/*
* Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved.
- * Copyright (C) 2004-2007 Red Hat, Inc. All rights reserved.
+ * Copyright (C) 2004-2008 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
#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 <linux/backing-dev.h>
#include "gfs2.h"
#include "incore.h"
#include "quota.h"
#include "trans.h"
#include "rgrp.h"
-#include "ops_file.h"
#include "super.h"
#include "util.h"
#include "glops.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)
-{
- 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
{
int error;
- error = gfs2_block_map(inode, lblock, 0, bh_result);
+ error = gfs2_block_map(inode, lblock, bh_result, 0);
if (error)
return error;
- if (bh_result->b_blocknr == 0)
+ 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);
+ return gfs2_block_map(inode, lblock, bh_result, 0);
}
/**
- * gfs2_writepage - Write complete page
- * @page: Page to write
+ * gfs2_writepage_common - Common bits of writepage
+ * @page: The page to be written
+ * @wbc: The writeback control
*
- * Returns: errno
- *
- * Some of this is copied from block_write_full_page() although we still
- * call it to do most of the work.
+ * Returns: 1 if writepage is ok, otherwise an error code or zero if no error.
*/
-static int gfs2_writepage(struct page *page, struct writeback_control *wbc)
+static int gfs2_writepage_common(struct page *page,
+ struct writeback_control *wbc)
{
struct inode *inode = page->mapping->host;
struct gfs2_inode *ip = GFS2_I(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 (gfs2_assert_withdraw(sdp, gfs2_glock_is_held_excl(ip->i_gl)))
+ goto out;
if (current->journal_info)
- goto out_ignore;
-
+ goto redirty;
/* Is the page fully outside i_size? (truncate in progress) */
- offset = i_size & (PAGE_CACHE_SIZE-1);
+ 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 */
+ goto out;
+ }
+ return 1;
+redirty:
+ redirty_page_for_writepage(wbc, page);
+out:
+ unlock_page(page);
+ return 0;
+}
+
+/**
+ * gfs2_writeback_writepage - Write page for writeback mappings
+ * @page: The page
+ * @wbc: The writeback control
+ *
+ */
+
+static int gfs2_writeback_writepage(struct page *page,
+ struct writeback_control *wbc)
+{
+ int ret;
+
+ ret = gfs2_writepage_common(page, wbc);
+ if (ret <= 0)
+ return ret;
+
+ ret = mpage_writepage(page, gfs2_get_block_noalloc, wbc);
+ if (ret == -EAGAIN)
+ ret = block_write_full_page(page, gfs2_get_block_noalloc, wbc);
+ return ret;
+}
+
+/**
+ * gfs2_ordered_writepage - Write page for ordered data files
+ * @page: The page to write
+ * @wbc: The writeback control
+ *
+ */
+
+static int gfs2_ordered_writepage(struct page *page,
+ struct writeback_control *wbc)
+{
+ struct inode *inode = page->mapping->host;
+ struct gfs2_inode *ip = GFS2_I(inode);
+ int ret;
+
+ ret = gfs2_writepage_common(page, wbc);
+ if (ret <= 0)
+ return ret;
+
+ 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, inode->i_sb->s_blocksize-1);
+ return block_write_full_page(page, gfs2_get_block_noalloc, wbc);
+}
- if ((sdp->sd_args.ar_data == GFS2_DATA_ORDERED || gfs2_is_jdata(ip)) &&
- PageChecked(page)) {
+/**
+ * __gfs2_jdata_writepage - The core of jdata writepage
+ * @page: The page to write
+ * @wbc: The writeback control
+ *
+ * This is shared between writepage and writepages and implements the
+ * core of the writepage operation. If a transaction is required then
+ * PageChecked will have been set and the transaction will have
+ * already been started before this is called.
