mm: change inlined allocation helpers to account at the call site

Main goal of memory allocation profiling patchset is to provide accounting
that is cheap enough to run in production. To achieve that we inject
counters using codetags at the allocation call sites to account every time
allocation is made. This injection allows us to perform accounting
efficiently because injected counters are immediately available as opposed
to the alternative methods, such as using _RET_IP_, which would require
counter lookup and appropriate locking that makes accounting much more
expensive. This method requires all allocation functions to inject
separate counters at their call sites so that their callers can be
individually accounted. Counter injection is implemented by allocation
hooks which should wrap all allocation functions.

Inlined functions which perform allocations but do not use allocation
hooks are directly charged for the allocations they perform. In most
cases these functions are just specialized allocation wrappers used from
multiple places to allocate objects of a specific type. It would be more
useful to do the accounting at their call sites instead. Instrument these
helpers to do accounting at the call site. Simple inlined allocation
wrappers are converted directly into macros. More complex allocators or
allocators with documentation are converted into _noprof versions and
allocation hooks are added. This allows memory allocation profiling
mechanism to charge allocations to the callers of these functions.

Link: https://lkml.kernel.org/r/[e-mail]
Signed-off-by: Suren Baghdasaryan <[e-mail]>
Acked-by: Jan Kara <[e-mail]> [jbd2]
Cc: Anna Schumaker <[e-mail]>
Cc: Arnd Bergmann <[e-mail]>
Cc: Benjamin Tissoires <[e-mail]>
Cc: Christoph Lameter <[e-mail]>
Cc: David Rientjes <[e-mail]>
Cc: David S. Miller <[e-mail]>
Cc: Dennis Zhou <[e-mail]>
Cc: Eric Dumazet <[e-mail]>
Cc: Herbert Xu <[e-mail]>
Cc: Jakub Kicinski <[e-mail]>
Cc: Jakub Sitnicki <[e-mail]>
Cc: Jiri Kosina <[e-mail]>
Cc: Joerg Roedel <[e-mail]>
Cc: Joonsoo Kim <[e-mail]>
Cc: Kent Overstreet <[e-mail]>
Cc: Matthew Wilcox (Oracle) <[e-mail]>
Cc: Paolo Abeni <[e-mail]>
Cc: Pekka Enberg <[e-mail]>
Cc: Tejun Heo <[e-mail]>
Cc: Theodore Ts'o <[e-mail]>
Cc: Trond Myklebust <[e-mail]>
Cc: Vlastimil Babka <[e-mail]>
Cc: Will Deacon <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>

drivers/iommu/amd/amd_iommu.h

···
 	return PCI_SEG_DEVID_TO_SBDF(seg, devid);
 }
 
-static inline void *alloc_pgtable_page(int nid, gfp_t gfp)
+static inline void *alloc_pgtable_page_noprof(int nid, gfp_t gfp)
 {
 	struct page *page;
 
-	page = alloc_pages_node(nid, gfp | __GFP_ZERO, 0);
+	page = alloc_pages_node_noprof(nid, gfp | __GFP_ZERO, 0);
 	return page ? page_address(page) : NULL;
 }
+#define alloc_pgtable_page(...)	alloc_hooks(alloc_pgtable_page_noprof(__VA_ARGS__))
 
 /*
  * This must be called after device probe completes. During probe

fs/nfs/iostat.h

···
 	nfs_add_server_stats(NFS_SERVER(inode), stat, addend);
 }
 
-static inline struct nfs_iostats __percpu *nfs_alloc_iostats(void)
-{
-	return alloc_percpu(struct nfs_iostats);
-}
+#define nfs_alloc_iostats()	alloc_percpu(struct nfs_iostats)
 
 static inline void nfs_free_iostats(struct nfs_iostats __percpu *stats)
 {

include/acpi/platform/aclinuxex.h

···
  * However, boot has  (system_state != SYSTEM_RUNNING)
  * to quiet __might_sleep() in kmalloc() and resume does not.
  */
-static inline void *acpi_os_allocate(acpi_size size)
-{
-	return kmalloc(size, irqs_disabled()? GFP_ATOMIC : GFP_KERNEL);
-}
+#define acpi_os_allocate(_size)	\
+		kmalloc(_size, irqs_disabled() ? GFP_ATOMIC : GFP_KERNEL)
 
