about the resulting pointer, and cannot play
 	 * protection games.
 	 */
-	return __vmalloc_node_range_noprof(size, 1, VMALLOC_START, VMALLOC_END,
+	return __vmalloc_node_range_noprof(size, align, VMALLOC_START, VMALLOC_END,
 			flags, PAGE_KERNEL, VM_ALLOW_HUGE_VMAP,
 			node, __builtin_return_address(0));
 }
@@ -5115,14 +5140,19 @@ void kvfree_sensitive(const void *addr, size_t len)
 EXPORT_SYMBOL(kvfree_sensitive);
 
 /**
- * kvrealloc - reallocate memory; contents remain unchanged
+ * kvrealloc_node_align - reallocate memory; contents remain unchanged
  * @p: object to reallocate memory for
  * @size: the size to reallocate
+ * @align: desired alignment
  * @flags: the flags for the page level allocator
+ * @nid: NUMA node id
  *
  * If @p is %NULL, kvrealloc() behaves exactly like kvmalloc(). If @size is 0
  * and @p is not a %NULL pointer, the object pointed to is freed.
  *
+ * Only alignments up to those guaranteed by kmalloc() will be honored. Please see
+ * Documentation/core-api/memory-allocation.rst for more details.
+ *
  * If __GFP_ZERO logic is requested, callers must ensure that, starting with the
  * initial memory allocation, every subsequent call to this API for the same
  * memory allocation is flagged with __GFP_ZERO. Otherwise, it is possible that
@@ -5136,17 +5166,18 @@ EXPORT_SYMBOL(kvfree_sensitive);
  *
  * Return: pointer to the allocated memory or %NULL in case of error
  */
-void *kvrealloc_noprof(const void *p, size_t size, gfp_t flags)
+void *kvrealloc_node_align_noprof(const void *p, size_t size, unsigned long align,
+				  gfp_t flags, int nid)
 {
 	void *n;
 
 	if (is_vmalloc_addr(p))
-		return vrealloc_noprof(p, size, flags);
+		return vrealloc_node_align_noprof(p, size, align, flags, nid);
 
-	n = krealloc_noprof(p, size, kmalloc_gfp_adjust(flags, size));
+	n = krealloc_node_align_noprof(p, size, align, kmalloc_gfp_adjust(flags, size), nid);
 	if (!n) {
 		/* We failed to krealloc(), fall back to kvmalloc(). */
-		n = kvmalloc_noprof(size, flags);
+		n = kvmalloc_node_align_noprof(size, align, flags, nid);
 		if (!n)
 			return NULL;
 
@@ -5162,7 +5193,7 @@ void *kvrealloc_noprof(const void *p, size_t size, gfp_t flags)
 
 	return n;
 }
-EXPORT_SYMBOL(kvrealloc_noprof);
+EXPORT_SYMBOL(kvrealloc_node_align_noprof);
 
 struct detached_freelist {
 	struct slab *slab;