vmalloc.c

/*
 *  linux/mm/vmalloc.c
 *
 *  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
 */

#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/debugobjects.h>
#include <linux/kallsyms.h>
#include <linux/list.h>
#include <linux/notifier.h>
#include <linux/rbtree.h>
#include <linux/radix-tree.h>
#include <linux/rcupdate.h>
#include <linux/pfn.h>
#include <linux/kmemleak.h>
#include <linux/atomic.h>
#include <linux/compiler.h>
#include <linux/llist.h>
#include <linux/bitops.h>

#include <linux/uaccess.h>
#include <asm/tlbflush.h>
#include <asm/shmparam.h>

#include "internal.h"

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

static void __vunmap(const void *, int);

static void free_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))
		__vunmap((void *)llnode, 1);
}

/*** Page table manipulation functions ***/

static void vunmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end)
{
	pte_t *pte;

	pte = pte_offset_kernel(pmd, addr);
	do {
		pte_t ptent = ptep_get_and_clear(&init_mm, addr, pte);
		WARN_ON(!pte_none(ptent) && !pte_present(ptent));
	} while (pte++, addr += PAGE_SIZE, addr != end);
}

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

	pmd = pmd_offset(pud, addr);
	do {
		next = pmd_addr_end(addr, end);
		if (pmd_clear_huge(pmd))
			continue;
		if (pmd_none_or_clear_bad(pmd))
			continue;
		vunmap_pte_range(pmd, addr, next);
	} while (pmd++, addr = next, addr != end);
}

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

	pud = pud_offset(p4d, addr);
	do {
		next = pud_addr_end(addr, end);
		if (pud_clear_huge(pud))
			continue;
		if (pud_none_or_clear_bad(pud))
			continue;
		vunmap_pmd_range(pud, addr, next);
	} while (pud++, addr = next, addr != end);
}

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

	p4d = p4d_offset(pgd, addr);
	do {
		next = p4d_addr_end(addr, end);
		if (p4d_clear_huge(p4d))
			continue;
		if (p4d_none_or_clear_bad(p4d))
			continue;
		vunmap_pud_range(p4d, addr, next);
	} while (p4d++, addr = next, addr != end);
}

static void vunmap_page_range(unsigned long addr, unsigned long end)
{
	pgd_t *pgd;
	unsigned long next;

	BUG_ON(addr >= end);
	pgd = pgd_offset_k(addr);
	do {
		next = pgd_addr_end(addr, end);
		if (pgd_none_or_clear_bad(pgd))
			continue;
		vunmap_p4d_range(pgd, addr, next);
	} while (pgd++, addr = next, addr != end);
}

static int vmap_pte_range(pmd_t *pmd, unsigned long addr,
		unsigned long end, pgprot_t prot, struct page **pages, int *nr)
{
	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(pmd, addr);
	if (!pte)
		return -ENOMEM;
	do {
		struct page *page = pages[*nr];

		if (WARN_ON(!pte_none(*pte)))
			return -EBUSY;
		if (WARN_ON(!page))
			return -ENOMEM;
		set_pte_at(&init_mm, addr, pte, mk_pte(page, prot));
		(*nr)++;
	} while (pte++, addr += PAGE_SIZE, addr != end);
	return 0;
}

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

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

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

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

static int vmap_p4d_range(pgd_t *pgd, unsigned long addr,
		unsigned long end, pgprot_t prot, struct page **pages, int *nr)
{
	p4d_t *p4d;
	unsigned long next;

	p4d = p4d_alloc(&init_mm, pgd, addr);
	if (!p4d)
		return -ENOMEM;
	do {
		next = p4d_addr_end(addr, end);
		if (vmap_pud_range(p4d, addr, next, prot, pages, nr))
			return -ENOMEM;
	} while (p4d++, addr = next, addr != end);
	return 0;
}

