xref: /linux/mm/vmalloc.c (revision 4e69c1856bfd9ffb7e9d335a25842fa211628929)

// SPDX-License-Identifier: GPL-2.0-only
/*
 *  Copyright (C) 1993  Linus Torvalds
 *  Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
 *  SMP-safe vmalloc/vfree/ioremap, Tigran Aivazian <tigran@veritas.com>, May 2000
 *  Major rework to support vmap/vunmap, Christoph Hellwig, SGI, August 2002
 *  Numa awareness, Christoph Lameter, SGI, June 2005
 *  Improving global KVA allocator, Uladzislau Rezki, Sony, May 2019
 */

#include <linux/vmalloc.h>
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/highmem.h>
#include <linux/sched/signal.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/interrupt.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/set_memory.h>
#include <linux/debugobjects.h>
#include <linux/kallsyms.h>
#include <linux/list.h>
#include <linux/notifier.h>
#include <linux/rbtree.h>
#include <linux/xarray.h>
#include <linux/io.h>
#include <linux/rcupdate.h>
#include <linux/pfn.h>
#include <linux/kmemleak.h>
#include <linux/atomic.h>
#include <linux/compiler.h>
#include <linux/memcontrol.h>
#include <linux/llist.h>
#include <linux/uio.h>
#include <linux/bitops.h>
#include <linux/rbtree_augmented.h>
#include <linux/overflow.h>
#include <linux/pgtable.h>
#include <linux/hugetlb.h>
#include <linux/sched/mm.h>
#include <asm/tlbflush.h>
#include <asm/shmparam.h>
#include <linux/page_owner.h>
#include <linux/cleanup.h>

#define CREATE_TRACE_POINTS
#include <trace/events/vmalloc.h>

#include "internal.h"
#include "pgalloc-track.h"
#include "vmalloc.h"

#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
static unsigned int __ro_after_init ioremap_max_page_shift = BITS_PER_LONG - 1;

static int __init set_nohugeiomap(char *str)
{
	ioremap_max_page_shift = PAGE_SHIFT;
	return 0;
}
early_param("nohugeiomap", set_nohugeiomap);
#else /* CONFIG_HAVE_ARCH_HUGE_VMAP */
static const unsigned int ioremap_max_page_shift = PAGE_SHIFT;
#endif	/* CONFIG_HAVE_ARCH_HUGE_VMAP */

#ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC
static bool __ro_after_init vmap_allow_huge = true;

static int __init set_nohugevmalloc(char *str)
{
	vmap_allow_huge = false;
	return 0;
}
early_param("nohugevmalloc", set_nohugevmalloc);
#else /* CONFIG_HAVE_ARCH_HUGE_VMALLOC */
static const bool vmap_allow_huge = false;
#endif	/* CONFIG_HAVE_ARCH_HUGE_VMALLOC */

bool is_vmalloc_addr(const void *x)
{
	unsigned long addr = (unsigned long)kasan_reset_tag(x);

	return addr >= VMALLOC_START && addr < VMALLOC_END;
}
EXPORT_SYMBOL(is_vmalloc_addr);

struct vfree_deferred {
	struct llist_head list;
	struct work_struct wq;
};
static DEFINE_PER_CPU(struct vfree_deferred, vfree_deferred);

/*** Page table manipulation functions ***/
static int vmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
			phys_addr_t phys_addr, pgprot_t prot,
			unsigned int max_page_shift, pgtbl_mod_mask *mask)
{
	pte_t *pte;
	u64 pfn;
	struct page *page;
	unsigned long size = PAGE_SIZE;

	if (WARN_ON_ONCE(!PAGE_ALIGNED(end - addr)))
		return -EINVAL;

	pfn = phys_addr >> PAGE_SHIFT;
	pte = pte_alloc_kernel_track(pmd, addr, mask);
	if (!pte)
		return -ENOMEM;

	lazy_mmu_mode_enable();

	do {
		if (unlikely(!pte_none(ptep_get(pte)))) {
			if (pfn_valid(pfn)) {
				page = pfn_to_page(pfn);
				dump_page(page, "remapping already mapped page");
			}
			BUG();
		}

#ifdef CONFIG_HUGETLB_PAGE
		size = arch_vmap_pte_range_map_size(addr, end, pfn, max_page_shift);
		if (size != PAGE_SIZE) {
			pte_t entry = pfn_pte(pfn, prot);

			entry = arch_make_huge_pte(entry, ilog2(size), 0);
			set_huge_pte_at(&init_mm, addr, pte, entry, size);
			pfn += PFN_DOWN(size);
			continue;
		}
#endif
		set_pte_at(&init_mm, addr, pte, pfn_pte(pfn, prot));
		pfn++;
	} while (pte += PFN_DOWN(size), addr += size, addr != end);

	lazy_mmu_mode_disable();
	*mask |= PGTBL_PTE_MODIFIED;
	return 0;
}

static int vmap_try_huge_pmd(pmd_t *pmd, unsigned long addr, unsigned long end,
			phys_addr_t phys_addr, pgprot_t prot,
			unsigned int max_page_shift)
{
	if (max_page_shift < PMD_SHIFT)
		return 0;

	if (!arch_vmap_pmd_supported(prot))
		return 0;

	if ((end - addr) != PMD_SIZE)
		return 0;

	if (!IS_ALIGNED(addr, PMD_SIZE))
		return 0;

	if (!IS_ALIGNED(phys_addr, PMD_SIZE))
		return 0;

	if (!pmd_present(*pmd))
		return pmd_set_huge(pmd, phys_addr, prot);

	/*
	 * Acquire the mmap read lock to exclude ptdump, which walks
	 * kernel page tables it does not own under the mmap write lock.
	 *
	 * Concurrent read lock holders are safe: each exclusively owns
	 * the range it operates on and cannot reach this page table.
	 */
	scoped_cond_guard(mmap_read_lock_try, return 0, &init_mm) {
		if (!pmd_free_pte_page(pmd, addr))
			return 0;
		return pmd_set_huge(pmd, phys_addr, prot);
	}
}

static int vmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
			phys_addr_t phys_addr, pgprot_t prot,
			unsigned int max_page_shift, pgtbl_mod_mask *mask)
{
	pmd_t *pmd;
	unsigned long next;
	int err = 0;

	pmd = pmd_alloc_track(&init_mm, pud, addr, mask);
	if (!pmd)
		return -ENOMEM;
	do {
		next = pmd_addr_end(addr, end);

		if (vmap_try_huge_pmd(pmd, addr, next, phys_addr, prot,
					max_page_shift)) {
			*mask |= PGTBL_PMD_MODIFIED;
			continue;
		}

		err = vmap_pte_range(pmd, addr, next, phys_addr, prot, max_page_shift, mask);
		if (err)
			break;
	} while (pmd++, phys_addr += (next - addr), addr = next, addr != end);
	return err;
}

static int vmap_try_huge_pud(pud_t *pud, unsigned long addr, unsigned long end,
			phys_addr_t phys_addr, pgprot_t prot,
			unsigned int max_page_shift)
{
	if (max_page_shift < PUD_SHIFT)
		return 0;

	if (!arch_vmap_pud_supported(prot))
		return 0;

	if ((end - addr) != PUD_SIZE)
		return 0;

	if (!IS_ALIGNED(addr, PUD_SIZE))
		return 0;

	if (!IS_ALIGNED(phys_addr, PUD_SIZE))
		return 0;

	if (!pud_present(*pud))
		return pud_set_huge(pud, phys_addr, prot);

	/* See comment in vmap_try_huge_pmd(). */
	scoped_cond_guard(mmap_read_lock_try, return 0, &init_mm) {
		if (!pud_free_pmd_page(pud, addr))
			return 0;
		return pud_set_huge(pud, phys_addr, prot);
	}
}

static int vmap_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end,
			phys_addr_t phys_addr, pgprot_t prot,
			unsigned int max_page_shift, pgtbl_mod_mask *mask)
{
	pud_t *pud;
	unsigned long next;
	int err = 0;

	pud = pud_alloc_track(&init_mm, p4d, addr, mask);
	if (!pud)
		return -ENOMEM;
	do {
		next = pud_addr_end(addr, end);

		if (vmap_try_huge_pud(pud, addr, next, phys_addr, prot,
					max_page_shift)) {
			*mask |= PGTBL_PUD_MODIFIED;
			continue;
		}

		err = vmap_pmd_range(pud, addr, next, phys_addr, prot, max_page_shift, mask);
		if (err)
			break;
	} while (pud++, phys_addr += (next - addr), addr = next, addr != end);
	return err;
}

static int vmap_try_huge_p4d(p4d_t *p4d, unsigned long addr, unsigned long end,
			phys_addr_t phys_addr, pgprot_t prot,
			unsigned int max_page_shift)
{
	if (max_page_shift < P4D_SHIFT)
		return 0;

	if (!arch_vmap_p4d_supported(prot))
		return 0;

	if ((end - addr) != P4D_SIZE)
		return 0;

	if (!IS_ALIGNED(addr, P4D_SIZE))
		return 0;

	if (!IS_ALIGNED(phys_addr, P4D_SIZE))
		return 0;

	if (!p4d_present(*p4d))
		return p4d_set_huge(p4d, phys_addr, prot);

	/* See comment in vmap_try_huge_pmd(). */
	scoped_cond_guard(mmap_read_lock_try, return 0, &init_mm) {
		if (!p4d_free_pud_page(p4d, addr))
			return 0;
		return p4d_set_huge(p4d, phys_addr, prot);
	}
}

static int vmap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end,
			phys_addr_t phys_addr, pgprot_t prot,
			unsigned int max_page_shift, pgtbl_mod_mask *mask)
{
	p4d_t *p4d;
	unsigned long next;
	int err = 0;

	p4d = p4d_alloc_track(&init_mm, pgd, addr, mask);
	if (!p4d)
		return -ENOMEM;
	do {
		next = p4d_addr_end(addr, end);

		if (vmap_try_huge_p4d(p4d, addr, next, phys_addr, prot,
					max_page_shift)) {
			*mask |= PGTBL_P4D_MODIFIED;
			continue;
		}

		err = vmap_pud_range(p4d, addr, next, phys_addr, prot, max_page_shift, mask);
		if (err)
			break;
	} while (p4d++, phys_addr += (next - addr), addr = next, addr != end);
	return err;
}

static int vmap_range_noflush(unsigned long addr, unsigned long end,
			phys_addr_t phys_addr, pgprot_t prot,
			unsigned int max_page_shift)
{
	pgd_t *pgd;
	unsigned long start;
	unsigned long next;
	int err;
	pgtbl_mod_mask mask = 0;

	/*
	 * Might allocate pagetables (for most archs a more precise annotation
	 * would be might_alloc(GFP_PGTABLE_KERNEL)). Also might shootdown TLB
	 * (requires IRQs enabled on x86).
	 */
	might_sleep();
	BUG_ON(addr >= end);

	start = addr;
	pgd = pgd_offset_k(addr);
	do {
		next = pgd_addr_end(addr, end);
		err = vmap_p4d_range(pgd, addr, next, phys_addr, prot,
					max_page_shift, &mask);
		if (err)
			break;
	} while (pgd++, phys_addr += (next - addr), addr = next, addr != end);

	if (mask & ARCH_PAGE_TABLE_SYNC_MASK)
		arch_sync_kernel_mappings(start, end);

	return err;
}

int vmap_page_range(unsigned long addr, unsigned long end,
		    phys_addr_t phys_addr, pgprot_t prot)
{
	int err;

	err = vmap_range_noflush(addr, end, phys_addr, pgprot_nx(prot),
				 ioremap_max_page_shift);
	flush_cache_vmap(addr, end);
	if (!err)
		err = kmsan_ioremap_page_range(addr, end, phys_addr, prot,
					       ioremap_max_page_shift);
	return err;
}

int ioremap_page_range(unsigned long addr, unsigned long end,
		phys_addr_t phys_addr, pgprot_t prot)
{
	struct vm_struct *area;

	area = find_vm_area((void *)addr);
	if (!area || !(area->flags & VM_IOREMAP)) {
		WARN_ONCE(1, "vm_area at addr %lx is not marked as VM_IOREMAP\n", addr);
		return -EINVAL;
	}
	if (addr != (unsigned long)area->addr ||
	    (void *)end != area->addr + get_vm_area_size(area)) {
		WARN_ONCE(1, "ioremap request [%lx,%lx) doesn't match vm_area [%lx, %lx)\n",
			  addr, end, (long)area->addr,
			  (long)area->addr + get_vm_area_size(area));
		return -ERANGE;
	}
	return vmap_page_range(addr, end, phys_addr, prot);
}

static void vunmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
			     pgtbl_mod_mask *mask)
{
	pte_t *pte;
	pte_t ptent;
	unsigned long size = PAGE_SIZE;

	pte = pte_offset_kernel(pmd, addr);
	lazy_mmu_mode_enable();

	do {
#ifdef CONFIG_HUGETLB_PAGE
		size = arch_vmap_pte_range_unmap_size(addr, pte);
		if (size != PAGE_SIZE) {
			if (WARN_ON(!IS_ALIGNED(addr, size))) {
				addr = ALIGN_DOWN(addr, size);
				pte = PTR_ALIGN_DOWN(pte, sizeof(*pte) * (size >> PAGE_SHIFT));
			}
			ptent = huge_ptep_get_and_clear(&init_mm, addr, pte, size);
			if (WARN_ON(end - addr < size))
				size = end - addr;
		} else
#endif
			ptent = ptep_get_and_clear(&init_mm, addr, pte);
		WARN_ON(!pte_none(ptent) && !pte_present(ptent));
	} while (pte += (size >> PAGE_SHIFT), addr += size, addr != end);

	lazy_mmu_mode_disable();
	*mask |= PGTBL_PTE_MODIFIED;
}

static void vunmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
			     pgtbl_mod_mask *mask)
{
	pmd_t *pmd;
	unsigned long next;
	int cleared;

	pmd = pmd_offset(pud, addr);
	do {
		next = pmd_addr_end(addr, end);

		cleared = pmd_clear_huge(pmd);
		if (cleared || pmd_bad(*pmd))
			*mask |= PGTBL_PMD_MODIFIED;

		if (cleared) {
			WARN_ON(next - addr < PMD_SIZE);
			continue;
		}
		if (pmd_none_or_clear_bad(pmd))
			continue;
		vunmap_pte_range(pmd, addr, next, mask);

		cond_resched();
	} while (pmd++, addr = next, addr != end);
}

static void vunmap_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end,
			     pgtbl_mod_mask *mask)
{
	pud_t *pud;
	unsigned long next;
	int cleared;

	pud = pud_offset(p4d, addr);
	do {
		next = pud_addr_end(addr, end);

		cleared = pud_clear_huge(pud);
		if (cleared || pud_bad(*pud))
			*mask |= PGTBL_PUD_MODIFIED;

		if (cleared) {
			WARN_ON(next - addr < PUD_SIZE);
			continue;
		}
		if (pud_none_or_clear_bad(pud))
			continue;
		vunmap_pmd_range(pud, addr, next, mask);
	} while (pud++, addr = next, addr != end);
}

static void vunmap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end,
			     pgtbl_mod_mask *mask)
{
	p4d_t *p4d;
	unsigned long next;

	p4d = p4d_offset(pgd, addr);
	do {
		next = p4d_addr_end(addr, end);

		p4d_clear_huge(p4d);
		if (p4d_bad(*p4d))
			*mask |= PGTBL_P4D_MODIFIED;

		if (p4d_none_or_clear_bad(p4d))
			continue;
		vunmap_pud_range(p4d, addr, next, mask);
	} while (p4d++, addr = next, addr != end);
}

/*
 * vunmap_range_noflush is similar to vunmap_range, but does not
 * flush caches or TLBs.
 *
 * The caller is responsible for calling flush_cache_vmap() before calling
 * this function, and flush_tlb_kernel_range after it has returned
 * successfully (and before the addresses are expected to cause a page fault
 * or be re-mapped for something else, if TLB flushes are being delayed or
 * coalesced).
 *
 * This is an internal function only. Do not use outside mm/.
 */
void __vunmap_range_noflush(unsigned long start, unsigned long end)
{
	unsigned long next;
	pgd_t *pgd;
	unsigned long addr = start;
	pgtbl_mod_mask mask = 0;

	BUG_ON(addr >= end);
	pgd = pgd_offset_k(addr);
	do {
		next = pgd_addr_end(addr, end);
		if (pgd_bad(*pgd))
			mask |= PGTBL_PGD_MODIFIED;
		if (pgd_none_or_clear_bad(pgd))
			continue;
		vunmap_p4d_range(pgd, addr, next, &mask);
	} while (pgd++, addr = next, addr != end);

	if (mask & ARCH_PAGE_TABLE_SYNC_MASK)
		arch_sync_kernel_mappings(start, end);
}

void vunmap_range_noflush(unsigned long start, unsigned long end)
{
	kmsan_vunmap_range_noflush(start, end);
	__vunmap_range_noflush(start, end);
}

/**
 * vunmap_range - unmap kernel virtual addresses
 * @addr: start of the VM area to unmap
 * @end: end of the VM area to unmap (non-inclusive)
 *
 * Clears any present PTEs in the virtual address range, flushes TLBs and
 * caches. Any subsequent access to the address before it has been re-mapped
 * is a kernel bug.
 */
void vunmap_range(unsigned long addr, unsigned long end)
{
	flush_cache_vunmap(addr, end);
	vunmap_range_noflush(addr, end);
	flush_tlb_kernel_range(addr, end);
}

static int vmap_pages_pte_range(pmd_t *pmd, unsigned long addr,
		unsigned long end, pgprot_t prot, struct page **pages, int *nr,
		pgtbl_mod_mask *mask)
{
	int err = 0;
	pte_t *pte;

	/*
	 * nr is a running index into the array which helps higher level
	 * callers keep track of where we're up to.
	 */

	pte = pte_alloc_kernel_track(pmd, addr, mask);
	if (!pte)
		return -ENOMEM;

	lazy_mmu_mode_enable();

	do {
		struct page *page = pages[*nr];

		if (WARN_ON(!pte_none(ptep_get(pte)))) {
			err = -EBUSY;
			break;
		}
		if (WARN_ON(!page)) {
			err = -ENOMEM;
			break;
		}
		if (WARN_ON(!pfn_valid(page_to_pfn(page)))) {
			err = -EINVAL;
			break;
		}

		set_pte_at(&init_mm, addr, pte, mk_pte(page, prot));
		(*nr)++;
	} while (pte++, addr += PAGE_SIZE, addr != end);

	lazy_mmu_mode_disable();
	*mask |= PGTBL_PTE_MODIFIED;

	return err;
}

static int vmap_pages_pmd_range(pud_t *pud, unsigned long addr,
		unsigned long end, pgprot_t prot, struct page **pages, int *nr,
		pgtbl_mod_mask *mask)
{
	pmd_t *pmd;
	unsigned long next;

	pmd = pmd_alloc_track(&init_mm, pud, addr, mask);
	if (!pmd)
		return -ENOMEM;
	do {
		next = pmd_addr_end(addr, end);
		if (vmap_pages_pte_range(pmd, addr, next, prot, pages, nr, mask))
			return -ENOMEM;
	} while (pmd++, addr = next, addr != end);
	return 0;
}

static int vmap_pages_pud_range(p4d_t *p4d, unsigned long addr,
		unsigned long end, pgprot_t prot, struct page **pages, int *nr,
		pgtbl_mod_mask *mask)
{
	pud_t *pud;
	unsigned long next;

	pud = pud_alloc_track(&init_mm, p4d, addr, mask);
	if (!pud)
		return -ENOMEM;
	do {
		next = pud_addr_end(addr, end);
		if (vmap_pages_pmd_range(pud, addr, next, prot, pages, nr, mask))
			return -ENOMEM;
	} while (pud++, addr = next, addr != end);
	return 0;
}

static int vmap_pages_p4d_range(pgd_t *pgd, unsigned long addr,
		unsigned long end, pgprot_t prot, struct page **pages, int *nr,
		pgtbl_mod_mask *mask)
{
	p4d_t *p4d;
	unsigned long next;

	p4d = p4d_alloc_track(&init_mm, pgd, addr, mask);
	if (!p4d)
		return -ENOMEM;
	do {
		next = p4d_addr_end(addr, end);
		if (vmap_pages_pud_range(p4d, addr, next, prot, pages, nr, mask))
			return -ENOMEM;
	} while (p4d++, addr = next, addr != end);
	return 0;
}

static int vmap_small_pages_range_noflush(unsigned long addr, unsigned long end,
		pgprot_t prot, struct page **pages)
{
	unsigned long start = addr;
	pgd_t *pgd;
	unsigned long next;
	int err = 0;
	int nr = 0;
	pgtbl_mod_mask mask = 0;

	BUG_ON(addr >= end);
	pgd = pgd_offset_k(addr);
	do {
		next = pgd_addr_end(addr, end);
		if (pgd_bad(*pgd))
			mask |= PGTBL_PGD_MODIFIED;
		err = vmap_pages_p4d_range(pgd, addr, next, prot, pages, &nr, &mask);
		if (err)
			break;
	} while (pgd++, addr = next, addr != end);

	if (mask & ARCH_PAGE_TABLE_SYNC_MASK)
		arch_sync_kernel_mappings(start, end);

	return err;
}

/*
 * vmap_pages_range_noflush is similar to vmap_pages_range, but does not
 * flush caches.
 *
 * The caller is responsible for calling flush_cache_vmap() after this
 * function returns successfully and before the addresses are accessed.
 *
 * This is an internal function only. Do not use outside mm/.
 */
int __vmap_pages_range_noflush(unsigned long addr, unsigned long end,
		pgprot_t prot, struct page **pages, unsigned int page_shift)
{
	unsigned int i, nr = (end - addr) >> PAGE_SHIFT;

