shmem.c

最新最稳定的Linux内存管理模块源代码

/*
 * Resizable virtual memory filesystem for Linux.
 *
 * Copyright (C) 2000 Linus Torvalds.
 *		 2000 Transmeta Corp.
 *		 2000-2001 Christoph Rohland
 *		 2000-2001 SAP AG
 *		 2002 Red Hat Inc.
 * Copyright (C) 2002-2005 Hugh Dickins.
 * Copyright (C) 2002-2005 VERITAS Software Corporation.
 * Copyright (C) 2004 Andi Kleen, SuSE Labs
 *
 * Extended attribute support for tmpfs:
 * Copyright (c) 2004, Luke Kenneth Casson Leighton <[e-mail]>
 * Copyright (c) 2004 Red Hat, Inc., James Morris <[e-mail]>
 *
 * tiny-shmem:
 * Copyright (c) 2004, 2008 Matt Mackall <[e-mail]>
 *
 * This file is released under the GPL.
 */

#include <linux/fs.h>
#include <linux/init.h>
#include <linux/vfs.h>
#include <linux/mount.h>
#include <linux/file.h>
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/swap.h>

static struct vfsmount *shm_mnt;

#ifdef CONFIG_SHMEM
/*
 * This virtual memory filesystem is heavily based on the ramfs. It
 * extends ramfs by the ability to use swap and honor resource limits
 * which makes it a completely usable filesystem.
 */

#include <linux/xattr.h>
#include <linux/exportfs.h>
#include <linux/generic_acl.h>
#include <linux/mman.h>
#include <linux/pagemap.h>
#include <linux/string.h>
#include <linux/slab.h>
#include <linux/backing-dev.h>
#include <linux/shmem_fs.h>
#include <linux/writeback.h>
#include <linux/vfs.h>
#include <linux/blkdev.h>
#include <linux/security.h>
#include <linux/swapops.h>
#include <linux/mempolicy.h>
#include <linux/namei.h>
#include <linux/ctype.h>
#include <linux/migrate.h>
#include <linux/highmem.h>
#include <linux/seq_file.h>
#include <linux/magic.h>

#include <asm/uaccess.h>
#include <asm/div64.h>
#include <asm/pgtable.h>

#define ENTRIES_PER_PAGE (PAGE_CACHE_SIZE/sizeof(unsigned long))
#define ENTRIES_PER_PAGEPAGE (ENTRIES_PER_PAGE*ENTRIES_PER_PAGE)
#define BLOCKS_PER_PAGE  (PAGE_CACHE_SIZE/512)

#define SHMEM_MAX_INDEX  (SHMEM_NR_DIRECT + (ENTRIES_PER_PAGEPAGE/2) * (ENTRIES_PER_PAGE+1))
#define SHMEM_MAX_BYTES  ((unsigned long long)SHMEM_MAX_INDEX << PAGE_CACHE_SHIFT)

#define VM_ACCT(size)    (PAGE_CACHE_ALIGN(size) >> PAGE_SHIFT)

/* info->flags needs VM_flags to handle pagein/truncate races efficiently */
#define SHMEM_PAGEIN	 VM_READ
#define SHMEM_TRUNCATE	 VM_WRITE

/* Definition to limit shmem_truncate's steps between cond_rescheds */
#define LATENCY_LIMIT	 64

/* Pretend that each entry is of this size in directory's i_size */
#define BOGO_DIRENT_SIZE 20

/* Flag allocation requirements to shmem_getpage and shmem_swp_alloc */
enum sgp_type {
	SGP_READ,	/* don't exceed i_size, don't allocate page */
	SGP_CACHE,	/* don't exceed i_size, may allocate page */
	SGP_DIRTY,	/* like SGP_CACHE, but set new page dirty */
	SGP_WRITE,	/* may exceed i_size, may allocate page */
};