-static inline void *acpi_os_allocate_zeroed(acpi_size size)
-{
-	return kzalloc(size, irqs_disabled()? GFP_ATOMIC : GFP_KERNEL);
-}
+#define acpi_os_allocate_zeroed(_size)	\
+		kzalloc(_size, irqs_disabled() ? GFP_ATOMIC : GFP_KERNEL)
 
 static inline void acpi_os_free(void *memory)
 {
 	kfree(memory);
 }
 
-static inline void *acpi_os_acquire_object(acpi_cache_t * cache)
-{
-	return kmem_cache_zalloc(cache,
-				 irqs_disabled()? GFP_ATOMIC : GFP_KERNEL);
-}
+#define acpi_os_acquire_object(_cache)	\
+		kmem_cache_zalloc(_cache, irqs_disabled() ? GFP_ATOMIC : GFP_KERNEL)
 
 static inline acpi_thread_id acpi_os_get_thread_id(void)
 {

include/asm-generic/pgalloc.h

···
  *
  * Return: pointer to the allocated memory or %NULL on error
  */
-static inline pte_t *__pte_alloc_one_kernel(struct mm_struct *mm)
+static inline pte_t *__pte_alloc_one_kernel_noprof(struct mm_struct *mm)
 {
-	struct ptdesc *ptdesc = pagetable_alloc(GFP_PGTABLE_KERNEL &
+	struct ptdesc *ptdesc = pagetable_alloc_noprof(GFP_PGTABLE_KERNEL &
 			~__GFP_HIGHMEM, 0);
 
 	if (!ptdesc)
 		return NULL;
 	return ptdesc_address(ptdesc);
 }
+#define __pte_alloc_one_kernel(...)	alloc_hooks(__pte_alloc_one_kernel_noprof(__VA_ARGS__))
 
 #ifndef __HAVE_ARCH_PTE_ALLOC_ONE_KERNEL
 /**
···
  *
  * Return: pointer to the allocated memory or %NULL on error
  */
-static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm)
+static inline pte_t *pte_alloc_one_kernel_noprof(struct mm_struct *mm)
 {
-	return __pte_alloc_one_kernel(mm);
+	return __pte_alloc_one_kernel_noprof(mm);
 }
+#define pte_alloc_one_kernel(...)	alloc_hooks(pte_alloc_one_kernel_noprof(__VA_ARGS__))
 #endif
 
 /**
···
  *
  * Return: `struct page` referencing the ptdesc or %NULL on error
  */
-static inline pgtable_t __pte_alloc_one(struct mm_struct *mm, gfp_t gfp)
+static inline pgtable_t __pte_alloc_one_noprof(struct mm_struct *mm, gfp_t gfp)
 {
 	struct ptdesc *ptdesc;
 
-	ptdesc = pagetable_alloc(gfp, 0);
+	ptdesc = pagetable_alloc_noprof(gfp, 0);
 	if (!ptdesc)
 		return NULL;
 	if (!pagetable_pte_ctor(ptdesc)) {
···
 
 	return ptdesc_page(ptdesc);
 }
+#define __pte_alloc_one(...)	alloc_hooks(__pte_alloc_one_noprof(__VA_ARGS__))
 
 #ifndef __HAVE_ARCH_PTE_ALLOC_ONE
 /**
···
  *
  * Return: `struct page` referencing the ptdesc or %NULL on error
  */
-static inline pgtable_t pte_alloc_one(struct mm_struct *mm)
+static inline pgtable_t pte_alloc_one_noprof(struct mm_struct *mm)
 {
-	return __pte_alloc_one(mm, GFP_PGTABLE_USER);
+	return __pte_alloc_one_noprof(mm, GFP_PGTABLE_USER);
 }
+#define pte_alloc_one(...)	alloc_hooks(pte_alloc_one_noprof(__VA_ARGS__))
 #endif
 
 /*
···
  *
  * Return: pointer to the allocated memory or %NULL on error
  */
-static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
+static inline pmd_t *pmd_alloc_one_noprof(struct mm_struct *mm, unsigned long addr)
 {
 	struct ptdesc *ptdesc;
 	gfp_t gfp = GFP_PGTABLE_USER;
 
 	if (mm == &init_mm)
 		gfp = GFP_PGTABLE_KERNEL;
-	ptdesc = pagetable_alloc(gfp, 0);
+	ptdesc = pagetable_alloc_noprof(gfp, 0);
 	if (!ptdesc)
 		return NULL;
 	if (!pagetable_pmd_ctor(ptdesc)) {
···
 	}
 	return ptdesc_address(ptdesc);
 }
+#define pmd_alloc_one(...)	alloc_hooks(pmd_alloc_one_noprof(__VA_ARGS__))
 #endif
 
