UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity
OpenCloudOS-Kernel/fs/gfs2/ops_address.c

671 lines
16 KiB
C
Raw Blame History

/*
* 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/pagemap.h>
#include <linux/pagevec.h>
#include <linux/mpage.h>
#include <linux/fs.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 "log.h"
#include "meta_io.h"
#include "ops_address.h"
#include "page.h"
#include "quota.h"
#include "trans.h"
#include "rgrp.h"
#include "ops_file.h"
#include "util.h"
/**
* 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)
{
int new = create;
uint64_t dblock;
int error;
int boundary;
error = gfs2_block_map(inode, lblock, &new, &dblock, &boundary);
if (error)
return error;
if (!dblock)
return 0;
map_bh(bh_result, inode->i_sb, dblock);
if (new)
set_buffer_new(bh_result);
if (boundary)
set_buffer_boundary(bh_result);
return 0;
}
/**
* 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 get_block_noalloc(struct inode *inode, sector_t lblock,
struct buffer_head *bh_result, int create)
{
struct gfs2_inode *ip = inode->u.generic_ip;
int new = 0;
uint64_t dblock;
int error;
int boundary;
error = gfs2_block_map(inode, lblock, &new, &dblock, &boundary);
if (error)
return error;
if (dblock)
map_bh(bh_result, inode->i_sb, dblock);
else if (gfs2_assert_withdraw(ip->i_sbd, !create))
error = -EIO;
if (boundary)
set_buffer_boundary(bh_result);
return error;
}
/**
* 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 = page->mapping->host->u.generic_ip;
struct gfs2_sbd *sdp = ip->i_sbd;
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)) {
error = gfs2_trans_begin(sdp, RES_DINODE + 1, 0);
if (error)
goto out_ignore;
gfs2_page_add_databufs(ip, page, 0, sdp->sd_vfs->s_blocksize-1);
done_trans = 1;
}
error = block_write_full_page(page, 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;
}
static int zero_readpage(struct page *page)
{
void *kaddr;
kaddr = kmap_atomic(page, KM_USER0);
memset(kaddr, 0, PAGE_CACHE_SIZE);
kunmap_atomic(page, KM_USER0);
SetPageUptodate(page);
return 0;
}
/**
* 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;
/* Only the first page of a stuffed file might contain data */
if (unlikely(page->index))
return zero_readpage(page);
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(page, KM_USER0);
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 = page->mapping->host->u.generic_ip;
struct gfs2_sbd *sdp = ip->i_sbd;
struct gfs2_holder gh;
int error;
if (likely(file != &gfs2_internal_file_sentinal)) {
gfs2_holder_init(ip->i_gl, LM_ST_SHARED, GL_ATIME|GL_AOP, &gh);
error = gfs2_glock_nq_m_atime(1, &gh);
if (unlikely(error))
goto out_unlock;
}
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 (file != &gfs2_internal_file_sentinal) {
gfs2_glock_dq_m(1, &gh);
gfs2_holder_uninit(&gh);
}
out:
return error;
out_unlock:
unlock_page(page);
if (file != &gfs2_internal_file_sentinal)
gfs2_holder_uninit(&gh);
goto out;
}
#define list_to_page(head) (list_entry((head)->prev, struct page, lru))
/**
* 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 have to handle stuffed files here too.
* 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 = inode->u.generic_ip;
struct gfs2_sbd *sdp = ip->i_sbd;
struct gfs2_holder gh;
unsigned page_idx;
int ret;
if (likely(file != &gfs2_internal_file_sentinal)) {
gfs2_holder_init(ip->i_gl, LM_ST_SHARED,
LM_FLAG_TRY_1CB|GL_ATIME|GL_AOP, &gh);
ret = gfs2_glock_nq_m_atime(1, &gh);
if (ret == GLR_TRYFAILED)
goto out_noerror;
if (unlikely(ret))
goto out_unlock;
}
if (gfs2_is_stuffed(ip)) {
struct pagevec lru_pvec;
pagevec_init(&lru_pvec, 0);
for (page_idx = 0; page_idx < nr_pages; page_idx++) {
struct page *page = list_to_page(pages);
list_del(&page->lru);
if (!add_to_page_cache(page, mapping,
page->index, GFP_KERNEL)) {
ret = stuffed_readpage(ip, page);
unlock_page(page);
if (!pagevec_add(&lru_pvec, page))
__pagevec_lru_add(&lru_pvec);
}
page_cache_release(page);