#ifdef CONFIG_TMPFS
static unsigned long shmem_default_max_blocks(void)
{
	return totalram_pages / 2;
}

static unsigned long shmem_default_max_inodes(void)
{
	return min(totalram_pages - totalhigh_pages, totalram_pages / 2);
}
#endif

static int shmem_getpage(struct inode *inode, unsigned long idx,
			 struct page **pagep, enum sgp_type sgp, int *type);

static inline struct page *shmem_dir_alloc(gfp_t gfp_mask)
{
	/*
	 * The above definition of ENTRIES_PER_PAGE, and the use of
	 * BLOCKS_PER_PAGE on indirect pages, assume PAGE_CACHE_SIZE:
	 * might be reconsidered if it ever diverges from PAGE_SIZE.
	 *
	 * Mobility flags are masked out as swap vectors cannot move
	 */
	return alloc_pages((gfp_mask & ~GFP_MOVABLE_MASK) | __GFP_ZERO,
				PAGE_CACHE_SHIFT-PAGE_SHIFT);
}

static inline void shmem_dir_free(struct page *page)
{
	__free_pages(page, PAGE_CACHE_SHIFT-PAGE_SHIFT);
}

static struct page **shmem_dir_map(struct page *page)
{
	return (struct page **)kmap_atomic(page, KM_USER0);
}

static inline void shmem_dir_unmap(struct page **dir)
{
	kunmap_atomic(dir, KM_USER0);
}

static swp_entry_t *shmem_swp_map(struct page *page)
{
	return (swp_entry_t *)kmap_atomic(page, KM_USER1);
}

static inline void shmem_swp_balance_unmap(void)
{
	/*
	 * When passing a pointer to an i_direct entry, to code which
	 * also handles indirect entries and so will shmem_swp_unmap,
	 * we must arrange for the preempt count to remain in balance.
	 * What kmap_atomic of a lowmem page does depends on config
	 * and architecture, so pretend to kmap_atomic some lowmem page.
	 */
	(void) kmap_atomic(ZERO_PAGE(0), KM_USER1);
}

static inline void shmem_swp_unmap(swp_entry_t *entry)
{
	kunmap_atomic(entry, KM_USER1);
}

static inline struct shmem_sb_info *SHMEM_SB(struct super_block *sb)
{
	return sb->s_fs_info;
}

/*
 * shmem_file_setup pre-accounts the whole fixed size of a VM object,
 * for shared memory and for shared anonymous (/dev/zero) mappings
 * (unless MAP_NORESERVE and sysctl_overcommit_memory <= 1),
 * consistent with the pre-accounting of private mappings ...
 */
static inline int shmem_acct_size(unsigned long flags, loff_t size)
{
	return (flags & VM_NORESERVE) ?
		0 : security_vm_enough_memory_kern(VM_ACCT(size));
}

static inline void shmem_unacct_size(unsigned long flags, loff_t size)
{
	if (!(flags & VM_NORESERVE))
		vm_unacct_memory(VM_ACCT(size));
}

/*
 * ... whereas tmpfs objects are accounted incrementally as
 * pages are allocated, in order to allow huge sparse files.
 * shmem_getpage reports shmem_acct_block failure as -ENOSPC not -ENOMEM,
 * so that a failure on a sparse tmpfs mapping will give SIGBUS not OOM.
 */
static inline int shmem_acct_block(unsigned long flags)
{
	return (flags & VM_NORESERVE) ?
		security_vm_enough_memory_kern(VM_ACCT(PAGE_CACHE_SIZE)) : 0;
}

static inline void shmem_unacct_blocks(unsigned long flags, long pages)
{
	if (flags & VM_NORESERVE)
		vm_unacct_memory(pages * VM_ACCT(PAGE_CACHE_SIZE));
}

static const struct super_operations shmem_ops;
static const struct address_space_operations shmem_aops;
static const struct file_operations shmem_file_operations;
static const struct inode_operations shmem_inode_operations;
static const struct inode_operations shmem_dir_inode_operations;
static const struct inode_operations shmem_special_inode_operations;
static struct vm_operations_struct shmem_vm_ops;

static struct backing_dev_info shmem_backing_dev_info  __read_mostly = {
	.ra_pages	= 0,	/* No readahead */
	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK | BDI_CAP_SWAP_BACKED,
	.unplug_io_fn	= default_unplug_io_fn,
};

static LIST_HEAD(shmem_swaplist);
static DEFINE_MUTEX(shmem_swaplist_mutex);

static void shmem_free_blocks(struct inode *inode, long pages)
{
	struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
	if (sbinfo->max_blocks) {
		spin_lock(&sbinfo->stat_lock);
		sbinfo->free_blocks += pages;
		inode->i_blocks -= pages*BLOCKS_PER_PAGE;
		spin_unlock(&sbinfo->stat_lock);
	}
}

static int shmem_reserve_inode(struct super_block *sb)
{
	struct shmem_sb_info *sbinfo = SHMEM_SB(sb);
	if (sbinfo->max_inodes) {
		spin_lock(&sbinfo->stat_lock);
		if (!sbinfo->free_inodes) {
			spin_unlock(&sbinfo->stat_lock);
			return -ENOSPC;
		}
		sbinfo->free_inodes--;
		spin_unlock(&sbinfo->stat_lock);
	}
	return 0;
}

static void shmem_free_inode(struct super_block *sb)
{
	struct shmem_sb_info *sbinfo = SHMEM_SB(sb);
	if (sbinfo->max_inodes) {
		spin_lock(&sbinfo->stat_lock);
		sbinfo->free_inodes++;
		spin_unlock(&sbinfo->stat_lock);
	}
}