/*
 * Set up page tables in kva (addr, end). The ptes shall have prot "prot", and
 * will have pfns corresponding to the "pages" array.
 *
 * Ie. pte at addr+N*PAGE_SIZE shall point to pfn corresponding to pages[N]
 */
static int vmap_page_range_noflush(unsigned long start, unsigned long end,
				   pgprot_t prot, struct page **pages)
{
	pgd_t *pgd;
	unsigned long next;
	unsigned long addr = start;
	int err = 0;
	int nr = 0;

	BUG_ON(addr >= end);
	pgd = pgd_offset_k(addr);
	do {
		next = pgd_addr_end(addr, end);
		err = vmap_p4d_range(pgd, addr, next, prot, pages, &nr);
		if (err)
			return err;
	} while (pgd++, addr = next, addr != end);

	return nr;
}

static int vmap_page_range(unsigned long start, unsigned long end,
			   pgprot_t prot, struct page **pages)
{
	int ret;

	ret = vmap_page_range_noflush(start, end, prot, pages);
	flush_cache_vmap(start, end);
	return ret;
}

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_MODULES) && defined(MODULES_VADDR)
	unsigned long addr = (unsigned long)x;
	if (addr >= MODULES_VADDR && addr < MODULES_END)
		return 1;
#endif
	return is_vmalloc_addr(x);
}

/*
 * Walk a vmap address to the struct page it maps.
 */
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;
	p4d = p4d_offset(pgd, addr);
	if (p4d_none(*p4d))
		return NULL;
	pud = pud_offset(p4d, addr);

	/*
	 * Don't dereference bad PUD or PMD (below) entries. This will also
	 * identify huge mappings, which we may encounter on architectures
	 * that define CONFIG_HAVE_ARCH_HUGE_VMAP=y. Such regions will be
	 * identified as vmalloc addresses by is_vmalloc_addr(), but are
	 * not [unambiguously] associated with a struct page, so there is
	 * no correct value to return for them.
	 */
	WARN_ON_ONCE(pud_bad(*pud));
	if (pud_none(*pud) || pud_bad(*pud))
		return NULL;
	pmd = pmd_offset(pud, addr);
	WARN_ON_ONCE(pmd_bad(*pmd));
	if (pmd_none(*pmd) || pmd_bad(*pmd))
		return NULL;

	ptep = pte_offset_map(pmd, addr);
	pte = *ptep;
	if (pte_present(pte))
		page = pte_page(pte);
	pte_unmap(ptep);
	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 VM_LAZY_FREE	0x02
#define VM_VM_AREA	0x04

static DEFINE_SPINLOCK(vmap_area_lock);
/* Export for kexec only */
LIST_HEAD(vmap_area_list);
static LLIST_HEAD(vmap_purge_list);
static struct rb_root vmap_area_root = RB_ROOT;

/* The vmap cache globals are protected by vmap_area_lock */
static struct rb_node *free_vmap_cache;
static unsigned long cached_hole_size;
static unsigned long cached_vstart;
static unsigned long cached_align;

static unsigned long vmap_area_pcpu_hole;

static struct vmap_area *__find_vmap_area(unsigned long addr)
{
	struct rb_node *n = vmap_area_root.rb_node;

	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;
}

static void __insert_vmap_area(struct vmap_area *va)
{
	struct rb_node **p = &vmap_area_root.rb_node;
	struct rb_node *parent = NULL;
	struct rb_node *tmp;

	while (*p) {
		struct vmap_area *tmp_va;

		parent = *p;
		tmp_va = rb_entry(parent, struct vmap_area, rb_node);
		if (va->va_start < tmp_va->va_end)
			p = &(*p)->rb_left;
		else if (va->va_end > tmp_va->va_start)
			p = &(*p)->rb_right;
		else
			BUG();
	}

	rb_link_node(&va->rb_node, parent, p);
	rb_insert_color(&va->rb_node, &vmap_area_root);