	WARN_ON(page_shift < PAGE_SHIFT);

	if (!IS_ENABLED(CONFIG_HAVE_ARCH_HUGE_VMALLOC) ||
			page_shift == PAGE_SHIFT)
		return vmap_small_pages_range_noflush(addr, end, prot, pages);

	for (i = 0; i < nr; i += 1U << (page_shift - PAGE_SHIFT)) {
		int err;

		err = vmap_range_noflush(addr, addr + (1UL << page_shift),
					page_to_phys(pages[i]), prot,
					page_shift);
		if (err)
			return err;

		addr += 1UL << page_shift;
	}

	return 0;
}

int vmap_pages_range_noflush(unsigned long addr, unsigned long end,
		pgprot_t prot, struct page **pages, unsigned int page_shift,
		gfp_t gfp_mask)
{
	int ret = kmsan_vmap_pages_range_noflush(addr, end, prot, pages,
						page_shift, gfp_mask);

	if (ret)
		return ret;
	return __vmap_pages_range_noflush(addr, end, prot, pages, page_shift);
}

static int __vmap_pages_range(unsigned long addr, unsigned long end,
		pgprot_t prot, struct page **pages, unsigned int page_shift,
		gfp_t gfp_mask)
{
	int err;

	err = vmap_pages_range_noflush(addr, end, prot, pages, page_shift, gfp_mask);
	flush_cache_vmap(addr, end);
	return err;
}

/**
 * vmap_pages_range - map pages to a kernel virtual address
 * @addr: start of the VM area to map
 * @end: end of the VM area to map (non-inclusive)
 * @prot: page protection flags to use
 * @pages: pages to map (always PAGE_SIZE pages)
 * @page_shift: maximum shift that the pages may be mapped with, @pages must
 * be aligned and contiguous up to at least this shift.
 *
 * RETURNS:
 * 0 on success, -errno on failure.
 */
int vmap_pages_range(unsigned long addr, unsigned long end,
		pgprot_t prot, struct page **pages, unsigned int page_shift)
{
	return __vmap_pages_range(addr, end, prot, pages, page_shift, GFP_KERNEL);
}

static int check_sparse_vm_area(struct vm_struct *area, unsigned long start,
				unsigned long end)
{
	might_sleep();
	if (WARN_ON_ONCE(area->flags & VM_FLUSH_RESET_PERMS))
		return -EINVAL;
	if (WARN_ON_ONCE(area->flags & VM_NO_GUARD))
		return -EINVAL;
	if (WARN_ON_ONCE(!(area->flags & VM_SPARSE)))
		return -EINVAL;
	if ((end - start) >> PAGE_SHIFT > totalram_pages())
		return -E2BIG;
	if (start < (unsigned long)area->addr ||
	    (void *)end > area->addr + get_vm_area_size(area))
		return -ERANGE;
	return 0;
}

/**
 * vm_area_map_pages - map pages inside given sparse vm_area
 * @area: vm_area
 * @start: start address inside vm_area
 * @end: end address inside vm_area
 * @pages: pages to map (always PAGE_SIZE pages)
 */
int vm_area_map_pages(struct vm_struct *area, unsigned long start,
		      unsigned long end, struct page **pages)
{
	int err;

	err = check_sparse_vm_area(area, start, end);
	if (err)
		return err;

	return vmap_pages_range(start, end, PAGE_KERNEL, pages, PAGE_SHIFT);
}

/**
 * vm_area_unmap_pages - unmap pages inside given sparse vm_area
 * @area: vm_area
 * @start: start address inside vm_area
 * @end: end address inside vm_area
 */
void vm_area_unmap_pages(struct vm_struct *area, unsigned long start,
			 unsigned long end)
{
	if (check_sparse_vm_area(area, start, end))
		return;

	vunmap_range(start, end);
}

int is_vmalloc_or_module_addr(const void *x)
{
	/*
	 * ARM, x86-64 and sparc64 put modules in a special place,
	 * and fall back on vmalloc() if that fails. Others
	 * just put it in the vmalloc space.
	 */
#if defined(CONFIG_EXECMEM) && defined(MODULES_VADDR)
	unsigned long addr = (unsigned long)kasan_reset_tag(x);
	if (addr >= MODULES_VADDR && addr < MODULES_END)
		return 1;
#endif
	return is_vmalloc_addr(x);
}
EXPORT_SYMBOL_GPL(is_vmalloc_or_module_addr);

/*
 * Walk a vmap address to the struct page it maps. Huge vmap mappings will
 * return the tail page that corresponds to the base page address, which
 * matches small vmap mappings.
 */
struct page *vmalloc_to_page(const void *vmalloc_addr)
{
	unsigned long addr = (unsigned long) vmalloc_addr;
	struct page *page = NULL;
	pgd_t *pgd = pgd_offset_k(addr);
	p4d_t *p4d;
	pud_t *pud;
	pmd_t *pmd;
	pte_t *ptep, pte;

	/*
	 * XXX we might need to change this if we add VIRTUAL_BUG_ON for
	 * architectures that do not vmalloc module space
	 */
	VIRTUAL_BUG_ON(!is_vmalloc_or_module_addr(vmalloc_addr));

	if (pgd_none(*pgd))
		return NULL;
	if (WARN_ON_ONCE(pgd_leaf(*pgd)))
		return NULL; /* XXX: no allowance for huge pgd */
	if (WARN_ON_ONCE(pgd_bad(*pgd)))
		return NULL;

	p4d = p4d_offset(pgd, addr);
	if (p4d_none(*p4d))
		return NULL;
	if (p4d_leaf(*p4d))
		return p4d_page(*p4d) + ((addr & ~P4D_MASK) >> PAGE_SHIFT);
	if (WARN_ON_ONCE(p4d_bad(*p4d)))
		return NULL;

	pud = pud_offset(p4d, addr);
	if (pud_none(*pud))
		return NULL;
	if (pud_leaf(*pud))
		return pud_page(*pud) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
	if (WARN_ON_ONCE(pud_bad(*pud)))
		return NULL;

	pmd = pmd_offset(pud, addr);
	if (pmd_none(*pmd))
		return NULL;
	if (pmd_leaf(*pmd))
		return pmd_page(*pmd) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
	if (WARN_ON_ONCE(pmd_bad(*pmd)))
		return NULL;

	ptep = pte_offset_kernel(pmd, addr);
	pte = ptep_get(ptep);
	if (pte_present(pte))
		page = pte_page(pte);

	return page;
}
EXPORT_SYMBOL(vmalloc_to_page);

/*
 * Map a vmalloc()-space virtual address to the physical page frame number.
 */
unsigned long vmalloc_to_pfn(const void *vmalloc_addr)
{
	return page_to_pfn(vmalloc_to_page(vmalloc_addr));
}
EXPORT_SYMBOL(vmalloc_to_pfn);


/*** Global kva allocator ***/

#define DEBUG_AUGMENT_PROPAGATE_CHECK 0
#define DEBUG_AUGMENT_LOWEST_MATCH_CHECK 0


static DEFINE_SPINLOCK(free_vmap_area_lock);
static bool vmap_initialized __read_mostly;

/*
 * This kmem_cache is used for vmap_area objects. Instead of
 * allocating from slab we reuse an object from this cache to
 * make things faster. Especially in "no edge" splitting of
 * free block.
 */
static struct kmem_cache *vmap_area_cachep;

/*
 * This linked list is used in pair with free_vmap_area_root.
 * It gives O(1) access to prev/next to perform fast coalescing.
 */
static LIST_HEAD(free_vmap_area_list);

/*
 * This augment red-black tree represents the free vmap space.
 * All vmap_area objects in this tree are sorted by va->va_start
 * address. It is used for allocation and merging when a vmap
 * object is released.
 *
 * Each vmap_area node contains a maximum available free block
 * of its sub-tree, right or left. Therefore it is possible to
 * find a lowest match of free area.
 */
static struct rb_root free_vmap_area_root = RB_ROOT;

/*
 * Preload a CPU with one object for "no edge" split case. The
 * aim is to get rid of allocations from the atomic context, thus
 * to use more permissive allocation masks.
 */
static DEFINE_PER_CPU(struct vmap_area *, ne_fit_preload_node);

/*
 * This structure defines a single, solid model where a list and
 * rb-tree are part of one entity protected by the lock. Nodes are
 * sorted in ascending order, thus for O(1) access to left/right
 * neighbors a list is used as well as for sequential traversal.
 */
struct rb_list {
	struct rb_root root;
	struct list_head head;
	spinlock_t lock;
};

/*
 * A fast size storage contains VAs up to 1M size. A pool consists
 * of linked between each other ready to go VAs of certain sizes.
 * An index in the pool-array corresponds to number of pages + 1.
 */
#define MAX_VA_SIZE_PAGES 256

struct vmap_pool {
	struct list_head head;
	unsigned long len;
};

/*
 * An effective vmap-node logic. Users make use of nodes instead
 * of a global heap. It allows to balance an access and mitigate
 * contention.
 */
static struct vmap_node {
	/* Simple size segregated storage. */
	struct vmap_pool pool[MAX_VA_SIZE_PAGES];
	spinlock_t pool_lock;
	bool skip_populate;

	/* Bookkeeping data of this node. */
	struct rb_list busy;
	struct rb_list lazy;

	/*
	 * Ready-to-free areas.
	 */
	struct list_head purge_list;
	struct work_struct purge_work;
	unsigned long nr_purged;
} single;

/*
 * Initial setup consists of one single node, i.e. a balancing
 * is fully disabled. Later on, after vmap is initialized these
 * parameters are updated based on a system capacity.
 */
static struct vmap_node *vmap_nodes = &single;
static __read_mostly unsigned int nr_vmap_nodes = 1;
static __read_mostly unsigned int vmap_zone_size = 1;

/* A simple iterator over all vmap-nodes. */
#define for_each_vmap_node(vn)	\
	for ((vn) = &vmap_nodes[0];	\
		(vn) < &vmap_nodes[nr_vmap_nodes]; (vn)++)

static inline unsigned int
addr_to_node_id(unsigned long addr)
{
	return (addr / vmap_zone_size) % nr_vmap_nodes;
}

static inline struct vmap_node *
addr_to_node(unsigned long addr)
{
	return &vmap_nodes[addr_to_node_id(addr)];
}

static inline struct vmap_node *
id_to_node(unsigned int id)
{
	return &vmap_nodes[id % nr_vmap_nodes];
}

static inline unsigned int
node_to_id(struct vmap_node *node)
{
	/* Pointer arithmetic. */
	unsigned int id = node - vmap_nodes;

	if (likely(id < nr_vmap_nodes))
		return id;

	WARN_ONCE(1, "An address 0x%p is out-of-bounds.\n", node);
	return 0;
}

/*
 * We use the value 0 to represent "no node", that is why
 * an encoded value will be the node-id incremented by 1.
 * It is always greater then 0. A valid node_id which can
 * be encoded is [0:nr_vmap_nodes - 1]. If a passed node_id
 * is not valid 0 is returned.
 */
static unsigned int
encode_vn_id(unsigned int node_id)
{
	/* Can store U8_MAX [0:254] nodes. */
	if (node_id < nr_vmap_nodes)
		return (node_id + 1) << BITS_PER_BYTE;

	/* Warn and no node encoded. */
	WARN_ONCE(1, "Encode wrong node id (%u)\n", node_id);
	return 0;
}

/*
 * Returns an encoded node-id, the valid range is within
 * [0:nr_vmap_nodes-1] values. Otherwise nr_vmap_nodes is
 * returned if extracted data is wrong.
 */
static unsigned int
decode_vn_id(unsigned int val)
{
	unsigned int node_id = (val >> BITS_PER_BYTE) - 1;

	/* Can store U8_MAX [0:254] nodes. */
	if (node_id < nr_vmap_nodes)
		return node_id;

	/* If it was _not_ zero, warn. */
	WARN_ONCE(node_id != UINT_MAX,
		"Decode wrong node id (%d)\n", node_id);

	return nr_vmap_nodes;
}

static bool
is_vn_id_valid(unsigned int node_id)
{
	if (node_id < nr_vmap_nodes)
		return true;

	return false;
}

static __always_inline unsigned long
va_size(struct vmap_area *va)
{
	return (va->va_end - va->va_start);
}

static __always_inline unsigned long
get_subtree_max_size(struct rb_node *node)
{
	struct vmap_area *va;

	va = rb_entry_safe(node, struct vmap_area, rb_node);
	return va ? va->subtree_max_size : 0;
}

RB_DECLARE_CALLBACKS_MAX(static, free_vmap_area_rb_augment_cb,
	struct vmap_area, rb_node, unsigned long, subtree_max_size, va_size)

static void reclaim_and_purge_vmap_areas(void);
static BLOCKING_NOTIFIER_HEAD(vmap_notify_list);
static void drain_vmap_area_work(struct work_struct *work);
static DECLARE_WORK(drain_vmap_work, drain_vmap_area_work);

static __cacheline_aligned_in_smp atomic_long_t vmap_lazy_nr;

static struct vmap_area *__find_vmap_area(unsigned long addr, struct rb_root *root)
{
	struct rb_node *n = root->rb_node;

	addr = (unsigned long)kasan_reset_tag((void *)addr);

	while (n) {
		struct vmap_area *va;

		va = rb_entry(n, struct vmap_area, rb_node);
		if (addr < va->va_start)
			n = n->rb_left;
		else if (addr >= va->va_end)
			n = n->rb_right;
		else
			return va;
	}

	return NULL;
}

/* Look up the first VA which satisfies addr < va_end, NULL if none. */
static struct vmap_area *
__find_vmap_area_exceed_addr(unsigned long addr, struct rb_root *root)
{
	struct vmap_area *va = NULL;
	struct rb_node *n = root->rb_node;

	addr = (unsigned long)kasan_reset_tag((void *)addr);

	while (n) {
		struct vmap_area *tmp;

		tmp = rb_entry(n, struct vmap_area, rb_node);
		if (tmp->va_end > addr) {
			va = tmp;
			if (tmp->va_start <= addr)
				break;

			n = n->rb_left;
		} else
			n = n->rb_right;
	}

	return va;
}

/*
 * Returns a node where a first VA, that satisfies addr < va_end, resides.
 * If success, a node is locked. A user is responsible to unlock it when a
 * VA is no longer needed to be accessed.
 *
 * Returns NULL if nothing found.
 */
static struct vmap_node *
find_vmap_area_exceed_addr_lock(unsigned long addr, struct vmap_area **va)
{
	unsigned long va_start_lowest;
	struct vmap_node *vn;

repeat:
	va_start_lowest = 0;

	for_each_vmap_node(vn) {
		spin_lock(&vn->busy.lock);
		*va = __find_vmap_area_exceed_addr(addr, &vn->busy.root);

		if (*va)
			if (!va_start_lowest || (*va)->va_start < va_start_lowest)
				va_start_lowest = (*va)->va_start;
		spin_unlock(&vn->busy.lock);
	}

	/*
	 * Check if found VA exists, it might have gone away.  In this case we
	 * repeat the search because a VA has been removed concurrently and we
	 * need to proceed to the next one, which is a rare case.
	 */
	if (va_start_lowest) {
		vn = addr_to_node(va_start_lowest);

		spin_lock(&vn->busy.lock);
		*va = __find_vmap_area(va_start_lowest, &vn->busy.root);

		if (*va)
			return vn;

		spin_unlock(&vn->busy.lock);
		goto repeat;
	}

	return NULL;
}

/*
 * This function returns back addresses of parent node
 * and its left or right link for further processing.
 *
 * Otherwise NULL is returned. In that case all further
 * steps regarding inserting of conflicting overlap range
 * have to be declined and actually considered as a bug.
 */
static __always_inline struct rb_node **
find_va_links(struct vmap_area *va,
	struct rb_root *root, struct rb_node *from,
	struct rb_node **parent)
{
	struct vmap_area *tmp_va;
	struct rb_node **link;

	if (root) {
		link = &root->rb_node;
		if (unlikely(!*link)) {
			*parent = NULL;
			return link;
		}
	} else {
		link = &from;
	}

	/*
	 * Go to the bottom of the tree. When we hit the last point
	 * we end up with parent rb_node and correct direction, i name
	 * it link, where the new va->rb_node will be attached to.
	 */
	do {
		tmp_va = rb_entry(*link, struct vmap_area, rb_node);

		/*
		 * During the traversal we also do some sanity check.
		 * Trigger the BUG() if there are sides(left/right)
		 * or full overlaps.
		 */
		if (va->va_end <= tmp_va->va_start)
			link = &(*link)->rb_left;
		else if (va->va_start >= tmp_va->va_end)
			link = &(*link)->rb_right;
		else {
			WARN(1, "vmalloc bug: 0x%lx-0x%lx overlaps with 0x%lx-0x%lx\n",
				va->va_start, va->va_end, tmp_va->va_start, tmp_va->va_end);

			return NULL;
		}
	} while (*link);

	*parent = &tmp_va->rb_node;
	return link;
}

static __always_inline struct list_head *
get_va_next_sibling(struct rb_node *parent, struct rb_node **link)
{
	struct list_head *list;

	if (unlikely(!parent))
		/*
		 * The red-black tree where we try to find VA neighbors
		 * before merging or inserting is empty, i.e. it means
		 * there is no free vmap space. Normally it does not
		 * happen but we handle this case anyway.
		 */
		return NULL;

	list = &rb_entry(parent, struct vmap_area, rb_node)->list;
	return (&parent->rb_right == link ? list->next : list);
}

static __always_inline void
__link_va(struct vmap_area *va, struct rb_root *root,
	struct rb_node *parent, struct rb_node **link,
	struct list_head *head, bool augment)
{
	/*
	 * VA is still not in the list, but we can
	 * identify its future previous list_head node.
	 */
	if (likely(parent)) {
		head = &rb_entry(parent, struct vmap_area, rb_node)->list;
		if (&parent->rb_right != link)
			head = head->prev;
	}

	/* Insert to the rb-tree */
	rb_link_node(&va->rb_node, parent, link);
	if (augment) {
		/*
		 * Some explanation here. Just perform simple insertion
		 * to the tree. We do not set va->subtree_max_size to
		 * its current size before calling rb_insert_augmented().
		 * It is because we populate the tree from the bottom
		 * to parent levels when the node _is_ in the tree.
		 *
		 * Therefore we set subtree_max_size to zero after insertion,
		 * to let __augment_tree_propagate_from() puts everything to
		 * the correct order later on.
		 */
		rb_insert_augmented(&va->rb_node,
			root, &free_vmap_area_rb_augment_cb);
		va->subtree_max_size = 0;
	} else {
		rb_insert_color(&va->rb_node, root);
	}

	/* Address-sort this list */
	list_add(&va->list, head);
}

static __always_inline void
link_va(struct vmap_area *va, struct rb_root *root,
	struct rb_node *parent, struct rb_node **link,
	struct list_head *head)
{
	__link_va(va, root, parent, link, head, false);
}

static __always_inline void
link_va_augment(struct vmap_area *va, struct rb_root *root,
	struct rb_node *parent, struct rb_node **link,
	struct list_head *head)
{
	__link_va(va, root, parent, link, head, true);
}

static __always_inline void
__unlink_va(struct vmap_area *va, struct rb_root *root, bool augment)
{
	if (WARN_ON(RB_EMPTY_NODE(&va->rb_node)))
		return;

	if (augment)
		rb_erase_augmented(&va->rb_node,
			root, &free_vmap_area_rb_augment_cb);
	else
		rb_erase(&va->rb_node, root);

	list_del_init(&va->list);
	RB_CLEAR_NODE(&va->rb_node);
}

static __always_inline void
unlink_va(struct vmap_area *va, struct rb_root *root)
{
	__unlink_va(va, root, false);
}

static __always_inline void
unlink_va_augment(struct vmap_area *va, struct rb_root *root)
{
	__unlink_va(va, root, true);
}

#if DEBUG_AUGMENT_PROPAGATE_CHECK
/*
 * Gets called when remove the node and rotate.
 */
static __always_inline unsigned long
compute_subtree_max_size(struct vmap_area *va)
{
	return max3(va_size(va),
		get_subtree_max_size(va->rb_node.rb_left),
		get_subtree_max_size(va->rb_node.rb_right));
}

static void
augment_tree_propagate_check(void)
{
	struct vmap_area *va;
	unsigned long computed_size;

	list_for_each_entry(va, &free_vmap_area_list, list) {
		computed_size = compute_subtree_max_size(va);
		if (computed_size != va->subtree_max_size)
			pr_emerg("tree is corrupted: %lu, %lu\n",
				va_size(va), va->subtree_max_size);
	}
}
#endif

/*
 * This function populates subtree_max_size from bottom to upper
 * levels starting from VA point. The propagation must be done
 * when VA size is modified by changing its va_start/va_end. Or
 * in case of newly inserting of VA to the tree.
 *
 * It means that __augment_tree_propagate_from() must be called:
 * - After VA has been inserted to the tree(free path);
 * - After VA has been shrunk(allocation path);
 * - After VA has been increased(merging path).
 *
 * Please note that, it does not mean that upper parent nodes
 * and their subtree_max_size are recalculated all the time up
 * to the root node.
 *
 *       4--8
 *        /\
 *       /  \
 *      /    \
 *    2--2  8--8
 *
 * For example if we modify the node 4, shrinking it to 2, then
 * no any modification is required. If we shrink the node 2 to 1
 * its subtree_max_size is updated only, and set to 1. If we shrink
 * the node 8 to 6, then its subtree_max_size is set to 6 and parent
 * node becomes 4--6.
 */
static __always_inline void
augment_tree_propagate_from(struct vmap_area *va)
{
	/*
	 * Populate the tree from bottom towards the root until
	 * the calculated maximum available size of checked node
	 * is equal to its current one.
	 */
	free_vmap_area_rb_augment_cb_propagate(&va->rb_node, NULL);

#if DEBUG_AUGMENT_PROPAGATE_CHECK
	augment_tree_propagate_check();
#endif
}

static void
insert_vmap_area(struct vmap_area *va,
	struct rb_root *root, struct list_head *head)
{
	struct rb_node **link;
	struct rb_node *parent;

	link = find_va_links(va, root, NULL, &parent);
	if (link)
		link_va(va, root, parent, link, head);
}

static void
insert_vmap_area_augment(struct vmap_area *va,
	struct rb_node *from, struct rb_root *root,
	struct list_head *head)
{
	struct rb_node **link;
	struct rb_node *parent;

	if (from)
		link = find_va_links(va, NULL, from, &parent);
	else
		link = find_va_links(va, root, NULL, &parent);

	if (link) {
		link_va_augment(va, root, parent, link, head);
		augment_tree_propagate_from(va);
	}
}

