linux_dsm_epyc7002/fs/nilfs2/gcinode.c

201 lines
5.6 KiB
C
Raw Normal View History

/*
* gcinode.c - dummy inodes to buffer blocks for garbage collection
*
* Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* Written by Seiji Kihara, Amagai Yoshiji, and Ryusuke Konishi.
* Revised by Ryusuke Konishi.
*
*/
/*
* This file adds the cache of on-disk blocks to be moved in garbage
* collection. The disk blocks are held with dummy inodes (called
* gcinodes), and this file provides lookup function of the dummy
* inodes and their buffer read function.
*
* Buffers and pages held by the dummy inodes will be released each
* time after they are copied to a new log. Dirty blocks made on the
* current generation and the blocks to be moved by GC never overlap
* because the dirty blocks make a new generation; they rather must be
* written individually.
*/
#include <linux/buffer_head.h>
#include <linux/mpage.h>
#include <linux/hash.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 15:04:11 +07:00
#include <linux/slab.h>
#include <linux/swap.h>
#include "nilfs.h"
#include "btree.h"
#include "btnode.h"
#include "page.h"
#include "mdt.h"
#include "dat.h"
#include "ifile.h"
/*
* nilfs_gccache_submit_read_data() - add data buffer and submit read request
* @inode - gc inode
* @blkoff - dummy offset treated as the key for the page cache
* @pbn - physical block number of the block
* @vbn - virtual block number of the block, 0 for non-virtual block
* @out_bh - indirect pointer to a buffer_head struct to receive the results
*
* Description: nilfs_gccache_submit_read_data() registers the data buffer
* specified by @pbn to the GC pagecache with the key @blkoff.
* This function sets @vbn (@pbn if @vbn is zero) in b_blocknr of the buffer.
*
* Return Value: On success, 0 is returned. On Error, one of the following
* negative error code is returned.
*
* %-EIO - I/O error.
*
* %-ENOMEM - Insufficient amount of memory available.
*
* %-ENOENT - The block specified with @pbn does not exist.
*/
int nilfs_gccache_submit_read_data(struct inode *inode, sector_t blkoff,
sector_t pbn, __u64 vbn,
struct buffer_head **out_bh)
{
struct buffer_head *bh;
int err;
bh = nilfs_grab_buffer(inode, inode->i_mapping, blkoff, 0);
if (unlikely(!bh))
return -ENOMEM;
if (buffer_uptodate(bh))
goto out;
if (pbn == 0) {
struct the_nilfs *nilfs = inode->i_sb->s_fs_info;
err = nilfs_dat_translate(nilfs->ns_dat, vbn, &pbn);
if (unlikely(err)) { /* -EIO, -ENOMEM, -ENOENT */
brelse(bh);
goto failed;
}
}
lock_buffer(bh);
if (buffer_uptodate(bh)) {
unlock_buffer(bh);
goto out;
}
if (!buffer_mapped(bh)) {
bh->b_bdev = inode->i_sb->s_bdev;
set_buffer_mapped(bh);
}
bh->b_blocknr = pbn;
bh->b_end_io = end_buffer_read_sync;
get_bh(bh);
submit_bh(REQ_OP_READ, 0, bh);
if (vbn)
bh->b_blocknr = vbn;
out:
err = 0;
*out_bh = bh;
failed:
unlock_page(bh->b_page);
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 19:29:47 +07:00
put_page(bh->b_page);
return err;
}
/*
* nilfs_gccache_submit_read_node() - add node buffer and submit read request
* @inode - gc inode
* @pbn - physical block number for the block
* @vbn - virtual block number for the block
* @out_bh - indirect pointer to a buffer_head struct to receive the results
*
* Description: nilfs_gccache_submit_read_node() registers the node buffer
* specified by @vbn to the GC pagecache. @pbn can be supplied by the
* caller to avoid translation of the disk block address.
*
* Return Value: On success, 0 is returned. On Error, one of the following
* negative error code is returned.
*
* %-EIO - I/O error.
*
* %-ENOMEM - Insufficient amount of memory available.
*/
int nilfs_gccache_submit_read_node(struct inode *inode, sector_t pbn,
__u64 vbn, struct buffer_head **out_bh)
{
int ret;
ret = nilfs_btnode_submit_block(&NILFS_I(inode)->i_btnode_cache,
vbn ? : pbn, pbn, REQ_OP_READ, 0,
out_bh, &pbn);
if (ret == -EEXIST) /* internal code (cache hit) */
ret = 0;
return ret;
}
int nilfs_gccache_wait_and_mark_dirty(struct buffer_head *bh)
{
wait_on_buffer(bh);
if (!buffer_uptodate(bh)) {
struct inode *inode = bh->b_page->mapping->host;
nilfs_msg(inode->i_sb, KERN_ERR,
"I/O error reading %s block for GC (ino=%lu, vblocknr=%llu)",
buffer_nilfs_node(bh) ? "node" : "data",
inode->i_ino, (unsigned long long)bh->b_blocknr);
return -EIO;
}
if (buffer_dirty(bh))
return -EEXIST;
if (buffer_nilfs_node(bh) && nilfs_btree_broken_node_block(bh)) {
clear_buffer_uptodate(bh);
return -EIO;
}
mark_buffer_dirty(bh);
return 0;
}
int nilfs_init_gcinode(struct inode *inode)
{
struct nilfs_inode_info *ii = NILFS_I(inode);
inode->i_mode = S_IFREG;
mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS);
inode->i_mapping->a_ops = &empty_aops;
ii->i_flags = 0;
nilfs_bmap_init_gc(ii->i_bmap);
return 0;
}
/**
* nilfs_remove_all_gcinodes() - remove all unprocessed gc inodes
*/
void nilfs_remove_all_gcinodes(struct the_nilfs *nilfs)
{
struct list_head *head = &nilfs->ns_gc_inodes;
struct nilfs_inode_info *ii;
while (!list_empty(head)) {
ii = list_first_entry(head, struct nilfs_inode_info, i_dirty);
list_del_init(&ii->i_dirty);
truncate_inode_pages(&ii->vfs_inode.i_data, 0);
nilfs_btnode_cache_clear(&ii->i_btnode_cache);
iput(&ii->vfs_inode);
}
}