/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __LINUX_GFP_H
#define __LINUX_GFP_H

#include <linux/gfp_types.h>

#include <linux/mmzone.h>
#include <linux/topology.h>

struct vm_area_struct;

/* Convert GFP flags to their corresponding migrate type */
#define GFP_MOVABLE_MASK (__GFP_RECLAIMABLE|__GFP_MOVABLE)
#define GFP_MOVABLE_SHIFT 3

static inline int gfp_migratetype(const gfp_t gfp_flags)
{
	VM_WARN_ON((gfp_flags & GFP_MOVABLE_MASK) == GFP_MOVABLE_MASK);
	BUILD_BUG_ON((1UL << GFP_MOVABLE_SHIFT) != ___GFP_MOVABLE);
	BUILD_BUG_ON((___GFP_MOVABLE >> GFP_MOVABLE_SHIFT) != MIGRATE_MOVABLE);
	BUILD_BUG_ON((___GFP_RECLAIMABLE >> GFP_MOVABLE_SHIFT) != MIGRATE_RECLAIMABLE);
	if (unlikely(page_group_by_mobility_disabled))
		return MIGRATE_UNMOVABLE;

	/* Group based on mobility */
	return (__force unsigned long)(gfp_flags & GFP_MOVABLE_MASK) >> GFP_MOVABLE_SHIFT;
}
#undef GFP_MOVABLE_MASK
#undef GFP_MOVABLE_SHIFT

static inline bool gfpflags_allow_blocking(const gfp_t gfp_flags)
{
	return !!(gfp_flags & __GFP_DIRECT_RECLAIM);
}

#ifdef CONFIG_HIGHMEM
#define OPT_ZONE_HIGHMEM ZONE_HIGHMEM
#else
#define OPT_ZONE_HIGHMEM ZONE_NORMAL
#endif

#ifdef CONFIG_ZONE_DMA
#define OPT_ZONE_DMA ZONE_DMA
#else
#define OPT_ZONE_DMA ZONE_NORMAL
#endif

#ifdef CONFIG_ZONE_DMA32
#define OPT_ZONE_DMA32 ZONE_DMA32
#else
#define OPT_ZONE_DMA32 ZONE_NORMAL
#endif

/*
 * GFP_ZONE_TABLE is a word size bitstring that is used for looking up the
 * zone to use given the lowest 4 bits of gfp_t. Entries are GFP_ZONES_SHIFT
 * bits long and there are 16 of them to cover all possible combinations of
 * __GFP_DMA, __GFP_DMA32, __GFP_MOVABLE and __GFP_HIGHMEM.
 *
 * The zone fallback order is MOVABLE=>HIGHMEM=>NORMAL=>DMA32=>DMA.
 * But GFP_MOVABLE is not only a zone specifier but also an allocation
 * policy. Therefore __GFP_MOVABLE plus another zone selector is valid.
 * Only 1 bit of the lowest 3 bits (DMA,DMA32,HIGHMEM) can be set to "1".
 *
 *       bit       result
 *       =================
 *       0x0    => NORMAL
 *       0x1    => DMA or NORMAL
 *       0x2    => HIGHMEM or NORMAL
 *       0x3    => BAD (DMA+HIGHMEM)
 *       0x4    => DMA32 or NORMAL
 *       0x5    => BAD (DMA+DMA32)
 *       0x6    => BAD (HIGHMEM+DMA32)
 *       0x7    => BAD (HIGHMEM+DMA32+DMA)
 *       0x8    => NORMAL (MOVABLE+0)
 *       0x9    => DMA or NORMAL (MOVABLE+DMA)
 *       0xa    => MOVABLE (Movable is valid only if HIGHMEM is set too)
 *       0xb    => BAD (MOVABLE+HIGHMEM+DMA)
 *       0xc    => DMA32 or NORMAL (MOVABLE+DMA32)
 *       0xd    => BAD (MOVABLE+DMA32+DMA)
 *       0xe    => BAD (MOVABLE+DMA32+HIGHMEM)
 *       0xf    => BAD (MOVABLE+DMA32+HIGHMEM+DMA)
 *
 * GFP_ZONES_SHIFT must be <= 2 on 32 bit platforms.
 */