	/* address-sort this list */
	tmp = rb_prev(&va->rb_node);
	if (tmp) {
		struct vmap_area *prev;
		prev = rb_entry(tmp, struct vmap_area, rb_node);
		list_add_rcu(&va->list, &prev->list);
	} else
		list_add_rcu(&va->list, &vmap_area_list);
}

static void purge_vmap_area_lazy(void);

static BLOCKING_NOTIFIER_HEAD(vmap_notify_list);

/*
 * Allocate a region of KVA of the specified size and alignment, within the
 * vstart and vend.
 */
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)
{
	struct vmap_area *va;
	struct rb_node *n;
	unsigned long addr;
	int purged = 0;
	struct vmap_area *first;

	BUG_ON(!size);
	BUG_ON(offset_in_page(size));
	BUG_ON(!is_power_of_2(align));

	might_sleep();

	va = kmalloc_node(sizeof(struct vmap_area),
			gfp_mask & GFP_RECLAIM_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 & GFP_RECLAIM_MASK);

retry:
	spin_lock(&vmap_area_lock);
	/*
	 * Invalidate cache if we have more permissive parameters.
	 * cached_hole_size notes the largest hole noticed _below_
	 * the vmap_area cached in free_vmap_cache: if size fits
	 * into that hole, we want to scan from vstart to reuse
	 * the hole instead of allocating above free_vmap_cache.
	 * Note that __free_vmap_area may update free_vmap_cache
	 * without updating cached_hole_size or cached_align.
	 */
	if (!free_vmap_cache ||
			size < cached_hole_size ||
			vstart < cached_vstart ||
			align < cached_align) {
nocache:
		cached_hole_size = 0;
		free_vmap_cache = NULL;
	}
	/* record if we encounter less permissive parameters */
	cached_vstart = vstart;
	cached_align = align;

	/* find starting point for our search */
	if (free_vmap_cache) {
		first = rb_entry(free_vmap_cache, struct vmap_area, rb_node);
		addr = ALIGN(first->va_end, align);
		if (addr < vstart)
			goto nocache;
		if (addr + size < addr)
			goto overflow;

	} else {
		addr = ALIGN(vstart, align);
		if (addr + size < addr)
			goto overflow;

		n = vmap_area_root.rb_node;
		first = NULL;

		while (n) {
			struct vmap_area *tmp;
			tmp = rb_entry(n, struct vmap_area, rb_node);
			if (tmp->va_end >= addr) {
				first = tmp;
				if (tmp->va_start <= addr)
					break;
				n = n->rb_left;
			} else
				n = n->rb_right;
		}

		if (!first)
			goto found;
	}

	/* from the starting point, walk areas until a suitable hole is found */
	while (addr + size > first->va_start && addr + size <= vend) {
		if (addr + cached_hole_size < first->va_start)
			cached_hole_size = first->va_start - addr;
		addr = ALIGN(first->va_end, align);
		if (addr + size < addr)
			goto overflow;

		if (list_is_last(&first->list, &vmap_area_list))
			goto found;

		first = list_next_entry(first, list);
	}

found:
	if (addr + size > vend)
		goto overflow;

	va->va_start = addr;
	va->va_end = addr + size;
	va->flags = 0;
	__insert_vmap_area(va);
	free_vmap_cache = &va->rb_node;
	spin_unlock(&vmap_area_lock);

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

	return va;

overflow:
	spin_unlock(&vmap_area_lock);
	if (!purged) {
		purge_vmap_area_lazy();
		purged = 1;
		goto retry;
	}

	if (gfpflags_allow_blocking(gfp_mask)) {
		unsigned long 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("vmap allocation for size %lu failed: use vmalloc=<size> to increase size\n",
			size);
	kfree(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);

static void __free_vmap_area(struct vmap_area *va)
{
	BUG_ON(RB_EMPTY_NODE(&va->rb_node));

	if (free_vmap_cache) {
		if (va->va_end < cached_vstart) {
			free_vmap_cache = NULL;
		} else {
			struct vmap_area *cache;
			cache = rb_entry(free_vmap_cache, struct vmap_area, rb_node);
			if (va->va_start <= cache->va_start) {
				free_vmap_cache = rb_prev(&va->rb_node);
				/*
				 * We don't try to update cached_hole_size or
				 * cached_align, but it won't go very wrong.
				 */
			}
		}
	}
	rb_erase(&va->rb_node, &vmap_area_root);
	RB_CLEAR_NODE(&va->rb_node);
	list_del_rcu(&va->list);

