ops_address.c

linux 内核源代码

/*
 * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
 * Copyright (C) 2004-2007 Red Hat, Inc.  All rights reserved.
 *
 * This copyrighted material is made available to anyone wishing to use,
 * modify, copy, or redistribute it subject to the terms and conditions
 * of the GNU General Public License version 2.
 */

#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/completion.h>
#include <linux/buffer_head.h>
#include <linux/pagemap.h>
#include <linux/pagevec.h>
#include <linux/mpage.h>
#include <linux/fs.h>
#include <linux/writeback.h>
#include <linux/swap.h>
#include <linux/gfs2_ondisk.h>
#include <linux/lm_interface.h>

#include "gfs2.h"
#include "incore.h"
#include "bmap.h"
#include "glock.h"
#include "inode.h"
#include "log.h"
#include "meta_io.h"
#include "ops_address.h"
#include "quota.h"
#include "trans.h"
#include "rgrp.h"
#include "ops_file.h"
#include "super.h"
#include "util.h"
#include "glops.h"


static void gfs2_page_add_databufs(struct gfs2_inode *ip, struct page *page,
				   unsigned int from, unsigned int to)
{
	struct buffer_head *head = page_buffers(page);
	unsigned int bsize = head->b_size;
	struct buffer_head *bh;
	unsigned int start, end;

	for (bh = head, start = 0; bh != head || !start;
	     bh = bh->b_this_page, start = end) {
		end = start + bsize;
		if (end <= from || start >= to)
			continue;
		if (gfs2_is_jdata(ip))
			set_buffer_uptodate(bh);
		gfs2_trans_add_bh(ip->i_gl, bh, 0);
	}
}

/**
 * gfs2_get_block - Fills in a buffer head with details about a block
 * @inode: The inode
 * @lblock: The block number to look up
 * @bh_result: The buffer head to return the result in
 * @create: Non-zero if we may add block to the file
 *
 * Returns: errno
 */

int gfs2_get_block(struct inode *inode, sector_t lblock,
	           struct buffer_head *bh_result, int create)
{
	return gfs2_block_map(inode, lblock, create, bh_result);
}

/**
 * gfs2_get_block_noalloc - Fills in a buffer head with details about a block
 * @inode: The inode
 * @lblock: The block number to look up
 * @bh_result: The buffer head to return the result in
 * @create: Non-zero if we may add block to the file
 *
 * Returns: errno
 */

static int gfs2_get_block_noalloc(struct inode *inode, sector_t lblock,
				  struct buffer_head *bh_result, int create)
{
	int error;

	error = gfs2_block_map(inode, lblock, 0, bh_result);
	if (error)
		return error;
	if (!buffer_mapped(bh_result))
		return -EIO;
	return 0;
}

static int gfs2_get_block_direct(struct inode *inode, sector_t lblock,
				 struct buffer_head *bh_result, int create)
{
	return gfs2_block_map(inode, lblock, 0, bh_result);
}

/**
 * gfs2_writepage - Write complete page
 * @page: Page to write
 *
 * Returns: errno
 *
 * Some of this is copied from block_write_full_page() although we still
 * call it to do most of the work.
 */

static int gfs2_writepage(struct page *page, struct writeback_control *wbc)
{
	struct inode *inode = page->mapping->host;
	struct gfs2_inode *ip = GFS2_I(inode);
	struct gfs2_sbd *sdp = GFS2_SB(inode);
	loff_t i_size = i_size_read(inode);
	pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT;
	unsigned offset;
	int error;
	int done_trans = 0;

	if (gfs2_assert_withdraw(sdp, gfs2_glock_is_held_excl(ip->i_gl))) {
		unlock_page(page);
		return -EIO;
	}
	if (current->journal_info)
		goto out_ignore;

	/* Is the page fully outside i_size? (truncate in progress) */
        offset = i_size & (PAGE_CACHE_SIZE-1);
	if (page->index > end_index || (page->index == end_index && !offset)) {
		page->mapping->a_ops->invalidatepage(page, 0);
		unlock_page(page);
		return 0; /* don't care */
	}

	if ((sdp->sd_args.ar_data == GFS2_DATA_ORDERED || gfs2_is_jdata(ip)) &&
	    PageChecked(page)) {
		ClearPageChecked(page);
		error = gfs2_trans_begin(sdp, RES_DINODE + 1, 0);
		if (error)
			goto out_ignore;
		if (!page_has_buffers(page)) {
			create_empty_buffers(page, inode->i_sb->s_blocksize,
					     (1 << BH_Dirty)|(1 << BH_Uptodate));
		}
		gfs2_page_add_databufs(ip, page, 0, sdp->sd_vfs->s_blocksize-1);
		done_trans = 1;
	}
	error = block_write_full_page(page, gfs2_get_block_noalloc, wbc);
	if (done_trans)
		gfs2_trans_end(sdp);
	gfs2_meta_cache_flush(ip);
	return error;

out_ignore:
	redirty_page_for_writepage(wbc, page);
	unlock_page(page);
	return 0;
}