/**
 * shmem_recalc_inode - recalculate the size of an inode
 * @inode: inode to recalc
 *
 * We have to calculate the free blocks since the mm can drop
 * undirtied hole pages behind our back.
 *
 * But normally   info->alloced == inode->i_mapping->nrpages + info->swapped
 * So mm freed is info->alloced - (inode->i_mapping->nrpages + info->swapped)
 *
 * It has to be called with the spinlock held.
 */
static void shmem_recalc_inode(struct inode *inode)
{
	struct shmem_inode_info *info = SHMEM_I(inode);
	long freed;

	freed = info->alloced - info->swapped - inode->i_mapping->nrpages;
	if (freed > 0) {
		info->alloced -= freed;
		shmem_unacct_blocks(info->flags, freed);
		shmem_free_blocks(inode, freed);
	}
}

/**
 * shmem_swp_entry - find the swap vector position in the info structure
 * @info:  info structure for the inode
 * @index: index of the page to find
 * @page:  optional page to add to the structure. Has to be preset to
 *         all zeros
 *
 * If there is no space allocated yet it will return NULL when
 * page is NULL, else it will use the page for the needed block,
 * setting it to NULL on return to indicate that it has been used.
 *
 * The swap vector is organized the following way:
 *
 * There are SHMEM_NR_DIRECT entries directly stored in the
 * shmem_inode_info structure. So small files do not need an addional
 * allocation.
 *
 * For pages with index > SHMEM_NR_DIRECT there is the pointer
 * i_indirect which points to a page which holds in the first half
 * doubly indirect blocks, in the second half triple indirect blocks:
 *
 * For an artificial ENTRIES_PER_PAGE = 4 this would lead to the
 * following layout (for SHMEM_NR_DIRECT == 16):
 *
 * i_indirect -> dir --> 16-19
 * 	      |	     +-> 20-23
 * 	      |
 * 	      +-->dir2 --> 24-27
 * 	      |	       +-> 28-31
 * 	      |	       +-> 32-35
 * 	      |	       +-> 36-39
 * 	      |
 * 	      +-->dir3 --> 40-43
 * 	       	       +-> 44-47
 * 	      	       +-> 48-51
 * 	      	       +-> 52-55
 */
static swp_entry_t *shmem_swp_entry(struct shmem_inode_info *info, unsigned long index, struct page **page)
{
	unsigned long offset;
	struct page **dir;
	struct page *subdir;

	if (index < SHMEM_NR_DIRECT) {
		shmem_swp_balance_unmap();
		return info->i_direct+index;
	}
	if (!info->i_indirect) {
		if (page) {
			info->i_indirect = *page;
			*page = NULL;
		}
		return NULL;			/* need another page */
	}

	index -= SHMEM_NR_DIRECT;
	offset = index % ENTRIES_PER_PAGE;
	index /= ENTRIES_PER_PAGE;
	dir = shmem_dir_map(info->i_indirect);

	if (index >= ENTRIES_PER_PAGE/2) {
		index -= ENTRIES_PER_PAGE/2;
		dir += ENTRIES_PER_PAGE/2 + index/ENTRIES_PER_PAGE;
		index %= ENTRIES_PER_PAGE;
		subdir = *dir;
		if (!subdir) {
			if (page) {
				*dir = *page;
				*page = NULL;
			}
			shmem_dir_unmap(dir);
			return NULL;		/* need another page */
		}
		shmem_dir_unmap(dir);
		dir = shmem_dir_map(subdir);
	}

	dir += index;
	subdir = *dir;
	if (!subdir) {
		if (!page || !(subdir = *page)) {
			shmem_dir_unmap(dir);
			return NULL;		/* need a page */
		}
		*dir = subdir;
		*page = NULL;
	}
	shmem_dir_unmap(dir);
	return shmem_swp_map(subdir) + offset;
}

static void shmem_swp_set(struct shmem_inode_info *info, swp_entry_t *entry, unsigned long value)
{
	long incdec = value? 1: -1;

	entry->val = value;
	info->swapped += incdec;
	if ((unsigned long)(entry - info->i_direct) >= SHMEM_NR_DIRECT) {
		struct page *page = kmap_atomic_to_page(entry);
		set_page_private(page, page_private(page) + incdec);
	}
}