+ */
+
+static int __gfs2_jdata_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);
+
+ if (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);
+ }
+ return block_write_full_page(page, gfs2_get_block_noalloc, wbc);
+}
+
+/**
+ * gfs2_jdata_writepage - Write complete page
+ * @page: Page to write
+ *
+ * Returns: errno
+ *
+ */
+
+static int gfs2_jdata_writepage(struct page *page, struct writeback_control *wbc)
+{
+ struct inode *inode = page->mapping->host;
+ struct gfs2_sbd *sdp = GFS2_SB(inode);
+ int ret;
+ int done_trans = 0;
+
+ if (PageChecked(page)) {
+ if (wbc->sync_mode != WB_SYNC_ALL)
+ goto out_ignore;
+ ret = gfs2_trans_begin(sdp, RES_DINODE + 1, 0);
+ if (ret)
+ goto out_ignore;
done_trans = 1;
}
- error = block_write_full_page(page, gfs2_get_block_noalloc, wbc);
+ ret = gfs2_writepage_common(page, wbc);
+ if (ret > 0)
+ ret = __gfs2_jdata_writepage(page, wbc);
if (done_trans)
gfs2_trans_end(sdp);
- gfs2_meta_cache_flush(ip);
- return error;
+ return ret;
out_ignore:
redirty_page_for_writepage(wbc, page);
}
/**
- * gfs2_writepages - Write a bunch of dirty pages back to disk
+ * gfs2_writeback_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
+ * For the data=writeback case 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)
+static int gfs2_writeback_writepages(struct address_space *mapping,
+ struct writeback_control *wbc)
+{
+ return mpage_writepages(mapping, wbc, gfs2_get_block_noalloc);
+}
+
+/**
+ * gfs2_write_jdata_pagevec - Write back a pagevec's worth of pages
+ * @mapping: The mapping
+ * @wbc: The writeback control
+ * @writepage: The writepage function to call for each page
+ * @pvec: The vector of pages
+ * @nr_pages: The number of pages to write
+ *
+ * Returns: non-zero if loop should terminate, zero otherwise
+ */
+
+static int gfs2_write_jdata_pagevec(struct address_space *mapping,
+ struct writeback_control *wbc,
+ struct pagevec *pvec,
+ int nr_pages, pgoff_t end)
{
struct inode *inode = 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 = i_size & (PAGE_CACHE_SIZE-1);
+ unsigned nrblocks = nr_pages * (PAGE_CACHE_SIZE/inode->i_sb->s_blocksize);
+ struct backing_dev_info *bdi = mapping->backing_dev_info;
+ int i;
+ int ret;
+
+ ret = gfs2_trans_begin(sdp, nrblocks, nrblocks);
+ if (ret < 0)
+ return ret;
+
+ for(i = 0; i < nr_pages; i++) {
+ struct page *page = pvec->pages[i];
+
+ lock_page(page);
+
+ if (unlikely(page->mapping != mapping)) {
+ unlock_page(page);
+ continue;
+ }
+
+ if (!wbc->range_cyclic && page->index > end) {
+ ret = 1;
+ unlock_page(page);
+ continue;
+ }
+
+ if (wbc->sync_mode != WB_SYNC_NONE)
+ wait_on_page_writeback(page);
+
+ if (PageWriteback(page) ||
+ !clear_page_dirty_for_io(page)) {
+ unlock_page(page);
+ continue;
+ }
+
+ /* Is the page fully outside i_size? (truncate in progress) */
+ if (page->index > end_index || (page->index == end_index && !offset)) {
+ page->mapping->a_ops->invalidatepage(page, 0);
+ unlock_page(page);
+ continue;
+ }
+
+ ret = __gfs2_jdata_writepage(page, wbc);
+
+ if (ret || (--(wbc->nr_to_write) <= 0))
+ ret = 1;
+ if (wbc->nonblocking && bdi_write_congested(bdi)) {
+ wbc->encountered_congestion = 1;
+ ret = 1;
+ }
+
+ }
+ gfs2_trans_end(sdp);
+ return ret;
+}
+
+/**
+ * gfs2_write_cache_jdata - Like write_cache_pages but different
+ * @mapping: The mapping to write
+ * @wbc: The writeback control
+ * @writepage: The writepage function to call
+ * @data: The data to pass to writepage
+ *
+ * The reason that we use our own function here is that we need to
+ * start transactions before we grab page locks. This allows us
+ * to get the ordering right.