/*
 * Merge de-allocated chunk of VA memory with previous
 * and next free blocks. If coalesce is not done a new
 * free area is inserted. If VA has been merged, it is
 * freed.
 *
 * Please note, it can return NULL in case of overlap
 * ranges, followed by WARN() report. Despite it is a
 * buggy behaviour, a system can be alive and keep
 * ongoing.
 */
static __always_inline struct vmap_area *
__merge_or_add_vmap_area(struct vmap_area *va,
	struct rb_root *root, struct list_head *head, bool augment)
{
	struct vmap_area *sibling;
	struct list_head *next;
	struct rb_node **link;
	struct rb_node *parent;
	bool merged = false;

	/*
	 * Find a place in the tree where VA potentially will be
	 * inserted, unless it is merged with its sibling/siblings.
	 */
	link = find_va_links(va, root, NULL, &parent);
	if (!link)
		return NULL;

	/*
	 * Get next node of VA to check if merging can be done.
	 */
	next = get_va_next_sibling(parent, link);
	if (unlikely(next == NULL))
		goto insert;

	/*
	 * start            end
	 * |                |
	 * |<------VA------>|<-----Next----->|
	 *                  |                |
	 *                  start            end
	 */
	if (next != head) {
		sibling = list_entry(next, struct vmap_area, list);
		if (sibling->va_start == va->va_end) {
			sibling->va_start = va->va_start;

			/* Free vmap_area object. */
			kmem_cache_free(vmap_area_cachep, va);

			/* Point to the new merged area. */
			va = sibling;
			merged = true;
		}
	}

	/*
	 * start            end
	 * |                |
	 * |<-----Prev----->|<------VA------>|
	 *                  |                |
	 *                  start            end
	 */
	if (next->prev != head) {
		sibling = list_entry(next->prev, struct vmap_area, list);
		if (sibling->va_end == va->va_start) {
			/*
			 * If both neighbors are coalesced, it is important
			 * to unlink the "next" node first, followed by merging
			 * with "previous" one. Otherwise the tree might not be
			 * fully populated if a sibling's augmented value is
			 * "normalized" because of rotation operations.
			 */
			if (merged)
				__unlink_va(va, root, augment);

			sibling->va_end = va->va_end;

			/* Free vmap_area object. */
			kmem_cache_free(vmap_area_cachep, va);

			/* Point to the new merged area. */
			va = sibling;
			merged = true;
		}
	}

insert:
	if (!merged)
		__link_va(va, root, parent, link, head, augment);

	return va;
}

static __always_inline struct vmap_area *
merge_or_add_vmap_area(struct vmap_area *va,
	struct rb_root *root, struct list_head *head)
{
	return __merge_or_add_vmap_area(va, root, head, false);
}

static __always_inline struct vmap_area *
merge_or_add_vmap_area_augment(struct vmap_area *va,
	struct rb_root *root, struct list_head *head)
{
	va = __merge_or_add_vmap_area(va, root, head, true);
	if (va)
		augment_tree_propagate_from(va);

	return va;
}

static __always_inline bool
is_within_this_va(struct vmap_area *va, unsigned long size,
	unsigned long align, unsigned long vstart)
{
	unsigned long nva_start_addr;

	if (va->va_start > vstart)
		nva_start_addr = ALIGN(va->va_start, align);
	else
		nva_start_addr = ALIGN(vstart, align);

	/* Can be overflowed due to big size or alignment. */
	if (nva_start_addr + size < nva_start_addr ||
			nva_start_addr < vstart)
		return false;

	return (nva_start_addr + size <= va->va_end);
}

/*
 * Find the first free block(lowest start address) in the tree,
 * that will accomplish the request corresponding to passing
 * parameters. Please note, with an alignment bigger than PAGE_SIZE,
 * a search length is adjusted to account for worst case alignment
 * overhead.
 */
static __always_inline struct vmap_area *
find_vmap_lowest_match(struct rb_root *root, unsigned long size,
	unsigned long align, unsigned long vstart, bool adjust_search_size)
{
	struct vmap_area *va;
	struct rb_node *node;
	unsigned long length;

	/* Start from the root. */
	node = root->rb_node;

	/* Adjust the search size for alignment overhead. */
	length = adjust_search_size ? size + align - 1 : size;

	while (node) {
		va = rb_entry(node, struct vmap_area, rb_node);

		if (get_subtree_max_size(node->rb_left) >= length &&
				vstart < va->va_start) {
			node = node->rb_left;
		} else {
			if (is_within_this_va(va, size, align, vstart))
				return va;

			/*
			 * Does not make sense to go deeper towards the right
			 * sub-tree if it does not have a free block that is
			 * equal or bigger to the requested search length.
			 */
			if (get_subtree_max_size(node->rb_right) >= length) {
				node = node->rb_right;
				continue;
			}

			/*
			 * OK. We roll back and find the first right sub-tree,
			 * that will satisfy the search criteria. It can happen
			 * due to "vstart" restriction or an alignment overhead
			 * that is bigger then PAGE_SIZE.
			 */
			while ((node = rb_parent(node))) {
				va = rb_entry(node, struct vmap_area, rb_node);
				if (is_within_this_va(va, size, align, vstart))
					return va;

				if (get_subtree_max_size(node->rb_right) >= length &&
						vstart <= va->va_start) {
					/*
					 * Shift the vstart forward. Please note, we update it with
					 * parent's start address adding "1" because we do not want
					 * to enter same sub-tree after it has already been checked
					 * and no suitable free block found there.
					 */
					vstart = va->va_start + 1;
					node = node->rb_right;
					break;
				}
			}
		}
	}

	return NULL;
}

#if DEBUG_AUGMENT_LOWEST_MATCH_CHECK
#include <linux/random.h>

static struct vmap_area *
find_vmap_lowest_linear_match(struct list_head *head, unsigned long size,
	unsigned long align, unsigned long vstart)
{
	struct vmap_area *va;

	list_for_each_entry(va, head, list) {
		if (!is_within_this_va(va, size, align, vstart))
			continue;

		return va;
	}

	return NULL;
}

static void
find_vmap_lowest_match_check(struct rb_root *root, struct list_head *head,
			     unsigned long size, unsigned long align)
{
	struct vmap_area *va_1, *va_2;
	unsigned long vstart;
	unsigned int rnd;

	get_random_bytes(&rnd, sizeof(rnd));
	vstart = VMALLOC_START + rnd;

	va_1 = find_vmap_lowest_match(root, size, align, vstart, false);
	va_2 = find_vmap_lowest_linear_match(head, size, align, vstart);

	if (va_1 != va_2)
		pr_emerg("not lowest: t: 0x%p, l: 0x%p, v: 0x%lx\n",
			va_1, va_2, vstart);
}
#endif

enum fit_type {
	NOTHING_FIT = 0,
	FL_FIT_TYPE = 1,	/* full fit */
	LE_FIT_TYPE = 2,	/* left edge fit */
	RE_FIT_TYPE = 3,	/* right edge fit */
	NE_FIT_TYPE = 4		/* no edge fit */
};

static __always_inline enum fit_type
classify_va_fit_type(struct vmap_area *va,
	unsigned long nva_start_addr, unsigned long size)
{
	enum fit_type type;

	/* Check if it is within VA. */
	if (nva_start_addr < va->va_start ||
			nva_start_addr + size > va->va_end)
		return NOTHING_FIT;

	/* Now classify. */
	if (va->va_start == nva_start_addr) {
		if (va->va_end == nva_start_addr + size)
			type = FL_FIT_TYPE;
		else
			type = LE_FIT_TYPE;
	} else if (va->va_end == nva_start_addr + size) {
		type = RE_FIT_TYPE;
	} else {
		type = NE_FIT_TYPE;
	}

	return type;
}

static __always_inline int
va_clip(struct rb_root *root, struct list_head *head,
		struct vmap_area *va, unsigned long nva_start_addr,
		unsigned long size)
{
	struct vmap_area *lva = NULL;
	enum fit_type type = classify_va_fit_type(va, nva_start_addr, size);

	if (type == FL_FIT_TYPE) {
		/*
		 * No need to split VA, it fully fits.
		 *
		 * |               |
		 * V      NVA      V
		 * |---------------|
		 */
		unlink_va_augment(va, root);
		kmem_cache_free(vmap_area_cachep, va);
	} else if (type == LE_FIT_TYPE) {
		/*
		 * Split left edge of fit VA.
		 *
		 * |       |
		 * V  NVA  V   R
		 * |-------|-------|
		 */
		va->va_start += size;
	} else if (type == RE_FIT_TYPE) {
		/*
		 * Split right edge of fit VA.
		 *
		 *         |       |
		 *     L   V  NVA  V
		 * |-------|-------|
		 */
		va->va_end = nva_start_addr;
	} else if (type == NE_FIT_TYPE) {
		/*
		 * Split no edge of fit VA.
		 *
		 *     |       |
		 *   L V  NVA  V R
		 * |---|-------|---|
		 */
		lva = __this_cpu_xchg(ne_fit_preload_node, NULL);
		if (unlikely(!lva)) {
			/*
			 * For percpu allocator we do not do any pre-allocation
			 * and leave it as it is. The reason is it most likely
			 * never ends up with NE_FIT_TYPE splitting. In case of
			 * percpu allocations offsets and sizes are aligned to
			 * fixed align request, i.e. RE_FIT_TYPE and FL_FIT_TYPE
			 * are its main fitting cases.
			 *
			 * There are a few exceptions though, as an example it is
			 * a first allocation (early boot up) when we have "one"
			 * big free space that has to be split.
			 *
			 * Also we can hit this path in case of regular "vmap"
			 * allocations, if "this" current CPU was not preloaded.
			 * See the comment in alloc_vmap_area() why. If so, then
			 * GFP_NOWAIT is used instead to get an extra object for
			 * split purpose. That is rare and most time does not
			 * occur.
			 *
			 * What happens if an allocation gets failed. Basically,
			 * an "overflow" path is triggered to purge lazily freed
			 * areas to free some memory, then, the "retry" path is
			 * triggered to repeat one more time. See more details
			 * in alloc_vmap_area() function.
			 */
			lva = kmem_cache_alloc(vmap_area_cachep, GFP_NOWAIT);
			if (!lva)
				return -ENOMEM;
		}

		/*
		 * Build the remainder.
		 */
		lva->va_start = va->va_start;
		lva->va_end = nva_start_addr;

		/*
		 * Shrink this VA to remaining size.
		 */
		va->va_start = nva_start_addr + size;
	} else {
		return -EINVAL;
	}

	if (type != FL_FIT_TYPE) {
		augment_tree_propagate_from(va);

		if (lva)	/* type == NE_FIT_TYPE */
			insert_vmap_area_augment(lva, &va->rb_node, root, head);
	}

	return 0;
}

static unsigned long
va_alloc(struct vmap_area *va,
		struct rb_root *root, struct list_head *head,
		unsigned long size, unsigned long align,
		unsigned long vstart, unsigned long vend)
{
	unsigned long nva_start_addr;
	int ret;

	if (va->va_start > vstart)
		nva_start_addr = ALIGN(va->va_start, align);
	else
		nva_start_addr = ALIGN(vstart, align);

	/* Check the "vend" restriction. */
	if (nva_start_addr + size > vend)
		return -ERANGE;

	/* Update the free vmap_area. */
	ret = va_clip(root, head, va, nva_start_addr, size);
	if (WARN_ON_ONCE(ret))
		return ret;

	return nva_start_addr;
}

/*
 * Returns a start address of the newly allocated area, if success.
 * Otherwise an error value is returned that indicates failure.
 */
static __always_inline unsigned long
__alloc_vmap_area(struct rb_root *root, struct list_head *head,
	unsigned long size, unsigned long align,
	unsigned long vstart, unsigned long vend)
{
	bool adjust_search_size = true;
	unsigned long nva_start_addr;
	struct vmap_area *va;

	/*
	 * Do not adjust when:
	 *   a) align <= PAGE_SIZE, because it does not make any sense.
	 *      All blocks(their start addresses) are at least PAGE_SIZE
	 *      aligned anyway;
	 *   b) a short range where a requested size corresponds to exactly
	 *      specified [vstart:vend] interval and an alignment > PAGE_SIZE.
	 *      With adjusted search length an allocation would not succeed.
	 */
	if (align <= PAGE_SIZE || (align > PAGE_SIZE && (vend - vstart) == size))
		adjust_search_size = false;

	va = find_vmap_lowest_match(root, size, align, vstart, adjust_search_size);
	if (unlikely(!va))
		return -ENOENT;

	nva_start_addr = va_alloc(va, root, head, size, align, vstart, vend);

#if DEBUG_AUGMENT_LOWEST_MATCH_CHECK
	if (!IS_ERR_VALUE(nva_start_addr))
		find_vmap_lowest_match_check(root, head, size, align);
#endif

	return nva_start_addr;
}

/*
 * Free a region of KVA allocated by alloc_vmap_area
 */
static void free_vmap_area(struct vmap_area *va)
{
	struct vmap_node *vn = addr_to_node(va->va_start);

	/*
	 * Remove from the busy tree/list.
	 */
	spin_lock(&vn->busy.lock);
	unlink_va(va, &vn->busy.root);
	spin_unlock(&vn->busy.lock);

	/*
	 * Insert/Merge it back to the free tree/list.
	 */
	spin_lock(&free_vmap_area_lock);
	merge_or_add_vmap_area_augment(va, &free_vmap_area_root, &free_vmap_area_list);
	spin_unlock(&free_vmap_area_lock);
}

static inline void
preload_this_cpu_lock(spinlock_t *lock, gfp_t gfp_mask, int node)
{
	struct vmap_area *va = NULL, *tmp;

	/*
	 * Preload this CPU with one extra vmap_area object. It is used
	 * when fit type of free area is NE_FIT_TYPE. It guarantees that
	 * a CPU that does an allocation is preloaded.
	 *
	 * We do it in non-atomic context, thus it allows us to use more
	 * permissive allocation masks to be more stable under low memory
	 * condition and high memory pressure.
	 */
	if (!this_cpu_read(ne_fit_preload_node))
		va = kmem_cache_alloc_node(vmap_area_cachep, gfp_mask, node);

	spin_lock(lock);

	tmp = NULL;
	if (va && !__this_cpu_try_cmpxchg(ne_fit_preload_node, &tmp, va))
		kmem_cache_free(vmap_area_cachep, va);
}

static struct vmap_pool *
size_to_va_pool(struct vmap_node *vn, unsigned long size)
{
	unsigned int idx = (size - 1) / PAGE_SIZE;

	if (idx < MAX_VA_SIZE_PAGES)
		return &vn->pool[idx];

	return NULL;
}

static bool
node_pool_add_va(struct vmap_node *n, struct vmap_area *va)
{
	struct vmap_pool *vp;

	vp = size_to_va_pool(n, va_size(va));
	if (!vp)
		return false;

	spin_lock(&n->pool_lock);
	list_add(&va->list, &vp->head);
	WRITE_ONCE(vp->len, vp->len + 1);
	spin_unlock(&n->pool_lock);

	return true;
}

static struct vmap_area *
node_pool_del_va(struct vmap_node *vn, unsigned long size,
		unsigned long align, unsigned long vstart,
		unsigned long vend)
{
	struct vmap_area *va = NULL;
	struct vmap_pool *vp;
	int err = 0;

	vp = size_to_va_pool(vn, size);
	if (!vp || list_empty(&vp->head))
		return NULL;

	spin_lock(&vn->pool_lock);
	if (!list_empty(&vp->head)) {
		va = list_first_entry(&vp->head, struct vmap_area, list);

		if (IS_ALIGNED(va->va_start, align)) {
			/*
			 * Do some sanity check and emit a warning
			 * if one of below checks detects an error.
			 */
			err |= (va_size(va) != size);
			err |= (va->va_start < vstart);
			err |= (va->va_end > vend);

			if (!WARN_ON_ONCE(err)) {
				list_del_init(&va->list);
				WRITE_ONCE(vp->len, vp->len - 1);
			} else {
				va = NULL;
			}
		} else {
			list_move_tail(&va->list, &vp->head);
			va = NULL;
		}
	}
	spin_unlock(&vn->pool_lock);

	return va;
}

static struct vmap_area *
node_alloc(unsigned long size, unsigned long align,
		unsigned long vstart, unsigned long vend,
		unsigned long *addr, unsigned int *vn_id)
{
	struct vmap_area *va;

	*vn_id = 0;
	*addr = -EINVAL;

	/*
	 * Fallback to a global heap if not vmalloc or there
	 * is only one node.
	 */
	if (vstart != VMALLOC_START || vend != VMALLOC_END ||
			nr_vmap_nodes == 1)
		return NULL;

	*vn_id = raw_smp_processor_id() % nr_vmap_nodes;
	va = node_pool_del_va(id_to_node(*vn_id), size, align, vstart, vend);
	*vn_id = encode_vn_id(*vn_id);

	if (va)
		*addr = va->va_start;

	return va;
}

static inline void setup_vmalloc_vm(struct vm_struct *vm,
	struct vmap_area *va, unsigned long flags, const void *caller)
{
	vm->flags = flags;
	vm->addr = (void *)va->va_start;
	vm->size = vm->requested_size = va_size(va);
	vm->caller = caller;
	va->vm = vm;
}

/*
 * Allocate a region of KVA of the specified size and alignment, within the
 * vstart and vend. If vm is passed in, the two will also be bound.
 */
static struct vmap_area *alloc_vmap_area(unsigned long size,
				unsigned long align,
				unsigned long vstart, unsigned long vend,
				int node, gfp_t gfp_mask,
				unsigned long va_flags, struct vm_struct *vm)
{
	struct vmap_node *vn;
	struct vmap_area *va;
	unsigned long freed;
	unsigned long addr;
	unsigned int vn_id;
	bool allow_block;
	int purged = 0;
	int ret;

	if (unlikely(!size || offset_in_page(size) || !is_power_of_2(align)))
		return ERR_PTR(-EINVAL);

	if (unlikely(!vmap_initialized))
		return ERR_PTR(-EBUSY);

	/* Only reclaim behaviour flags are relevant. */
	gfp_mask = gfp_mask & GFP_RECLAIM_MASK;
	allow_block = gfpflags_allow_blocking(gfp_mask);
	might_sleep_if(allow_block);

	/*
	 * If a VA is obtained from a global heap(if it fails here)
	 * it is anyway marked with this "vn_id" so it is returned
	 * to this pool's node later. Such way gives a possibility
	 * to populate pools based on users demand.
	 *
	 * On success a ready to go VA is returned.
	 */
	va = node_alloc(size, align, vstart, vend, &addr, &vn_id);
	if (!va) {
		va = kmem_cache_alloc_node(vmap_area_cachep, gfp_mask, node);
		if (unlikely(!va))
			return ERR_PTR(-ENOMEM);

		/*
		 * Only scan the relevant parts containing pointers to other objects
		 * to avoid false negatives.
		 */
		kmemleak_scan_area(&va->rb_node, SIZE_MAX, gfp_mask);
	}

retry:
	if (IS_ERR_VALUE(addr)) {
		preload_this_cpu_lock(&free_vmap_area_lock, gfp_mask, node);
		addr = __alloc_vmap_area(&free_vmap_area_root, &free_vmap_area_list,
			size, align, vstart, vend);
		spin_unlock(&free_vmap_area_lock);

		/*
		 * This is not a fast path.  Check if yielding is needed. This
		 * is the only reschedule point in the vmalloc() path.
		 */
		if (allow_block)
			cond_resched();
	}

	trace_alloc_vmap_area(addr, size, align, vstart, vend, IS_ERR_VALUE(addr));

	/*
	 * If an allocation fails, the error value is
	 * returned. Therefore trigger the overflow path.
	 */
	if (IS_ERR_VALUE(addr)) {
		if (allow_block)
			goto overflow;

		/*
		 * We can not trigger any reclaim logic because
		 * sleeping is not allowed, thus fail an allocation.
		 */
		goto out_free_va;
	}

	va->va_start = addr;
	va->va_end = addr + size;
	va->vm = NULL;
	va->flags = (va_flags | vn_id);

	if (vm) {
		vm->addr = (void *)va->va_start;
		vm->size = va_size(va);
		va->vm = vm;
	}

	vn = addr_to_node(va->va_start);

	spin_lock(&vn->busy.lock);
	insert_vmap_area(va, &vn->busy.root, &vn->busy.head);
	spin_unlock(&vn->busy.lock);

	BUG_ON(!IS_ALIGNED(va->va_start, align));
	BUG_ON(va->va_start < vstart);
	BUG_ON(va->va_end > vend);

	ret = kasan_populate_vmalloc(addr, size, gfp_mask);
	if (ret) {
		free_vmap_area(va);
		return ERR_PTR(ret);
	}

	return va;

overflow:
	if (!purged) {
		reclaim_and_purge_vmap_areas();
		purged = 1;
		goto retry;
	}

	freed = 0;
	blocking_notifier_call_chain(&vmap_notify_list, 0, &freed);

	if (freed > 0) {
		purged = 0;
		goto retry;
	}

	if (!(gfp_mask & __GFP_NOWARN) && printk_ratelimit())
		pr_warn("vmalloc_node_range for size %lu failed: Address range restricted to %#lx - %#lx\n",
				size, vstart, vend);

out_free_va:
	kmem_cache_free(vmap_area_cachep, va);
	return ERR_PTR(-EBUSY);
}

int register_vmap_purge_notifier(struct notifier_block *nb)
{
	return blocking_notifier_chain_register(&vmap_notify_list, nb);
}
EXPORT_SYMBOL_GPL(register_vmap_purge_notifier);

int unregister_vmap_purge_notifier(struct notifier_block *nb)
{
	return blocking_notifier_chain_unregister(&vmap_notify_list, nb);
}
EXPORT_SYMBOL_GPL(unregister_vmap_purge_notifier);