	/*
	 * Track the highest possible candidate for pcpu area
	 * allocation.  Areas outside of vmalloc area can be returned
	 * here too, consider only end addresses which fall inside
	 * vmalloc area proper.
	 */
	if (va->va_end > VMALLOC_START && va->va_end <= VMALLOC_END)
		vmap_area_pcpu_hole = max(vmap_area_pcpu_hole, va->va_end);

	kfree_rcu(va, rcu_head);
}

/*
 * Free a region of KVA allocated by alloc_vmap_area
 */
static void free_vmap_area(struct vmap_area *va)
{
	spin_lock(&vmap_area_lock);
	__free_vmap_area(va);
	spin_unlock(&vmap_area_lock);
}

/*
 * Clear the pagetable entries of a given vmap_area
 */
static void unmap_vmap_area(struct vmap_area *va)
{
	vunmap_page_range(va->va_start, va->va_end);
}

/*
 * 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);
}

static atomic_t vmap_lazy_nr = ATOMIC_INIT(0);

/*
 * Serialize vmap purging.  There is no actual criticial section protected
 * by this look, 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);

/*
 * called before a call to iounmap() if the caller wants vm_area_struct's
 * immediately freed.
 */
void set_iounmap_nonlazy(void)
{
	atomic_set(&vmap_lazy_nr, lazy_max_pages()+1);
}

/*
 * Purges all lazily-freed vmap areas.
 */
static bool __purge_vmap_area_lazy(unsigned long start, unsigned long end)
{
	struct llist_node *valist;
	struct vmap_area *va;
	struct vmap_area *n_va;
	bool do_free = false;

	lockdep_assert_held(&vmap_purge_lock);

	valist = llist_del_all(&vmap_purge_list);
	llist_for_each_entry(va, valist, purge_list) {
		if (va->va_start < start)
			start = va->va_start;
		if (va->va_end > end)
			end = va->va_end;
		do_free = true;
	}

	if (!do_free)
		return false;

	flush_tlb_kernel_range(start, end);

	spin_lock(&vmap_area_lock);
	llist_for_each_entry_safe(va, n_va, valist, purge_list) {
		int nr = (va->va_end - va->va_start) >> PAGE_SHIFT;

		__free_vmap_area(va);
		atomic_sub(nr, &vmap_lazy_nr);
		cond_resched_lock(&vmap_area_lock);
	}
	spin_unlock(&vmap_area_lock);
	return true;
}

/*
 * Kick off a purge of the outstanding lazy areas. Don't bother if somebody
 * is already purging.
 */
static void try_purge_vmap_area_lazy(void)
{
	if (mutex_trylock(&vmap_purge_lock)) {
		__purge_vmap_area_lazy(ULONG_MAX, 0);
		mutex_unlock(&vmap_purge_lock);
	}
}

/*
 * Kick off a purge of the outstanding lazy areas.
 */
static void purge_vmap_area_lazy(void)
{
	mutex_lock(&vmap_purge_lock);
	purge_fragmented_blocks_allcpus();
	__purge_vmap_area_lazy(ULONG_MAX, 0);
	mutex_unlock(&vmap_purge_lock);
}