+ */
- if (sdp->sd_args.ar_data == GFS2_DATA_WRITEBACK && !gfs2_is_jdata(ip))
- return mpage_writepages(mapping, wbc, gfs2_get_block_noalloc);
+static int gfs2_write_cache_jdata(struct address_space *mapping,
+ struct writeback_control *wbc)
+{
+ struct backing_dev_info *bdi = mapping->backing_dev_info;
+ int ret = 0;
+ int done = 0;
+ struct pagevec pvec;
+ int nr_pages;
+ pgoff_t index;
+ pgoff_t end;
+ int scanned = 0;
+ int range_whole = 0;
+
+ if (wbc->nonblocking && bdi_write_congested(bdi)) {
+ wbc->encountered_congestion = 1;
+ return 0;
+ }
- return generic_writepages(mapping, wbc);
+ pagevec_init(&pvec, 0);
+ if (wbc->range_cyclic) {
+ index = mapping->writeback_index; /* Start from prev offset */
+ end = -1;
+ } else {
+ index = wbc->range_start >> PAGE_CACHE_SHIFT;
+ end = wbc->range_end >> PAGE_CACHE_SHIFT;
+ if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
+ range_whole = 1;
+ scanned = 1;
+ }
+
+retry:
+ while (!done && (index <= end) &&
+ (nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
+ PAGECACHE_TAG_DIRTY,
+ min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1))) {
+ scanned = 1;
+ ret = gfs2_write_jdata_pagevec(mapping, wbc, &pvec, nr_pages, end);
+ if (ret)
+ done = 1;
+ if (ret > 0)
+ ret = 0;
+
+ pagevec_release(&pvec);
+ cond_resched();
+ }
+
+ if (!scanned && !done) {
+ /*
+ * We hit the last page and there is more work to be done: wrap
+ * back to the start of the file
+ */
+ scanned = 1;
+ index = 0;
+ goto retry;
+ }
+
+ if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
+ mapping->writeback_index = index;
+ return ret;
+}
+
+
+/**
+ * gfs2_jdata_writepages - Write a bunch of dirty pages back to disk
+ * @mapping: The mapping to write
+ * @wbc: The writeback control
+ *
+ */
+
+static int gfs2_jdata_writepages(struct address_space *mapping,
+ struct writeback_control *wbc)
+{
+ struct gfs2_inode *ip = GFS2_I(mapping->host);
+ struct gfs2_sbd *sdp = GFS2_SB(mapping->host);
+ int ret;
+
+ ret = gfs2_write_cache_jdata(mapping, wbc);
+ if (ret == 0 && wbc->sync_mode == WB_SYNC_ALL) {
+ gfs2_log_flush(sdp, ip->i_gl);
+ ret = gfs2_write_cache_jdata(mapping, wbc);
+ }
+ return ret;
}
/**
int error;
/*
- * Due to the order of unstuffing files and ->nopage(), we can be
+ * Due to the order of unstuffing files and ->fault(), 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);
+ zero_user(page, 0, PAGE_CACHE_SIZE);
+ SetPageUptodate(page);
return 0;
}
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);
+ ip->i_disksize);
+ memset(kaddr + ip->i_disksize, 0, PAGE_CACHE_SIZE - ip->i_disksize);
kunmap_atomic(kaddr, KM_USER0);
flush_dcache_page(page);
brelse(dibh);
/**
- * 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.
+ * __gfs2_readpage - readpage
+ * @file: The file to read a page for
* @page: The page to read
*
- * Returns: errno
+ * This is the core of gfs2's readpage. Its used by the internal file
+ * reading code as in that case we already hold the glock. Also its
+ * called by gfs2_readpage() once the required lock has been granted.