}
pagevec_lru_add(&lru_pvec);
ret = 0;
} else {
/* What we really want to do .... */
ret = mpage_readpages(mapping, pages, nr_pages, gfs2_get_block);
}
if (likely(file != &gfs2_internal_file_sentinal)) {
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:
/* unlock all pages, we can't do any I/O right now */
for (page_idx = 0; page_idx < nr_pages; page_idx++) {
struct page *page = list_to_page(pages);
list_del(&page->lru);
unlock_page(page);
page_cache_release(page);
}
if (likely(file != &gfs2_internal_file_sentinal))
gfs2_holder_uninit(&gh);
goto out;
}
/**
* gfs2_prepare_write - Prepare to write a page to a file
* @file: The file to write to
* @page: The page which is to be prepared for writing
* @from: From (byte range within page)
* @to: To (byte range within page)
*
* Returns: errno
*/
static int gfs2_prepare_write(struct file *file, struct page *page,
unsigned from, unsigned to)
{
struct gfs2_inode *ip = page->mapping->host->u.generic_ip;
struct gfs2_sbd *sdp = ip->i_sbd;
unsigned int data_blocks, ind_blocks, rblocks;
int alloc_required;
int error = 0;
loff_t pos = ((loff_t)page->index << PAGE_CACHE_SHIFT) + from;
loff_t end = ((loff_t)page->index << PAGE_CACHE_SHIFT) + to;
struct gfs2_alloc *al;
gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, GL_ATIME|GL_AOP, &ip->i_gh);
error = gfs2_glock_nq_m_atime(1, &ip->i_gh);
if (error)
goto out_uninit;
gfs2_write_calc_reserv(ip, to - from, &data_blocks, &ind_blocks);
error = gfs2_write_alloc_required(ip, pos, from - to, &alloc_required);
if (error)
goto out_unlock;
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_di.di_uid, ip->i_di.di_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, 0);
if (error)
goto out;
if (gfs2_is_stuffed(ip)) {
if (end > sdp->sd_sb.sb_bsize - sizeof(struct gfs2_dinode)) {
error = gfs2_unstuff_dinode(ip, gfs2_unstuffer_page,
page);
if (error == 0)
goto prepare_write;
} else if (!PageUptodate(page))
error = stuffed_readpage(ip, page);
goto out;
}
prepare_write:
error = block_prepare_write(page, from, to, gfs2_get_block);
out:
if (error) {
gfs2_trans_end(sdp);
if (alloc_required) {
gfs2_inplace_release(ip);
out_qunlock:
gfs2_quota_unlock(ip);
out_alloc_put:
gfs2_alloc_put(ip);
}
out_unlock:
gfs2_glock_dq_m(1, &ip->i_gh);
out_uninit:
gfs2_holder_uninit(&ip->i_gh);
}
return error;
}
/**
* gfs2_commit_write - Commit write to a file
* @file: The file to write to
* @page: The page containing the data
* @from: From (byte range within page)
* @to: To (byte range within page)
*
* Returns: errno
*/
static int gfs2_commit_write(struct file *file, struct page *page,
unsigned from, unsigned to)
{
struct inode *inode = page->mapping->host;
struct gfs2_inode *ip = inode->u.generic_ip;
struct gfs2_sbd *sdp = ip->i_sbd;
int error = -EOPNOTSUPP;
struct buffer_head *dibh;
struct gfs2_alloc *al = &ip->i_alloc;;
if (gfs2_assert_withdraw(sdp, gfs2_glock_is_locked_by_me(ip->i_gl)))
goto fail_nounlock;
error = gfs2_meta_inode_buffer(ip, &dibh);
if (error)
goto fail_endtrans;
gfs2_trans_add_bh(ip->i_gl, dibh, 1);
if (gfs2_is_stuffed(ip)) {
uint64_t file_size;
void *kaddr;
file_size = ((uint64_t)page->index << PAGE_CACHE_SHIFT) + to;
kaddr = kmap_atomic(page, KM_USER0);
memcpy(dibh->b_data + sizeof(struct gfs2_dinode) + from,
(char *)kaddr + from, to - from);
kunmap_atomic(page, KM_USER0);
SetPageUptodate(page);
if (inode->i_size < file_size)
i_size_write(inode, file_size);
} else {
if (sdp->sd_args.ar_data == GFS2_DATA_ORDERED ||
gfs2_is_jdata(ip))
gfs2_page_add_databufs(ip, page, from, to);
error = generic_commit_write(file, page, from, to);
if (error)
goto fail;
}
if (ip->i_di.di_size < inode->i_size)
ip->i_di.di_size = inode->i_size;
gfs2_dinode_out(&ip->i_di, dibh->b_data);
brelse(dibh);
gfs2_trans_end(sdp);
if (al->al_requested) {
gfs2_inplace_release(ip);
gfs2_quota_unlock(ip);
gfs2_alloc_put(ip);
}
gfs2_glock_dq_m(1, &ip->i_gh);
gfs2_holder_uninit(&ip->i_gh);