/*
 * lazy_max_pages is the maximum amount of virtual address space we gather up
 * before attempting to purge with a TLB flush.
 *
 * There is a tradeoff here: a larger number will cover more kernel page tables
 * and take slightly longer to purge, but it will linearly reduce the number of
 * global TLB flushes that must be performed. It would seem natural to scale
 * this number up linearly with the number of CPUs (because vmapping activity
 * could also scale linearly with the number of CPUs), however it is likely
 * that in practice, workloads might be constrained in other ways that mean
 * vmap activity will not scale linearly with CPUs. Also, I want to be
 * conservative and not introduce a big latency on huge systems, so go with
 * a less aggressive log scale. It will still be an improvement over the old
 * code, and it will be simple to change the scale factor if we find that it
 * becomes a problem on bigger systems.
 */
static unsigned long lazy_max_pages(void)
{
	unsigned int log;

	log = fls(num_online_cpus());

	return log * (32UL * 1024 * 1024 / PAGE_SIZE);
}

/*
 * Serialize vmap purging.  There is no actual critical section protected
 * by this lock, but we want to avoid concurrent calls for performance
 * reasons and to make the pcpu_get_vm_areas more deterministic.
 */
static DEFINE_MUTEX(vmap_purge_lock);

/* for per-CPU blocks */
static void purge_fragmented_blocks_allcpus(void);

static void
reclaim_list_global(struct list_head *head)
{
	struct vmap_area *va, *n;

	if (list_empty(head))
		return;

	spin_lock(&free_vmap_area_lock);
	list_for_each_entry_safe(va, n, head, list)
		merge_or_add_vmap_area_augment(va,
			&free_vmap_area_root, &free_vmap_area_list);
	spin_unlock(&free_vmap_area_lock);
}

static void
decay_va_pool_node(struct vmap_node *vn, bool full_decay)
{
	LIST_HEAD(decay_list);
	struct rb_root decay_root = RB_ROOT;
	struct vmap_area *va, *nva;
	unsigned long n_decay, pool_len;
	int i;

	for (i = 0; i < MAX_VA_SIZE_PAGES; i++) {
		LIST_HEAD(tmp_list);

		if (list_empty(&vn->pool[i].head))
			continue;

		/* Detach the pool, so no-one can access it. */
		spin_lock(&vn->pool_lock);
		list_replace_init(&vn->pool[i].head, &tmp_list);
		spin_unlock(&vn->pool_lock);

		pool_len = n_decay = vn->pool[i].len;
		WRITE_ONCE(vn->pool[i].len, 0);

		/* Decay a pool by ~25% out of left objects. */
		if (!full_decay)
			n_decay >>= 2;
		pool_len -= n_decay;

		list_for_each_entry_safe(va, nva, &tmp_list, list) {
			if (!n_decay--)
				break;

			list_del_init(&va->list);
			merge_or_add_vmap_area(va, &decay_root, &decay_list);
		}

		/*
		 * Attach the pool back if it has been partly decayed.
		 * Please note, it is supposed that nobody(other contexts)
		 * can populate the pool therefore a simple list replace
		 * operation takes place here.
		 */
		if (!list_empty(&tmp_list)) {
			spin_lock(&vn->pool_lock);
			list_replace_init(&tmp_list, &vn->pool[i].head);
			WRITE_ONCE(vn->pool[i].len, pool_len);
			spin_unlock(&vn->pool_lock);
		}
	}

	reclaim_list_global(&decay_list);
}

#define KASAN_RELEASE_BATCH_SIZE 32

static void
kasan_release_vmalloc_node(struct vmap_node *vn)
{
	struct vmap_area *va;
	unsigned long start, end;
	unsigned int batch_count = 0;

	start = list_first_entry(&vn->purge_list, struct vmap_area, list)->va_start;
	end = list_last_entry(&vn->purge_list, struct vmap_area, list)->va_end;

	list_for_each_entry(va, &vn->purge_list, list) {
		if (is_vmalloc_or_module_addr((void *) va->va_start))
			kasan_release_vmalloc(va->va_start, va->va_end,
				va->va_start, va->va_end,
				KASAN_VMALLOC_PAGE_RANGE);

		if (need_resched() || (++batch_count >= KASAN_RELEASE_BATCH_SIZE)) {
			cond_resched();
			batch_count = 0;
		}
	}

	kasan_release_vmalloc(start, end, start, end, KASAN_VMALLOC_TLB_FLUSH);
}

static void purge_vmap_node(struct work_struct *work)
{
	struct vmap_node *vn = container_of(work,
		struct vmap_node, purge_work);
	unsigned long nr_purged_pages = 0;
	struct vmap_area *va, *n_va;
	LIST_HEAD(local_list);

	if (IS_ENABLED(CONFIG_KASAN_VMALLOC))
		kasan_release_vmalloc_node(vn);

	vn->nr_purged = 0;

	list_for_each_entry_safe(va, n_va, &vn->purge_list, list) {
		unsigned long nr = va_size(va) >> PAGE_SHIFT;
		unsigned int vn_id = decode_vn_id(va->flags);

		list_del_init(&va->list);

		nr_purged_pages += nr;
		vn->nr_purged++;

		if (is_vn_id_valid(vn_id) && !vn->skip_populate)
			if (node_pool_add_va(vn, va))
				continue;

		/* Go back to global. */
		list_add(&va->list, &local_list);
	}

	atomic_long_sub(nr_purged_pages, &vmap_lazy_nr);

	reclaim_list_global(&local_list);
}

/*
 * Purges all lazily-freed vmap areas.
 */
static bool __purge_vmap_area_lazy(unsigned long start, unsigned long end,
		bool full_pool_decay)
{
	unsigned long nr_purged_areas = 0;
	unsigned int nr_purge_helpers;
	static cpumask_t purge_nodes;
	unsigned int nr_purge_nodes;
	struct vmap_node *vn;
	int i;

	lockdep_assert_held(&vmap_purge_lock);

	/*
	 * Use cpumask to mark which node has to be processed.
	 */
	purge_nodes = CPU_MASK_NONE;

	for_each_vmap_node(vn) {
		INIT_LIST_HEAD(&vn->purge_list);
		vn->skip_populate = full_pool_decay;
		decay_va_pool_node(vn, full_pool_decay);

		if (RB_EMPTY_ROOT(&vn->lazy.root))
			continue;

		spin_lock(&vn->lazy.lock);
		WRITE_ONCE(vn->lazy.root.rb_node, NULL);
		list_replace_init(&vn->lazy.head, &vn->purge_list);
		spin_unlock(&vn->lazy.lock);

		start = min(start, list_first_entry(&vn->purge_list,
			struct vmap_area, list)->va_start);

		end = max(end, list_last_entry(&vn->purge_list,
			struct vmap_area, list)->va_end);

		cpumask_set_cpu(node_to_id(vn), &purge_nodes);
	}

	nr_purge_nodes = cpumask_weight(&purge_nodes);
	if (nr_purge_nodes > 0) {
		flush_tlb_kernel_range(start, end);

		/* One extra worker is per a lazy_max_pages() full set minus one. */
		nr_purge_helpers = atomic_long_read(&vmap_lazy_nr) / lazy_max_pages();
		nr_purge_helpers = clamp(nr_purge_helpers, 1U, nr_purge_nodes) - 1;

		for_each_cpu(i, &purge_nodes) {
			vn = &vmap_nodes[i];

			if (nr_purge_helpers > 0) {
				INIT_WORK(&vn->purge_work, purge_vmap_node);

				if (cpumask_test_cpu(i, cpu_online_mask))
					schedule_work_on(i, &vn->purge_work);
				else
					schedule_work(&vn->purge_work);

				nr_purge_helpers--;
			} else {
				vn->purge_work.func = NULL;
				purge_vmap_node(&vn->purge_work);
				nr_purged_areas += vn->nr_purged;
			}
		}

		for_each_cpu(i, &purge_nodes) {
			vn = &vmap_nodes[i];

			if (vn->purge_work.func) {
				flush_work(&vn->purge_work);
				nr_purged_areas += vn->nr_purged;
			}
		}
	}

	trace_purge_vmap_area_lazy(start, end, nr_purged_areas);
	return nr_purged_areas > 0;
}

/*
 * Reclaim vmap areas by purging fragmented blocks and purge_vmap_area_list.
 */
static void reclaim_and_purge_vmap_areas(void)

{
	mutex_lock(&vmap_purge_lock);
	purge_fragmented_blocks_allcpus();
	__purge_vmap_area_lazy(ULONG_MAX, 0, true);
	mutex_unlock(&vmap_purge_lock);
}

static void drain_vmap_area_work(struct work_struct *work)
{
	mutex_lock(&vmap_purge_lock);
	__purge_vmap_area_lazy(ULONG_MAX, 0, false);
	mutex_unlock(&vmap_purge_lock);
}

/*
 * Free a vmap area, caller ensuring that the area has been unmapped,
 * unlinked and flush_cache_vunmap had been called for the correct
 * range previously.
 */
static void free_vmap_area_noflush(struct vmap_area *va)
{
	unsigned long nr_lazy_max = lazy_max_pages();
	unsigned long va_start = va->va_start;
	unsigned int vn_id = decode_vn_id(va->flags);
	struct vmap_node *vn;
	unsigned long nr_lazy;

	if (WARN_ON_ONCE(!list_empty(&va->list)))
		return;

	nr_lazy = atomic_long_add_return_relaxed(va_size(va) >> PAGE_SHIFT,
					 &vmap_lazy_nr);

	/*
	 * If it was request by a certain node we would like to
	 * return it to that node, i.e. its pool for later reuse.
	 */
	vn = is_vn_id_valid(vn_id) ?
		id_to_node(vn_id):addr_to_node(va->va_start);

	spin_lock(&vn->lazy.lock);
	insert_vmap_area(va, &vn->lazy.root, &vn->lazy.head);
	spin_unlock(&vn->lazy.lock);

	trace_free_vmap_area_noflush(va_start, nr_lazy, nr_lazy_max);

	/* After this point, we may free va at any time */
	if (unlikely(nr_lazy > nr_lazy_max))
		schedule_work(&drain_vmap_work);
}

/*
 * Free and unmap a vmap area
 */
static void free_unmap_vmap_area(struct vmap_area *va)
{
	flush_cache_vunmap(va->va_start, va->va_end);
	vunmap_range_noflush(va->va_start, va->va_end);
	if (debug_pagealloc_enabled_static())
		flush_tlb_kernel_range(va->va_start, va->va_end);

	free_vmap_area_noflush(va);
}

struct vmap_area *find_vmap_area(unsigned long addr)
{
	struct vmap_node *vn;
	struct vmap_area *va;
	int i, j;

	if (unlikely(!vmap_initialized))
		return NULL;

	/*
	 * An addr_to_node_id(addr) converts an address to a node index
	 * where a VA is located. If VA spans several zones and passed
	 * addr is not the same as va->va_start, what is not common, we
	 * may need to scan extra nodes. See an example:
	 *
	 *      <----va---->
	 * -|-----|-----|-----|-----|-
	 *     1     2     0     1
	 *
	 * VA resides in node 1 whereas it spans 1, 2 an 0. If passed
	 * addr is within 2 or 0 nodes we should do extra work.
	 */
	i = j = addr_to_node_id(addr);
	do {
		vn = &vmap_nodes[i];

		spin_lock(&vn->busy.lock);
		va = __find_vmap_area(addr, &vn->busy.root);
		spin_unlock(&vn->busy.lock);

		if (va)
			return va;
	} while ((i = (i + nr_vmap_nodes - 1) % nr_vmap_nodes) != j);

	return NULL;
}

static struct vmap_area *find_unlink_vmap_area(unsigned long addr)
{
	struct vmap_node *vn;
	struct vmap_area *va;
	int i, j;

	/*
	 * Check the comment in the find_vmap_area() about the loop.
	 */
	i = j = addr_to_node_id(addr);
	do {
		vn = &vmap_nodes[i];

		spin_lock(&vn->busy.lock);
		va = __find_vmap_area(addr, &vn->busy.root);
		if (va)
			unlink_va(va, &vn->busy.root);
		spin_unlock(&vn->busy.lock);

		if (va)
			return va;
	} while ((i = (i + nr_vmap_nodes - 1) % nr_vmap_nodes) != j);

	return NULL;
}

/*** Per cpu kva allocator ***/

/*
 * vmap space is limited especially on 32 bit architectures. Ensure there is
 * room for at least 16 percpu vmap blocks per CPU.
 */
/*
 * If we had a constant VMALLOC_START and VMALLOC_END, we'd like to be able
 * to #define VMALLOC_SPACE		(VMALLOC_END-VMALLOC_START). Guess
 * instead (we just need a rough idea)
 */
#if BITS_PER_LONG == 32
#define VMALLOC_SPACE		(128UL*1024*1024)
#else
#define VMALLOC_SPACE		(128UL*1024*1024*1024)
#endif

#define VMALLOC_PAGES		(VMALLOC_SPACE / PAGE_SIZE)
#define VMAP_MAX_ALLOC		BITS_PER_LONG	/* 256K with 4K pages */
#define VMAP_BBMAP_BITS_MAX	1024	/* 4MB with 4K pages */
#define VMAP_BBMAP_BITS_MIN	(VMAP_MAX_ALLOC*2)
#define VMAP_MIN(x, y)		((x) < (y) ? (x) : (y)) /* can't use min() */
#define VMAP_MAX(x, y)		((x) > (y) ? (x) : (y)) /* can't use max() */
#define VMAP_BBMAP_BITS		\
		VMAP_MIN(VMAP_BBMAP_BITS_MAX,	\
		VMAP_MAX(VMAP_BBMAP_BITS_MIN,	\
			VMALLOC_PAGES / roundup_pow_of_two(NR_CPUS) / 16))

#define VMAP_BLOCK_SIZE		(VMAP_BBMAP_BITS * PAGE_SIZE)

/*
 * Purge threshold to prevent overeager purging of fragmented blocks for
 * regular operations: Purge if vb->free is less than 1/4 of the capacity.
 */
#define VMAP_PURGE_THRESHOLD	(VMAP_BBMAP_BITS / 4)

#define VMAP_RAM		0x1 /* indicates vm_map_ram area*/
#define VMAP_BLOCK		0x2 /* mark out the vmap_block sub-type*/
#define VMAP_FLAGS_MASK		0x3

struct vmap_block_queue {
	spinlock_t lock;
	struct list_head free;

	/*
	 * An xarray requires an extra memory dynamically to
	 * be allocated. If it is an issue, we can use rb-tree
	 * instead.
	 */
	struct xarray vmap_blocks;
};

struct vmap_block {
	spinlock_t lock;
	struct vmap_area *va;
	unsigned long free, dirty;
	DECLARE_BITMAP(used_map, VMAP_BBMAP_BITS);
	unsigned long dirty_min, dirty_max; /*< dirty range */
	struct list_head free_list;
	struct rcu_head rcu_head;
	struct list_head purge;
	unsigned int cpu;
};

/* Queue of free and dirty vmap blocks, for allocation and flushing purposes */
static DEFINE_PER_CPU(struct vmap_block_queue, vmap_block_queue);

/*
 * In order to fast access to any "vmap_block" associated with a
 * specific address, we use a hash.
 *
 * A per-cpu vmap_block_queue is used in both ways, to serialize
 * an access to free block chains among CPUs(alloc path) and it
 * also acts as a vmap_block hash(alloc/free paths). It means we
 * overload it, since we already have the per-cpu array which is
 * used as a hash table. When used as a hash a 'cpu' passed to
 * per_cpu() is not actually a CPU but rather a hash index.
 *
 * A hash function is addr_to_vb_xa() which hashes any address
 * to a specific index(in a hash) it belongs to. This then uses a
 * per_cpu() macro to access an array with generated index.
 *
 * An example:
 *
 *  CPU_1  CPU_2  CPU_0
 *    |      |      |
 *    V      V      V
 * 0     10     20     30     40     50     60
 * |------|------|------|------|------|------|...<vmap address space>
 *   CPU0   CPU1   CPU2   CPU0   CPU1   CPU2
 *
 * - CPU_1 invokes vm_unmap_ram(6), 6 belongs to CPU0 zone, thus
 *   it access: CPU0/INDEX0 -> vmap_blocks -> xa_lock;
 *
 * - CPU_2 invokes vm_unmap_ram(11), 11 belongs to CPU1 zone, thus
 *   it access: CPU1/INDEX1 -> vmap_blocks -> xa_lock;
 *
 * - CPU_0 invokes vm_unmap_ram(20), 20 belongs to CPU2 zone, thus
 *   it access: CPU2/INDEX2 -> vmap_blocks -> xa_lock.
 *
 * This technique almost always avoids lock contention on insert/remove,
 * however xarray spinlocks protect against any contention that remains.
 */
static struct xarray *
addr_to_vb_xa(unsigned long addr)
{
	int index = (addr / VMAP_BLOCK_SIZE) % nr_cpu_ids;

	/*
	 * Please note, nr_cpu_ids points on a highest set
	 * possible bit, i.e. we never invoke cpumask_next()
	 * if an index points on it which is nr_cpu_ids - 1.
	 */
	if (!cpu_possible(index))
		index = cpumask_next(index, cpu_possible_mask);

	return &per_cpu(vmap_block_queue, index).vmap_blocks;
}

/*
 * We should probably have a fallback mechanism to allocate virtual memory
 * out of partially filled vmap blocks. However vmap block sizing should be
 * fairly reasonable according to the vmalloc size, so it shouldn't be a
 * big problem.
 */

static unsigned long addr_to_vb_idx(unsigned long addr)
{
	addr -= VMALLOC_START & ~(VMAP_BLOCK_SIZE-1);
	addr /= VMAP_BLOCK_SIZE;
	return addr;
}

static void *vmap_block_vaddr(unsigned long va_start, unsigned long pages_off)
{
	unsigned long addr;

	addr = va_start + (pages_off << PAGE_SHIFT);
	BUG_ON(addr_to_vb_idx(addr) != addr_to_vb_idx(va_start));
	return (void *)addr;
}

/**
 * new_vmap_block - allocates new vmap_block and occupies 2^order pages in this
 *                  block. Of course pages number can't exceed VMAP_BBMAP_BITS
 * @order:    how many 2^order pages should be occupied in newly allocated block
 * @gfp_mask: flags for the page level allocator
 *
 * Return: virtual address in a newly allocated block or ERR_PTR(-errno)
 */
static void *new_vmap_block(unsigned int order, gfp_t gfp_mask)
{
	struct vmap_block_queue *vbq;
	struct vmap_block *vb;
	struct vmap_area *va;
	struct xarray *xa;
	unsigned long vb_idx;
	int node, err;
	void *vaddr;

	node = numa_node_id();

	vb = kmalloc_node(sizeof(struct vmap_block), gfp_mask, node);
	if (unlikely(!vb))
		return ERR_PTR(-ENOMEM);

	va = alloc_vmap_area(VMAP_BLOCK_SIZE, VMAP_BLOCK_SIZE,
					VMALLOC_START, VMALLOC_END,
					node, gfp_mask,
					VMAP_RAM|VMAP_BLOCK, NULL);
	if (IS_ERR(va)) {
		kfree(vb);
		return ERR_CAST(va);
	}

	vaddr = vmap_block_vaddr(va->va_start, 0);
	spin_lock_init(&vb->lock);
	vb->va = va;
	/* At least something should be left free */
	BUG_ON(VMAP_BBMAP_BITS <= (1UL << order));
	bitmap_zero(vb->used_map, VMAP_BBMAP_BITS);
	vb->free = VMAP_BBMAP_BITS - (1UL << order);
	vb->dirty = 0;
	vb->dirty_min = VMAP_BBMAP_BITS;
	vb->dirty_max = 0;
	bitmap_set(vb->used_map, 0, (1UL << order));
	INIT_LIST_HEAD(&vb->free_list);
	vb->cpu = raw_smp_processor_id();

	xa = addr_to_vb_xa(va->va_start);
	vb_idx = addr_to_vb_idx(va->va_start);
	err = xa_insert(xa, vb_idx, vb, gfp_mask);
	if (err) {
		kfree(vb);
		free_vmap_area(va);
		return ERR_PTR(err);
	}
	/*
	 * list_add_tail_rcu could happened in another core
	 * rather than vb->cpu due to task migration, which
	 * is safe as list_add_tail_rcu will ensure the list's
	 * integrity together with list_for_each_rcu from read
	 * side.
	 */
	vbq = per_cpu_ptr(&vmap_block_queue, vb->cpu);
	spin_lock(&vbq->lock);
	list_add_tail_rcu(&vb->free_list, &vbq->free);
	spin_unlock(&vbq->lock);

	return vaddr;
}

static void free_vmap_block(struct vmap_block *vb)
{
	struct vmap_node *vn;
	struct vmap_block *tmp;
	struct xarray *xa;

	xa = addr_to_vb_xa(vb->va->va_start);
	tmp = xa_erase(xa, addr_to_vb_idx(vb->va->va_start));
	BUG_ON(tmp != vb);

	vn = addr_to_node(vb->va->va_start);
	spin_lock(&vn->busy.lock);
	unlink_va(vb->va, &vn->busy.root);
	spin_unlock(&vn->busy.lock);

	free_vmap_area_noflush(vb->va);
	kfree_rcu(vb, rcu_head);
}

static bool purge_fragmented_block(struct vmap_block *vb,
		struct list_head *purge_list, bool force_purge)
{
	struct vmap_block_queue *vbq = &per_cpu(vmap_block_queue, vb->cpu);

	if (vb->free + vb->dirty != VMAP_BBMAP_BITS ||
	    vb->dirty == VMAP_BBMAP_BITS)
		return false;

	/* Don't overeagerly purge usable blocks unless requested */
	if (!(force_purge || vb->free < VMAP_PURGE_THRESHOLD))
		return false;