+ *
*/
-static int gfs2_readpage(struct file *file, struct page *page)
+static int __gfs2_readpage(void *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);
+ } else {
+ error = mpage_readpage(page, gfs2_block_map);
+ }
if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
- error = -EIO;
+ return -EIO;
- if (do_unlock) {
- gfs2_glock_dq_m(1, &gh);
- gfs2_holder_uninit(&gh);
- }
-out:
return error;
-out_unlock:
+}
+
+/**
+ * gfs2_readpage - read a page of a file
+ * @file: The file to read
+ * @page: The page of the file
+ *
+ * This deals with the locking required. We have to unlock and
+ * relock the page in order to get the locking in the right
+ * order.
+ */
+
+static int gfs2_readpage(struct file *file, struct page *page)
+{
+ struct address_space *mapping = page->mapping;
+ struct gfs2_inode *ip = GFS2_I(mapping->host);
+ struct gfs2_holder gh;
+ int error;
+
unlock_page(page);
- if (error == GLR_TRYFAILED) {
- error = AOP_TRUNCATED_PAGE;
- yield();
- }
- if (do_unlock)
- gfs2_holder_uninit(&gh);
- goto out;
+ gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
+ error = gfs2_glock_nq(&gh);
+ if (unlikely(error))
+ goto out;
+ error = AOP_TRUNCATED_PAGE;
+ lock_page(page);
+ if (page->mapping == mapping && !PageUptodate(page))
+ error = __gfs2_readpage(file, page);
+ else
+ unlock_page(page);
+ gfs2_glock_dq(&gh);
+out:
+ gfs2_holder_uninit(&gh);
+ if (error && error != AOP_TRUNCATED_PAGE)
+ lock_page(page);
+ return error;
+}
+
+/**
+ * gfs2_internal_read - read an internal file
+ * @ip: The gfs2 inode
+ * @ra_state: The readahead state (or NULL for no readahead)
+ * @buf: The buffer to fill
+ * @pos: The file position
+ * @size: The amount to read
+ *
+ */
+
+int gfs2_internal_read(struct gfs2_inode *ip, struct file_ra_state *ra_state,
+ char *buf, loff_t *pos, unsigned size)
+{
+ struct address_space *mapping = ip->i_inode.i_mapping;
+ unsigned long index = *pos / PAGE_CACHE_SIZE;
+ unsigned offset = *pos & (PAGE_CACHE_SIZE - 1);
+ unsigned copied = 0;
+ unsigned amt;
+ struct page *page;
+ void *p;
+
+ do {
+ amt = size - copied;
+ if (offset + size > PAGE_CACHE_SIZE)
+ amt = PAGE_CACHE_SIZE - offset;
+ page = read_cache_page(mapping, index, __gfs2_readpage, NULL);
+ if (IS_ERR(page))
+ return PTR_ERR(page);
+ p = kmap_atomic(page, KM_USER0);
+ memcpy(buf + copied, p + offset, amt);
+ kunmap_atomic(p, KM_USER0);
+ mark_page_accessed(page);
+ page_cache_release(page);
+ copied += amt;
+ index++;
+ offset = 0;
+ } while(copied < size);
+ (*pos) += size;
+ return size;
}
/**
* 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.
+ * 4. gfs2_block_map() is relied upon to set BH_Boundary in the right places.
