support large align and nid in Rust allocators

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,
-				    gfp_t flags) __realloc_size(2);
-#define krealloc(...)				alloc_hooks(krealloc_noprof(__VA_ARGS__))
+void * __must_check krealloc_node_align_noprof(const void *objp, size_t new_size,
+					       unsigned long align,
+					       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);
-#define kvmalloc_node_noprof(size, flags, node)	\
-	__kvmalloc_node_noprof(PASS_BUCKET_PARAMS(size, NULL), flags, node)
-#define kvmalloc_node(...)			alloc_hooks(kvmalloc_node_noprof(__VA_ARGS__))
-
-#define kvmalloc(_size, _flags)			kvmalloc_node(_size, _flags, NUMA_NO_NODE)
-#define kvmalloc_noprof(_size, _flags)		kvmalloc_node_noprof(_size, _flags, NUMA_NO_NODE)
+void *__kvmalloc_node_noprof(DECL_BUCKET_PARAMS(size, b), unsigned long align,
+			     gfp_t flags, int node) __alloc_size(1);
+#define kvmalloc_node_align_noprof(_size, _align, _flags, _node)	\
+	__kvmalloc_node_noprof(PASS_BUCKET_PARAMS(_size, NULL), _align, _flags, _node)
+#define kvmalloc_node_align(...)		\
+	alloc_hooks(kvmalloc_node_align_noprof(__VA_ARGS__))
+#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 +1079,11 @@ 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)
-		__realloc_size(2);
-#define kvrealloc(...)				alloc_hooks(kvrealloc_noprof(__VA_ARGS__))
+void *kvrealloc_node_align_noprof(const void *p, size_t size, unsigned long align,
+				  gfp_t flags, int nid) __realloc_size(2);
+#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))

include/linux/vmalloc.h

@@ -197,9 +197,15 @@ extern void *__vcalloc_noprof(size_t n, size_t size, gfp_t flags) __alloc_size(1
 extern void *vcalloc_noprof(size_t n, size_t size) __alloc_size(1, 2);
 #define vcalloc(...)		alloc_hooks(vcalloc_noprof(__VA_ARGS__))
 
-void * __must_check vrealloc_noprof(const void *p, size_t size, gfp_t flags)
-		__realloc_size(2);
-#define vrealloc(...)		alloc_hooks(vrealloc_noprof(__VA_ARGS__))
+void *__must_check vrealloc_node_align_noprof(const void *p, size_t size,
+		unsigned long align, gfp_t flags, int nid) __realloc_size(2);
+#define vrealloc_node_noprof(_p, _s, _f, _nid)	\
+	vrealloc_node_align_noprof(_p, _s, 1, _f, _nid)
+#define vrealloc_noprof(_p, _s, _f)		\
+	vrealloc_node_align_noprof(_p, _s, 1, _f, NUMA_NO_NODE)
+#define vrealloc_node_align(...)		alloc_hooks(vrealloc_node_align_noprof(__VA_ARGS__))
+#define vrealloc_node(...)			alloc_hooks(vrealloc_node_noprof(__VA_ARGS__))
+#define vrealloc(...)				alloc_hooks(vrealloc_noprof(__VA_ARGS__))
 
 extern void vfree(const void *addr);
 extern void vfree_atomic(const void *addr);

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),
-					     gfp|__GFP_ZERO, NUMA_NO_NODE));
+			kvmalloc_node_align_noprof(struct_size(tbl, buckets, nbuckets),
+					     1, gfp|__GFP_ZERO, NUMA_NO_NODE));
 
 	size = nbuckets;
 

mm/nommu.c

@@ -119,7 +119,8 @@ void *__vmalloc_noprof(unsigned long size, gfp_t gfp_mask)
 }
 EXPORT_SYMBOL(__vmalloc_noprof);
 
-void *vrealloc_noprof(const void *p, size_t size, gfp_t flags)
+void *vrealloc_node_align_noprof(const void *p, size_t size, unsigned long align,
+				 gfp_t flags, int node)
 {
 	return krealloc_noprof(p, size, (flags | __GFP_COMP) & ~__GFP_HIGHMEM);
 }

mm/slub.c

@@ -4844,7 +4844,7 @@ 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;
@@ -4858,6 +4858,20 @@ __do_krealloc(const void *p, size_t new_size, gfp_t flags)
 	if (!kasan_check_byte(p))
 		return NULL;
 
+	/* refuse to proceed if alignment is bigger than what kmalloc() provides */
+	if (!IS_ALIGNED((unsigned long)p, align) || new_size < align)
+		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 {
@@ -4902,7 +4916,7 @@ __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();
@@ -4914,10 +4928,12 @@ __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.
@@ -4946,7 +4962,8 @@ __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;
 
@@ -4955,13 +4972,13 @@ 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)
 {
@@ -4992,6 +5009,7 @@ 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
  *
@@ -5004,19 +5022,22 @@ 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;
 