/*
 * Free a vmap area, caller ensuring that the area has been unmapped
 * and flush_cache_vunmap had been called for the correct range
 * previously.
 */
static void free_vmap_area_noflush(struct vmap_area *va)
{
	int nr_lazy;

	nr_lazy = atomic_add_return((va->va_end - va->va_start) >> PAGE_SHIFT,
				    &vmap_lazy_nr);

	/* After this point, we may free va at any time */
	llist_add(&va->purge_list, &vmap_purge_list);

	if (unlikely(nr_lazy > lazy_max_pages()))
		try_purge_vmap_area_lazy();
}

/*
 * 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);
	unmap_vmap_area(va);
	if (debug_pagealloc_enabled())
		flush_tlb_kernel_range(va->va_start, va->va_end);

	free_vmap_area_noflush(va);
}

static struct vmap_area *find_vmap_area(unsigned long addr)
{
	struct vmap_area *va;

	spin_lock(&vmap_area_lock);
	va = __find_vmap_area(addr);
	spin_unlock(&vmap_area_lock);

	return va;
}

/*** 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)

static bool vmap_initialized __read_mostly = false;

struct vmap_block_queue {
	spinlock_t lock;
	struct list_head free;
};

struct vmap_block {
	spinlock_t lock;
	struct vmap_area *va;
	unsigned long free, dirty;
	unsigned long dirty_min, dirty_max; /*< dirty range */
	struct list_head free_list;
	struct rcu_head rcu_head;
	struct list_head purge;
};

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

/*
 * Radix tree of vmap blocks, indexed by address, to quickly find a vmap block
 * in the free path. Could get rid of this if we change the API to return a
 * "cookie" from alloc, to be passed to free. But no big deal yet.
 */
static DEFINE_SPINLOCK(vmap_block_tree_lock);
static RADIX_TREE(vmap_block_tree, GFP_ATOMIC);

/*
 * 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
 *
 * Returns: 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;
	unsigned long vb_idx;
	int node, err;
	void *vaddr;

	node = numa_node_id();

	vb = kmalloc_node(sizeof(struct vmap_block),
			gfp_mask & GFP_RECLAIM_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);
	if (IS_ERR(va)) {
		kfree(vb);
		return ERR_CAST(va);
	}

	err = radix_tree_preload(gfp_mask);
	if (unlikely(err)) {
		kfree(vb);
		free_vmap_area(va);
		return ERR_PTR(err);
	}

	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));
	vb->free = VMAP_BBMAP_BITS - (1UL << order);
	vb->dirty = 0;
	vb->dirty_min = VMAP_BBMAP_BITS;
	vb->dirty_max = 0;
	INIT_LIST_HEAD(&vb->free_list);

	vb_idx = addr_to_vb_idx(va->va_start);
	spin_lock(&vmap_block_tree_lock);
	err = radix_tree_insert(&vmap_block_tree, vb_idx, vb);
	spin_unlock(&vmap_block_tree_lock);
	BUG_ON(err);
	radix_tree_preload_end();

	vbq = &get_cpu_var(vmap_block_queue);
	spin_lock(&vbq->lock);
	list_add_tail_rcu(&vb->free_list, &vbq->free);
	spin_unlock(&vbq->lock);
	put_cpu_var(vmap_block_queue);

	return vaddr;
}

static void free_vmap_block(struct vmap_block *vb)
{
	struct vmap_block *tmp;
	unsigned long vb_idx;

	vb_idx = addr_to_vb_idx(vb->va->va_start);
	spin_lock(&vmap_block_tree_lock);
	tmp = radix_tree_delete(&vmap_block_tree, vb_idx);
	spin_unlock(&vmap_block_tree_lock);
	BUG_ON(tmp != vb);