 #ifndef __HAVE_ARCH_PMD_FREE
···
 
 #if CONFIG_PGTABLE_LEVELS > 3
 
-static inline pud_t *__pud_alloc_one(struct mm_struct *mm, unsigned long addr)
+static inline pud_t *__pud_alloc_one_noprof(struct mm_struct *mm, unsigned long addr)
 {
 	gfp_t gfp = GFP_PGTABLE_USER;
 	struct ptdesc *ptdesc;
···
 		gfp = GFP_PGTABLE_KERNEL;
 	gfp &= ~__GFP_HIGHMEM;
 
-	ptdesc = pagetable_alloc(gfp, 0);
+	ptdesc = pagetable_alloc_noprof(gfp, 0);
 	if (!ptdesc)
 		return NULL;
 
 	pagetable_pud_ctor(ptdesc);
 	return ptdesc_address(ptdesc);
 }
+#define __pud_alloc_one(...)	alloc_hooks(__pud_alloc_one_noprof(__VA_ARGS__))
 
 #ifndef __HAVE_ARCH_PUD_ALLOC_ONE
 /**
···
  *
  * Return: pointer to the allocated memory or %NULL on error
  */
-static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
+static inline pud_t *pud_alloc_one_noprof(struct mm_struct *mm, unsigned long addr)
 {
-	return __pud_alloc_one(mm, addr);
+	return __pud_alloc_one_noprof(mm, addr);
 }
+#define pud_alloc_one(...)	alloc_hooks(pud_alloc_one_noprof(__VA_ARGS__))
 #endif
 
 static inline void __pud_free(struct mm_struct *mm, pud_t *pud)

include/crypto/hash.h

···
  *
  * Return: allocated request handle in case of success, or NULL if out of memory
  */
-static inline struct ahash_request *ahash_request_alloc(
+static inline struct ahash_request *ahash_request_alloc_noprof(
 	struct crypto_ahash *tfm, gfp_t gfp)
 {
 	struct ahash_request *req;
 
-	req = kmalloc(sizeof(struct ahash_request) +
-		      crypto_ahash_reqsize(tfm), gfp);
+	req = kmalloc_noprof(sizeof(struct ahash_request) +
+			     crypto_ahash_reqsize(tfm), gfp);
 
 	if (likely(req))
 		ahash_request_set_tfm(req, tfm);
 
 	return req;
 }
+#define ahash_request_alloc(...)	alloc_hooks(ahash_request_alloc_noprof(__VA_ARGS__))
 
 /**
  * ahash_request_free() - zeroize and free the request data structure

include/crypto/internal/acompress.h

···
 	crypto_request_complete(&req->base, err);
 }
 
-static inline struct acomp_req *__acomp_request_alloc(struct crypto_acomp *tfm)
+static inline struct acomp_req *__acomp_request_alloc_noprof(struct crypto_acomp *tfm)
 {
 	struct acomp_req *req;
 
-	req = kzalloc(sizeof(*req) + crypto_acomp_reqsize(tfm), GFP_KERNEL);
+	req = kzalloc_noprof(sizeof(*req) + crypto_acomp_reqsize(tfm), GFP_KERNEL);
 	if (likely(req))
 		acomp_request_set_tfm(req, tfm);
 	return req;
 }
+#define __acomp_request_alloc(...)	alloc_hooks(__acomp_request_alloc_noprof(__VA_ARGS__))
 
 static inline void __acomp_request_free(struct acomp_req *req)
 {

include/crypto/skcipher.h

···
  *
  * Return: allocated request handle in case of success, or NULL if out of memory
  */
-static inline struct skcipher_request *skcipher_request_alloc(
+static inline struct skcipher_request *skcipher_request_alloc_noprof(
 	struct crypto_skcipher *tfm, gfp_t gfp)
 {
 	struct skcipher_request *req;
 
-	req = kmalloc(sizeof(struct skcipher_request) +
-		      crypto_skcipher_reqsize(tfm), gfp);
+	req = kmalloc_noprof(sizeof(struct skcipher_request) +
+			     crypto_skcipher_reqsize(tfm), gfp);
 
 	if (likely(req))
 		skcipher_request_set_tfm(req, tfm);
 
 	return req;
 }
+#define skcipher_request_alloc(...)	alloc_hooks(skcipher_request_alloc_noprof(__VA_ARGS__))
 