 	/*
 	 * It doesn't really make sense to fallback to vmalloc for sub page
-	 * requests
+	 * requests and small alignments
 	 */
-	ret = __do_kmalloc_node(size, PASS_BUCKET_PARAM(b),
-				kmalloc_gfp_adjust(flags, size),
-				node, _RET_IP_);
-	if (ret || size <= PAGE_SIZE)
-		return ret;
+	if (size >= align) {
+		ret = __do_kmalloc_node(size, PASS_BUCKET_PARAM(b),
+					kmalloc_gfp_adjust(flags, size),
+					node, _RET_IP_);
+		if (ret || size <= PAGE_SIZE)
+			return ret;
+	}
 
 	/* non-sleeping allocations are not supported by vmalloc */
 	if (!gfpflags_allow_blocking(flags))
@@ -5034,7 +5055,7 @@ 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));
 }
@@ -5078,10 +5099,12 @@ 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.
@@ -5099,17 +5122,18 @@ 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;
 
@@ -5125,7 +5149,7 @@ 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;

mm/vmalloc.c

@@ -4081,19 +4081,31 @@ void *vzalloc_node_noprof(unsigned long size, int node)
 EXPORT_SYMBOL(vzalloc_node_noprof);
 
 /**
- * vrealloc - reallocate virtually contiguous memory; contents remain unchanged
+ * vrealloc_node_align_noprof - reallocate virtually contiguous memory; contents
+ * remain unchanged
  * @p: object to reallocate memory for
  * @size: the size to reallocate
+ * @align: requested alignment
  * @flags: the flags for the page level allocator
+ * @nid: node number of the target node
+ *
+ * If @p is %NULL, vrealloc_XXX() behaves exactly like vmalloc(). If @size is
+ * 0 and @p is not a %NULL pointer, the object pointed to is freed.
  *
- * If @p is %NULL, vrealloc() behaves exactly like vmalloc(). If @size is 0 and
- * @p is not a %NULL pointer, the object pointed to is freed.
+ * if @nid is not NUMA_NO_NODE, this function will try to allocate memory on
+ * the given node. 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 __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
  * __GFP_ZERO is not fully honored by this API.
  *
+ * If the requested alignment is bigger than the one the *existing* allocation
+ * has, this function will fail.
+ *
  * In any case, the contents of the object pointed to are preserved up to the
  * lesser of the new and old sizes.
  *
@@ -4103,7 +4115,8 @@ EXPORT_SYMBOL(vzalloc_node_noprof);
  * Return: pointer to the allocated memory; %NULL if @size is zero or in case of
  *         failure
  */
-void *vrealloc_noprof(const void *p, size_t size, gfp_t flags)
+void *vrealloc_node_align_noprof(const void *p, size_t size, unsigned long align,
+				 gfp_t flags, int nid)
 {
 	struct vm_struct *vm = NULL;
 	size_t alloced_size = 0;
@@ -4127,6 +4140,12 @@ void *vrealloc_noprof(const void *p, size_t size, gfp_t flags)
 		if (WARN(alloced_size < old_size,
 			 "vrealloc() has mismatched area vs requested sizes (%p)\n", p))
 			return NULL;
+		if (WARN(!IS_ALIGNED((unsigned long)p, align),
+			 "will not reallocate with a bigger alignment (0x%lx)\n", align))
+			return NULL;
+		if (unlikely(flags & __GFP_THISNODE) && nid != NUMA_NO_NODE &&
+			     nid != page_to_nid(vmalloc_to_page(p)))
+			goto need_realloc;
 	}
 
 	/*
@@ -4157,8 +4176,10 @@ void *vrealloc_noprof(const void *p, size_t size, gfp_t flags)
 		return (void *)p;
 	}
 
+need_realloc:
 	/* TODO: Grow the vm_area, i.e. allocate and map additional pages. */
-	n = __vmalloc_noprof(size, flags);
+	n = __vmalloc_node_noprof(size, align, flags, nid, __builtin_return_address(0));
+
 	if (!n)
 		return NULL;
 

rust/helpers/slab.c

@@ -3,13 +3,15 @@
 #include <linux/slab.h>
 
 void * __must_check __realloc_size(2)
-rust_helper_krealloc(const void *objp, size_t new_size, gfp_t flags)
+rust_helper_krealloc_node_align(const void *objp, size_t new_size, unsigned long align,
+				gfp_t flags, int node)
 {
-	return krealloc(objp, new_size, flags);
+	return krealloc_node_align(objp, new_size, align, flags, node);
 }
 
 void * __must_check __realloc_size(2)
-rust_helper_kvrealloc(const void *p, size_t size, gfp_t flags)
+rust_helper_kvrealloc_node_align(const void *p, size_t size, unsigned long align,
+				gfp_t flags, int node)
 {
-	return kvrealloc(p, size, flags);
+	return kvrealloc_node_align(p, size, align, flags, node);
 }