feaa7bba02
This patch fixes the way we have been dealing with unlinked, but still open files. It removes all limits (other than memory for inodes, as per every other filesystem) on numbers of these which we can support on GFS2. It also means that (like other fs) its the responsibility of the last process to close the file to deallocate the storage, rather than the person who did the unlinking. Note that with GFS2, those two events might take place on different nodes. Also there are a number of other changes: o We use the Linux inode subsystem as it was intended to be used, wrt allocating GFS2 inodes o The Linux inode cache is now the point which we use for local enforcement of only holding one copy of the inode in core at once (previous to this we used the glock layer). o We no longer use the unlinked "special" file. We just ignore it completely. This makes unlinking more efficient. o We now use the 4th block allocation state. The previously unused state is used to track unlinked but still open inodes. o gfs2_inoded is no longer needed o Several fields are now no longer needed (and removed) from the in core struct gfs2_inode o Several fields are no longer needed (and removed) from the in core superblock There are a number of future possible optimisations and clean ups which have been made possible by this patch. Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
196 lines
4.2 KiB
C
196 lines
4.2 KiB
C
/*
|
|
* Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved.
|
|
* Copyright (C) 2004-2006 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 v.2.
|
|
*/
|
|
|
|
#include <linux/sched.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/spinlock.h>
|
|
#include <linux/completion.h>
|
|
#include <linux/buffer_head.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/pagemap.h>
|
|
#include <linux/gfs2_ondisk.h>
|
|
|
|
#include "gfs2.h"
|
|
#include "lm_interface.h"
|
|
#include "incore.h"
|
|
#include "bmap.h"
|
|
#include "glock.h"
|
|
#include "inode.h"
|
|
#include "ops_vm.h"
|
|
#include "page.h"
|
|
#include "quota.h"
|
|
#include "rgrp.h"
|
|
#include "trans.h"
|
|
#include "util.h"
|
|
|
|
static void pfault_be_greedy(struct gfs2_inode *ip)
|
|
{
|
|
unsigned int time;
|
|
|
|
spin_lock(&ip->i_spin);
|
|
time = ip->i_greedy;
|
|
ip->i_last_pfault = jiffies;
|
|
spin_unlock(&ip->i_spin);
|
|
|
|
igrab(&ip->i_inode);
|
|
if (gfs2_glock_be_greedy(ip->i_gl, time))
|
|
iput(&ip->i_inode);
|
|
}
|
|
|
|
static struct page *gfs2_private_nopage(struct vm_area_struct *area,
|
|
unsigned long address, int *type)
|
|
{
|
|
struct gfs2_inode *ip = GFS2_I(area->vm_file->f_mapping->host);
|
|
struct gfs2_holder i_gh;
|
|
struct page *result;
|
|
int error;
|
|
|
|
error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, 0, &i_gh);
|
|
if (error)
|
|
return NULL;
|
|
|
|
set_bit(GIF_PAGED, &ip->i_flags);
|
|
|
|
result = filemap_nopage(area, address, type);
|
|
|
|
if (result && result != NOPAGE_OOM)
|
|
pfault_be_greedy(ip);
|
|
|
|
gfs2_glock_dq_uninit(&i_gh);
|
|
|
|
return result;
|
|
}
|
|
|
|