/**
 * gfs2_writepages - Write a bunch of dirty pages back to disk
 * @mapping: The mapping to write
 * @wbc: Write-back control
 *
 * For journaled files and/or ordered writes this just falls back to the
 * kernel's default writepages path for now. We will probably want to change
 * that eventually (i.e. when we look at allocate on flush).
 *
 * For the data=writeback case though we can already ignore buffer heads
 * and write whole extents at once. This is a big reduction in the
 * number of I/O requests we send and the bmap calls we make in this case.
 */
static int gfs2_writepages(struct address_space *mapping,
			   struct writeback_control *wbc)
{
	struct inode *inode = mapping->host;
	struct gfs2_inode *ip = GFS2_I(inode);
	struct gfs2_sbd *sdp = GFS2_SB(inode);

	if (sdp->sd_args.ar_data == GFS2_DATA_WRITEBACK && !gfs2_is_jdata(ip))
		return mpage_writepages(mapping, wbc, gfs2_get_block_noalloc);

	return generic_writepages(mapping, wbc);
}

/**
 * stuffed_readpage - Fill in a Linux page with stuffed file data
 * @ip: the inode
 * @page: the page
 *
 * Returns: errno
 */

static int stuffed_readpage(struct gfs2_inode *ip, struct page *page)
{
	struct buffer_head *dibh;
	void *kaddr;
	int error;

	/*
	 * Due to the order of unstuffing files and ->nopage(), we can be
	 * asked for a zero page in the case of a stuffed file being extended,
	 * so we need to supply one here. It doesn't happen often.
	 */
	if (unlikely(page->index)) {
		zero_user_page(page, 0, PAGE_CACHE_SIZE, KM_USER0);
		return 0;
	}

	error = gfs2_meta_inode_buffer(ip, &dibh);
	if (error)
		return error;

	kaddr = kmap_atomic(page, KM_USER0);
	memcpy(kaddr, dibh->b_data + sizeof(struct gfs2_dinode),
	       ip->i_di.di_size);
	memset(kaddr + ip->i_di.di_size, 0, PAGE_CACHE_SIZE - ip->i_di.di_size);
	kunmap_atomic(kaddr, KM_USER0);
	flush_dcache_page(page);
	brelse(dibh);
	SetPageUptodate(page);

	return 0;
}


/**
 * gfs2_readpage - readpage with locking
 * @file: The file to read a page for. N.B. This may be NULL if we are
 * reading an internal file.
 * @page: The page to read
 *
 * Returns: errno
 */

static int gfs2_readpage(struct file *file, struct page *page)
{
	struct gfs2_inode *ip = GFS2_I(page->mapping->host);
	struct gfs2_sbd *sdp = GFS2_SB(page->mapping->host);
	struct gfs2_file *gf = NULL;
	struct gfs2_holder gh;
	int error;
	int do_unlock = 0;

	if (likely(file != &gfs2_internal_file_sentinel)) {
		if (file) {
			gf = file->private_data;
			if (test_bit(GFF_EXLOCK, &gf->f_flags))
				/* gfs2_sharewrite_fault has grabbed the ip->i_gl already */
				goto skip_lock;
		}
		gfs2_holder_init(ip->i_gl, LM_ST_SHARED, GL_ATIME|LM_FLAG_TRY_1CB, &gh);
		do_unlock = 1;
		error = gfs2_glock_nq_atime(&gh);
		if (unlikely(error))
			goto out_unlock;
	}

skip_lock:
	if (gfs2_is_stuffed(ip)) {
		error = stuffed_readpage(ip, page);
		unlock_page(page);
	} else
		error = mpage_readpage(page, gfs2_get_block);

	if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
		error = -EIO;

	if (do_unlock) {
		gfs2_glock_dq_m(1, &gh);
		gfs2_holder_uninit(&gh);
	}
out:
	return error;
out_unlock:
	unlock_page(page);
	if (error == GLR_TRYFAILED) {
		error = AOP_TRUNCATED_PAGE;
		yield();
	}
	if (do_unlock)
		gfs2_holder_uninit(&gh);
	goto out;
}