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

static void purge_fragmented_blocks(int cpu)
{
	LIST_HEAD(purge);
	struct vmap_block *vb;
	struct vmap_block *n_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) {

		if (!(vb->free + vb->dirty == VMAP_BBMAP_BITS && vb->dirty != VMAP_BBMAP_BITS))
			continue;

		spin_lock(&vb->lock);
		if (vb->free + vb->dirty == VMAP_BBMAP_BITS && vb->dirty != VMAP_BBMAP_BITS) {
			vb->free = 0; /* prevent further allocs after releasing lock */
			vb->dirty = VMAP_BBMAP_BITS; /* prevent purging it again */
			vb->dirty_min = 0;
			vb->dirty_max = VMAP_BBMAP_BITS;
			spin_lock(&vbq->lock);
			list_del_rcu(&vb->free_list);
			spin_unlock(&vbq->lock);
			spin_unlock(&vb->lock);
			list_add_tail(&vb->purge, &purge);
		} else
			spin_unlock(&vb->lock);
	}
	rcu_read_unlock();

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

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 NULL;
	}
	order = get_order(size);

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

		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);
		vb->free -= 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;
	}

	put_cpu_var(vmap_block_queue);
	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(const void *addr, unsigned long size)
{
	unsigned long offset;
	unsigned long vb_idx;
	unsigned int order;
	struct vmap_block *vb;

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

	flush_cache_vunmap((unsigned long)addr, (unsigned long)addr + size);

	order = get_order(size);

	offset = (unsigned long)addr & (VMAP_BLOCK_SIZE - 1);
	offset >>= PAGE_SHIFT;

	vb_idx = addr_to_vb_idx((unsigned long)addr);
	rcu_read_lock();
	vb = radix_tree_lookup(&vmap_block_tree, vb_idx);
	rcu_read_unlock();
	BUG_ON(!vb);

	vunmap_page_range((unsigned long)addr, (unsigned long)addr + size);

	if (debug_pagealloc_enabled())
		flush_tlb_kernel_range((unsigned long)addr,
					(unsigned long)addr + size);

	spin_lock(&vb->lock);

	/* Expand dirty range */
	vb->dirty_min = min(vb->dirty_min, offset);
	vb->dirty_max = max(vb->dirty_max, offset + (1UL << order));

	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);
}

/**
 * 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)
{
	unsigned long start = ULONG_MAX, end = 0;
	int cpu;
	int flush = 0;

	if (unlikely(!vmap_initialized))
		return;

	might_sleep();

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

		rcu_read_lock();
		list_for_each_entry_rcu(vb, &vbq->free, free_list) {
			spin_lock(&vb->lock);
			if (vb->dirty) {
				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);

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

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

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

	va = find_vmap_area(addr);
	BUG_ON(!va);
	debug_check_no_locks_freed((void *)va->va_start,
				    (va->va_end - va->va_start));
	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
 * @prot: memory protection to use. PAGE_KERNEL for regular RAM
 *
 * 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, pgprot_t prot)
{
	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);
		if (IS_ERR(va))
			return NULL;

		addr = va->va_start;
		mem = (void *)addr;
	}
	if (vmap_page_range(addr, addr + size, prot, pages) < 0) {
		vm_unmap_ram(mem, count);
		return NULL;
	}
	return mem;
}
EXPORT_SYMBOL(vm_map_ram);

static struct vm_struct *vmlist __initdata;
/**
 * 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)
{
	static size_t vm_init_off __initdata;
	unsigned long addr;

	addr = ALIGN(VMALLOC_START + vm_init_off, align);
	vm_init_off = PFN_ALIGN(addr + vm->size) - VMALLOC_START;

	vm->addr = (void *)addr;

	vm_area_add_early(vm);
}

void __init vmalloc_init(void)
{
	struct vmap_area *va;
	struct vm_struct *tmp;
	int i;

	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, free_work);
	}

	/* Import existing vmlist entries. */
	for (tmp = vmlist; tmp; tmp = tmp->next) {
		va = kzalloc(sizeof(struct vmap_area), GFP_NOWAIT);
		va->flags = VM_VM_AREA;
		va->va_start = (unsigned long)tmp->addr;
		va->va_end = va->va_start + tmp->size;
		va->vm = tmp;