	/* prevent further allocs after releasing lock */
	WRITE_ONCE(vb->free, 0);
	/* prevent purging it again */
	WRITE_ONCE(vb->dirty, VMAP_BBMAP_BITS);
	vb->dirty_min = 0;
	vb->dirty_max = VMAP_BBMAP_BITS;
	spin_lock(&vbq->lock);
	list_del_rcu(&vb->free_list);
	spin_unlock(&vbq->lock);
	list_add_tail(&vb->purge, purge_list);
	return true;
}

static void free_purged_blocks(struct list_head *purge_list)
{
	struct vmap_block *vb, *n_vb;

	list_for_each_entry_safe(vb, n_vb, purge_list, purge) {
		list_del(&vb->purge);
		free_vmap_block(vb);
	}
}

static void purge_fragmented_blocks(int cpu)
{
	LIST_HEAD(purge);
	struct vmap_block *vb;
	struct vmap_block_queue *vbq = &per_cpu(vmap_block_queue, cpu);

	rcu_read_lock();
	list_for_each_entry_rcu(vb, &vbq->free, free_list) {
		unsigned long free = READ_ONCE(vb->free);
		unsigned long dirty = READ_ONCE(vb->dirty);

		if (free + dirty != VMAP_BBMAP_BITS ||
		    dirty == VMAP_BBMAP_BITS)
			continue;

		spin_lock(&vb->lock);
		purge_fragmented_block(vb, &purge, true);
		spin_unlock(&vb->lock);
	}
	rcu_read_unlock();
	free_purged_blocks(&purge);
}

static void purge_fragmented_blocks_allcpus(void)
{
	int cpu;

	for_each_possible_cpu(cpu)
		purge_fragmented_blocks(cpu);
}

static void *vb_alloc(unsigned long size, gfp_t gfp_mask)
{
	struct vmap_block_queue *vbq;
	struct vmap_block *vb;
	void *vaddr = NULL;
	unsigned int order;

	BUG_ON(offset_in_page(size));
	BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC);
	if (WARN_ON(size == 0)) {
		/*
		 * Allocating 0 bytes isn't what caller wants since
		 * get_order(0) returns funny result. Just warn and terminate
		 * early.
		 */
		return ERR_PTR(-EINVAL);
	}
	order = get_order(size);

	rcu_read_lock();
	vbq = raw_cpu_ptr(&vmap_block_queue);
	list_for_each_entry_rcu(vb, &vbq->free, free_list) {
		unsigned long pages_off;

		if (READ_ONCE(vb->free) < (1UL << order))
			continue;

		spin_lock(&vb->lock);
		if (vb->free < (1UL << order)) {
			spin_unlock(&vb->lock);
			continue;
		}

		pages_off = VMAP_BBMAP_BITS - vb->free;
		vaddr = vmap_block_vaddr(vb->va->va_start, pages_off);
		WRITE_ONCE(vb->free, vb->free - (1UL << order));
		bitmap_set(vb->used_map, pages_off, (1UL << order));
		if (vb->free == 0) {
			spin_lock(&vbq->lock);
			list_del_rcu(&vb->free_list);
			spin_unlock(&vbq->lock);
		}

		spin_unlock(&vb->lock);
		break;
	}

	rcu_read_unlock();

	/* Allocate new block if nothing was found */
	if (!vaddr)
		vaddr = new_vmap_block(order, gfp_mask);

	return vaddr;
}

static void vb_free(unsigned long addr, unsigned long size)
{
	unsigned long offset;
	unsigned int order;
	struct vmap_block *vb;
	struct xarray *xa;

	BUG_ON(offset_in_page(size));
	BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC);

	flush_cache_vunmap(addr, addr + size);

	order = get_order(size);
	offset = (addr & (VMAP_BLOCK_SIZE - 1)) >> PAGE_SHIFT;

	xa = addr_to_vb_xa(addr);
	vb = xa_load(xa, addr_to_vb_idx(addr));

	spin_lock(&vb->lock);
	bitmap_clear(vb->used_map, offset, (1UL << order));
	spin_unlock(&vb->lock);

	vunmap_range_noflush(addr, addr + size);

	if (debug_pagealloc_enabled_static())
		flush_tlb_kernel_range(addr, addr + size);

	spin_lock(&vb->lock);

	/* Expand the not yet TLB flushed dirty range */
	vb->dirty_min = min(vb->dirty_min, offset);
	vb->dirty_max = max(vb->dirty_max, offset + (1UL << order));

	WRITE_ONCE(vb->dirty, vb->dirty + (1UL << order));
	if (vb->dirty == VMAP_BBMAP_BITS) {
		BUG_ON(vb->free);
		spin_unlock(&vb->lock);
		free_vmap_block(vb);
	} else
		spin_unlock(&vb->lock);
}

static void _vm_unmap_aliases(unsigned long start, unsigned long end, int flush)
{
	LIST_HEAD(purge_list);
	int cpu;

	if (unlikely(!vmap_initialized))
		return;

	mutex_lock(&vmap_purge_lock);

	for_each_possible_cpu(cpu) {
		struct vmap_block_queue *vbq = &per_cpu(vmap_block_queue, cpu);
		struct vmap_block *vb;
		unsigned long idx;

		rcu_read_lock();
		xa_for_each(&vbq->vmap_blocks, idx, vb) {
			spin_lock(&vb->lock);

			/*
			 * Try to purge a fragmented block first. If it's
			 * not purgeable, check whether there is dirty
			 * space to be flushed.
			 */
			if (!purge_fragmented_block(vb, &purge_list, false) &&
			    vb->dirty_max && vb->dirty != VMAP_BBMAP_BITS) {
				unsigned long va_start = vb->va->va_start;
				unsigned long s, e;

				s = va_start + (vb->dirty_min << PAGE_SHIFT);
				e = va_start + (vb->dirty_max << PAGE_SHIFT);

				start = min(s, start);
				end   = max(e, end);

				/* Prevent that this is flushed again */
				vb->dirty_min = VMAP_BBMAP_BITS;
				vb->dirty_max = 0;

				flush = 1;
			}
			spin_unlock(&vb->lock);
		}
		rcu_read_unlock();
	}
	free_purged_blocks(&purge_list);

	if (!__purge_vmap_area_lazy(start, end, false) && flush)
		flush_tlb_kernel_range(start, end);
	mutex_unlock(&vmap_purge_lock);
}

/**
 * vm_unmap_aliases - unmap outstanding lazy aliases in the vmap layer
 *
 * The vmap/vmalloc layer lazily flushes kernel virtual mappings primarily
 * to amortize TLB flushing overheads. What this means is that any page you
 * have now, may, in a former life, have been mapped into kernel virtual
 * address by the vmap layer and so there might be some CPUs with TLB entries
 * still referencing that page (additional to the regular 1:1 kernel mapping).
 *
 * vm_unmap_aliases flushes all such lazy mappings. After it returns, we can
 * be sure that none of the pages we have control over will have any aliases
 * from the vmap layer.
 */
void vm_unmap_aliases(void)
{
	_vm_unmap_aliases(ULONG_MAX, 0, 0);
}
EXPORT_SYMBOL_GPL(vm_unmap_aliases);

/**
 * vm_unmap_ram - unmap linear kernel address space set up by vm_map_ram
 * @mem: the pointer returned by vm_map_ram
 * @count: the count passed to that vm_map_ram call (cannot unmap partial)
 */
void vm_unmap_ram(const void *mem, unsigned int count)
{
	unsigned long size = (unsigned long)count << PAGE_SHIFT;
	unsigned long addr = (unsigned long)kasan_reset_tag(mem);
	struct vmap_area *va;

	might_sleep();
	BUG_ON(!addr);
	BUG_ON(addr < VMALLOC_START);
	BUG_ON(addr > VMALLOC_END);
	BUG_ON(!PAGE_ALIGNED(addr));

	kasan_poison_vmalloc(mem, size);

	if (likely(count <= VMAP_MAX_ALLOC)) {
		debug_check_no_locks_freed(mem, size);
		vb_free(addr, size);
		return;
	}

	va = find_unlink_vmap_area(addr);
	if (WARN_ON_ONCE(!va))
		return;

	debug_check_no_locks_freed((void *)va->va_start, va_size(va));
	free_unmap_vmap_area(va);
}
EXPORT_SYMBOL(vm_unmap_ram);

/**
 * vm_map_ram - map pages linearly into kernel virtual address (vmalloc space)
 * @pages: an array of pointers to the pages to be mapped
 * @count: number of pages
 * @node: prefer to allocate data structures on this node
 *
 * If you use this function for less than VMAP_MAX_ALLOC pages, it could be
 * faster than vmap so it's good.  But if you mix long-life and short-life
 * objects with vm_map_ram(), it could consume lots of address space through
 * fragmentation (especially on a 32bit machine).  You could see failures in
 * the end.  Please use this function for short-lived objects.
 *
 * Returns: a pointer to the address that has been mapped, or %NULL on failure
 */
void *vm_map_ram(struct page **pages, unsigned int count, int node)
{
	unsigned long size = (unsigned long)count << PAGE_SHIFT;
	unsigned long addr;
	void *mem;

	if (likely(count <= VMAP_MAX_ALLOC)) {
		mem = vb_alloc(size, GFP_KERNEL);
		if (IS_ERR(mem))
			return NULL;
		addr = (unsigned long)mem;
	} else {
		struct vmap_area *va;
		va = alloc_vmap_area(size, PAGE_SIZE,
				VMALLOC_START, VMALLOC_END,
				node, GFP_KERNEL, VMAP_RAM,
				NULL);
		if (IS_ERR(va))
			return NULL;

		addr = va->va_start;
		mem = (void *)addr;
	}

	if (vmap_pages_range(addr, addr + size, PAGE_KERNEL,
				pages, PAGE_SHIFT) < 0) {
		vm_unmap_ram(mem, count);
		return NULL;
	}

	/*
	 * Mark the pages as accessible, now that they are mapped.
	 * With hardware tag-based KASAN, marking is skipped for
	 * non-VM_ALLOC mappings, see __kasan_unpoison_vmalloc().
	 */
	mem = kasan_unpoison_vmalloc(mem, size, KASAN_VMALLOC_PROT_NORMAL);

	return mem;
}
EXPORT_SYMBOL(vm_map_ram);

static struct vm_struct *vmlist __initdata;

static inline unsigned int vm_area_page_order(struct vm_struct *vm)
{
#ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC
	return vm->page_order;
#else
	return 0;
#endif
}

unsigned int get_vm_area_page_order(struct vm_struct *vm)
{
	return vm_area_page_order(vm);
}

static inline void set_vm_area_page_order(struct vm_struct *vm, unsigned int order)
{
#ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC
	vm->page_order = order;
#else
	BUG_ON(order != 0);
#endif
}

/**
 * vm_area_add_early - add vmap area early during boot
 * @vm: vm_struct to add
 *
 * This function is used to add fixed kernel vm area to vmlist before
 * vmalloc_init() is called.  @vm->addr, @vm->size, and @vm->flags
 * should contain proper values and the other fields should be zero.
 *
 * DO NOT USE THIS FUNCTION UNLESS YOU KNOW WHAT YOU'RE DOING.
 */
void __init vm_area_add_early(struct vm_struct *vm)
{
	struct vm_struct *tmp, **p;

	BUG_ON(vmap_initialized);
	for (p = &vmlist; (tmp = *p) != NULL; p = &tmp->next) {
		if (tmp->addr >= vm->addr) {
			BUG_ON(tmp->addr < vm->addr + vm->size);
			break;
		} else
			BUG_ON(tmp->addr + tmp->size > vm->addr);
	}
	vm->next = *p;
	*p = vm;
}

/**
 * vm_area_register_early - register vmap area early during boot
 * @vm: vm_struct to register
 * @align: requested alignment
 *
 * This function is used to register kernel vm area before
 * vmalloc_init() is called.  @vm->size and @vm->flags should contain
 * proper values on entry and other fields should be zero.  On return,
 * vm->addr contains the allocated address.
 *
 * DO NOT USE THIS FUNCTION UNLESS YOU KNOW WHAT YOU'RE DOING.
 */
void __init vm_area_register_early(struct vm_struct *vm, size_t align)
{
	unsigned long addr = ALIGN(VMALLOC_START, align);
	struct vm_struct *cur, **p;

	BUG_ON(vmap_initialized);

	for (p = &vmlist; (cur = *p) != NULL; p = &cur->next) {
		if ((unsigned long)cur->addr - addr >= vm->size)
			break;
		addr = ALIGN((unsigned long)cur->addr + cur->size, align);
	}

	BUG_ON(addr > VMALLOC_END - vm->size);
	vm->addr = (void *)addr;
	vm->next = *p;
	*p = vm;
	kasan_populate_early_vm_area_shadow(vm->addr, vm->size);
}

void clear_vm_uninitialized_flag(struct vm_struct *vm)
{
	/*
	 * Before removing VM_UNINITIALIZED,
	 * we should make sure that vm has proper values.
	 * Pair with smp_rmb() in vread_iter() and vmalloc_info_show().
	 */
	smp_wmb();
	vm->flags &= ~VM_UNINITIALIZED;
}

struct vm_struct *__get_vm_area_node(unsigned long size,
		unsigned long align, unsigned long shift, unsigned long flags,
		unsigned long start, unsigned long end, int node,
		gfp_t gfp_mask, const void *caller)
{
	struct vmap_area *va;
	struct vm_struct *area;
	unsigned long requested_size = size;

	BUG_ON(in_nmi() || in_hardirq());
	size = ALIGN(size, 1ul << shift);
	if (unlikely(!size))
		return NULL;

	if (flags & VM_IOREMAP)
		align = 1ul << clamp_t(int, get_count_order_long(size),
				       PAGE_SHIFT, IOREMAP_MAX_ORDER);

	area = kzalloc_node(sizeof(*area), gfp_mask & GFP_RECLAIM_MASK, node);
	if (unlikely(!area))
		return NULL;

	if (!(flags & VM_NO_GUARD))
		size += PAGE_SIZE;

	area->flags = flags;
	area->caller = caller;
	area->requested_size = requested_size;

	va = alloc_vmap_area(size, align, start, end, node, gfp_mask, 0, area);
	if (IS_ERR(va)) {
		kfree(area);
		return NULL;
	}

	/*
	 * Mark pages for non-VM_ALLOC mappings as accessible. Do it now as a
	 * best-effort approach, as they can be mapped outside of vmalloc code.
	 * For VM_ALLOC mappings, the pages are marked as accessible after
	 * getting mapped in __vmalloc_node_range().
	 * With hardware tag-based KASAN, marking is skipped for
	 * non-VM_ALLOC mappings, see __kasan_unpoison_vmalloc().
	 */
	if (!(flags & VM_ALLOC))
		area->addr = kasan_unpoison_vmalloc(area->addr, requested_size,
						    KASAN_VMALLOC_PROT_NORMAL);

	return area;
}

struct vm_struct *__get_vm_area_caller(unsigned long size, unsigned long flags,
				       unsigned long start, unsigned long end,
				       const void *caller)
{
	return __get_vm_area_node(size, 1, PAGE_SHIFT, flags, start, end,
				  NUMA_NO_NODE, GFP_KERNEL, caller);
}

/**
 * get_vm_area - reserve a contiguous kernel virtual area
 * @size:	 size of the area
 * @flags:	 %VM_IOREMAP for I/O mappings or VM_ALLOC
 *
 * Search an area of @size in the kernel virtual mapping area,
 * and reserved it for out purposes.  Returns the area descriptor
 * on success or %NULL on failure.
 *
 * Return: the area descriptor on success or %NULL on failure.
 */
struct vm_struct *get_vm_area(unsigned long size, unsigned long flags)
{
	return __get_vm_area_node(size, 1, PAGE_SHIFT, flags,
				  VMALLOC_START, VMALLOC_END,
				  NUMA_NO_NODE, GFP_KERNEL,
				  __builtin_return_address(0));
}

struct vm_struct *get_vm_area_caller(unsigned long size, unsigned long flags,
				const void *caller)
{
	return __get_vm_area_node(size, 1, PAGE_SHIFT, flags,
				  VMALLOC_START, VMALLOC_END,
				  NUMA_NO_NODE, GFP_KERNEL, caller);
}

/**
 * find_vm_area - find a continuous kernel virtual area
 * @addr:	  base address
 *
 * Search for the kernel VM area starting at @addr, and return it.
 * It is up to the caller to do all required locking to keep the returned
 * pointer valid.
 *
 * Return: the area descriptor on success or %NULL on failure.
 */
struct vm_struct *find_vm_area(const void *addr)
{
	struct vmap_area *va;

	va = find_vmap_area((unsigned long)addr);
	if (!va)
		return NULL;

	return va->vm;
}

/**
 * remove_vm_area - find and remove a continuous kernel virtual area
 * @addr:	    base address
 *
 * Search for the kernel VM area starting at @addr, and remove it.
 * This function returns the found VM area, but using it is NOT safe
 * on SMP machines, except for its size or flags.
 *
 * Return: the area descriptor on success or %NULL on failure.
 */
struct vm_struct *remove_vm_area(const void *addr)
{
	struct vmap_area *va;
	struct vm_struct *vm;

	might_sleep();

	if (WARN(!PAGE_ALIGNED(addr), "Trying to vfree() bad address (%p)\n",
			addr))
		return NULL;

	va = find_unlink_vmap_area((unsigned long)addr);
	if (!va || !va->vm)
		return NULL;
	vm = va->vm;

	debug_check_no_locks_freed(vm->addr, get_vm_area_size(vm));
	debug_check_no_obj_freed(vm->addr, get_vm_area_size(vm));
	kasan_free_module_shadow(vm);
	kasan_poison_vmalloc(vm->addr, get_vm_area_size(vm));

	free_unmap_vmap_area(va);
	return vm;
}

static inline void set_area_direct_map(const struct vm_struct *area,
				       int (*set_direct_map)(struct page *page))
{
	int i;

	/* HUGE_VMALLOC passes small pages to set_direct_map */
	for (i = 0; i < area->nr_pages; i++)
		if (page_address(area->pages[i]))
			set_direct_map(area->pages[i]);
}

/*
 * Flush the vm mapping and reset the direct map.
 */
static void vm_reset_perms(struct vm_struct *area)
{
	unsigned long start = ULONG_MAX, end = 0;
	unsigned int page_order = vm_area_page_order(area);
	int flush_dmap = 0;
	int i;

	/*
	 * Find the start and end range of the direct mappings to make sure that
	 * the vm_unmap_aliases() flush includes the direct map.
	 */
	for (i = 0; i < area->nr_pages; i += 1U << page_order) {
		unsigned long addr = (unsigned long)page_address(area->pages[i]);

		if (addr) {
			unsigned long page_size;

			page_size = PAGE_SIZE << page_order;
			start = min(addr, start);
			end = max(addr + page_size, end);
			flush_dmap = 1;
		}
	}

	/*
	 * Set direct map to something invalid so that it won't be cached if
	 * there are any accesses after the TLB flush, then flush the TLB and
	 * reset the direct map permissions to the default.
	 */
	set_area_direct_map(area, set_direct_map_invalid_noflush);
	_vm_unmap_aliases(start, end, flush_dmap);
	set_area_direct_map(area, set_direct_map_default_noflush);
}

static void delayed_vfree_work(struct work_struct *w)
{
	struct vfree_deferred *p = container_of(w, struct vfree_deferred, wq);
	struct llist_node *t, *llnode;

	llist_for_each_safe(llnode, t, llist_del_all(&p->list))
		vfree(llnode);
}

/**
 * vfree_atomic - release memory allocated by vmalloc()
 * @addr:	  memory base address
 *
 * This one is just like vfree() but can be called in any atomic context
 * except NMIs.
 */
void vfree_atomic(const void *addr)
{
	struct vfree_deferred *p = raw_cpu_ptr(&vfree_deferred);

	BUG_ON(in_nmi());
	kmemleak_free(addr);

	/*
	 * Use raw_cpu_ptr() because this can be called from preemptible
	 * context. Preemption is absolutely fine here, because the llist_add()
	 * implementation is lockless, so it works even if we are adding to
	 * another cpu's list. schedule_work() should be fine with this too.
	 */
	if (addr && llist_add((struct llist_node *)addr, &p->list))
		schedule_work(&p->wq);
}

/*
 * vm_area_free_pages - free a range of pages from a vmalloc allocation
 * @vm: the vm_struct containing the pages
 * @start_idx: first page index to free (inclusive)
 * @end_idx: last page index to free (exclusive)
 *
 * Free pages [start_idx, end_idx) updating NR_VMALLOC stat accounting.
 * Freed vm->pages[] entries are set to NULL.
 * Caller is responsible for unmapping (vunmap_range) and KASAN
 * poisoning before calling this.
 */
static void vm_area_free_pages(struct vm_struct *vm, unsigned int start_idx,
			       unsigned int end_idx)
{
	unsigned int i;

	if (!(vm->flags & VM_MAP_PUT_PAGES)) {
		for (i = start_idx; i < end_idx; i++)
			mod_lruvec_page_state(vm->pages[i], NR_VMALLOC, -1);
	}
	free_pages_bulk(vm->pages + start_idx, end_idx - start_idx);

	for (i = start_idx; i < end_idx; i++)
		vm->pages[i] = NULL;
}

/**
 * vfree - Release memory allocated by vmalloc()
 * @addr:  Memory base address
 *
 * Free the virtually continuous memory area starting at @addr, as obtained
 * from one of the vmalloc() family of APIs.  This will usually also free the
 * physical memory underlying the virtual allocation, but that memory is
 * reference counted, so it will not be freed until the last user goes away.
 *
 * If @addr is NULL, no operation is performed.
 *
 * Context:
 * May sleep if called *not* from interrupt context.
 * Must not be called in NMI context (strictly speaking, it could be
 * if we have CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG, but making the calling
 * conventions for vfree() arch-dependent would be a really bad idea).
 */
void vfree(const void *addr)
{
	struct vm_struct *vm;

	if (unlikely(in_interrupt())) {
		vfree_atomic(addr);
		return;
	}

	BUG_ON(in_nmi());
	kmemleak_free(addr);
	might_sleep();

	if (!addr)
		return;

	vm = remove_vm_area(addr);
	if (unlikely(!vm)) {
		WARN(1, KERN_ERR "Trying to vfree() nonexistent vm area (%p)\n",
				addr);
		return;
	}

	if (unlikely(vm->flags & VM_FLUSH_RESET_PERMS))
		vm_reset_perms(vm);

	vm_area_free_pages(vm, 0, vm->nr_pages);
	kvfree(vm->pages);
	kfree(vm);
}
EXPORT_SYMBOL(vfree);