/**
 * gfs2_readpages - Read a bunch of pages at once
 *
 * Some notes:
 * 1. This is only for readahead, so we can simply ignore any things
 *    which are slightly inconvenient (such as locking conflicts between
 *    the page lock and the glock) and return having done no I/O. Its
 *    obviously not something we'd want to do on too regular a basis.
 *    Any I/O we ignore at this time will be done via readpage later.
 * 2. We don't handle stuffed files here we let readpage do the honours.
 * 3. mpage_readpages() does most of the heavy lifting in the common case.
 * 4. gfs2_get_block() is relied upon to set BH_Boundary in the right places.
 * 5. We use LM_FLAG_TRY_1CB here, effectively we then have lock-ahead as
 *    well as read-ahead.
 */
static int gfs2_readpages(struct file *file, struct address_space *mapping,
			  struct list_head *pages, unsigned nr_pages)
{
	struct inode *inode = mapping->host;
	struct gfs2_inode *ip = GFS2_I(inode);
	struct gfs2_sbd *sdp = GFS2_SB(inode);
	struct gfs2_holder gh;
	int ret = 0;
	int do_unlock = 0;

	if (likely(file != &gfs2_internal_file_sentinel)) {
		if (file) {
			struct gfs2_file *gf = file->private_data;
			if (test_bit(GFF_EXLOCK, &gf->f_flags))
				goto skip_lock;
		}
		gfs2_holder_init(ip->i_gl, LM_ST_SHARED,
				 LM_FLAG_TRY_1CB|GL_ATIME, &gh);
		do_unlock = 1;
		ret = gfs2_glock_nq_atime(&gh);
		if (ret == GLR_TRYFAILED)
			goto out_noerror;
		if (unlikely(ret))
			goto out_unlock;
	}
skip_lock:
	if (!gfs2_is_stuffed(ip))
		ret = mpage_readpages(mapping, pages, nr_pages, gfs2_get_block);

	if (do_unlock) {
		gfs2_glock_dq_m(1, &gh);
		gfs2_holder_uninit(&gh);
	}
out:
	if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
		ret = -EIO;
	return ret;
out_noerror:
	ret = 0;
out_unlock:
	if (do_unlock)
		gfs2_holder_uninit(&gh);
	goto out;
}

/**
 * gfs2_write_begin - Begin to write to a file
 * @file: The file to write to
 * @mapping: The mapping in which to write
 * @pos: The file offset at which to start writing
 * @len: Length of the write
 * @flags: Various flags
 * @pagep: Pointer to return the page
 * @fsdata: Pointer to return fs data (unused by GFS2)
 *
 * Returns: errno
 */

static int gfs2_write_begin(struct file *file, struct address_space *mapping,
			    loff_t pos, unsigned len, unsigned flags,
			    struct page **pagep, void **fsdata)
{
	struct gfs2_inode *ip = GFS2_I(mapping->host);
	struct gfs2_sbd *sdp = GFS2_SB(mapping->host);
	unsigned int data_blocks, ind_blocks, rblocks;
	int alloc_required;
	int error = 0;
	struct gfs2_alloc *al;
	pgoff_t index = pos >> PAGE_CACHE_SHIFT;
	unsigned from = pos & (PAGE_CACHE_SIZE - 1);
	unsigned to = from + len;
	struct page *page;

	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, GL_ATIME, &ip->i_gh);
	error = gfs2_glock_nq_atime(&ip->i_gh);
	if (unlikely(error))
		goto out_uninit;

	error = -ENOMEM;
	page = __grab_cache_page(mapping, index);
	*pagep = page;
	if (!page)
		goto out_unlock;

	gfs2_write_calc_reserv(ip, len, &data_blocks, &ind_blocks);

	error = gfs2_write_alloc_required(ip, pos, len, &alloc_required);
	if (error)
		goto out_putpage;


	ip->i_alloc.al_requested = 0;
	if (alloc_required) {
		al = gfs2_alloc_get(ip);

		error = gfs2_quota_lock(ip, NO_QUOTA_CHANGE, NO_QUOTA_CHANGE);
		if (error)
			goto out_alloc_put;

		error = gfs2_quota_check(ip, ip->i_inode.i_uid, ip->i_inode.i_gid);
		if (error)
			goto out_qunlock;

		al->al_requested = data_blocks + ind_blocks;
		error = gfs2_inplace_reserve(ip);
		if (error)
			goto out_qunlock;
	}

	rblocks = RES_DINODE + ind_blocks;
	if (gfs2_is_jdata(ip))
		rblocks += data_blocks ? data_blocks : 1;
	if (ind_blocks || data_blocks)
		rblocks += RES_STATFS + RES_QUOTA;

	error = gfs2_trans_begin(sdp, rblocks,
				 PAGE_CACHE_SIZE/sdp->sd_sb.sb_bsize);
	if (error)
		goto out_trans_fail;

	if (gfs2_is_stuffed(ip)) {