vmalloc.c

最新最稳定的Linux内存管理模块源代码

/*
 *  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 <[e-mail]>, 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/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/rbtree.h>
#include <linux/radix-tree.h>
#include <linux/rcupdate.h>
#include <linux/bootmem.h>

#include <asm/atomic.h>
#include <asm/uaccess.h>
#include <asm/tlbflush.h>


/*** 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_none_or_clear_bad(pmd))
			continue;
		vunmap_pte_range(pmd, addr, next);
	} while (pmd++, addr = next, addr != end);
}

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

	pud = pud_offset(pgd, addr);
	do {
		next = pud_addr_end(addr, end);
		if (pud_none_or_clear_bad(pud))
			continue;
		vunmap_pmd_range(pud, addr, next);
	} while (pud++, 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_pud_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(pgd_t *pgd, 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, pgd, 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;
}

/*
 * 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(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_pud_range(pgd, addr, next, prot, pages, &nr);
		if (err)
			break;
	} while (pgd++, addr = next, addr != end);
	flush_cache_vmap(start, end);

	if (unlikely(err))
		return err;
	return nr;
}

static inline 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);

	/*
	 * 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)) {
		pud_t *pud = pud_offset(pgd, addr);
		if (!pud_none(*pud)) {
			pmd_t *pmd = pmd_offset(pud, addr);
			if (!pmd_none(*pmd)) {
				pte_t *ptep, pte;

				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	0x01
#define VM_LAZY_FREEING	0x02
#define VM_VM_AREA	0x04

struct vmap_area {
	unsigned long va_start;
	unsigned long va_end;
	unsigned long flags;
	struct rb_node rb_node;		/* address sorted rbtree */
	struct list_head list;		/* address sorted list */
	struct list_head purge_list;	/* "lazy purge" list */
	void *private;
	struct rcu_head rcu_head;
};

static DEFINE_SPINLOCK(vmap_area_lock);
static struct rb_root vmap_area_root = RB_ROOT;
static LIST_HEAD(vmap_area_list);

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_start)
			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;

		parent = *p;
		tmp = rb_entry(parent, struct vmap_area, rb_node);
		if (va->va_start < tmp->va_end)
			p = &(*p)->rb_left;
		else if (va->va_end > tmp->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 so it is usable like the vmlist */
	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);

/*
 * 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;

	BUG_ON(!size);
	BUG_ON(size & ~PAGE_MASK);

	va = kmalloc_node(sizeof(struct vmap_area),
			gfp_mask & GFP_RECLAIM_MASK, node);
	if (unlikely(!va))
		return ERR_PTR(-ENOMEM);

retry:
	addr = ALIGN(vstart, align);

	spin_lock(&vmap_area_lock);
	if (addr + size - 1 < addr)
		goto overflow;

	/* XXX: could have a last_hole cache */
	n = vmap_area_root.rb_node;
	if (n) {
		struct vmap_area *first = NULL;

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

		if (!first)
			goto found;

		if (first->va_end < addr) {
			n = rb_next(&first->rb_node);
			if (n)
				first = rb_entry(n, struct vmap_area, rb_node);
			else
				goto found;
		}

		while (addr + size > first->va_start && addr + size <= vend) {
			addr = ALIGN(first->va_end + PAGE_SIZE, align);
			if (addr + size - 1 < addr)
				goto overflow;

			n = rb_next(&first->rb_node);
			if (n)
				first = rb_entry(n, struct vmap_area, rb_node);
			else
				goto found;
		}
	}
found:
	if (addr + size > vend) {
overflow:
		spin_unlock(&vmap_area_lock);
		if (!purged) {
			purge_vmap_area_lazy();
			purged = 1;
			goto retry;
		}
		if (printk_ratelimit())
			printk(KERN_WARNING
				"vmap allocation for size %lu failed: "
				"use vmalloc=<size> to increase size.\n", size);
		return ERR_PTR(-EBUSY);
	}

	BUG_ON(addr & (align-1));