static int alloc_page_backing(struct gfs2_inode *ip, struct page *page)
|
|
{
|
|
struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
|
|
unsigned long index = page->index;
|
|
uint64_t lblock = index << (PAGE_CACHE_SHIFT -
|
|
sdp->sd_sb.sb_bsize_shift);
|
|
unsigned int blocks = PAGE_CACHE_SIZE >> sdp->sd_sb.sb_bsize_shift;
|
|
struct gfs2_alloc *al;
|
|
unsigned int data_blocks, ind_blocks;
|
|
unsigned int x;
|
|
int error;
|
|
|
|
al = gfs2_alloc_get(ip);
|
|
|
|
error = gfs2_quota_lock(ip, NO_QUOTA_CHANGE, NO_QUOTA_CHANGE);
|
|
if (error)
|
|
goto out;
|
|
|
|
error = gfs2_quota_check(ip, ip->i_di.di_uid, ip->i_di.di_gid);
|
|
if (error)
|
|
goto out_gunlock_q;
|
|
|
|
gfs2_write_calc_reserv(ip, PAGE_CACHE_SIZE, &data_blocks, &ind_blocks);
|
|
|
|
al->al_requested = data_blocks + ind_blocks;
|
|
|
|
error = gfs2_inplace_reserve(ip);
|
|
if (error)
|
|
goto out_gunlock_q;
|
|
|
|
error = gfs2_trans_begin(sdp, al->al_rgd->rd_ri.ri_length +
|
|
ind_blocks + RES_DINODE +
|
|
RES_STATFS + RES_QUOTA, 0);
|
|
if (error)
|
|
goto out_ipres;
|
|
|
|
if (gfs2_is_stuffed(ip)) {
|
|
error = gfs2_unstuff_dinode(ip, gfs2_unstuffer_page, NULL);
|
|
if (error)
|
|
goto out_trans;
|
|
}
|
|
|
|
for (x = 0; x < blocks; ) {
|
|
uint64_t dblock;
|
|
unsigned int extlen;
|
|
int new = 1;
|
|
|
|
error = gfs2_extent_map(&ip->i_inode, lblock, &new, &dblock, &extlen);
|
|
if (error)
|
|
goto out_trans;
|
|
|
|
lblock += extlen;
|
|
x += extlen;
|
|
}
|
|
|
|
gfs2_assert_warn(sdp, al->al_alloced);
|
|
|
|
out_trans:
|
|
gfs2_trans_end(sdp);
|
|
|
|
out_ipres:
|
|
gfs2_inplace_release(ip);
|
|
|
|
out_gunlock_q:
|
|
gfs2_quota_unlock(ip);
|
|
|
|
out:
|
|
gfs2_alloc_put(ip);
|
|
|
|
return error;
|
|
}
|
|
|
|
static struct page *gfs2_sharewrite_nopage(struct vm_area_struct *area,
|
|
unsigned long address, int *type)
|
|
{
|
|
struct gfs2_inode *ip = GFS2_I(area->vm_file->f_mapping->host);
|
|
struct gfs2_holder i_gh;
|
|
struct page *result = NULL;
|
|
unsigned long index = ((address - area->vm_start) >> PAGE_CACHE_SHIFT) +
|
|
area->vm_pgoff;
|
|
int alloc_required;
|
|
int error;
|
|
|
|
error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &i_gh);
|
|
if (error)
|
|
return NULL;
|
|
|
|
set_bit(GIF_PAGED, &ip->i_flags);
|
|
set_bit(GIF_SW_PAGED, &ip->i_flags);
|
|
|
|
error = gfs2_write_alloc_required(ip,
|
|
(uint64_t)index << PAGE_CACHE_SHIFT,
|
|
PAGE_CACHE_SIZE, &alloc_required);
|
|
if (error)
|
|
goto out;
|
|
|
|
result = filemap_nopage(area, address, type);
|
|
if (!result || result == NOPAGE_OOM)
|
|
goto out;
|
|
|
|
if (alloc_required) {
|
|
error = alloc_page_backing(ip, result);
|
|
if (error) {
|
|
page_cache_release(result);
|
|
result = NULL;
|
|
goto out;
|
|
}
|
|
set_page_dirty(result);
|
|
}
|
|
|
|
pfault_be_greedy(ip);
|
|
|
|
out:
|
|
gfs2_glock_dq_uninit(&i_gh);
|
|
|
|
return result;
|
|
}
|
|
|
|
struct vm_operations_struct gfs2_vm_ops_private = {
|
|
.nopage = gfs2_private_nopage,
|
|
};
|
|
|
|
struct vm_operations_struct gfs2_vm_ops_sharewrite = {
|
|
.nopage = gfs2_sharewrite_nopage,
|
|
};
|
|
|