#if defined(CONFIG_ZONE_DEVICE) && (MAX_NR_ZONES-1) <= 4
/* ZONE_DEVICE is not a valid GFP zone specifier */
#define GFP_ZONES_SHIFT 2
#else
#define GFP_ZONES_SHIFT ZONES_SHIFT
#endif

#if 16 * GFP_ZONES_SHIFT > BITS_PER_LONG
#error GFP_ZONES_SHIFT too large to create GFP_ZONE_TABLE integer
#endif

#define GFP_ZONE_TABLE ( \
	(ZONE_NORMAL << 0 * GFP_ZONES_SHIFT)				       \
	| (OPT_ZONE_DMA << ___GFP_DMA * GFP_ZONES_SHIFT)		       \
	| (OPT_ZONE_HIGHMEM << ___GFP_HIGHMEM * GFP_ZONES_SHIFT)	       \
	| (OPT_ZONE_DMA32 << ___GFP_DMA32 * GFP_ZONES_SHIFT)		       \
	| (ZONE_NORMAL << ___GFP_MOVABLE * GFP_ZONES_SHIFT)		       \
	| (OPT_ZONE_DMA << (___GFP_MOVABLE | ___GFP_DMA) * GFP_ZONES_SHIFT)    \
	| (ZONE_MOVABLE << (___GFP_MOVABLE | ___GFP_HIGHMEM) * GFP_ZONES_SHIFT)\
	| (OPT_ZONE_DMA32 << (___GFP_MOVABLE | ___GFP_DMA32) * GFP_ZONES_SHIFT)\
)

/*
 * GFP_ZONE_BAD is a bitmap for all combinations of __GFP_DMA, __GFP_DMA32
 * __GFP_HIGHMEM and __GFP_MOVABLE that are not permitted. One flag per
 * entry starting with bit 0. Bit is set if the combination is not
 * allowed.
 */
#define GFP_ZONE_BAD ( \
	1 << (___GFP_DMA | ___GFP_HIGHMEM)				      \
	| 1 << (___GFP_DMA | ___GFP_DMA32)				      \
	| 1 << (___GFP_DMA32 | ___GFP_HIGHMEM)				      \
	| 1 << (___GFP_DMA | ___GFP_DMA32 | ___GFP_HIGHMEM)		      \
	| 1 << (___GFP_MOVABLE | ___GFP_HIGHMEM | ___GFP_DMA)		      \
	| 1 << (___GFP_MOVABLE | ___GFP_DMA32 | ___GFP_DMA)		      \
	| 1 << (___GFP_MOVABLE | ___GFP_DMA32 | ___GFP_HIGHMEM)		      \
	| 1 << (___GFP_MOVABLE | ___GFP_DMA32 | ___GFP_DMA | ___GFP_HIGHMEM)  \
)

static inline enum zone_type __gfp_zone(gfp_t flags)
{
	enum zone_type z;
	int bit = (__force int) (flags & GFP_ZONEMASK);

	z = (GFP_ZONE_TABLE >> (bit * GFP_ZONES_SHIFT)) &
					 ((1 << GFP_ZONES_SHIFT) - 1);
	VM_BUG_ON((GFP_ZONE_BAD >> bit) & 1);
	return z;
}

enum zone_type gfp_zone(gfp_t flags);

/*
 * There is only one page-allocator function, and two main namespaces to
 * it. The alloc_page*() variants return 'struct page *' and as such
 * can allocate highmem pages, the *get*page*() variants return
 * virtual kernel addresses to the allocated page(s).
 */

static inline int gfp_zonelist(gfp_t flags)
{
#ifdef CONFIG_NUMA
	if (unlikely(flags & __GFP_THISNODE))
		return ZONELIST_NOFALLBACK;
#endif
	return ZONELIST_FALLBACK;
}