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

	return va;
}

static void rcu_free_va(struct rcu_head *head)
{
	struct vmap_area *va = container_of(head, struct vmap_area, rcu_head);

	kfree(va);
}

static void __free_vmap_area(struct vmap_area *va)
{
	BUG_ON(RB_EMPTY_NODE(&va->rb_node));
	rb_erase(&va->rb_node, &vmap_area_root);
	RB_CLEAR_NODE(&va->rb_node);
	list_del_rcu(&va->list);

	call_rcu(&va->rcu_head, rcu_free_va);
}

/*
 * 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);
}

static void vmap_debug_free_range(unsigned long start, unsigned long end)
{
	/*
	 * Unmap page tables and force a TLB flush immediately if
	 * CONFIG_DEBUG_PAGEALLOC is set. This catches use after free
	 * bugs similarly to those in linear kernel virtual address
	 * space after a page has been freed.
	 *
	 * All the lazy freeing logic is still retained, in order to
	 * minimise intrusiveness of this debugging feature.
	 *
	 * This is going to be *slow* (linear kernel virtual address
	 * debugging doesn't do a broadcast TLB flush so it is a lot
	 * faster).
	 */
#ifdef CONFIG_DEBUG_PAGEALLOC
	vunmap_page_range(start, end);
	flush_tlb_kernel_range(start, end);
#endif
}

/*
 * 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);

/*
 * Purges all lazily-freed vmap areas.
 *
 * If sync is 0 then don't purge if there is already a purge in progress.
 * If force_flush is 1, then flush kernel TLBs between *start and *end even
 * if we found no lazy vmap areas to unmap (callers can use this to optimise
 * their own TLB flushing).
 * Returns with *start = min(*start, lowest purged address)
 *              *end = max(*end, highest purged address)
 */
static void __purge_vmap_area_lazy(unsigned long *start, unsigned long *end,
					int sync, int force_flush)
{
	static DEFINE_SPINLOCK(purge_lock);
	LIST_HEAD(valist);
	struct vmap_area *va;
	struct vmap_area *n_va;
	int nr = 0;

	/*
	 * If sync is 0 but force_flush is 1, we'll go sync anyway but callers
	 * should not expect such behaviour. This just simplifies locking for
	 * the case that isn't actually used at the moment anyway.
	 */
	if (!sync && !force_flush) {
		if (!spin_trylock(&purge_lock))
			return;
	} else
		spin_lock(&purge_lock);

	rcu_read_lock();
	list_for_each_entry_rcu(va, &vmap_area_list, list) {
		if (va->flags & VM_LAZY_FREE) {
			if (va->va_start < *start)
				*start = va->va_start;
			if (va->va_end > *end)
				*end = va->va_end;
			nr += (va->va_end - va->va_start) >> PAGE_SHIFT;
			unmap_vmap_area(va);
			list_add_tail(&va->purge_list, &valist);
			va->flags |= VM_LAZY_FREEING;
			va->flags &= ~VM_LAZY_FREE;
		}
	}
	rcu_read_unlock();

	if (nr) {
		BUG_ON(nr > atomic_read(&vmap_lazy_nr));
		atomic_sub(nr, &vmap_lazy_nr);
	}

	if (nr || force_flush)
		flush_tlb_kernel_range(*start, *end);

	if (nr) {
		spin_lock(&vmap_area_lock);
		list_for_each_entry_safe(va, n_va, &valist, purge_list)
			__free_vmap_area(va);
		spin_unlock(&vmap_area_lock);
	}
	spin_unlock(&purge_lock);
}

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

	__purge_vmap_area_lazy(&start, &end, 0, 0);
}

/*
 * Kick off a purge of the outstanding lazy areas.
 */
static void purge_vmap_area_lazy(void)
{
	unsigned long start = ULONG_MAX, end = 0;

	__purge_vmap_area_lazy(&start, &end, 1, 0);
}

/*
 * Free and unmap a vmap area, caller ensuring flush_cache_vunmap had been
 * called for the correct range previously.
 */
static void free_unmap_vmap_area_noflush(struct vmap_area *va)
{
	va->flags |= VM_LAZY_FREE;
	atomic_add((va->va_end - va->va_start) >> PAGE_SHIFT, &vmap_lazy_nr);
	if (unlikely(atomic_read(&vmap_lazy_nr) > 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);
	free_unmap_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;
}

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

	va = find_vmap_area(addr);
	BUG_ON(!va);
	free_unmap_vmap_area(va);
}