 /**
  * skcipher_request_free() - zeroize and free request data structure

include/linux/bpf.h

···
 void __percpu *bpf_map_alloc_percpu(const struct bpf_map *map, size_t size,
 				    size_t align, gfp_t flags);
 #else
-static inline void *
-bpf_map_kmalloc_node(const struct bpf_map *map, size_t size, gfp_t flags,
-		     int node)
-{
-	return kmalloc_node(size, flags, node);
-}
-
-static inline void *
-bpf_map_kzalloc(const struct bpf_map *map, size_t size, gfp_t flags)
-{
-	return kzalloc(size, flags);
-}
-
-static inline void *
-bpf_map_kvcalloc(struct bpf_map *map, size_t n, size_t size, gfp_t flags)
-{
-	return kvcalloc(n, size, flags);
-}
-
-static inline void __percpu *
-bpf_map_alloc_percpu(const struct bpf_map *map, size_t size, size_t align,
-		     gfp_t flags)
-{
-	return __alloc_percpu_gfp(size, align, flags);
-}
+#define bpf_map_kmalloc_node(_map, _size, _flags, _node)	\
+		kmalloc_node(_size, _flags, _node)
+#define bpf_map_kzalloc(_map, _size, _flags)			\
+		kzalloc(_size, _flags)
+#define bpf_map_kvcalloc(_map, _n, _size, _flags)		\
+		kvcalloc(_n, _size, _flags)
+#define bpf_map_alloc_percpu(_map, _size, _align, _flags)	\
+		__alloc_percpu_gfp(_size, _align, _flags)
 #endif
 
 static inline int

include/linux/bpfptr.h

···
 	return copy_to_sockptr_offset((sockptr_t) dst, offset, src, size);
 }
 
-static inline void *kvmemdup_bpfptr(bpfptr_t src, size_t len)
+static inline void *kvmemdup_bpfptr_noprof(bpfptr_t src, size_t len)
 {
-	void *p = kvmalloc(len, GFP_USER | __GFP_NOWARN);
+	void *p = kvmalloc_noprof(len, GFP_USER | __GFP_NOWARN);
 
 	if (!p)
 		return ERR_PTR(-ENOMEM);
···
 	}
 	return p;
 }
+#define kvmemdup_bpfptr(...)	alloc_hooks(kvmemdup_bpfptr_noprof(__VA_ARGS__))
 
 static inline long strncpy_from_bpfptr(char *dst, bpfptr_t src, size_t count)
 {

include/linux/dma-fence-chain.h

···
  *
  * Returns a new struct dma_fence_chain object or NULL on failure.
  */
-static inline struct dma_fence_chain *dma_fence_chain_alloc(void)
-{
-	return kmalloc(sizeof(struct dma_fence_chain), GFP_KERNEL);
-};
+#define dma_fence_chain_alloc()	\
+		((struct dma_fence_chain *)kmalloc(sizeof(struct dma_fence_chain), GFP_KERNEL))
 
 /**
  * dma_fence_chain_free

include/linux/hid_bpf.h

···
 static inline void hid_bpf_disconnect_device(struct hid_device *hdev) {}
 static inline void hid_bpf_destroy_device(struct hid_device *hid) {}
 static inline void hid_bpf_device_init(struct hid_device *hid) {}
-static inline u8 *call_hid_bpf_rdesc_fixup(struct hid_device *hdev, u8 *rdesc, unsigned int *size)
-{
-	return kmemdup(rdesc, *size, GFP_KERNEL);
-}
+#define call_hid_bpf_rdesc_fixup(_hdev, _rdesc, _size)	\
+		((u8 *)kmemdup(_rdesc, *(_size), GFP_KERNEL))
 
 #endif /* CONFIG_HID_BPF */
 

include/linux/jbd2.h

···
  */
 extern struct kmem_cache *jbd2_handle_cache;
 
-static inline handle_t *jbd2_alloc_handle(gfp_t gfp_flags)
-{
-	return kmem_cache_zalloc(jbd2_handle_cache, gfp_flags);
-}
+#define jbd2_alloc_handle(_gfp_flags)	\
+		((handle_t *)kmem_cache_zalloc(jbd2_handle_cache, _gfp_flags))
 
 static inline void jbd2_free_handle(handle_t *handle)
 {
···
  */
 extern struct kmem_cache *jbd2_inode_cache;
 