*/
+
static int gfs2_readpages(struct file *file, struct address_space *mapping,
struct list_head *pages, unsigned nr_pages)
{
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;
+ int ret;
- 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:
+ gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
+ ret = gfs2_glock_nq(&gh);
+ if (unlikely(ret))
+ goto out_uninit;
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:
+ ret = mpage_readpages(mapping, pages, nr_pages, gfs2_block_map);
+ gfs2_glock_dq(&gh);
+out_uninit:
+ gfs2_holder_uninit(&gh);
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_prepare_write - Prepare to write a page to a file
+ * gfs2_write_begin - Begin to write 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)
+ * @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_prepare_write(struct file *file, struct page *page,
- unsigned from, unsigned to)
+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(page->mapping->host);
- struct gfs2_sbd *sdp = GFS2_SB(page->mapping->host);
- unsigned int data_blocks, ind_blocks, rblocks;
+ struct gfs2_inode *ip = GFS2_I(mapping->host);
+ struct gfs2_sbd *sdp = GFS2_SB(mapping->host);
+ unsigned int data_blocks = 0, ind_blocks = 0, 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;
- unsigned int write_len = to - from;
-
-
- gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, GL_ATIME|LM_FLAG_TRY_1CB, &ip->i_gh);
- error = gfs2_glock_nq_atime(&ip->i_gh);
- if (unlikely(error)) {
- if (error == GLR_TRYFAILED) {
- unlock_page(page);
- error = AOP_TRUNCATED_PAGE;
- yield();
- }
+ 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, 0, &ip->i_gh);
+ error = gfs2_glock_nq(&ip->i_gh);
+ if (unlikely(error))
goto out_uninit;
- }
-
- gfs2_write_calc_reserv(ip, write_len, &data_blocks, &ind_blocks);
- error = gfs2_write_alloc_required(ip, pos, write_len, &alloc_required);
+ error = gfs2_write_alloc_required(ip, pos, len, &alloc_required);
if (error)
goto out_unlock;
+ if (alloc_required || gfs2_is_jdata(ip))
+ gfs2_write_calc_reserv(ip, len, &data_blocks, &ind_blocks);
- ip->i_alloc.al_requested = 0;
if (alloc_required) {
al = gfs2_alloc_get(ip);
+ if (!al) {
+ error = -ENOMEM;
+ goto out_unlock;
+ }
- error = gfs2_quota_lock(ip, NO_QUOTA_CHANGE, NO_QUOTA_CHANGE);
+ error = gfs2_quota_lock_check(ip);
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)
if (ind_blocks || data_blocks)
rblocks += RES_STATFS + RES_QUOTA;
- error = gfs2_trans_begin(sdp, rblocks, 0);
+ error = gfs2_trans_begin(sdp, rblocks,
+ PAGE_CACHE_SIZE/sdp->sd_sb.sb_bsize);
if (error)
goto out_trans_fail;
+ error = -ENOMEM;
+ flags |= AOP_FLAG_NOFS;
+ page = grab_cache_page_write_begin(mapping, index, flags);
+ *pagep = page;
+ if (unlikely(!page))
+ goto out_endtrans;
+
if (gfs2_is_stuffed(ip)) {
- if (end > sdp->sd_sb.sb_bsize - sizeof(struct gfs2_dinode)) {
+ error = 0;
+ if (pos + len > sdp->sd_sb.sb_bsize - sizeof(struct gfs2_dinode)) {
error = gfs2_unstuff_dinode(ip, page);
if (error == 0)
goto prepare_write;
- } else if (!PageUptodate(page))
+ } else if (!PageUptodate(page)) {
error = stuffed_readpage(ip, page);
+ }
goto out;
}
prepare_write:
- error = block_prepare_write(page, from, to, gfs2_get_block);
-
+ error = block_prepare_write(page, from, to, gfs2_block_map);
out:
- if (error) {
- gfs2_trans_end(sdp);
+ if (error == 0)
+ return 0;
+
+ page_cache_release(page);
+ if (pos + len > ip->i_inode.i_size)
+ vmtruncate(&ip->i_inode, ip->i_inode.i_size);
+out_endtrans:
+ gfs2_trans_end(sdp);
out_trans_fail:
- if (alloc_required) {
- gfs2_inplace_release(ip);
+ if (alloc_required) {
+ gfs2_inplace_release(ip);
out_qunlock:
- gfs2_quota_unlock(ip);
+ gfs2_quota_unlock(ip);
out_alloc_put:
- gfs2_alloc_put(ip);
- }
+ gfs2_alloc_put(ip);
+ }
out_unlock:
- gfs2_glock_dq_m(1, &ip->i_gh);
+ gfs2_glock_dq(&ip->i_gh);
out_uninit:
- gfs2_holder_uninit(&ip->i_gh);
- }
-
+ gfs2_holder_uninit(&ip->i_gh);
return error;
}
}
/**
- * gfs2_commit_write - Commit write to a file
+ * gfs2_stuffed_write_end - Write end for stuffed files
+ * @inode: The inode
+ * @dibh: The buffer_head containing the on-disk inode
+ * @pos: The file position
+ * @len: The length of the write
+ * @copied: How much was actually copied by the VFS
+ * @page: The page
+ *
+ * This copies the data from the page into the inode block after
+ * the inode data structure itself.