return 0;
fail:
brelse(dibh);
fail_endtrans:
gfs2_trans_end(sdp);
if (al->al_requested) {
gfs2_inplace_release(ip);
gfs2_quota_unlock(ip);
gfs2_alloc_put(ip);
}
gfs2_glock_dq_m(1, &ip->i_gh);
gfs2_holder_uninit(&ip->i_gh);
fail_nounlock:
ClearPageUptodate(page);
return error;
}
/**
* gfs2_bmap - Block map function
* @mapping: Address space info
* @lblock: The block to map
*
* Returns: The disk address for the block or 0 on hole or error
*/
static sector_t gfs2_bmap(struct address_space *mapping, sector_t lblock)
{
struct gfs2_inode *ip = mapping->host->u.generic_ip;
struct gfs2_holder i_gh;
sector_t dblock = 0;
int error;
error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, &i_gh);
if (error)
return 0;
if (!gfs2_is_stuffed(ip))
dblock = generic_block_bmap(mapping, lblock, gfs2_get_block);
gfs2_glock_dq_uninit(&i_gh);
return dblock;
}
static void discard_buffer(struct gfs2_sbd *sdp, struct buffer_head *bh)
{
struct gfs2_bufdata *bd;
gfs2_log_lock(sdp);
bd = bh->b_private;
if (bd) {
bd->bd_bh = NULL;
bh->b_private = NULL;
gfs2_log_unlock(sdp);
brelse(bh);
} else
gfs2_log_unlock(sdp);
lock_buffer(bh);
clear_buffer_dirty(bh);
bh->b_bdev = NULL;
clear_buffer_mapped(bh);
clear_buffer_req(bh);
clear_buffer_new(bh);
clear_buffer_delay(bh);
unlock_buffer(bh);
}
static void gfs2_invalidatepage(struct page *page, unsigned long offset)
{
struct gfs2_sbd *sdp = page->mapping->host->i_sb->s_fs_info;
struct buffer_head *head, *bh, *next;
unsigned int curr_off = 0;
BUG_ON(!PageLocked(page));
if (!page_has_buffers(page))
return;
bh = head = page_buffers(page);
do {
unsigned int next_off = curr_off + bh->b_size;
next = bh->b_this_page;
if (offset <= curr_off)
discard_buffer(sdp, bh);
curr_off = next_off;
bh = next;
} while (bh != head);
if (!offset)
try_to_release_page(page, 0);
return;
}
static ssize_t gfs2_direct_IO_write(struct kiocb *iocb, const struct iovec *iov,
loff_t offset, unsigned long nr_segs)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
struct gfs2_inode *ip = inode->u.generic_ip;
struct gfs2_holder gh;
int rv;
/*
* Shared lock, even though its write, since we do no allocation
* on this path. All we need change is atime.
*/
gfs2_holder_init(ip->i_gl, LM_ST_SHARED, GL_ATIME, &gh);
rv = gfs2_glock_nq_m_atime(1, &gh);
if (rv)
goto out;
/*
* Should we return an error here? I can't see that O_DIRECT for
* a journaled file makes any sense. For now we'll silently fall
* back to buffered I/O, likewise we do the same for stuffed
* files since they are (a) small and (b) unaligned.
*/
if (gfs2_is_jdata(ip))
goto out;
if (gfs2_is_stuffed(ip))
goto out;
rv = __blockdev_direct_IO(WRITE, iocb, inode, inode->i_sb->s_bdev,
iov, offset, nr_segs, gfs2_get_block,
NULL, DIO_OWN_LOCKING);
out:
gfs2_glock_dq_m(1, &gh);
gfs2_holder_uninit(&gh);
return rv;
}
/**
* gfs2_direct_IO
*
* This is called with a shared lock already held for the read path.
* Currently, no locks are held when the write path is called.
*/
static ssize_t gfs2_direct_IO(int rw, struct kiocb *iocb,
const struct iovec *iov, loff_t offset,
unsigned long nr_segs)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
struct gfs2_inode *ip = inode->u.generic_ip;
struct gfs2_sbd *sdp = ip->i_sbd;
if (rw == WRITE)
return gfs2_direct_IO_write(iocb, iov, offset, nr_segs);
if (gfs2_assert_warn(sdp, gfs2_glock_is_locked_by_me(ip->i_gl)) ||
gfs2_assert_warn(sdp, !gfs2_is_stuffed(ip)))
return -EINVAL;
return __blockdev_direct_IO(READ, iocb, inode, inode->i_sb->s_bdev, iov,
offset, nr_segs, gfs2_get_block, NULL,
DIO_OWN_LOCKING);
}
struct address_space_operations gfs2_file_aops = {
.writepage = gfs2_writepage,
.readpage = gfs2_readpage,
.readpages = gfs2_readpages,
.sync_page = block_sync_page,
.prepare_write = gfs2_prepare_write,
.commit_write = gfs2_commit_write,
.bmap = gfs2_bmap,
.invalidatepage = gfs2_invalidatepage,
.direct_IO = gfs2_direct_IO,
};
Reference in New Issue View Git Blame Copy Permalink