/**
 * vunmap - release virtual mapping obtained by vmap()
 * @addr:   memory base address
 *
 * Free the virtually contiguous memory area starting at @addr,
 * which was created from the page array passed to vmap().
 *
 * Must not be called in interrupt context.
 */
void vunmap(const void *addr)
{
	struct vm_struct *vm;

	BUG_ON(in_interrupt());
	might_sleep();

	if (!addr)
		return;
	vm = remove_vm_area(addr);
	if (unlikely(!vm)) {
		WARN(1, KERN_ERR "Trying to vunmap() nonexistent vm area (%p)\n",
				addr);
		return;
	}
	kfree(vm);
}
EXPORT_SYMBOL(vunmap);

/**
 * vmap - map an array of pages into virtually contiguous space
 * @pages: array of page pointers
 * @count: number of pages to map
 * @flags: vm_area->flags
 * @prot: page protection for the mapping
 *
 * Maps @count pages from @pages into contiguous kernel virtual space.
 * If @flags contains %VM_MAP_PUT_PAGES the ownership of the pages array itself
 * (which must be kmalloc or vmalloc memory) and one reference per pages in it
 * are transferred from the caller to vmap(), and will be freed / dropped when
 * vfree() is called on the return value.
 *
 * Return: the address of the area or %NULL on failure
 */
void *vmap(struct page **pages, unsigned int count,
	   unsigned long flags, pgprot_t prot)
{
	struct vm_struct *area;
	unsigned long addr;
	unsigned long size;		/* In bytes */

	might_sleep();

	if (WARN_ON_ONCE(flags & VM_FLUSH_RESET_PERMS))
		return NULL;

	/*
	 * Your top guard is someone else's bottom guard. Not having a top
	 * guard compromises someone else's mappings too.
	 */
	if (WARN_ON_ONCE(flags & VM_NO_GUARD))
		flags &= ~VM_NO_GUARD;

	if (count > totalram_pages())
		return NULL;

	size = (unsigned long)count << PAGE_SHIFT;
	area = get_vm_area_caller(size, flags, __builtin_return_address(0));
	if (!area)
		return NULL;

	addr = (unsigned long)area->addr;
	if (vmap_pages_range(addr, addr + size, pgprot_nx(prot),
				pages, PAGE_SHIFT) < 0) {
		vunmap(area->addr);
		return NULL;
	}

	if (flags & VM_MAP_PUT_PAGES) {
		area->pages = pages;
		area->nr_pages = count;
	}
	return area->addr;
}
EXPORT_SYMBOL(vmap);

#ifdef CONFIG_VMAP_PFN
struct vmap_pfn_data {
	unsigned long	*pfns;
	pgprot_t	prot;
	unsigned int	idx;
};

static int vmap_pfn_apply(pte_t *pte, unsigned long addr, void *private)
{
	struct vmap_pfn_data *data = private;
	unsigned long pfn = data->pfns[data->idx];
	pte_t ptent;

	if (WARN_ON_ONCE(pfn_valid(pfn)))
		return -EINVAL;

	ptent = pte_mkspecial(pfn_pte(pfn, data->prot));
	set_pte_at(&init_mm, addr, pte, ptent);

	data->idx++;
	return 0;
}

/**
 * vmap_pfn - map an array of PFNs into virtually contiguous space
 * @pfns: array of PFNs
 * @count: number of pages to map
 * @prot: page protection for the mapping
 *
 * Maps @count PFNs from @pfns into contiguous kernel virtual space and returns
 * the start address of the mapping.
 */
void *vmap_pfn(unsigned long *pfns, unsigned int count, pgprot_t prot)
{
	struct vmap_pfn_data data = { .pfns = pfns, .prot = pgprot_nx(prot) };
	struct vm_struct *area;

	area = get_vm_area_caller(count * PAGE_SIZE, VM_IOREMAP,
			__builtin_return_address(0));
	if (!area)
		return NULL;
	if (apply_to_page_range(&init_mm, (unsigned long)area->addr,
			count * PAGE_SIZE, vmap_pfn_apply, &data)) {
		free_vm_area(area);
		return NULL;
	}

	flush_cache_vmap((unsigned long)area->addr,
			 (unsigned long)area->addr + count * PAGE_SIZE);

	return area->addr;
}
EXPORT_SYMBOL_GPL(vmap_pfn);
#endif /* CONFIG_VMAP_PFN */

/*
 * Helper for vmalloc to adjust the gfp flags for certain allocations.
 */
static inline gfp_t vmalloc_gfp_adjust(gfp_t flags, const bool large)
{
	flags |= __GFP_NOWARN;
	if (large)
		flags &= ~__GFP_NOFAIL;
	return flags;
}

static inline unsigned int
vm_area_alloc_pages(gfp_t gfp, int nid,
		unsigned int order, unsigned int nr_pages, struct page **pages)
{
	unsigned int nr_allocated = 0;
	unsigned int nr_remaining = nr_pages;
	unsigned int max_attempt_order = MAX_PAGE_ORDER;
	struct page *page;
	int i;
	unsigned int large_order = ilog2(nr_remaining);
	gfp_t large_gfp = vmalloc_gfp_adjust(gfp, large_order) & ~__GFP_DIRECT_RECLAIM;

	large_order = min(max_attempt_order, large_order);

	/*
	 * Initially, attempt to have the page allocator give us large order
	 * pages. Do not attempt allocating smaller than order chunks since
	 * __vmap_pages_range() expects physically contigous pages of exactly
	 * order long chunks.
	 */
	while (large_order > order && nr_remaining) {
		if (nid == NUMA_NO_NODE)
			page = alloc_pages_noprof(large_gfp, large_order);
		else
			page = alloc_pages_node_noprof(nid, large_gfp, large_order);

		if (unlikely(!page)) {
			max_attempt_order = --large_order;
			continue;
		}

		mod_lruvec_page_state(page, NR_VMALLOC, 1 << large_order);

		split_page(page, large_order);
		for (i = 0; i < (1U << large_order); i++)
			pages[nr_allocated + i] = page + i;

		nr_allocated += 1U << large_order;
		nr_remaining = nr_pages - nr_allocated;

		large_order = ilog2(nr_remaining);
		large_order = min(max_attempt_order, large_order);
	}

	/*
	 * For order-0 pages we make use of bulk allocator, if
	 * the page array is partly or not at all populated due
	 * to fails, fallback to a single page allocator that is
	 * more permissive.
	 */
	if (!order) {
		while (nr_allocated < nr_pages) {
			unsigned int nr, nr_pages_request;
			int i;

			/*
			 * A maximum allowed request is hard-coded and is 100
			 * pages per call. That is done in order to prevent a
			 * long preemption off scenario in the bulk-allocator
			 * so the range is [1:100].
			 */
			nr_pages_request = min(100U, nr_pages - nr_allocated);

			/* memory allocation should consider mempolicy, we can't
			 * wrongly use nearest node when nid == NUMA_NO_NODE,
			 * otherwise memory may be allocated in only one node,
			 * but mempolicy wants to alloc memory by interleaving.
			 */
			if (IS_ENABLED(CONFIG_NUMA) && nid == NUMA_NO_NODE)
				nr = alloc_pages_bulk_mempolicy_noprof(gfp,
							nr_pages_request,
							pages + nr_allocated);
			else
				nr = alloc_pages_bulk_node_noprof(gfp, nid,
							nr_pages_request,
							pages + nr_allocated);

			for (i = nr_allocated; i < nr_allocated + nr; i++)
				mod_lruvec_page_state(pages[i], NR_VMALLOC, 1);

			nr_allocated += nr;

			/*
			 * If zero or pages were obtained partly,
			 * fallback to a single page allocator.
			 */
			if (nr != nr_pages_request)
				break;
		}
	}

	/* High-order pages or fallback path if "bulk" fails. */
	while (nr_allocated < nr_pages) {
		if (!(gfp & __GFP_NOFAIL) && fatal_signal_pending(current))
			break;

		if (nid == NUMA_NO_NODE)
			page = alloc_pages_noprof(gfp, order);
		else
			page = alloc_pages_node_noprof(nid, gfp, order);

		if (unlikely(!page))
			break;

		mod_lruvec_page_state(page, NR_VMALLOC, 1 << order);

		/*
		 * High-order allocations must be able to be treated as
		 * independent small pages by callers (as they can with
		 * small-page vmallocs). Some drivers do their own refcounting
		 * on vmalloc_to_page() pages, some use page->mapping,
		 * page->lru, etc.
		 */
		if (order)
			split_page(page, order);

		/*
		 * Careful, we allocate and map page-order pages, but
		 * tracking is done per PAGE_SIZE page so as to keep the
		 * vm_struct APIs independent of the physical/mapped size.
		 */
		for (i = 0; i < (1U << order); i++)
			pages[nr_allocated + i] = page + i;

		nr_allocated += 1U << order;
	}

	return nr_allocated;
}

static LLIST_HEAD(pending_vm_area_cleanup);
static void cleanup_vm_area_work(struct work_struct *work)
{
	struct vm_struct *area, *tmp;
	struct llist_node *head;

	head = llist_del_all(&pending_vm_area_cleanup);
	if (!head)
		return;

	llist_for_each_entry_safe(area, tmp, head, llnode) {
		if (!area->pages)
			free_vm_area(area);
		else
			vfree(area->addr);
	}
}

/*
 * Helper for __vmalloc_area_node() to defer cleanup
 * of partially initialized vm_struct in error paths.
 */
static DECLARE_WORK(cleanup_vm_area, cleanup_vm_area_work);
static void defer_vm_area_cleanup(struct vm_struct *area)
{
	if (llist_add(&area->llnode, &pending_vm_area_cleanup))
		schedule_work(&cleanup_vm_area);
}

/*
 * Page tables allocations ignore external GFP. Enforces it by
 * the memalloc scope API. It is used by vmalloc internals and
 * KASAN shadow population only.
 *
 * GFP to scope mapping:
 *
 * non-blocking (no __GFP_DIRECT_RECLAIM) - memalloc_noreclaim_save()
 * GFP_NOFS - memalloc_nofs_save()
 * GFP_NOIO - memalloc_noio_save()
 * __GFP_RETRY_MAYFAIL, __GFP_NORETRY - memalloc_noreclaim_save()
 * to prevent OOMs
 *
 * Returns a flag cookie to pair with restore.
 */
unsigned int
memalloc_apply_gfp_scope(gfp_t gfp_mask)
{
	unsigned int flags = 0;

	if (!gfpflags_allow_blocking(gfp_mask) ||
			(gfp_mask & (__GFP_RETRY_MAYFAIL | __GFP_NORETRY)))
		flags = memalloc_noreclaim_save();
	else if ((gfp_mask & (__GFP_FS | __GFP_IO)) == __GFP_IO)
		flags = memalloc_nofs_save();
	else if ((gfp_mask & (__GFP_FS | __GFP_IO)) == 0)
		flags = memalloc_noio_save();

	/* 0 - no scope applied. */
	return flags;
}

void
memalloc_restore_scope(unsigned int flags)
{
	if (flags)
		memalloc_flags_restore(flags);
}

static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
				 pgprot_t prot, unsigned int page_shift,
				 int node)
{
	const gfp_t nested_gfp = (gfp_mask & GFP_RECLAIM_MASK) | __GFP_ZERO;
	bool nofail = gfp_mask & __GFP_NOFAIL;
	unsigned long addr = (unsigned long)area->addr;
	unsigned long size = get_vm_area_size(area);
	unsigned long array_size;
	unsigned int nr_small_pages = size >> PAGE_SHIFT;
	unsigned int page_order;
	unsigned int flags;
	int ret;

	array_size = (unsigned long)nr_small_pages * sizeof(struct page *);

	/* __GFP_NOFAIL and "noblock" flags are mutually exclusive. */
	if (!gfpflags_allow_blocking(gfp_mask))
		nofail = false;

	if (!(gfp_mask & (GFP_DMA | GFP_DMA32)))
		gfp_mask |= __GFP_HIGHMEM;

	/* Please note that the recursion is strictly bounded. */
	if (array_size > PAGE_SIZE) {
		area->pages = __vmalloc_node_noprof(array_size, 1, nested_gfp, node,
					area->caller);
	} else {
		area->pages = kmalloc_node_noprof(array_size, nested_gfp, node);
	}

	if (!area->pages) {
		warn_alloc(gfp_mask, NULL,
			"vmalloc error: size %lu, failed to allocated page array size %lu",
			nr_small_pages * PAGE_SIZE, array_size);
		goto fail;
	}

	set_vm_area_page_order(area, page_shift - PAGE_SHIFT);
	page_order = vm_area_page_order(area);

	/*
	 * High-order nofail allocations are really expensive and
	 * potentially dangerous (pre-mature OOM, disruptive reclaim
	 * and compaction etc.
	 *
	 * Please note, the __vmalloc_node_range_noprof() falls-back
	 * to order-0 pages if high-order attempt is unsuccessful.
	 */
	area->nr_pages = vm_area_alloc_pages(
			vmalloc_gfp_adjust(gfp_mask, page_order), node,
			page_order, nr_small_pages, area->pages);

	/*
	 * If not enough pages were obtained to accomplish an
	 * allocation request, free them via vfree() if any.
	 */
	if (area->nr_pages != nr_small_pages) {
		/*
		 * vm_area_alloc_pages() can fail due to insufficient memory but
		 * also:-
		 *
		 * - a pending fatal signal
		 * - insufficient huge page-order pages
		 *
		 * Since we always retry allocations at order-0 in the huge page
		 * case a warning for either is spurious.
		 */
		if (!fatal_signal_pending(current) && page_order == 0)
			warn_alloc(gfp_mask, NULL,
				"vmalloc error: size %lu, failed to allocate pages",
				nr_small_pages * PAGE_SIZE);
		goto fail;
	}

	/*
	 * page tables allocations ignore external gfp mask, enforce it
	 * by the scope API
	 */
	flags = memalloc_apply_gfp_scope(gfp_mask);
	do {
		ret = __vmap_pages_range(addr, addr + size, prot, area->pages,
				page_shift, nested_gfp);
		if (nofail && (ret < 0))
			schedule_timeout_uninterruptible(1);
	} while (nofail && (ret < 0));
	memalloc_restore_scope(flags);

	if (ret < 0) {
		warn_alloc(gfp_mask, NULL,
			"vmalloc error: size %lu, failed to map pages",
			area->nr_pages * PAGE_SIZE);
		goto fail;
	}

	return area->addr;

fail:
	defer_vm_area_cleanup(area);
	return NULL;
}

/*
 * See __vmalloc_node_range() for a clear list of supported vmalloc flags.
 * This gfp lists all flags currently passed through vmalloc. Currently,
 * __GFP_ZERO is used by BPF and __GFP_NORETRY is used by percpu. Both drm
 * and BPF also use GFP_USER. Additionally, various users pass
 * GFP_KERNEL_ACCOUNT. Xfs uses __GFP_NOLOCKDEP.
 */
#define GFP_VMALLOC_SUPPORTED (GFP_KERNEL | GFP_ATOMIC | GFP_NOWAIT |\
				__GFP_NOFAIL | __GFP_ZERO |\
				__GFP_NORETRY | __GFP_RETRY_MAYFAIL |\
				GFP_NOFS | GFP_NOIO | GFP_KERNEL_ACCOUNT |\
				GFP_USER | __GFP_NOLOCKDEP | __GFP_SKIP_KASAN)

static gfp_t vmalloc_fix_flags(gfp_t flags)
{
	gfp_t invalid_mask = flags & ~GFP_VMALLOC_SUPPORTED;

	flags &= GFP_VMALLOC_SUPPORTED;
	WARN_ONCE(1, "Unexpected gfp: %#x (%pGg). Fixing up to gfp: %#x (%pGg). Fix your code!\n",
		  invalid_mask, &invalid_mask, flags, &flags);
	return flags;
}

/**
 * __vmalloc_node_range - allocate virtually contiguous memory
 * @size:		  allocation size
 * @align:		  desired alignment
 * @start:		  vm area range start
 * @end:		  vm area range end
 * @gfp_mask:		  flags for the page level allocator
 * @prot:		  protection mask for the allocated pages
 * @vm_flags:		  additional vm area flags (e.g. %VM_NO_GUARD)
 * @node:		  node to use for allocation or NUMA_NO_NODE
 * @caller:		  caller's return address
 *
 * Allocate enough pages to cover @size from the page level
 * allocator with @gfp_mask flags and map them into contiguous
 * virtual range with protection @prot.
 *
 * Supported GFP classes: %GFP_KERNEL, %GFP_ATOMIC, %GFP_NOWAIT,
 * %__GFP_RETRY_MAYFAIL, %__GFP_NORETRY, %GFP_NOFS and %GFP_NOIO.
 * Zone modifiers are not supported.
 * Please note %GFP_ATOMIC and %GFP_NOWAIT are supported only
 * by __vmalloc().
 *
 * Retry modifiers: only %__GFP_NOFAIL is fully supported;
 * %__GFP_NORETRY and %__GFP_RETRY_MAYFAIL are supported with limitation,
 * i.e. page tables are allocated with NOWAIT semantic so they might fail
 * under moderate memory pressure.
 *
 * %__GFP_NOWARN can be used to suppress failure messages.
 *
 * %__GFP_SKIP_KASAN can be used to skip unpoisoning of mapped pages
 * (when prot=%PAGE_KERNEL).
 *
 * Can not be called from interrupt nor NMI contexts.
 * Return: the address of the area or %NULL on failure
 */
void *__vmalloc_node_range_noprof(unsigned long size, unsigned long align,
			unsigned long start, unsigned long end, gfp_t gfp_mask,
			pgprot_t prot, unsigned long vm_flags, int node,
			const void *caller)
{
	struct vm_struct *area;
	void *ret;
	kasan_vmalloc_flags_t kasan_flags = KASAN_VMALLOC_NONE;
	unsigned long original_align = align;
	unsigned int shift = PAGE_SHIFT;
	bool skip_vmalloc_kasan = kasan_hw_tags_enabled() && (gfp_mask & __GFP_SKIP_KASAN);

	if (WARN_ON_ONCE(!size))
		return NULL;

	if ((size >> PAGE_SHIFT) > totalram_pages()) {
		warn_alloc(gfp_mask, NULL,
			"vmalloc error: size %lu, exceeds total pages",
			size);
		return NULL;
	}

	if (vmap_allow_huge && (vm_flags & VM_ALLOW_HUGE_VMAP)) {
		/*
		 * Try huge pages. Only try for PAGE_KERNEL allocations,
		 * others like modules don't yet expect huge pages in
		 * their allocations due to apply_to_page_range not
		 * supporting them.
		 */

		if (arch_vmap_pmd_supported(prot) && size >= PMD_SIZE)
			shift = PMD_SHIFT;
		else
			shift = arch_vmap_pte_supported_shift(size);

		align = max(original_align, 1UL << shift);
	}

again:
	area = __get_vm_area_node(size, align, shift, VM_ALLOC |
				  VM_UNINITIALIZED | vm_flags, start, end, node,
				  gfp_mask & ~__GFP_SKIP_KASAN, caller);
	if (!area) {
		bool nofail = gfp_mask & __GFP_NOFAIL;
		warn_alloc(gfp_mask, NULL,
			"vmalloc error: size %lu, align 0x%lx, vm_struct allocation failed%s",
			size, align, (nofail) ? ". Retrying." : "");
		if (nofail) {
			schedule_timeout_uninterruptible(1);
			goto again;
		}
		goto fail;
	}

	/*
	 * Prepare arguments for __vmalloc_area_node() and
	 * kasan_unpoison_vmalloc().
	 */
	if (pgprot_val(prot) == pgprot_val(PAGE_KERNEL)) {
		if (kasan_hw_tags_enabled() && !skip_vmalloc_kasan) {
			/*
			 * Modify protection bits to allow tagging.
			 * This must be done before mapping.
			 */
			prot = arch_vmap_pgprot_tagged(prot);

			/*
			 * Skip page_alloc poisoning and zeroing for physical
			 * pages backing VM_ALLOC mapping. Memory is instead
			 * poisoned and zeroed by kasan_unpoison_vmalloc().
			 */
			gfp_mask |= __GFP_SKIP_KASAN | __GFP_SKIP_ZERO;
		}

		/* Take note that the mapping is PAGE_KERNEL. */
		kasan_flags |= KASAN_VMALLOC_PROT_NORMAL;
	}

	/* Allocate physical pages and map them into vmalloc space. */
	ret = __vmalloc_area_node(area, gfp_mask, prot, shift, node);
	if (!ret)
		goto fail;

	/*
	 * Mark the pages as accessible, now that they are mapped.
	 * The condition for setting KASAN_VMALLOC_INIT should complement the
	 * one in post_alloc_hook() with regards to the __GFP_SKIP_ZERO check
	 * to make sure that memory is initialized under the same conditions.
	 * Tag-based KASAN modes only assign tags to normal non-executable
	 * allocations, see __kasan_unpoison_vmalloc().
	 */
	kasan_flags |= KASAN_VMALLOC_VM_ALLOC;
	if (!want_init_on_free() && want_init_on_alloc(gfp_mask) &&
	    (gfp_mask & __GFP_SKIP_ZERO))
		kasan_flags |= KASAN_VMALLOC_INIT;
	/* KASAN_VMALLOC_PROT_NORMAL already set if required. */
	if (!skip_vmalloc_kasan)
		area->addr = kasan_unpoison_vmalloc(area->addr, size, kasan_flags);