-static inline struct jbd2_inode *jbd2_alloc_inode(gfp_t gfp_flags)
-{
-	return kmem_cache_alloc(jbd2_inode_cache, gfp_flags);
-}
+#define jbd2_alloc_inode(_gfp_flags)	\
+		((struct jbd2_inode *)kmem_cache_alloc(jbd2_inode_cache, _gfp_flags))
 
 static inline void jbd2_free_inode(struct jbd2_inode *jinode)
 {

include/linux/mm.h

···
  *
  * Return: The ptdesc describing the allocated page tables.
  */
-static inline struct ptdesc *pagetable_alloc(gfp_t gfp, unsigned int order)
+static inline struct ptdesc *pagetable_alloc_noprof(gfp_t gfp, unsigned int order)
 {
-	struct page *page = alloc_pages(gfp | __GFP_COMP, order);
+	struct page *page = alloc_pages_noprof(gfp | __GFP_COMP, order);
 
 	return page_ptdesc(page);
 }
+#define pagetable_alloc(...)	alloc_hooks(pagetable_alloc_noprof(__VA_ARGS__))
 
 /**
  * pagetable_free - Free pagetables

include/linux/mm_types.h

···
 	cpumask_clear(mm_cidmask(mm));
 }
 
-static inline int mm_alloc_cid(struct mm_struct *mm)
+static inline int mm_alloc_cid_noprof(struct mm_struct *mm)
 {
-	mm->pcpu_cid = alloc_percpu(struct mm_cid);
+	mm->pcpu_cid = alloc_percpu_noprof(struct mm_cid);
 	if (!mm->pcpu_cid)
 		return -ENOMEM;
 	mm_init_cid(mm);
 	return 0;
 }
+#define mm_alloc_cid(...)	alloc_hooks(mm_alloc_cid_noprof(__VA_ARGS__))
 
 static inline void mm_destroy_cid(struct mm_struct *mm)
 {

include/linux/percpu.h

···
 #define alloc_percpu(type)						\
 	(typeof(type) __percpu *)__alloc_percpu(sizeof(type),		\
 						__alignof__(type))
+#define alloc_percpu_noprof(type)					\
+	((typeof(type) __percpu *)pcpu_alloc_noprof(sizeof(type),	\
+					__alignof__(type), false, GFP_KERNEL))
 
 extern void free_percpu(void __percpu *__pdata);
 

include/linux/ptr_ring.h

···
 /* Not all gfp_t flags (besides GFP_KERNEL) are allowed. See
  * documentation for vmalloc for which of them are legal.
  */
-static inline void **__ptr_ring_init_queue_alloc(unsigned int size, gfp_t gfp)
+static inline void **__ptr_ring_init_queue_alloc_noprof(unsigned int size, gfp_t gfp)
 {
 	if (size > KMALLOC_MAX_SIZE / sizeof(void *))
 		return NULL;
-	return kvmalloc_array(size, sizeof(void *), gfp | __GFP_ZERO);
+	return kvmalloc_array_noprof(size, sizeof(void *), gfp | __GFP_ZERO);
 }
 
 static inline void __ptr_ring_set_size(struct ptr_ring *r, int size)
···
 		r->batch = 1;
 }
 
-static inline int ptr_ring_init(struct ptr_ring *r, int size, gfp_t gfp)
+static inline int ptr_ring_init_noprof(struct ptr_ring *r, int size, gfp_t gfp)
 {
-	r->queue = __ptr_ring_init_queue_alloc(size, gfp);
+	r->queue = __ptr_ring_init_queue_alloc_noprof(size, gfp);
 	if (!r->queue)
 		return -ENOMEM;
 
···
 
 	return 0;
 }
+#define ptr_ring_init(...)	alloc_hooks(ptr_ring_init_noprof(__VA_ARGS__))
 
 /*
  * Return entries into ring. Destroy entries that don't fit.
···
  * In particular if you consume ring in interrupt or BH context, you must
  * disable interrupts/BH when doing so.
  */
-static inline int ptr_ring_resize(struct ptr_ring *r, int size, gfp_t gfp,
+static inline int ptr_ring_resize_noprof(struct ptr_ring *r, int size, gfp_t gfp,
 				  void (*destroy)(void *))
 {
 	unsigned long flags;
-	void **queue = __ptr_ring_init_queue_alloc(size, gfp);
+	void **queue = __ptr_ring_init_queue_alloc_noprof(size, gfp);
 	void **old;
 
 	if (!queue)
···
 
 	return 0;
 }
+#define ptr_ring_resize(...)	alloc_hooks(ptr_ring_resize_noprof(__VA_ARGS__))
 