+ *
+ * Returns: errno
+ */
+static int gfs2_stuffed_write_end(struct inode *inode, struct buffer_head *dibh,
+ loff_t pos, unsigned len, unsigned copied,
+ struct page *page)
+{
+ struct gfs2_inode *ip = GFS2_I(inode);
+ struct gfs2_sbd *sdp = GFS2_SB(inode);
+ u64 to = pos + copied;
+ void *kaddr;
+ unsigned char *buf = dibh->b_data + sizeof(struct gfs2_dinode);
+ struct gfs2_dinode *di = (struct gfs2_dinode *)dibh->b_data;
+
+ BUG_ON((pos + len) > (dibh->b_size - sizeof(struct gfs2_dinode)));
+ kaddr = kmap_atomic(page, KM_USER0);
+ memcpy(buf + pos, kaddr + pos, copied);
+ memset(kaddr + pos + copied, 0, len - copied);
+ flush_dcache_page(page);
+ kunmap_atomic(kaddr, KM_USER0);
+
+ if (!PageUptodate(page))
+ SetPageUptodate(page);
+ unlock_page(page);
+ page_cache_release(page);
+
+ if (inode->i_size < to) {
+ i_size_write(inode, to);
+ ip->i_disksize = inode->i_size;
+ di->di_size = cpu_to_be64(inode->i_size);
+ mark_inode_dirty(inode);
+ }
+
+ if (inode == sdp->sd_rindex)
+ adjust_fs_space(inode);
+
+ brelse(dibh);
+ gfs2_trans_end(sdp);
+ gfs2_glock_dq(&ip->i_gh);
+ gfs2_holder_uninit(&ip->i_gh);
+ return copied;
+}
+
+/**
+ * gfs2_write_end
* @file: The file to write to
- * @page: The page containing the data
- * @from: From (byte range within page)
- * @to: To (byte range within page)
+ * @mapping: The address space to write to
+ * @pos: The file position
+ * @len: The length of the data
+ * @copied:
+ * @page: The page that has been written
+ * @fsdata: The fsdata (unused in GFS2)
+ *
+ * The main write_end function for GFS2. We have a separate one for
+ * stuffed files as they are slightly different, otherwise we just
+ * put our locking around the VFS provided functions.