	/*
	 * In this function, newly allocated vm_struct has VM_UNINITIALIZED
	 * flag. It means that vm_struct is not fully initialized.
	 * Now, it is fully initialized, so remove this flag here.
	 */
	clear_vm_uninitialized_flag(area);

	if (!(vm_flags & VM_DEFER_KMEMLEAK))
		kmemleak_vmalloc(area, PAGE_ALIGN(size), gfp_mask);

	return area->addr;

fail:
	if (shift > PAGE_SHIFT) {
		shift = PAGE_SHIFT;
		align = original_align;
		goto again;
	}

	return NULL;
}

/**
 * __vmalloc_node - allocate virtually contiguous memory
 * @size:	    allocation size
 * @align:	    desired alignment
 * @gfp_mask:	    flags for the page level allocator
 * @node:	    node to use for allocation or NUMA_NO_NODE
 * @caller:	    caller's return address
 *
 * Allocate enough pages to cover @size from the page level allocator with
 * @gfp_mask flags.  Map them into contiguous kernel virtual space.
 *
 * Semantics of @gfp_mask (including reclaim/retry modifiers such as
 * __GFP_NOFAIL) are the same as in __vmalloc_node_range_noprof().
 *
 * Return: pointer to the allocated memory or %NULL on error
 */
void *__vmalloc_node_noprof(unsigned long size, unsigned long align,
			    gfp_t gfp_mask, int node, const void *caller)
{
	return __vmalloc_node_range_noprof(size, align, VMALLOC_START, VMALLOC_END,
				gfp_mask, PAGE_KERNEL, 0, node, caller);
}
/*
 * This is only for performance analysis of vmalloc and stress purpose.
 * It is required by vmalloc test module, therefore do not use it other
 * than that.
 */
#ifdef CONFIG_TEST_VMALLOC_MODULE
EXPORT_SYMBOL_GPL(__vmalloc_node_noprof);
#endif

void *__vmalloc_noprof(unsigned long size, gfp_t gfp_mask)
{
	if (unlikely(gfp_mask & ~GFP_VMALLOC_SUPPORTED))
		gfp_mask = vmalloc_fix_flags(gfp_mask);
	return __vmalloc_node_noprof(size, 1, gfp_mask, NUMA_NO_NODE,
				__builtin_return_address(0));
}
EXPORT_SYMBOL(__vmalloc_noprof);

/**
 * vmalloc - allocate virtually contiguous memory
 * @size:    allocation size
 *
 * Allocate enough pages to cover @size from the page level
 * allocator and map them into contiguous kernel virtual space.
 *
 * For tight control over page level allocator and protection flags
 * use __vmalloc() instead.
 *
 * Return: pointer to the allocated memory or %NULL on error
 */
void *vmalloc_noprof(unsigned long size)
{
	return __vmalloc_node_noprof(size, 1, GFP_KERNEL, NUMA_NO_NODE,
				__builtin_return_address(0));
}
EXPORT_SYMBOL(vmalloc_noprof);

/**
 * vmalloc_huge_node - allocate virtually contiguous memory, allow huge pages
 * @size:      allocation size
 * @gfp_mask:  flags for the page level allocator
 * @node:	    node to use for allocation or NUMA_NO_NODE
 *
 * Allocate enough pages to cover @size from the page level
 * allocator and map them into contiguous kernel virtual space.
 * If @size is greater than or equal to PMD_SIZE, allow using
 * huge pages for the memory
 *
 * Return: pointer to the allocated memory or %NULL on error
 */
void *vmalloc_huge_node_noprof(unsigned long size, gfp_t gfp_mask, int node)
{
	if (unlikely(gfp_mask & ~GFP_VMALLOC_SUPPORTED))
		gfp_mask = vmalloc_fix_flags(gfp_mask);
	return __vmalloc_node_range_noprof(size, 1, VMALLOC_START, VMALLOC_END,
					   gfp_mask, PAGE_KERNEL, VM_ALLOW_HUGE_VMAP,
					   node, __builtin_return_address(0));
}
EXPORT_SYMBOL_GPL(vmalloc_huge_node_noprof);

/**
 * vzalloc - allocate virtually contiguous memory with zero fill
 * @size:    allocation size
 *
 * Allocate enough pages to cover @size from the page level
 * allocator and map them into contiguous kernel virtual space.
 * The memory allocated is set to zero.
 *
 * For tight control over page level allocator and protection flags
 * use __vmalloc() instead.
 *
 * Return: pointer to the allocated memory or %NULL on error
 */
void *vzalloc_noprof(unsigned long size)
{
	return __vmalloc_node_noprof(size, 1, GFP_KERNEL | __GFP_ZERO, NUMA_NO_NODE,
				__builtin_return_address(0));
}
EXPORT_SYMBOL(vzalloc_noprof);

/**
 * vmalloc_user - allocate zeroed virtually contiguous memory for userspace
 * @size: allocation size
 *
 * The resulting memory area is zeroed so it can be mapped to userspace
 * without leaking data.
 *
 * Return: pointer to the allocated memory or %NULL on error
 */
void *vmalloc_user_noprof(unsigned long size)
{
	return __vmalloc_node_range_noprof(size, SHMLBA,  VMALLOC_START, VMALLOC_END,
				    GFP_KERNEL | __GFP_ZERO, PAGE_KERNEL,
				    VM_USERMAP, NUMA_NO_NODE,
				    __builtin_return_address(0));
}
EXPORT_SYMBOL(vmalloc_user_noprof);

/**
 * vmalloc_node - allocate memory on a specific node
 * @size:	  allocation size
 * @node:	  numa node
 *
 * Allocate enough pages to cover @size from the page level
 * allocator and map them into contiguous kernel virtual space.
 *
 * For tight control over page level allocator and protection flags
 * use __vmalloc() instead.
 *
 * Return: pointer to the allocated memory or %NULL on error
 */
void *vmalloc_node_noprof(unsigned long size, int node)
{
	return __vmalloc_node_noprof(size, 1, GFP_KERNEL, node,
			__builtin_return_address(0));
}
EXPORT_SYMBOL(vmalloc_node_noprof);

/**
 * vzalloc_node - allocate memory on a specific node with zero fill
 * @size:	allocation size
 * @node:	numa node
 *
 * Allocate enough pages to cover @size from the page level
 * allocator and map them into contiguous kernel virtual space.
 * The memory allocated is set to zero.
 *
 * Return: pointer to the allocated memory or %NULL on error
 */
void *vzalloc_node_noprof(unsigned long size, int node)
{
	return __vmalloc_node_noprof(size, 1, GFP_KERNEL | __GFP_ZERO, node,
				__builtin_return_address(0));
}
EXPORT_SYMBOL(vzalloc_node_noprof);

/**
 * vrealloc_node_align - 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_XXX(). If @size
 * is 0 and @p is not a %NULL pointer, the object pointed to is freed.
 *
 * If the caller wants the new memory to be on specific node *only*,
 * __GFP_THISNODE flag should be set, otherwise the function will try to avoid
 * reallocation and possibly disregard the specified @nid.
 *
 * 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.
 *
 * Requesting an alignment that is bigger than the alignment of the existing
 * allocation will fail.
 *
 * In any case, the contents of the object pointed to are preserved up to the
 * lesser of the new and old sizes.
 *
 * This function must not be called concurrently with itself or vfree() for the
 * same memory allocation.
 *
 * Return: pointer to the allocated memory; %NULL if @size is zero or in case of
 *         failure
 */
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;
	size_t old_size = 0;
	void *n;

	if (!size) {
		vfree(p);
		return NULL;
	}

	if (p) {
		vm = find_vm_area(p);
		if (unlikely(!vm)) {
			WARN(1, "Trying to vrealloc() nonexistent vm area (%p)\n", p);
			return NULL;
		}

		alloced_size = get_vm_area_size(vm);
		old_size = vm->requested_size;
		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;
	} else {
		/*
		 * If p is NULL, vrealloc behaves exactly like vmalloc.
		 * Skip the shrink and in-place grow paths.
		 */
		goto need_realloc;
	}

	if (size <= old_size) {
		unsigned int new_nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT;

		/* Zero out "freed" memory, potentially for future realloc. */
		if (want_init_on_free() || want_init_on_alloc(flags))
			memset((void *)p + size, 0, old_size - size);

		/*
		 * Free tail pages when shrink crosses a page boundary.
		 *
		 * Skip huge page allocations (page_order > 0) as partial
		 * freeing would require splitting.
		 *
		 * Skip VM_FLUSH_RESET_PERMS, as direct-map permissions must
		 * be reset before pages are returned to the allocator.
		 *
		 * Skip VM_USERMAP, as remap_vmalloc_range_partial() validates
		 * mapping requests against the unchanged vm->size; freeing
		 * tail pages would cause vmalloc_to_page() to return NULL for
		 * the unmapped range.
		 *
		 * Skip if either GFP_NOFS or GFP_NOIO are used.
		 * kmemleak_free_part() internally allocates with
		 * GFP_KERNEL, which could trigger a recursive deadlock
		 * if we are under filesystem or I/O reclaim.
		 */
		if (new_nr_pages < vm->nr_pages && !vm_area_page_order(vm) &&
		    !(vm->flags & (VM_FLUSH_RESET_PERMS | VM_USERMAP)) &&
		    gfp_has_io_fs(flags)) {
			unsigned long addr = (unsigned long)kasan_reset_tag(p);
			unsigned int old_nr_pages = vm->nr_pages;

			/*
			 * Use the node lock to synchronize with concurrent
			 * readers (vmalloc_info_show).
			 */
			struct vmap_node *vn = addr_to_node(addr);

			spin_lock(&vn->busy.lock);
			vm->nr_pages = new_nr_pages;
			spin_unlock(&vn->busy.lock);

			/* Notify kmemleak of the reduced allocation size before unmapping. */
			kmemleak_free_part(
				(void *)addr + ((unsigned long)new_nr_pages
						<< PAGE_SHIFT),
				(unsigned long)(old_nr_pages - new_nr_pages)
					<< PAGE_SHIFT);

			vunmap_range(addr + ((unsigned long)new_nr_pages
					     << PAGE_SHIFT),
				     addr + ((unsigned long)old_nr_pages
					     << PAGE_SHIFT));

			vm_area_free_pages(vm, new_nr_pages, old_nr_pages);
		}
		vm->requested_size = size;
		kasan_vrealloc(p, old_size, size);
		return (void *)p;
	}

	/*
	 * We already have the bytes available in the allocation; use them.
	 */
	if (size <= vm->nr_pages << PAGE_SHIFT) {
		/*
		 * No need to zero memory here, as unused memory will have
		 * already been zeroed at initial allocation time or during
		 * realloc shrink time.
		 */
		vm->requested_size = size;
		kasan_vrealloc(p, old_size, size);
		return (void *)p;
	}

need_realloc:
	/* TODO: Grow the vm_area, i.e. allocate and map additional pages. */
	n = __vmalloc_node_noprof(size, align, flags, nid, __builtin_return_address(0));

	if (!n)
		return NULL;

	if (p) {
		memcpy(n, p, min(size, old_size));
		vfree(p);
	}

	return n;
}
EXPORT_SYMBOL(vrealloc_node_align_noprof);

#if defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA32)
#define GFP_VMALLOC32 (GFP_DMA32 | GFP_KERNEL)
#elif defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA)
#define GFP_VMALLOC32 (GFP_DMA | GFP_KERNEL)
#else
/*
 * 64b systems should always have either DMA or DMA32 zones. For others
 * GFP_DMA32 should do the right thing and use the normal zone.
 */
#define GFP_VMALLOC32 (GFP_DMA32 | GFP_KERNEL)
#endif

/**
 * vmalloc_32 - allocate virtually contiguous memory (32bit addressable)
 * @size:	allocation size
 *
 * Allocate enough 32bit PA addressable pages to cover @size from the
 * page level allocator and map them into contiguous kernel virtual space.
 *
 * Return: pointer to the allocated memory or %NULL on error
 */
void *vmalloc_32_noprof(unsigned long size)
{
	return __vmalloc_node_noprof(size, 1, GFP_VMALLOC32, NUMA_NO_NODE,
			__builtin_return_address(0));
}
EXPORT_SYMBOL(vmalloc_32_noprof);

/**
 * vmalloc_32_user - allocate zeroed virtually contiguous 32bit memory
 * @size:	     allocation size
 *
 * The resulting memory area is 32bit addressable and zeroed so it can be
 * mapped to userspace without leaking data.
 *
 * Return: pointer to the allocated memory or %NULL on error
 */
void *vmalloc_32_user_noprof(unsigned long size)
{
	return __vmalloc_node_range_noprof(size, SHMLBA,  VMALLOC_START, VMALLOC_END,
				    GFP_VMALLOC32 | __GFP_ZERO, PAGE_KERNEL,
				    VM_USERMAP, NUMA_NO_NODE,
				    __builtin_return_address(0));
}
EXPORT_SYMBOL(vmalloc_32_user_noprof);

/*
 * Atomically zero bytes in the iterator.
 *
 * Returns the number of zeroed bytes.
 */
static size_t zero_iter(struct iov_iter *iter, size_t count)
{
	size_t remains = count;

	while (remains > 0) {
		size_t num, copied;

		num = min_t(size_t, remains, PAGE_SIZE);
		copied = copy_page_to_iter_nofault(ZERO_PAGE(0), 0, num, iter);
		remains -= copied;

		if (copied < num)
			break;
	}

	return count - remains;
}

/*
 * small helper routine, copy contents to iter from addr.
 * If the page is not present, fill zero.
 *
 * Returns the number of copied bytes.
 */
static size_t aligned_vread_iter(struct iov_iter *iter,
				 const char *addr, size_t count)
{
	size_t remains = count;
	struct page *page;

	while (remains > 0) {
		unsigned long offset, length;
		size_t copied = 0;

		offset = offset_in_page(addr);
		length = PAGE_SIZE - offset;
		if (length > remains)
			length = remains;
		page = vmalloc_to_page(addr);
		/*
		 * To do safe access to this _mapped_ area, we need lock. But
		 * adding lock here means that we need to add overhead of
		 * vmalloc()/vfree() calls for this _debug_ interface, rarely
		 * used. Instead of that, we'll use an local mapping via
		 * copy_page_to_iter_nofault() and accept a small overhead in
		 * this access function.
		 */
		if (page)
			copied = copy_page_to_iter_nofault(page, offset,
							   length, iter);
		else
			copied = zero_iter(iter, length);

		addr += copied;
		remains -= copied;

		if (copied != length)
			break;
	}

	return count - remains;
}

/*
 * Read from a vm_map_ram region of memory.
 *
 * Returns the number of copied bytes.
 */
static size_t vmap_ram_vread_iter(struct iov_iter *iter, const char *addr,
				  size_t count, unsigned long flags)
{
	char *start;
	struct vmap_block *vb;
	struct xarray *xa;
	unsigned long offset;
	unsigned int rs, re;
	size_t remains, n;

	/*
	 * If it's area created by vm_map_ram() interface directly, but
	 * not further subdividing and delegating management to vmap_block,
	 * handle it here.
	 */
	if (!(flags & VMAP_BLOCK))
		return aligned_vread_iter(iter, addr, count);

	remains = count;

	/*
	 * Area is split into regions and tracked with vmap_block, read out
	 * each region and zero fill the hole between regions.
	 */
	xa = addr_to_vb_xa((unsigned long) addr);
	vb = xa_load(xa, addr_to_vb_idx((unsigned long)addr));
	if (!vb)
		goto finished_zero;

	spin_lock(&vb->lock);
	if (bitmap_empty(vb->used_map, VMAP_BBMAP_BITS)) {
		spin_unlock(&vb->lock);
		goto finished_zero;
	}

	for_each_set_bitrange(rs, re, vb->used_map, VMAP_BBMAP_BITS) {
		size_t copied;

		if (remains == 0)
			goto finished;

		start = vmap_block_vaddr(vb->va->va_start, rs);

		if (addr < start) {
			size_t to_zero = min_t(size_t, start - addr, remains);
			size_t zeroed = zero_iter(iter, to_zero);

			addr += zeroed;
			remains -= zeroed;

			if (remains == 0 || zeroed != to_zero)
				goto finished;
		}

		/*it could start reading from the middle of used region*/
		offset = offset_in_page(addr);
		n = ((re - rs + 1) << PAGE_SHIFT) - offset;
		if (n > remains)
			n = remains;

		copied = aligned_vread_iter(iter, start + offset, n);

		addr += copied;
		remains -= copied;

		if (copied != n)
			goto finished;
	}

	spin_unlock(&vb->lock);

finished_zero:
	/* zero-fill the left dirty or free regions */
	return count - remains + zero_iter(iter, remains);
finished:
	/* We couldn't copy/zero everything */
	spin_unlock(&vb->lock);
	return count - remains;
}

/**
 * vread_iter() - read vmalloc area in a safe way to an iterator.
 * @iter:         the iterator to which data should be written.
 * @addr:         vm address.
 * @count:        number of bytes to be read.
 *
 * This function checks that addr is a valid vmalloc'ed area, and
 * copies data from that area to a given iterator. If the given memory range
 * of [addr...addr+count) includes some valid address, data is copied to
 * proper area of @iter. If there are memory holes, they'll be zero-filled.
 * IOREMAP area is treated as memory hole and no copy is done.
 *
 * If [addr...addr+count) doesn't includes any intersects with alive
 * vm_struct area, returns 0.
 *
 * Note: In usual ops, vread_iter() is never necessary because the caller
 * should know vmalloc() area is valid and can use memcpy().
 * This is for routines which have to access vmalloc area without
 * any information, as /proc/kcore.
 *
 * Return: number of bytes for which addr and iter should be advanced
 * (same number as @count) or %0 if [addr...addr+count) doesn't
 * include any intersection with valid vmalloc area
 */
long vread_iter(struct iov_iter *iter, const char *addr, size_t count)
{
	struct vmap_node *vn;
	struct vmap_area *va;
	struct vm_struct *vm;
	char *vaddr;
	size_t n, size, flags, remains;
	unsigned long next;

	addr = kasan_reset_tag(addr);

	/* Don't allow overflow */
	if ((unsigned long) addr + count < count)
		count = -(unsigned long) addr;

	remains = count;

	vn = find_vmap_area_exceed_addr_lock((unsigned long) addr, &va);
	if (!vn)
		goto finished_zero;

	/* no intersects with alive vmap_area */
	if ((unsigned long)addr + remains <= va->va_start)
		goto finished_zero;

	do {
		size_t copied;

		if (remains == 0)
			goto finished;

		vm = va->vm;
		flags = va->flags & VMAP_FLAGS_MASK;
		/*
		 * VMAP_BLOCK indicates a sub-type of vm_map_ram area, need
		 * be set together with VMAP_RAM.
		 */
		WARN_ON(flags == VMAP_BLOCK);

		if (!vm && !flags)
			goto next_va;

		if (vm && (vm->flags & VM_UNINITIALIZED))
			goto next_va;

		/* Pair with smp_wmb() in clear_vm_uninitialized_flag() */
		smp_rmb();

		vaddr = (char *) va->va_start;
		if (vm)
			/*
			 * For VM_ALLOC areas, use nr_pages rather than
			 * get_vm_area_size() because vrealloc() may shrink
			 * the mapping without updating area->size. Other
			 * mapping types (vmap, ioremap) don't set nr_pages.
			 */
			size = (vm->flags & VM_ALLOC && vm->nr_pages) ?
				       (vm->nr_pages << PAGE_SHIFT) :
				       get_vm_area_size(vm);
		else
			size = va_size(va);

		if (addr >= vaddr + size)
			goto next_va;

		if (addr < vaddr) {
			size_t to_zero = min_t(size_t, vaddr - addr, remains);
			size_t zeroed = zero_iter(iter, to_zero);

			addr += zeroed;
			remains -= zeroed;

			if (remains == 0 || zeroed != to_zero)
				goto finished;
		}

		n = vaddr + size - addr;
		if (n > remains)
			n = remains;

		if (flags & VMAP_RAM)
			copied = vmap_ram_vread_iter(iter, addr, n, flags);
		else if (!(vm && (vm->flags & (VM_IOREMAP | VM_SPARSE))))
			copied = aligned_vread_iter(iter, addr, n);
		else /* IOREMAP | SPARSE area is treated as memory hole */
			copied = zero_iter(iter, n);

		addr += copied;
		remains -= copied;

		if (copied != n)
			goto finished;

	next_va:
		next = va->va_end;
		spin_unlock(&vn->busy.lock);
	} while ((vn = find_vmap_area_exceed_addr_lock(next, &va)));

finished_zero:
	if (vn)
		spin_unlock(&vn->busy.lock);

	/* zero-fill memory holes */
	return count - remains + zero_iter(iter, remains);
finished:
	/* Nothing remains, or We couldn't copy/zero everything. */
	if (vn)
		spin_unlock(&vn->busy.lock);

	return count - remains;
}

/**
 * remap_vmalloc_range_partial - map vmalloc pages to userspace
 * @vma:		vma to cover
 * @uaddr:		target user address to start at
 * @kaddr:		virtual address of vmalloc kernel memory
 * @pgoff:		offset from @kaddr to start at
 * @size:		size of map area
 *
 * Returns:	0 for success, -Exxx on failure
 *
 * This function checks that @kaddr is a valid vmalloc'ed area,
 * and that it is big enough to cover the range starting at
 * @uaddr in @vma. Will return failure if that criteria isn't
 * met.
 *
 * Similar to remap_pfn_range() (see mm/memory.c)
 */
int remap_vmalloc_range_partial(struct vm_area_struct *vma, unsigned long uaddr,
				void *kaddr, unsigned long pgoff,
				unsigned long size)
{
	struct vm_struct *area;
	unsigned long off;
	unsigned long end_index;

	if (check_shl_overflow(pgoff, PAGE_SHIFT, &off))
		return -EINVAL;

	size = PAGE_ALIGN(size);

	if (!PAGE_ALIGNED(uaddr) || !PAGE_ALIGNED(kaddr))
		return -EINVAL;

	area = find_vm_area(kaddr);
	if (!area)
		return -EINVAL;

	if (!(area->flags & (VM_USERMAP | VM_DMA_COHERENT)))
		return -EINVAL;

	if (check_add_overflow(size, off, &end_index) ||
	    end_index > get_vm_area_size(area))
		return -EINVAL;
	kaddr += off;

	do {
		struct page *page = vmalloc_to_page(kaddr);
		int ret;

		ret = vm_insert_page(vma, uaddr, page);
		if (ret)
			return ret;

		uaddr += PAGE_SIZE;
		kaddr += PAGE_SIZE;
		size -= PAGE_SIZE;
	} while (size > 0);

	vm_flags_set(vma, VM_DONTEXPAND | VM_DONTDUMP);

	return 0;
}

/**
 * remap_vmalloc_range - map vmalloc pages to userspace
 * @vma:		vma to cover (map full range of vma)
 * @addr:		vmalloc memory
 * @pgoff:		number of pages into addr before first page to map
 *
 * Returns:	0 for success, -Exxx on failure
 *
 * This function checks that addr is a valid vmalloc'ed area, and
 * that it is big enough to cover the vma. Will return failure if
 * that criteria isn't met.
 *
 * Similar to remap_pfn_range() (see mm/memory.c)
 */
int remap_vmalloc_range(struct vm_area_struct *vma, void *addr,
						unsigned long pgoff)
{
	return remap_vmalloc_range_partial(vma, vma->vm_start,
					   addr, pgoff,
					   vma->vm_end - vma->vm_start);
}
EXPORT_SYMBOL(remap_vmalloc_range);

void free_vm_area(struct vm_struct *area)
{
	struct vm_struct *ret;
	ret = remove_vm_area(area->addr);
	BUG_ON(ret != area);
	kfree(area);
}
EXPORT_SYMBOL_GPL(free_vm_area);