 /*
  * Note: producer lock is nested within consumer lock, so if you
···
  * In particular if you consume ring in interrupt or BH context, you must
  * disable interrupts/BH when doing so.
  */
-static inline int ptr_ring_resize_multiple(struct ptr_ring **rings,
-					   unsigned int nrings,
-					   int size,
-					   gfp_t gfp, void (*destroy)(void *))
+static inline int ptr_ring_resize_multiple_noprof(struct ptr_ring **rings,
+						  unsigned int nrings,
+						  int size,
+						  gfp_t gfp, void (*destroy)(void *))
 {
 	unsigned long flags;
 	void ***queues;
 	int i;
 
-	queues = kmalloc_array(nrings, sizeof(*queues), gfp);
+	queues = kmalloc_array_noprof(nrings, sizeof(*queues), gfp);
 	if (!queues)
 		goto noqueues;
 
 	for (i = 0; i < nrings; ++i) {
-		queues[i] = __ptr_ring_init_queue_alloc(size, gfp);
+		queues[i] = __ptr_ring_init_queue_alloc_noprof(size, gfp);
 		if (!queues[i])
 			goto nomem;
 	}
···
 noqueues:
 	return -ENOMEM;
 }
+#define ptr_ring_resize_multiple(...) \
+		alloc_hooks(ptr_ring_resize_multiple_noprof(__VA_ARGS__))
 
 static inline void ptr_ring_cleanup(struct ptr_ring *r, void (*destroy)(void *))
 {

include/linux/skb_array.h

···
 	return PTR_RING_PEEK_CALL_ANY(&a->ring, __skb_array_len_with_tag);
 }
 
-static inline int skb_array_init(struct skb_array *a, int size, gfp_t gfp)
+static inline int skb_array_init_noprof(struct skb_array *a, int size, gfp_t gfp)
 {
-	return ptr_ring_init(&a->ring, size, gfp);
+	return ptr_ring_init_noprof(&a->ring, size, gfp);
 }
+#define skb_array_init(...)	alloc_hooks(skb_array_init_noprof(__VA_ARGS__))
 
 static void __skb_array_destroy_skb(void *ptr)
 {
···
 	return ptr_ring_resize(&a->ring, size, gfp, __skb_array_destroy_skb);
 }
 
-static inline int skb_array_resize_multiple(struct skb_array **rings,
-					    int nrings, unsigned int size,
-					    gfp_t gfp)
+static inline int skb_array_resize_multiple_noprof(struct skb_array **rings,
+						   int nrings, unsigned int size,
+						   gfp_t gfp)
 {
 	BUILD_BUG_ON(offsetof(struct skb_array, ring));
-	return ptr_ring_resize_multiple((struct ptr_ring **)rings,
-					nrings, size, gfp,
-					__skb_array_destroy_skb);
+	return ptr_ring_resize_multiple_noprof((struct ptr_ring **)rings,
+					       nrings, size, gfp,
+					       __skb_array_destroy_skb);
 }
+#define skb_array_resize_multiple(...)	\
+		alloc_hooks(skb_array_resize_multiple_noprof(__VA_ARGS__))
 
 static inline void skb_array_cleanup(struct skb_array *a)
 {

include/linux/skbuff.h

···
  *
  * %NULL is returned if there is no free memory.
 */
-static inline struct page *__dev_alloc_pages(gfp_t gfp_mask,
+static inline struct page *__dev_alloc_pages_noprof(gfp_t gfp_mask,
 					     unsigned int order)
 {
 	/* This piece of code contains several assumptions.
···
 	 */
 	gfp_mask |= __GFP_COMP | __GFP_MEMALLOC;
 
-	return alloc_pages_node(NUMA_NO_NODE, gfp_mask, order);
+	return alloc_pages_node_noprof(NUMA_NO_NODE, gfp_mask, order);
 }
+#define __dev_alloc_pages(...)	alloc_hooks(__dev_alloc_pages_noprof(__VA_ARGS__))
 
-static inline struct page *dev_alloc_pages(unsigned int order)
-{
-	return __dev_alloc_pages(GFP_ATOMIC | __GFP_NOWARN, order);
-}
+#define dev_alloc_pages(_order) __dev_alloc_pages(GFP_ATOMIC | __GFP_NOWARN, _order)
 
 /**
  * __dev_alloc_page - allocate a page for network Rx
···
  *
  * %NULL is returned if there is no free memory.
  */
-static inline struct page *__dev_alloc_page(gfp_t gfp_mask)
+static inline struct page *__dev_alloc_page_noprof(gfp_t gfp_mask)
 {
-	return __dev_alloc_pages(gfp_mask, 0);
+	return __dev_alloc_pages_noprof(gfp_mask, 0);
 }
+#define __dev_alloc_page(...)	alloc_hooks(__dev_alloc_page_noprof(__VA_ARGS__))
 