/*
 * We get the zone list from the current node and the gfp_mask.
 * This zone list contains a maximum of MAX_NUMNODES*MAX_NR_ZONES zones.
 * There are two zonelists per node, one for all zones with memory and
 * one containing just zones from the node the zonelist belongs to.
 *
 * For the case of non-NUMA systems the NODE_DATA() gets optimized to
 * &contig_page_data at compile-time.
 */
static inline struct zonelist *node_zonelist(int nid, gfp_t flags)
{
	return NODE_DATA(nid)->node_zonelists + gfp_zonelist(flags);
}

#ifndef HAVE_ARCH_FREE_PAGE
static inline void arch_free_page(struct page *page, int order) { }
#endif
#ifndef HAVE_ARCH_ALLOC_PAGE
static inline void arch_alloc_page(struct page *page, int order) { }
#endif

struct page *__alloc_pages(gfp_t gfp, unsigned int order, int preferred_nid,
		nodemask_t *nodemask);
struct folio *__folio_alloc(gfp_t gfp, unsigned int order, int preferred_nid,
		nodemask_t *nodemask);

unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid,
				nodemask_t *nodemask, int nr_pages,
				struct list_head *page_list,
				struct page **page_array);

unsigned long alloc_pages_bulk_array_mempolicy(gfp_t gfp,
				unsigned long nr_pages,
				struct page **page_array);

/* Bulk allocate order-0 pages */
static inline unsigned long
alloc_pages_bulk_list(gfp_t gfp, unsigned long nr_pages, struct list_head *list)
{
	return __alloc_pages_bulk(gfp, numa_mem_id(), NULL, nr_pages, list, NULL);
}

static inline unsigned long
alloc_pages_bulk_array(gfp_t gfp, unsigned long nr_pages, struct page **page_array)
{
	return __alloc_pages_bulk(gfp, numa_mem_id(), NULL, nr_pages, NULL, page_array);
}

static inline unsigned long
alloc_pages_bulk_array_node(gfp_t gfp, int nid, unsigned long nr_pages, struct page **page_array)
{
	if (nid == NUMA_NO_NODE)
		nid = numa_mem_id();

	return __alloc_pages_bulk(gfp, nid, NULL, nr_pages, NULL, page_array);
}

static inline void warn_if_node_offline(int this_node, gfp_t gfp_mask)
{
	gfp_t warn_gfp = gfp_mask & (__GFP_THISNODE|__GFP_NOWARN);

	if (warn_gfp != (__GFP_THISNODE|__GFP_NOWARN))
		return;

	if (node_online(this_node))
		return;

	pr_warn("%pGg allocation from offline node %d\n", &gfp_mask, this_node);
	dump_stack();
}

/*
 * Allocate pages, preferring the node given as nid. The node must be valid and
 * online. For more general interface, see alloc_pages_node().
 */
static inline struct page *
__alloc_pages_node(int nid, gfp_t gfp_mask, unsigned int order)
{
	VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES);
	warn_if_node_offline(nid, gfp_mask);

	return __alloc_pages(gfp_mask, order, nid, NULL);
}

static inline
struct folio *__folio_alloc_node(gfp_t gfp, unsigned int order, int nid)
{
	VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES);
	warn_if_node_offline(nid, gfp);

	return __folio_alloc(gfp, order, nid, NULL);
}

/*
 * Allocate pages, preferring the node given as nid. When nid == NUMA_NO_NODE,
 * prefer the current CPU's closest node. Otherwise node must be valid and
 * online.
 */
static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask,
						unsigned int order)
{
	if (nid == NUMA_NO_NODE)
		nid = numa_mem_id();