#ifdef CONFIG_SMP
static struct vmap_area *node_to_va(struct rb_node *n)
{
	return rb_entry_safe(n, struct vmap_area, rb_node);
}

/**
 * pvm_find_va_enclose_addr - find the vmap_area @addr belongs to
 * @addr: target address
 *
 * Returns: vmap_area if it is found. If there is no such area
 *   the first highest(reverse order) vmap_area is returned
 *   i.e. va->va_start < addr && va->va_end < addr or NULL
 *   if there are no any areas before @addr.
 */
static struct vmap_area *
pvm_find_va_enclose_addr(unsigned long addr)
{
	struct vmap_area *va, *tmp;
	struct rb_node *n;

	n = free_vmap_area_root.rb_node;
	va = NULL;

	while (n) {
		tmp = rb_entry(n, struct vmap_area, rb_node);
		if (tmp->va_start <= addr) {
			va = tmp;
			if (tmp->va_end >= addr)
				break;

			n = n->rb_right;
		} else {
			n = n->rb_left;
		}
	}

	return va;
}

/**
 * pvm_determine_end_from_reverse - find the highest aligned address
 * of free block below VMALLOC_END
 * @va:
 *   in - the VA we start the search(reverse order);
 *   out - the VA with the highest aligned end address.
 * @align: alignment for required highest address
 *
 * Returns: determined end address within vmap_area
 */
static unsigned long
pvm_determine_end_from_reverse(struct vmap_area **va, unsigned long align)
{
	unsigned long vmalloc_end = VMALLOC_END & ~(align - 1);
	unsigned long addr;

	if (likely(*va)) {
		list_for_each_entry_from_reverse((*va),
				&free_vmap_area_list, list) {
			addr = min((*va)->va_end & ~(align - 1), vmalloc_end);
			if ((*va)->va_start < addr)
				return addr;
		}
	}

	return 0;
}

/**
 * pcpu_get_vm_areas - allocate vmalloc areas for percpu allocator
 * @offsets: array containing offset of each area
 * @sizes: array containing size of each area
 * @nr_vms: the number of areas to allocate
 * @align: alignment, all entries in @offsets and @sizes must be aligned to this
 * @gfp: allocation flags passed to the underlying memory allocator
 *
 * Returns: kmalloc'd vm_struct pointer array pointing to allocated
 *	    vm_structs on success, %NULL on failure
 *
 * Percpu allocator wants to use congruent vm areas so that it can
 * maintain the offsets among percpu areas.  This function allocates
 * congruent vmalloc areas for it. These areas tend to be scattered
 * pretty far, distance between two areas easily going up to gigabytes.
 * To avoid interacting with regular vmallocs, these areas are allocated
 * from top.
 *
 * Despite its complicated look, this allocator is rather simple. It
 * does everything top-down and scans free blocks from the end looking
 * for matching base. While scanning, if any of the areas do not fit the
 * base address is pulled down to fit the area. Scanning is repeated till
 * all the areas fit and then all necessary data structures are inserted
 * and the result is returned.
 */
struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets,
				     const size_t *sizes, int nr_vms,
				     size_t align, gfp_t gfp)
{
	const unsigned long vmalloc_start = ALIGN(VMALLOC_START, align);
	const unsigned long vmalloc_end = VMALLOC_END & ~(align - 1);
	struct vmap_area **vas, *va;
	struct vm_struct **vms;
	int area, area2, last_area, term_area;
	unsigned long base, start, size, end, last_end, orig_start, orig_end;
	bool purged = false;

	/* verify parameters and allocate data structures */
	BUG_ON(offset_in_page(align) || !is_power_of_2(align));
	for (last_area = 0, area = 0; area < nr_vms; area++) {
		start = offsets[area];
		end = start + sizes[area];

		/* is everything aligned properly? */
		BUG_ON(!IS_ALIGNED(offsets[area], align));
		BUG_ON(!IS_ALIGNED(sizes[area], align));

		/* detect the area with the highest address */
		if (start > offsets[last_area])
			last_area = area;

		for (area2 = area + 1; area2 < nr_vms; area2++) {
			unsigned long start2 = offsets[area2];
			unsigned long end2 = start2 + sizes[area2];

			BUG_ON(start2 < end && start < end2);
		}
	}
	last_end = offsets[last_area] + sizes[last_area];

	if (vmalloc_end - vmalloc_start < last_end) {
		WARN_ON(true);
		return NULL;
	}

	vms = kzalloc_objs(vms[0], nr_vms, gfp);
	vas = kzalloc_objs(vas[0], nr_vms, gfp);
	if (!vas || !vms)
		goto err_free2;

	for (area = 0; area < nr_vms; area++) {
		vas[area] = kmem_cache_zalloc(vmap_area_cachep, gfp);
		vms[area] = kzalloc_obj(struct vm_struct, gfp);
		if (!vas[area] || !vms[area])
			goto err_free;
	}
retry:
	spin_lock(&free_vmap_area_lock);

	/* start scanning - we scan from the top, begin with the last area */
	area = term_area = last_area;
	start = offsets[area];
	end = start + sizes[area];

	va = pvm_find_va_enclose_addr(vmalloc_end);
	base = pvm_determine_end_from_reverse(&va, align) - end;

	while (true) {
		/*
		 * base might have underflowed, add last_end before
		 * comparing.
		 */
		if (base + last_end < vmalloc_start + last_end)
			goto overflow;

		/*
		 * Fitting base has not been found.
		 */
		if (va == NULL)
			goto overflow;

		/*
		 * If required width exceeds current VA block, move
		 * base downwards and then recheck.
		 */
		if (base + end > va->va_end) {
			base = pvm_determine_end_from_reverse(&va, align) - end;
			term_area = area;
			continue;
		}

		/*
		 * If this VA does not fit, move base downwards and recheck.
		 */
		if (base + start < va->va_start) {
			va = node_to_va(rb_prev(&va->rb_node));
			base = pvm_determine_end_from_reverse(&va, align) - end;
			term_area = area;
			continue;
		}

		/*
		 * This area fits, move on to the previous one.  If
		 * the previous one is the terminal one, we're done.
		 */
		area = (area + nr_vms - 1) % nr_vms;
		if (area == term_area)
			break;

		start = offsets[area];
		end = start + sizes[area];
		va = pvm_find_va_enclose_addr(base + end);
	}

	/* we've found a fitting base, insert all va's */
	for (area = 0; area < nr_vms; area++) {
		int ret;

		start = base + offsets[area];
		size = sizes[area];

		va = pvm_find_va_enclose_addr(start);
		if (WARN_ON_ONCE(va == NULL))
			/* It is a BUG(), but trigger recovery instead. */
			goto recovery;

		ret = va_clip(&free_vmap_area_root,
			&free_vmap_area_list, va, start, size);
		if (WARN_ON_ONCE(unlikely(ret)))
			/* It is a BUG(), but trigger recovery instead. */
			goto recovery;

		/* Allocated area. */
		va = vas[area];
		va->va_start = start;
		va->va_end = start + size;
	}

	spin_unlock(&free_vmap_area_lock);

	/* populate the kasan shadow space */
	for (area = 0; area < nr_vms; area++) {
		if (kasan_populate_vmalloc(vas[area]->va_start, sizes[area], gfp))
			goto err_free_shadow;
	}

	/* insert all vm's */
	for (area = 0; area < nr_vms; area++) {
		struct vmap_node *vn = addr_to_node(vas[area]->va_start);

		spin_lock(&vn->busy.lock);
		insert_vmap_area(vas[area], &vn->busy.root, &vn->busy.head);
		setup_vmalloc_vm(vms[area], vas[area], VM_ALLOC,
				 pcpu_get_vm_areas);
		spin_unlock(&vn->busy.lock);
	}

	/*
	 * Mark allocated areas as accessible. Do it now as a best-effort
	 * approach, as they can be mapped outside of vmalloc code.
	 * With hardware tag-based KASAN, marking is skipped for
	 * non-VM_ALLOC mappings, see __kasan_unpoison_vmalloc().
	 */
	kasan_unpoison_vmap_areas(vms, nr_vms, KASAN_VMALLOC_PROT_NORMAL);

	kfree(vas);
	return vms;

recovery:
	/*
	 * Remove previously allocated areas. There is no
	 * need in removing these areas from the busy tree,
	 * because they are inserted only on the final step
	 * and when pcpu_get_vm_areas() is success.
	 */
	while (area--) {
		orig_start = vas[area]->va_start;
		orig_end = vas[area]->va_end;
		va = merge_or_add_vmap_area_augment(vas[area], &free_vmap_area_root,
				&free_vmap_area_list);
		if (va)
			kasan_release_vmalloc(orig_start, orig_end,
				va->va_start, va->va_end,
				KASAN_VMALLOC_PAGE_RANGE | KASAN_VMALLOC_TLB_FLUSH);
		vas[area] = NULL;
	}

overflow:
	spin_unlock(&free_vmap_area_lock);
	if (!purged) {
		reclaim_and_purge_vmap_areas();
		purged = true;

		/* Before "retry", check if we recover. */
		for (area = 0; area < nr_vms; area++) {
			if (vas[area])
				continue;

			vas[area] = kmem_cache_zalloc(
				vmap_area_cachep, gfp);
			if (!vas[area])
				goto err_free;
		}

		goto retry;
	}

err_free:
	for (area = 0; area < nr_vms; area++) {
		if (vas[area])
			kmem_cache_free(vmap_area_cachep, vas[area]);

		kfree(vms[area]);
	}
err_free2:
	kfree(vas);
	kfree(vms);
	return NULL;

err_free_shadow:
	spin_lock(&free_vmap_area_lock);
	/*
	 * We release all the vmalloc shadows, even the ones for regions that
	 * hadn't been successfully added. This relies on kasan_release_vmalloc
	 * being able to tolerate this case.
	 */
	for (area = 0; area < nr_vms; area++) {
		orig_start = vas[area]->va_start;
		orig_end = vas[area]->va_end;
		va = merge_or_add_vmap_area_augment(vas[area], &free_vmap_area_root,
				&free_vmap_area_list);
		if (va)
			kasan_release_vmalloc(orig_start, orig_end,
				va->va_start, va->va_end,
				KASAN_VMALLOC_PAGE_RANGE | KASAN_VMALLOC_TLB_FLUSH);
		vas[area] = NULL;
		kfree(vms[area]);
	}
	spin_unlock(&free_vmap_area_lock);
	goto err_free2;
}

/**
 * pcpu_free_vm_areas - free vmalloc areas for percpu allocator
 * @vms: vm_struct pointer array returned by pcpu_get_vm_areas()
 * @nr_vms: the number of allocated areas
 *
 * Free vm_structs and the array allocated by pcpu_get_vm_areas().
 */
void pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms)
{
	int i;

	for (i = 0; i < nr_vms; i++)
		free_vm_area(vms[i]);
	kfree(vms);
}
#endif	/* CONFIG_SMP */

#ifdef CONFIG_PRINTK
bool vmalloc_dump_obj(void *object)
{
	const void *caller;
	struct vm_struct *vm;
	struct vmap_area *va;
	struct vmap_node *vn;
	unsigned long addr;
	unsigned int nr_pages;

	addr = PAGE_ALIGN((unsigned long) object);
	vn = addr_to_node(addr);

	if (!spin_trylock(&vn->busy.lock))
		return false;

	va = __find_vmap_area(addr, &vn->busy.root);
	if (!va || !va->vm) {
		spin_unlock(&vn->busy.lock);
		return false;
	}

	vm = va->vm;
	addr = (unsigned long) vm->addr;
	caller = vm->caller;
	nr_pages = vm->nr_pages;
	spin_unlock(&vn->busy.lock);

	pr_cont(" %u-page vmalloc region starting at %#lx allocated at %pS\n",
		nr_pages, addr, caller);

	return true;
}
#endif

#ifdef CONFIG_PROC_FS

/*
 * Print number of pages allocated on each memory node.
 *
 * This function can only be called if CONFIG_NUMA is enabled
 * and VM_UNINITIALIZED bit in v->flags is disabled.
 */
static void show_numa_info(struct seq_file *m, struct vm_struct *v,
				 unsigned int *counters)
{
	unsigned int nr;
	unsigned int step = 1U << vm_area_page_order(v);

	if (!counters)
		return;

	memset(counters, 0, nr_node_ids * sizeof(unsigned int));

	for (nr = 0; nr < v->nr_pages; nr += step)
		counters[page_to_nid(v->pages[nr])] += step;
	for_each_node_state(nr, N_HIGH_MEMORY)
		if (counters[nr])
			seq_printf(m, " N%u=%u", nr, counters[nr]);
}

static void show_purge_info(struct seq_file *m)
{
	struct vmap_node *vn;
	struct vmap_area *va;

	for_each_vmap_node(vn) {
		spin_lock(&vn->lazy.lock);
		list_for_each_entry(va, &vn->lazy.head, list) {
			seq_printf(m, "0x%pK-0x%pK %7ld unpurged vm_area\n",
				(void *)va->va_start, (void *)va->va_end,
				va_size(va));
		}
		spin_unlock(&vn->lazy.lock);
	}
}

static int vmalloc_info_show(struct seq_file *m, void *p)
{
	struct vmap_node *vn;
	struct vmap_area *va;
	struct vm_struct *v;
	unsigned int *counters;

	if (IS_ENABLED(CONFIG_NUMA))
		counters = kmalloc_array(nr_node_ids, sizeof(unsigned int), GFP_KERNEL);

	for_each_vmap_node(vn) {
		spin_lock(&vn->busy.lock);
		list_for_each_entry(va, &vn->busy.head, list) {
			if (!va->vm) {
				if (va->flags & VMAP_RAM)
					seq_printf(m, "0x%pK-0x%pK %7ld vm_map_ram\n",
						(void *)va->va_start, (void *)va->va_end,
						va_size(va));

				continue;
			}

			v = va->vm;
			if (v->flags & VM_UNINITIALIZED)
				continue;

			/* Pair with smp_wmb() in clear_vm_uninitialized_flag() */
			smp_rmb();

			seq_printf(m, "0x%pK-0x%pK %7ld",
				v->addr, v->addr + v->size, v->size);

			if (v->caller)
				seq_printf(m, " %pS", v->caller);

			if (v->nr_pages)
				seq_printf(m, " pages=%d", v->nr_pages);

			if (v->phys_addr)
				seq_printf(m, " phys=%pa", &v->phys_addr);

			if (v->flags & VM_IOREMAP)
				seq_puts(m, " ioremap");

			if (v->flags & VM_SPARSE)
				seq_puts(m, " sparse");

			if (v->flags & VM_ALLOC)
				seq_puts(m, " vmalloc");

			if (v->flags & VM_MAP)
				seq_puts(m, " vmap");

			if (v->flags & VM_USERMAP)
				seq_puts(m, " user");

			if (v->flags & VM_DMA_COHERENT)
				seq_puts(m, " dma-coherent");

			if (is_vmalloc_addr(v->pages))
				seq_puts(m, " vpages");

			if (IS_ENABLED(CONFIG_NUMA))
				show_numa_info(m, v, counters);

			seq_putc(m, '\n');
		}
		spin_unlock(&vn->busy.lock);
	}

	/*
	 * As a final step, dump "unpurged" areas.
	 */
	show_purge_info(m);
	if (IS_ENABLED(CONFIG_NUMA))
		kfree(counters);
	return 0;
}

static int __init proc_vmalloc_init(void)
{
	proc_create_single("vmallocinfo", 0400, NULL, vmalloc_info_show);
	return 0;
}
module_init(proc_vmalloc_init);

#endif

static void __init vmap_init_free_space(void)
{
	unsigned long vmap_start = 1;
	const unsigned long vmap_end = ULONG_MAX;
	struct vmap_area *free;
	struct vm_struct *busy;

	/*
	 *     B     F     B     B     B     F
	 * -|-----|.....|-----|-----|-----|.....|-
	 *  |           The KVA space           |
	 *  |<--------------------------------->|
	 */
	for (busy = vmlist; busy; busy = busy->next) {
		if ((unsigned long) busy->addr - vmap_start > 0) {
			free = kmem_cache_zalloc(vmap_area_cachep, GFP_NOWAIT);
			if (!WARN_ON_ONCE(!free)) {
				free->va_start = vmap_start;
				free->va_end = (unsigned long) busy->addr;

				insert_vmap_area_augment(free, NULL,
					&free_vmap_area_root,
						&free_vmap_area_list);
			}
		}

		vmap_start = (unsigned long) busy->addr + busy->size;
	}

	if (vmap_end - vmap_start > 0) {
		free = kmem_cache_zalloc(vmap_area_cachep, GFP_NOWAIT);
		if (!WARN_ON_ONCE(!free)) {
			free->va_start = vmap_start;
			free->va_end = vmap_end;

			insert_vmap_area_augment(free, NULL,
				&free_vmap_area_root,
					&free_vmap_area_list);
		}
	}
}

static void vmap_init_nodes(void)
{
	struct vmap_node *vn;
	int i;

#if BITS_PER_LONG == 64
	/*
	 * A high threshold of max nodes is fixed and bound to 128,
	 * thus a scale factor is 1 for systems where number of cores
	 * are less or equal to specified threshold.
	 *
	 * As for NUMA-aware notes. For bigger systems, for example
	 * NUMA with multi-sockets, where we can end-up with thousands
	 * of cores in total, a "sub-numa-clustering" should be added.
	 *
	 * In this case a NUMA domain is considered as a single entity
	 * with dedicated sub-nodes in it which describe one group or
	 * set of cores. Therefore a per-domain purging is supposed to
	 * be added as well as a per-domain balancing.
	 */
	int n = clamp_t(unsigned int, num_possible_cpus(), 1, 128);

	if (n > 1) {
		vn = kmalloc_objs(*vn, n, GFP_NOWAIT);
		if (vn) {
			/* Node partition is 16 pages. */
			vmap_zone_size = (1 << 4) * PAGE_SIZE;
			nr_vmap_nodes = n;
			vmap_nodes = vn;
		} else {
			pr_err("Failed to allocate an array. Disable a node layer\n");
		}
	}
#endif

	for_each_vmap_node(vn) {
		vn->busy.root = RB_ROOT;
		INIT_LIST_HEAD(&vn->busy.head);
		spin_lock_init(&vn->busy.lock);

		vn->lazy.root = RB_ROOT;
		INIT_LIST_HEAD(&vn->lazy.head);
		spin_lock_init(&vn->lazy.lock);

		for (i = 0; i < MAX_VA_SIZE_PAGES; i++) {
			INIT_LIST_HEAD(&vn->pool[i].head);
			WRITE_ONCE(vn->pool[i].len, 0);
		}

		spin_lock_init(&vn->pool_lock);
	}
}

static unsigned long
vmap_node_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
{
	unsigned long count = 0;
	struct vmap_node *vn;
	int i;

	for_each_vmap_node(vn) {
		for (i = 0; i < MAX_VA_SIZE_PAGES; i++)
			count += READ_ONCE(vn->pool[i].len);
	}

	return count ? count : SHRINK_EMPTY;
}

static unsigned long
vmap_node_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
{
	struct vmap_node *vn;

	guard(mutex)(&vmap_purge_lock);
	for_each_vmap_node(vn)
		decay_va_pool_node(vn, true);

	return SHRINK_STOP;
}

void __init vmalloc_init(void)
{
	struct shrinker *vmap_node_shrinker;
	struct vmap_area *va;
	struct vmap_node *vn;
	struct vm_struct *tmp;
	int i;

	/*
	 * Create the cache for vmap_area objects.
	 */
	vmap_area_cachep = KMEM_CACHE(vmap_area, SLAB_PANIC);

	for_each_possible_cpu(i) {
		struct vmap_block_queue *vbq;
		struct vfree_deferred *p;

		vbq = &per_cpu(vmap_block_queue, i);
		spin_lock_init(&vbq->lock);
		INIT_LIST_HEAD(&vbq->free);
		p = &per_cpu(vfree_deferred, i);
		init_llist_head(&p->list);
		INIT_WORK(&p->wq, delayed_vfree_work);
		xa_init(&vbq->vmap_blocks);
	}

	/*
	 * Setup nodes before importing vmlist.
	 */
	vmap_init_nodes();

	/* Import existing vmlist entries. */
	for (tmp = vmlist; tmp; tmp = tmp->next) {
		va = kmem_cache_zalloc(vmap_area_cachep, GFP_NOWAIT);
		if (WARN_ON_ONCE(!va))
			continue;

		va->va_start = (unsigned long)tmp->addr;
		va->va_end = va->va_start + tmp->size;
		va->vm = tmp;

		vn = addr_to_node(va->va_start);
		insert_vmap_area(va, &vn->busy.root, &vn->busy.head);
	}

	/*
	 * Now we can initialize a free vmap space.
	 */
	vmap_init_free_space();
	vmap_initialized = true;

	vmap_node_shrinker = shrinker_alloc(0, "vmap-node");
	if (!vmap_node_shrinker) {
		pr_err("Failed to allocate vmap-node shrinker!\n");
		return;
	}

	vmap_node_shrinker->count_objects = vmap_node_shrink_count;
	vmap_node_shrinker->scan_objects = vmap_node_shrink_scan;
	shrinker_register(vmap_node_shrinker);
}