-static inline struct page *dev_alloc_page(void)
-{
-	return dev_alloc_pages(0);
-}
+#define dev_alloc_page()	dev_alloc_pages(0)
 
 /**
  * dev_page_is_reusable - check whether a page can be reused for network Rx

include/linux/skmsg.h

···
 int sk_psock_msg_verdict(struct sock *sk, struct sk_psock *psock,
 			 struct sk_msg *msg);
 
-static inline struct sk_psock_link *sk_psock_init_link(void)
-{
-	return kzalloc(sizeof(struct sk_psock_link),
-		       GFP_ATOMIC | __GFP_NOWARN);
-}
+#define sk_psock_init_link()	\
+		((struct sk_psock_link *)kzalloc(sizeof(struct sk_psock_link),	\
+						 GFP_ATOMIC | __GFP_NOWARN))
 
 static inline void sk_psock_free_link(struct sk_psock_link *link)
 {

include/linux/slab.h

···
  */
 #define kmalloc_track_caller(...)		kmalloc_node_track_caller(__VA_ARGS__, NUMA_NO_NODE)
 
+#define kmalloc_track_caller_noprof(...)	\
+		kmalloc_node_track_caller_noprof(__VA_ARGS__, NUMA_NO_NODE, _RET_IP_)
+
 static inline __alloc_size(1, 2) void *kmalloc_array_node_noprof(size_t n, size_t size, gfp_t flags,
 							  int 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)
 #define kvzalloc(_size, _flags)			kvmalloc(_size, _flags|__GFP_ZERO)
 
 #define kvzalloc_node(_size, _flags, _node)	kvmalloc_node(_size, _flags|__GFP_ZERO, _node)
···
 
 #define kvmalloc_array(...)			alloc_hooks(kvmalloc_array_noprof(__VA_ARGS__))
 #define kvcalloc(_n, _size, _flags)		kvmalloc_array(_n, _size, _flags|__GFP_ZERO)
+#define kvcalloc_noprof(_n, _size, _flags)	kvmalloc_array_noprof(_n, _size, _flags|__GFP_ZERO)
 
 extern void *kvrealloc_noprof(const void *p, size_t oldsize, size_t newsize, gfp_t flags)
 		      __realloc_size(3);

include/linux/sockptr.h

···
 	return copy_to_sockptr_offset(dst, 0, src, size);
 }
 
-static inline void *memdup_sockptr(sockptr_t src, size_t len)
+static inline void *memdup_sockptr_noprof(sockptr_t src, size_t len)
 {
-	void *p = kmalloc_track_caller(len, GFP_USER | __GFP_NOWARN);
+	void *p = kmalloc_track_caller_noprof(len, GFP_USER | __GFP_NOWARN);
 
 	if (!p)
 		return ERR_PTR(-ENOMEM);
···
 	}
 	return p;
 }
+#define memdup_sockptr(...)	alloc_hooks(memdup_sockptr_noprof(__VA_ARGS__))
 
-static inline void *memdup_sockptr_nul(sockptr_t src, size_t len)
+static inline void *memdup_sockptr_nul_noprof(sockptr_t src, size_t len)
 {
-	char *p = kmalloc_track_caller(len + 1, GFP_KERNEL);
+	char *p = kmalloc_track_caller_noprof(len + 1, GFP_KERNEL);
 
 	if (!p)
 		return ERR_PTR(-ENOMEM);
···
 	p[len] = '\0';
 	return p;
 }
+#define memdup_sockptr_nul(...)	alloc_hooks(memdup_sockptr_nul_noprof(__VA_ARGS__))
 
 static inline long strncpy_from_sockptr(char *dst, sockptr_t src, size_t count)
 {

include/net/netlabel.h

···
  * on success, NULL on failure.
  *
  */
-static inline struct netlbl_lsm_cache *netlbl_secattr_cache_alloc(gfp_t flags)
+static inline struct netlbl_lsm_cache *netlbl_secattr_cache_alloc_noprof(gfp_t flags)
 {
 	struct netlbl_lsm_cache *cache;
 
-	cache = kzalloc(sizeof(*cache), flags);
+	cache = kzalloc_noprof(sizeof(*cache), flags);
 	if (cache)
 		refcount_set(&cache->refcount, 1);
 	return cache;
 }
+#define netlbl_secattr_cache_alloc(...)	\
+		alloc_hooks(netlbl_secattr_cache_alloc_noprof(__VA_ARGS__))
 