	return __alloc_pages_node(nid, gfp_mask, order);
}

#ifdef CONFIG_NUMA
struct page *alloc_pages(gfp_t gfp, unsigned int order);
struct folio *folio_alloc(gfp_t gfp, unsigned order);
struct folio *vma_alloc_folio(gfp_t gfp, int order, struct vm_area_struct *vma,
		unsigned long addr, bool hugepage);
#else
static inline struct page *alloc_pages(gfp_t gfp_mask, unsigned int order)
{
	return alloc_pages_node(numa_node_id(), gfp_mask, order);
}
static inline struct folio *folio_alloc(gfp_t gfp, unsigned int order)
{
	return __folio_alloc_node(gfp, order, numa_node_id());
}
#define vma_alloc_folio(gfp, order, vma, addr, hugepage)		\
	folio_alloc(gfp, order)
#endif
#define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0)
static inline struct page *alloc_page_vma(gfp_t gfp,
		struct vm_area_struct *vma, unsigned long addr)
{
	struct folio *folio = vma_alloc_folio(gfp, 0, vma, addr, false);

	return &folio->page;
}

extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order);
extern unsigned long get_zeroed_page(gfp_t gfp_mask);

void *alloc_pages_exact(size_t size, gfp_t gfp_mask) __alloc_size(1);
void free_pages_exact(void *virt, size_t size);
__meminit void *alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask) __alloc_size(2);

#define __get_free_page(gfp_mask) \
		__get_free_pages((gfp_mask), 0)

#define __get_dma_pages(gfp_mask, order) \
		__get_free_pages((gfp_mask) | GFP_DMA, (order))

extern void __free_pages(struct page *page, unsigned int order);
extern void free_pages(unsigned long addr, unsigned int order);

struct page_frag_cache;
extern void __page_frag_cache_drain(struct page *page, unsigned int count);
extern void *page_frag_alloc_align(struct page_frag_cache *nc,
				   unsigned int fragsz, gfp_t gfp_mask,
				   unsigned int align_mask);

static inline void *page_frag_alloc(struct page_frag_cache *nc,
			     unsigned int fragsz, gfp_t gfp_mask)
{
	return page_frag_alloc_align(nc, fragsz, gfp_mask, ~0u);
}

extern void page_frag_free(void *addr);

#define __free_page(page) __free_pages((page), 0)
#define free_page(addr) free_pages((addr), 0)

void page_alloc_init(void);
void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp);
void drain_all_pages(struct zone *zone);
void drain_local_pages(struct zone *zone);

void page_alloc_init_late(void);

/*
 * gfp_allowed_mask is set to GFP_BOOT_MASK during early boot to restrict what
 * GFP flags are used before interrupts are enabled. Once interrupts are
 * enabled, it is set to __GFP_BITS_MASK while the system is running. During
 * hibernation, it is used by PM to avoid I/O during memory allocation while
 * devices are suspended.
 */
extern gfp_t gfp_allowed_mask;

/* Returns true if the gfp_mask allows use of ALLOC_NO_WATERMARK */
bool gfp_pfmemalloc_allowed(gfp_t gfp_mask);

extern void pm_restrict_gfp_mask(void);
extern void pm_restore_gfp_mask(void);

extern gfp_t vma_thp_gfp_mask(struct vm_area_struct *vma);

#ifdef CONFIG_PM_SLEEP
extern bool pm_suspended_storage(void);
#else
static inline bool pm_suspended_storage(void)
{
	return false;
}
#endif /* CONFIG_PM_SLEEP */

#ifdef CONFIG_CONTIG_ALLOC
/* The below functions must be run on a range from a single zone. */
extern int alloc_contig_range(unsigned long start, unsigned long end,
			      unsigned migratetype, gfp_t gfp_mask);
extern struct page *alloc_contig_pages(unsigned long nr_pages, gfp_t gfp_mask,
				       int nid, nodemask_t *nodemask);
#endif
void free_contig_range(unsigned long pfn, unsigned long nr_pages);

#ifdef CONFIG_CMA
/* CMA stuff */
extern void init_cma_reserved_pageblock(struct page *page);
#endif

#endif /* __LINUX_GFP_H */