/**
 * shmem_swp_alloc - get the position of the swap entry for the page.
 * @info:	info structure for the inode
 * @index:	index of the page to find
 * @sgp:	check and recheck i_size? skip allocation?
 *
 * If the entry does not exist, allocate it.
 */
static swp_entry_t *shmem_swp_alloc(struct shmem_inode_info *info, unsigned long index, enum sgp_type sgp)
{
	struct inode *inode = &info->vfs_inode;
	struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
	struct page *page = NULL;
	swp_entry_t *entry;

	if (sgp != SGP_WRITE &&
	    ((loff_t) index << PAGE_CACHE_SHIFT) >= i_size_read(inode))
		return ERR_PTR(-EINVAL);

	while (!(entry = shmem_swp_entry(info, index, &page))) {
		if (sgp == SGP_READ)
			return shmem_swp_map(ZERO_PAGE(0));
		/*
		 * Test free_blocks against 1 not 0, since we have 1 data
		 * page (and perhaps indirect index pages) yet to allocate:
		 * a waste to allocate index if we cannot allocate data.
		 */
		if (sbinfo->max_blocks) {
			spin_lock(&sbinfo->stat_lock);
			if (sbinfo->free_blocks <= 1) {
				spin_unlock(&sbinfo->stat_lock);
				return ERR_PTR(-ENOSPC);
			}
			sbinfo->free_blocks--;
			inode->i_blocks += BLOCKS_PER_PAGE;
			spin_unlock(&sbinfo->stat_lock);
		}

		spin_unlock(&info->lock);
		page = shmem_dir_alloc(mapping_gfp_mask(inode->i_mapping));
		if (page)
			set_page_private(page, 0);
		spin_lock(&info->lock);

		if (!page) {
			shmem_free_blocks(inode, 1);
			return ERR_PTR(-ENOMEM);
		}
		if (sgp != SGP_WRITE &&
		    ((loff_t) index << PAGE_CACHE_SHIFT) >= i_size_read(inode)) {
			entry = ERR_PTR(-EINVAL);
			break;
		}
		if (info->next_index <= index)
			info->next_index = index + 1;
	}
	if (page) {
		/* another task gave its page, or truncated the file */
		shmem_free_blocks(inode, 1);
		shmem_dir_free(page);
	}
	if (info->next_index <= index && !IS_ERR(entry))
		info->next_index = index + 1;
	return entry;
}

/**
 * shmem_free_swp - free some swap entries in a directory
 * @dir:        pointer to the directory
 * @edir:       pointer after last entry of the directory
 * @punch_lock: pointer to spinlock when needed for the holepunch case
 */
static int shmem_free_swp(swp_entry_t *dir, swp_entry_t *edir,
						spinlock_t *punch_lock)
{
	spinlock_t *punch_unlock = NULL;
	swp_entry_t *ptr;
	int freed = 0;

	for (ptr = dir; ptr < edir; ptr++) {
		if (ptr->val) {
			if (unlikely(punch_lock)) {
				punch_unlock = punch_lock;
				punch_lock = NULL;
				spin_lock(punch_unlock);
				if (!ptr->val)
					continue;
			}
			free_swap_and_cache(*ptr);
			*ptr = (swp_entry_t){0};
			freed++;
		}
	}
	if (punch_unlock)
		spin_unlock(punch_unlock);
	return freed;
}

static int shmem_map_and_free_swp(struct page *subdir, int offset,
		int limit, struct page ***dir, spinlock_t *punch_lock)
{
	swp_entry_t *ptr;
	int freed = 0;

	ptr = shmem_swp_map(subdir);
	for (; offset < limit; offset += LATENCY_LIMIT) {
		int size = limit - offset;
		if (size > LATENCY_LIMIT)
			size = LATENCY_LIMIT;
		freed += shmem_free_swp(ptr+offset, ptr+offset+size,
							punch_lock);
		if (need_resched()) {
			shmem_swp_unmap(ptr);
			if (*dir) {
				shmem_dir_unmap(*dir);
				*dir = NULL;
			}
			cond_resched();