 /**
  * netlbl_secattr_cache_free - Frees a netlbl_lsm_cache struct
···
  * on failure.
  *
  */
-static inline struct netlbl_lsm_catmap *netlbl_catmap_alloc(gfp_t flags)
+static inline struct netlbl_lsm_catmap *netlbl_catmap_alloc_noprof(gfp_t flags)
 {
-	return kzalloc(sizeof(struct netlbl_lsm_catmap), flags);
+	return kzalloc_noprof(sizeof(struct netlbl_lsm_catmap), flags);
 }
+#define netlbl_catmap_alloc(...)	alloc_hooks(netlbl_catmap_alloc_noprof(__VA_ARGS__))
 
 /**
  * netlbl_catmap_free - Free a LSM secattr catmap
···
  * pointer on success, or NULL on failure.
  *
  */
-static inline struct netlbl_lsm_secattr *netlbl_secattr_alloc(gfp_t flags)
+static inline struct netlbl_lsm_secattr *netlbl_secattr_alloc_noprof(gfp_t flags)
 {
-	return kzalloc(sizeof(struct netlbl_lsm_secattr), flags);
+	return kzalloc_noprof(sizeof(struct netlbl_lsm_secattr), flags);
 }
+#define netlbl_secattr_alloc(...)	alloc_hooks(netlbl_secattr_alloc_noprof(__VA_ARGS__))
 
 /**
  * netlbl_secattr_free - Frees a netlbl_lsm_secattr struct

include/net/netlink.h

···
  * @src: netlink attribute to duplicate from
  * @gfp: GFP mask
  */
-static inline void *nla_memdup(const struct nlattr *src, gfp_t gfp)
+static inline void *nla_memdup_noprof(const struct nlattr *src, gfp_t gfp)
 {
-	return kmemdup(nla_data(src), nla_len(src), gfp);
+	return kmemdup_noprof(nla_data(src), nla_len(src), gfp);
 }
+#define nla_memdup(...)	alloc_hooks(nla_memdup_noprof(__VA_ARGS__))
 
 /**
  * nla_nest_start_noflag - Start a new level of nested attributes

include/net/request_sock.h

···
 }
 
 static inline struct request_sock *
-reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener,
+reqsk_alloc_noprof(const struct request_sock_ops *ops, struct sock *sk_listener,
 	    bool attach_listener)
 {
 	struct request_sock *req;
 
-	req = kmem_cache_alloc(ops->slab, GFP_ATOMIC | __GFP_NOWARN);
+	req = kmem_cache_alloc_noprof(ops->slab, GFP_ATOMIC | __GFP_NOWARN);
 	if (!req)
 		return NULL;
 	req->rsk_listener = NULL;
···
 
 	return req;
 }
+#define reqsk_alloc(...)	alloc_hooks(reqsk_alloc_noprof(__VA_ARGS__))
 
 static inline void __reqsk_free(struct request_sock *req)
 {

include/net/tcx.h

···
 		return rcu_dereference_rtnl(dev->tcx_egress);
 }
 
-static inline struct bpf_mprog_entry *tcx_entry_create(void)
+static inline struct bpf_mprog_entry *tcx_entry_create_noprof(void)
 {
-	struct tcx_entry *tcx = kzalloc(sizeof(*tcx), GFP_KERNEL);
+	struct tcx_entry *tcx = kzalloc_noprof(sizeof(*tcx), GFP_KERNEL);
 
 	if (tcx) {
 		bpf_mprog_bundle_init(&tcx->bundle);
···
 	}
 	return NULL;
 }
+#define tcx_entry_create(...)	alloc_hooks(tcx_entry_create_noprof(__VA_ARGS__))
 
 static inline void tcx_entry_free(struct bpf_mprog_entry *entry)
 {

net/sunrpc/auth_gss/auth_gss_internal.h

···
 }
 
 static inline const void *
-simple_get_netobj(const void *p, const void *end, struct xdr_netobj *dest)
+simple_get_netobj_noprof(const void *p, const void *end, struct xdr_netobj *dest)
 {
 	const void *q;
 	unsigned int len;
···
 	if (unlikely(q > end || q < p))
 		return ERR_PTR(-EFAULT);
 	if (len) {
-		dest->data = kmemdup(p, len, GFP_KERNEL);
+		dest->data = kmemdup_noprof(p, len, GFP_KERNEL);
 		if (unlikely(dest->data == NULL))
 			return ERR_PTR(-ENOMEM);
 	} else
···
 	dest->len = len;
 	return q;
 }
+
+#define simple_get_netobj(...)	alloc_hooks(simple_get_netobj_noprof(__VA_ARGS__))