*
* Returns: errno
*/
-static int gfs2_commit_write(struct file *file, struct page *page,
- unsigned from, unsigned to)
+static int gfs2_write_end(struct file *file, struct address_space *mapping,
+ loff_t pos, unsigned len, unsigned copied,
+ struct page *page, void *fsdata)
{
struct inode *inode = page->mapping->host;
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_sbd *sdp = GFS2_SB(inode);
- int error = -EOPNOTSUPP;
struct buffer_head *dibh;
- struct gfs2_alloc *al = &ip->i_alloc;
+ struct gfs2_alloc *al = ip->i_alloc;
struct gfs2_dinode *di;
+ unsigned int from = pos & (PAGE_CACHE_SIZE - 1);
+ unsigned int to = from + len;
+ int ret;
- if (gfs2_assert_withdraw(sdp, gfs2_glock_is_locked_by_me(ip->i_gl)))
- goto fail_nounlock;
+ BUG_ON(gfs2_glock_is_locked_by_me(ip->i_gl) == NULL);
- error = gfs2_meta_inode_buffer(ip, &dibh);
- if (error)
- goto fail_endtrans;
+ ret = gfs2_meta_inode_buffer(ip, &dibh);
+ if (unlikely(ret)) {
+ unlock_page(page);
+ page_cache_release(page);
+ goto failed;
+ }
gfs2_trans_add_bh(ip->i_gl, dibh, 1);
- di = (struct gfs2_dinode *)dibh->b_data;
-
- if (gfs2_is_stuffed(ip)) {
- u64 file_size;
- void *kaddr;
-
- file_size = ((u64)page->index << PAGE_CACHE_SHIFT) + to;
- kaddr = kmap_atomic(page, KM_USER0);
- memcpy(dibh->b_data + sizeof(struct gfs2_dinode) + from,
- kaddr + from, to - from);
- kunmap_atomic(kaddr, KM_USER0);
+ if (gfs2_is_stuffed(ip))
+ return gfs2_stuffed_write_end(inode, dibh, pos, len, copied, page);
- SetPageUptodate(page);
+ if (!gfs2_is_writeback(ip))
+ gfs2_page_add_databufs(ip, page, from, to);
- if (inode->i_size < file_size) {
- i_size_write(inode, file_size);
- mark_inode_dirty(inode);
- }
- } 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;
- }
+ ret = generic_write_end(file, mapping, pos, len, copied, page, fsdata);
- if (ip->i_di.di_size < inode->i_size) {
- ip->i_di.di_size = inode->i_size;
+ if (likely(ret >= 0) && (inode->i_size > ip->i_disksize)) {
+ di = (struct gfs2_dinode *)dibh->b_data;
+ ip->i_disksize = inode->i_size;
di->di_size = cpu_to_be64(inode->i_size);
+ mark_inode_dirty(inode);
}
if (inode == sdp->sd_rindex)
brelse(dibh);
gfs2_trans_end(sdp);
- if (al->al_requested) {
+failed:
+ if (al) {
gfs2_inplace_release(ip);
gfs2_quota_unlock(ip);
gfs2_alloc_put(ip);
}
- unlock_page(page);
- gfs2_glock_dq_m(1, &ip->i_gh);
- lock_page(page);
+ gfs2_glock_dq(&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);
- }
- unlock_page(page);
- gfs2_glock_dq_m(1, &ip->i_gh);
- lock_page(page);
- gfs2_holder_uninit(&ip->i_gh);
-fail_nounlock:
- ClearPageUptodate(page);
- return error;
+ return ret;
}
/**
static int gfs2_set_page_dirty(struct page *page)
{
- struct gfs2_inode *ip = GFS2_I(page->mapping->host);
- struct gfs2_sbd *sdp = GFS2_SB(page->mapping->host);
-
- if (sdp->sd_args.ar_data == GFS2_DATA_ORDERED || gfs2_is_jdata(ip))
- SetPageChecked(page);
+ SetPageChecked(page);
return __set_page_dirty_buffers(page);
}
return 0;
if (!gfs2_is_stuffed(ip))
- dblock = generic_block_bmap(mapping, lblock, gfs2_get_block);
+ dblock = generic_block_bmap(mapping, lblock, gfs2_block_map);
gfs2_glock_dq_uninit(&i_gh);
clear_buffer_dirty(bh);
bd = bh->b_private;
if (bd) {
- if (!list_empty(&bd->bd_le.le_list)) {
- if (!buffer_pinned(bh))
- list_del_init(&bd->bd_le.le_list);
- }
+ if (!list_empty(&bd->bd_le.le_list) && !buffer_pinned(bh))
+ list_del_init(&bd->bd_le.le_list);
+ else
+ gfs2_remove_from_journal(bh, current->journal_info, 0);
}
bh->b_bdev = NULL;
clear_buffer_mapped(bh);
{
/*
* 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.
+ * a stuffed file makes any sense. For now we'll silently fall
+ * back to buffered I/O
*/
- if (gfs2_is_jdata(ip))
- return 0;
-
if (gfs2_is_stuffed(ip))
return 0;
- if (offset > i_size_read(&ip->i_inode))
+ if (offset >= i_size_read(&ip->i_inode))
return 0;
return 1;
}
* unfortunately have the option of only flushing a range like
* the VFS does.
*/
- gfs2_holder_init(ip->i_gl, LM_ST_DEFERRED, GL_ATIME, &gh);
- rv = gfs2_glock_nq_atime(&gh);
+ gfs2_holder_init(ip->i_gl, LM_ST_DEFERRED, 0, &gh);
+ rv = gfs2_glock_nq(&gh);
if (rv)
return rv;
rv = gfs2_ok_for_dio(ip, rw, offset);
struct gfs2_bufdata *bd;
if (!page_has_buffers(page))
- goto out;
+ return 0;
gfs2_log_lock(sdp);
head = bh = page_buffers(page);
bh = bh->b_this_page;
} while (bh != head);
-out:
return try_to_free_buffers(page);
cannot_release:
gfs2_log_unlock(sdp);
return 0;
}
-const struct address_space_operations gfs2_file_aops = {
- .writepage = gfs2_writepage,
- .writepages = gfs2_writepages,
+static const struct address_space_operations gfs2_writeback_aops = {
+ .writepage = gfs2_writeback_writepage,
+ .writepages = gfs2_writeback_writepages,
+ .readpage = gfs2_readpage,
+ .readpages = gfs2_readpages,
+ .sync_page = block_sync_page,
+ .write_begin = gfs2_write_begin,
+ .write_end = gfs2_write_end,
+ .bmap = gfs2_bmap,
+ .invalidatepage = gfs2_invalidatepage,
+ .releasepage = gfs2_releasepage,
+ .direct_IO = gfs2_direct_IO,
+ .migratepage = buffer_migrate_page,
+ .is_partially_uptodate = block_is_partially_uptodate,
+};
+
+static const struct address_space_operations gfs2_ordered_aops = {
+ .writepage = gfs2_ordered_writepage,
.readpage = gfs2_readpage,
.readpages = gfs2_readpages,
.sync_page = block_sync_page,
- .prepare_write = gfs2_prepare_write,
- .commit_write = gfs2_commit_write,
+ .write_begin = gfs2_write_begin,
+ .write_end = gfs2_write_end,
.set_page_dirty = gfs2_set_page_dirty,
.bmap = gfs2_bmap,
.invalidatepage = gfs2_invalidatepage,
.releasepage = gfs2_releasepage,
.direct_IO = gfs2_direct_IO,
+ .migratepage = buffer_migrate_page,
+ .is_partially_uptodate = block_is_partially_uptodate,
+};
+
+static const struct address_space_operations gfs2_jdata_aops = {
+ .writepage = gfs2_jdata_writepage,
+ .writepages = gfs2_jdata_writepages,
+ .readpage = gfs2_readpage,
+ .readpages = gfs2_readpages,
+ .sync_page = block_sync_page,
+ .write_begin = gfs2_write_begin,
+ .write_end = gfs2_write_end,
+ .set_page_dirty = gfs2_set_page_dirty,
+ .bmap = gfs2_bmap,
+ .invalidatepage = gfs2_invalidatepage,
+ .releasepage = gfs2_releasepage,
+ .is_partially_uptodate = block_is_partially_uptodate,
};
+void gfs2_set_aops(struct inode *inode)
+{
+ struct gfs2_inode *ip = GFS2_I(inode);
+
+ if (gfs2_is_writeback(ip))
+ inode->i_mapping->a_ops = &gfs2_writeback_aops;
+ else if (gfs2_is_ordered(ip))
+ inode->i_mapping->a_ops = &gfs2_ordered_aops;
+ else if (gfs2_is_jdata(ip))
+ inode->i_mapping->a_ops = &gfs2_jdata_aops;
+ else
+ BUG();
+}
+
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff