linux/fs/mpage.c

732 lines
20 KiB
C
Raw Normal View History

/*
* fs/mpage.c
*
* Copyright (C) 2002, Linus Torvalds.
*
* Contains functions related to preparing and submitting BIOs which contain
* multiple pagecache pages.
*
* 15May2002 Andrew Morton
* Initial version
* 27Jun2002 axboe@suse.de
* use bio_add_page() to build bio's just the right size
*/
#include <linux/kernel.h>
#include <linux/export.h>
#include <linux/mm.h>
#include <linux/kdev_t.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 08:04:11 +00:00
#include <linux/gfp.h>
#include <linux/bio.h>
#include <linux/fs.h>
#include <linux/buffer_head.h>
#include <linux/blkdev.h>
#include <linux/highmem.h>
#include <linux/prefetch.h>
#include <linux/mpage.h>
#include <linux/mm_inline.h>
#include <linux/writeback.h>
#include <linux/backing-dev.h>
#include <linux/pagevec.h>
#include <linux/cleancache.h>
#include "internal.h"
/*
* I/O completion handler for multipage BIOs.
*
* The mpage code never puts partial pages into a BIO (except for end-of-file).
* If a page does not map to a contiguous run of blocks then it simply falls
* back to block_read_full_page().
*
* Why is this? If a page's completion depends on a number of different BIOs
* which can complete in any order (or at the same time) then determining the
* status of that page is hard. See end_buffer_async_read() for the details.
* There is no point in duplicating all that complexity.
*/
static void mpage_end_io(struct bio *bio)
{
struct bio_vec *bv;
int i;
bio_for_each_segment_all(bv, bio, i) {
struct page *page = bv->bv_page;
page_endio(page, bio_data_dir(bio), bio->bi_error);
}
bio_put(bio);
}
static struct bio *mpage_bio_submit(int rw, struct bio *bio)
{
bio->bi_end_io = mpage_end_io;
guard_bio_eod(rw, bio);
submit_bio(rw, bio);
return NULL;
}
static struct bio *
mpage_alloc(struct block_device *bdev,
sector_t first_sector, int nr_vecs,
gfp_t gfp_flags)
{
struct bio *bio;
bio = bio_alloc(gfp_flags, nr_vecs);
if (bio == NULL && (current->flags & PF_MEMALLOC)) {
while (!bio && (nr_vecs /= 2))
bio = bio_alloc(gfp_flags, nr_vecs);
}
if (bio) {
bio->bi_bdev = bdev;
block: Abstract out bvec iterator Immutable biovecs are going to require an explicit iterator. To implement immutable bvecs, a later patch is going to add a bi_bvec_done member to this struct; for now, this patch effectively just renames things. Signed-off-by: Kent Overstreet <kmo@daterainc.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: "Ed L. Cashin" <ecashin@coraid.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Lars Ellenberg <drbd-dev@lists.linbit.com> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Matthew Wilcox <willy@linux.intel.com> Cc: Geoff Levand <geoff@infradead.org> Cc: Yehuda Sadeh <yehuda@inktank.com> Cc: Sage Weil <sage@inktank.com> Cc: Alex Elder <elder@inktank.com> Cc: ceph-devel@vger.kernel.org Cc: Joshua Morris <josh.h.morris@us.ibm.com> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Neil Brown <neilb@suse.de> Cc: Alasdair Kergon <agk@redhat.com> Cc: Mike Snitzer <snitzer@redhat.com> Cc: dm-devel@redhat.com Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: linux390@de.ibm.com Cc: Boaz Harrosh <bharrosh@panasas.com> Cc: Benny Halevy <bhalevy@tonian.com> Cc: "James E.J. Bottomley" <JBottomley@parallels.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: "Nicholas A. Bellinger" <nab@linux-iscsi.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Chris Mason <chris.mason@fusionio.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Jaegeuk Kim <jaegeuk.kim@samsung.com> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Dave Kleikamp <shaggy@kernel.org> Cc: Joern Engel <joern@logfs.org> Cc: Prasad Joshi <prasadjoshi.linux@gmail.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Cc: KONISHI Ryusuke <konishi.ryusuke@lab.ntt.co.jp> Cc: Mark Fasheh <mfasheh@suse.com> Cc: Joel Becker <jlbec@evilplan.org> Cc: Ben Myers <bpm@sgi.com> Cc: xfs@oss.sgi.com Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Len Brown <len.brown@intel.com> Cc: Pavel Machek <pavel@ucw.cz> Cc: "Rafael J. Wysocki" <rjw@sisk.pl> Cc: Herton Ronaldo Krzesinski <herton.krzesinski@canonical.com> Cc: Ben Hutchings <ben@decadent.org.uk> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Guo Chao <yan@linux.vnet.ibm.com> Cc: Tejun Heo <tj@kernel.org> Cc: Asai Thambi S P <asamymuthupa@micron.com> Cc: Selvan Mani <smani@micron.com> Cc: Sam Bradshaw <sbradshaw@micron.com> Cc: Wei Yongjun <yongjun_wei@trendmicro.com.cn> Cc: "Roger Pau Monné" <roger.pau@citrix.com> Cc: Jan Beulich <jbeulich@suse.com> Cc: Stefano Stabellini <stefano.stabellini@eu.citrix.com> Cc: Ian Campbell <Ian.Campbell@citrix.com> Cc: Sebastian Ott <sebott@linux.vnet.ibm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Jerome Marchand <jmarchand@redhat.com> Cc: Joe Perches <joe@perches.com> Cc: Peng Tao <tao.peng@emc.com> Cc: Andy Adamson <andros@netapp.com> Cc: fanchaoting <fanchaoting@cn.fujitsu.com> Cc: Jie Liu <jeff.liu@oracle.com> Cc: Sunil Mushran <sunil.mushran@gmail.com> Cc: "Martin K. Petersen" <martin.petersen@oracle.com> Cc: Namjae Jeon <namjae.jeon@samsung.com> Cc: Pankaj Kumar <pankaj.km@samsung.com> Cc: Dan Magenheimer <dan.magenheimer@oracle.com> Cc: Mel Gorman <mgorman@suse.de>6
2013-10-11 22:44:27 +00:00
bio->bi_iter.bi_sector = first_sector;
}
return bio;
}
/*
* support function for mpage_readpages. The fs supplied get_block might
* return an up to date buffer. This is used to map that buffer into
* the page, which allows readpage to avoid triggering a duplicate call
* to get_block.
*
* The idea is to avoid adding buffers to pages that don't already have
* them. So when the buffer is up to date and the page size == block size,
* this marks the page up to date instead of adding new buffers.
*/
static void
map_buffer_to_page(struct page *page, struct buffer_head *bh, int page_block)
{
struct inode *inode = page->mapping->host;
struct buffer_head *page_bh, *head;
int block = 0;
if (!page_has_buffers(page)) {
/*
* don't make any buffers if there is only one buffer on
* the page and the page just needs to be set up to date
*/
if (inode->i_blkbits == PAGE_CACHE_SHIFT &&
buffer_uptodate(bh)) {
SetPageUptodate(page);
return;
}
create_empty_buffers(page, 1 << inode->i_blkbits, 0);
}
head = page_buffers(page);
page_bh = head;
do {
if (block == page_block) {
page_bh->b_state = bh->b_state;
page_bh->b_bdev = bh->b_bdev;
page_bh->b_blocknr = bh->b_blocknr;
break;
}
page_bh = page_bh->b_this_page;
block++;
} while (page_bh != head);
}
/*
* This is the worker routine which does all the work of mapping the disk
* blocks and constructs largest possible bios, submits them for IO if the
* blocks are not contiguous on the disk.
*
* We pass a buffer_head back and forth and use its buffer_mapped() flag to
* represent the validity of its disk mapping and to decide when to do the next
* get_block() call.
*/
static struct bio *
do_mpage_readpage(struct bio *bio, struct page *page, unsigned nr_pages,
sector_t *last_block_in_bio, struct buffer_head *map_bh,
mm, fs: obey gfp_mapping for add_to_page_cache() Commit 6afdb859b710 ("mm: do not ignore mapping_gfp_mask in page cache allocation paths") has caught some users of hardcoded GFP_KERNEL used in the page cache allocation paths. This, however, wasn't complete and there were others which went unnoticed. Dave Chinner has reported the following deadlock for xfs on loop device: : With the recent merge of the loop device changes, I'm now seeing : XFS deadlock on my single CPU, 1GB RAM VM running xfs/073. : : The deadlocked is as follows: : : kloopd1: loop_queue_read_work : xfs_file_iter_read : lock XFS inode XFS_IOLOCK_SHARED (on image file) : page cache read (GFP_KERNEL) : radix tree alloc : memory reclaim : reclaim XFS inodes : log force to unpin inodes : <wait for log IO completion> : : xfs-cil/loop1: <does log force IO work> : xlog_cil_push : xlog_write : <loop issuing log writes> : xlog_state_get_iclog_space() : <blocks due to all log buffers under write io> : <waits for IO completion> : : kloopd1: loop_queue_write_work : xfs_file_write_iter : lock XFS inode XFS_IOLOCK_EXCL (on image file) : <wait for inode to be unlocked> : : i.e. the kloopd, with it's split read and write work queues, has : introduced a dependency through memory reclaim. i.e. that writes : need to be able to progress for reads make progress. : : The problem, fundamentally, is that mpage_readpages() does a : GFP_KERNEL allocation, rather than paying attention to the inode's : mapping gfp mask, which is set to GFP_NOFS. : : The didn't used to happen, because the loop device used to issue : reads through the splice path and that does: : : error = add_to_page_cache_lru(page, mapping, index, : GFP_KERNEL & mapping_gfp_mask(mapping)); This has changed by commit aa4d86163e4 ("block: loop: switch to VFS ITER_BVEC"). This patch changes mpage_readpage{s} to follow gfp mask set for the mapping. There are, however, other places which are doing basically the same. lustre:ll_dir_filler is doing GFP_KERNEL from the function which apparently uses GFP_NOFS for other allocations so let's make this consistent. cifs:readpages_get_pages is called from cifs_readpages and __cifs_readpages_from_fscache called from the same path obeys mapping gfp. ramfs_nommu_expand_for_mapping is hardcoding GFP_KERNEL as well regardless it uses mapping_gfp_mask for the page allocation. ext4_mpage_readpages is the called from the page cache allocation path same as read_pages and read_cache_pages As I've noticed in my previous post I cannot say I would be happy about sprinkling mapping_gfp_mask all over the place and it sounds like we should drop gfp_mask argument altogether and use it internally in __add_to_page_cache_locked that would require all the filesystems to use mapping gfp consistently which I am not sure is the case here. From a quick glance it seems that some file system use it all the time while others are selective. Signed-off-by: Michal Hocko <mhocko@suse.com> Reported-by: Dave Chinner <david@fromorbit.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Ming Lei <ming.lei@canonical.com> Cc: Andreas Dilger <andreas.dilger@intel.com> Cc: Oleg Drokin <oleg.drokin@intel.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Christoph Hellwig <hch@lst.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-10-15 22:28:24 +00:00
unsigned long *first_logical_block, get_block_t get_block,
gfp_t gfp)
{
struct inode *inode = page->mapping->host;
const unsigned blkbits = inode->i_blkbits;
const unsigned blocks_per_page = PAGE_CACHE_SIZE >> blkbits;
const unsigned blocksize = 1 << blkbits;
sector_t block_in_file;
sector_t last_block;
sector_t last_block_in_file;
sector_t blocks[MAX_BUF_PER_PAGE];
unsigned page_block;
unsigned first_hole = blocks_per_page;
struct block_device *bdev = NULL;
int length;
int fully_mapped = 1;
unsigned nblocks;
unsigned relative_block;
if (page_has_buffers(page))
goto confused;
[PATCH] fix possible PAGE_CACHE_SHIFT overflows We've had two instances recently of overflows when doing 64_bit_value = (32_bit_value << PAGE_CACHE_SHIFT) I did a tree-wide grep of `<<.*PAGE_CACHE_SHIFT' and this is the result. - afs_rxfs_fetch_descriptor.offset is of type off_t, which seems broken. - jfs and jffs are limited to 4GB anyway. - reiserfs map_block_for_writepage() takes an unsigned long for the block - it should take sector_t. (It'll fail for huge filesystems with blocksize<PAGE_CACHE_SIZE) - cramfs_read() needs to use sector_t (I think cramsfs is busted on large filesystems anyway) - affs is limited in file size anyway. - I generally didn't fix 32-bit overflows in directory operations. - arm's __flush_dcache_page() is peculiar. What if the page lies beyond 4G? - gss_wrap_req_priv() needs checking (snd_buf->page_base) Cc: Oleg Drokin <green@linuxhacker.ru> Cc: David Howells <dhowells@redhat.com> Cc: David Woodhouse <dwmw2@infradead.org> Cc: <reiserfs-dev@namesys.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Anton Altaparmakov <aia21@cantab.net> Cc: Jeff Dike <jdike@addtoit.com> Cc: Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it> Cc: Roman Zippel <zippel@linux-m68k.org> Cc: <linux-fsdevel@vger.kernel.org> Cc: Miklos Szeredi <miklos@szeredi.hu> Cc: Russell King <rmk@arm.linux.org.uk> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Cc: Neil Brown <neilb@cse.unsw.edu.au> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 09:03:05 +00:00
block_in_file = (sector_t)page->index << (PAGE_CACHE_SHIFT - blkbits);
last_block = block_in_file + nr_pages * blocks_per_page;
last_block_in_file = (i_size_read(inode) + blocksize - 1) >> blkbits;
if (last_block > last_block_in_file)
last_block = last_block_in_file;
page_block = 0;
/*
* Map blocks using the result from the previous get_blocks call first.
*/
nblocks = map_bh->b_size >> blkbits;
if (buffer_mapped(map_bh) && block_in_file > *first_logical_block &&
block_in_file < (*first_logical_block + nblocks)) {
unsigned map_offset = block_in_file - *first_logical_block;
unsigned last = nblocks - map_offset;
for (relative_block = 0; ; relative_block++) {
if (relative_block == last) {
clear_buffer_mapped(map_bh);
break;
}
if (page_block == blocks_per_page)
break;
blocks[page_block] = map_bh->b_blocknr + map_offset +
relative_block;
page_block++;
block_in_file++;
}
bdev = map_bh->b_bdev;
}
/*
* Then do more get_blocks calls until we are done with this page.
*/
map_bh->b_page = page;
while (page_block < blocks_per_page) {
map_bh->b_state = 0;
map_bh->b_size = 0;
if (block_in_file < last_block) {
map_bh->b_size = (last_block-block_in_file) << blkbits;
if (get_block(inode, block_in_file, map_bh, 0))
goto confused;
*first_logical_block = block_in_file;
}
if (!buffer_mapped(map_bh)) {
fully_mapped = 0;
if (first_hole == blocks_per_page)
first_hole = page_block;
page_block++;
block_in_file++;
continue;
}
/* some filesystems will copy data into the page during
* the get_block call, in which case we don't want to
* read it again. map_buffer_to_page copies the data
* we just collected from get_block into the page's buffers
* so readpage doesn't have to repeat the get_block call
*/
if (buffer_uptodate(map_bh)) {
map_buffer_to_page(page, map_bh, page_block);
goto confused;
}
if (first_hole != blocks_per_page)
goto confused; /* hole -> non-hole */
/* Contiguous blocks? */
if (page_block && blocks[page_block-1] != map_bh->b_blocknr-1)
goto confused;
nblocks = map_bh->b_size >> blkbits;
for (relative_block = 0; ; relative_block++) {
if (relative_block == nblocks) {
clear_buffer_mapped(map_bh);
break;
} else if (page_block == blocks_per_page)
break;
blocks[page_block] = map_bh->b_blocknr+relative_block;
page_block++;
block_in_file++;
}
bdev = map_bh->b_bdev;
}
if (first_hole != blocks_per_page) {
Pagecache zeroing: zero_user_segment, zero_user_segments and zero_user Simplify page cache zeroing of segments of pages through 3 functions zero_user_segments(page, start1, end1, start2, end2) Zeros two segments of the page. It takes the position where to start and end the zeroing which avoids length calculations and makes code clearer. zero_user_segment(page, start, end) Same for a single segment. zero_user(page, start, length) Length variant for the case where we know the length. We remove the zero_user_page macro. Issues: 1. Its a macro. Inline functions are preferable. 2. The KM_USER0 macro is only defined for HIGHMEM. Having to treat this special case everywhere makes the code needlessly complex. The parameter for zeroing is always KM_USER0 except in one single case that we open code. Avoiding KM_USER0 makes a lot of code not having to be dealing with the special casing for HIGHMEM anymore. Dealing with kmap is only necessary for HIGHMEM configurations. In those configurations we use KM_USER0 like we do for a series of other functions defined in highmem.h. Since KM_USER0 is depends on HIGHMEM the existing zero_user_page function could not be a macro. zero_user_* functions introduced here can be be inline because that constant is not used when these functions are called. Also extract the flushing of the caches to be outside of the kmap. [akpm@linux-foundation.org: fix nfs and ntfs build] [akpm@linux-foundation.org: fix ntfs build some more] Signed-off-by: Christoph Lameter <clameter@sgi.com> Cc: Steven French <sfrench@us.ibm.com> Cc: Michael Halcrow <mhalcrow@us.ibm.com> Cc: <linux-ext4@vger.kernel.org> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Cc: "J. Bruce Fields" <bfields@fieldses.org> Cc: Anton Altaparmakov <aia21@cantab.net> Cc: Mark Fasheh <mark.fasheh@oracle.com> Cc: David Chinner <dgc@sgi.com> Cc: Michael Halcrow <mhalcrow@us.ibm.com> Cc: Steven French <sfrench@us.ibm.com> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 06:28:29 +00:00
zero_user_segment(page, first_hole << blkbits, PAGE_CACHE_SIZE);
if (first_hole == 0) {
SetPageUptodate(page);
unlock_page(page);
goto out;
}
} else if (fully_mapped) {
SetPageMappedToDisk(page);
}
if (fully_mapped && blocks_per_page == 1 && !PageUptodate(page) &&
cleancache_get_page(page) == 0) {
SetPageUptodate(page);
goto confused;
}
/*
* This page will go to BIO. Do we need to send this BIO off first?
*/
if (bio && (*last_block_in_bio != blocks[0] - 1))
bio = mpage_bio_submit(READ, bio);
alloc_new:
if (bio == NULL) {
if (first_hole == blocks_per_page) {
if (!bdev_read_page(bdev, blocks[0] << (blkbits - 9),
page))
goto out;
}
bio = mpage_alloc(bdev, blocks[0] << (blkbits - 9),
mm, fs: obey gfp_mapping for add_to_page_cache() Commit 6afdb859b710 ("mm: do not ignore mapping_gfp_mask in page cache allocation paths") has caught some users of hardcoded GFP_KERNEL used in the page cache allocation paths. This, however, wasn't complete and there were others which went unnoticed. Dave Chinner has reported the following deadlock for xfs on loop device: : With the recent merge of the loop device changes, I'm now seeing : XFS deadlock on my single CPU, 1GB RAM VM running xfs/073. : : The deadlocked is as follows: : : kloopd1: loop_queue_read_work : xfs_file_iter_read : lock XFS inode XFS_IOLOCK_SHARED (on image file) : page cache read (GFP_KERNEL) : radix tree alloc : memory reclaim : reclaim XFS inodes : log force to unpin inodes : <wait for log IO completion> : : xfs-cil/loop1: <does log force IO work> : xlog_cil_push : xlog_write : <loop issuing log writes> : xlog_state_get_iclog_space() : <blocks due to all log buffers under write io> : <waits for IO completion> : : kloopd1: loop_queue_write_work : xfs_file_write_iter : lock XFS inode XFS_IOLOCK_EXCL (on image file) : <wait for inode to be unlocked> : : i.e. the kloopd, with it's split read and write work queues, has : introduced a dependency through memory reclaim. i.e. that writes : need to be able to progress for reads make progress. : : The problem, fundamentally, is that mpage_readpages() does a : GFP_KERNEL allocation, rather than paying attention to the inode's : mapping gfp mask, which is set to GFP_NOFS. : : The didn't used to happen, because the loop device used to issue : reads through the splice path and that does: : : error = add_to_page_cache_lru(page, mapping, index, : GFP_KERNEL & mapping_gfp_mask(mapping)); This has changed by commit aa4d86163e4 ("block: loop: switch to VFS ITER_BVEC"). This patch changes mpage_readpage{s} to follow gfp mask set for the mapping. There are, however, other places which are doing basically the same. lustre:ll_dir_filler is doing GFP_KERNEL from the function which apparently uses GFP_NOFS for other allocations so let's make this consistent. cifs:readpages_get_pages is called from cifs_readpages and __cifs_readpages_from_fscache called from the same path obeys mapping gfp. ramfs_nommu_expand_for_mapping is hardcoding GFP_KERNEL as well regardless it uses mapping_gfp_mask for the page allocation. ext4_mpage_readpages is the called from the page cache allocation path same as read_pages and read_cache_pages As I've noticed in my previous post I cannot say I would be happy about sprinkling mapping_gfp_mask all over the place and it sounds like we should drop gfp_mask argument altogether and use it internally in __add_to_page_cache_locked that would require all the filesystems to use mapping gfp consistently which I am not sure is the case here. From a quick glance it seems that some file system use it all the time while others are selective. Signed-off-by: Michal Hocko <mhocko@suse.com> Reported-by: Dave Chinner <david@fromorbit.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Ming Lei <ming.lei@canonical.com> Cc: Andreas Dilger <andreas.dilger@intel.com> Cc: Oleg Drokin <oleg.drokin@intel.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Christoph Hellwig <hch@lst.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-10-15 22:28:24 +00:00
min_t(int, nr_pages, BIO_MAX_PAGES), gfp);
if (bio == NULL)
goto confused;
}
length = first_hole << blkbits;
if (bio_add_page(bio, page, length, 0) < length) {
bio = mpage_bio_submit(READ, bio);
goto alloc_new;
}
relative_block = block_in_file - *first_logical_block;
nblocks = map_bh->b_size >> blkbits;
if ((buffer_boundary(map_bh) && relative_block == nblocks) ||
(first_hole != blocks_per_page))
bio = mpage_bio_submit(READ, bio);
else
*last_block_in_bio = blocks[blocks_per_page - 1];
out:
return bio;
confused:
if (bio)
bio = mpage_bio_submit(READ, bio);
if (!PageUptodate(page))
block_read_full_page(page, get_block);
else
unlock_page(page);
goto out;
}
/**
* mpage_readpages - populate an address space with some pages & start reads against them
* @mapping: the address_space
* @pages: The address of a list_head which contains the target pages. These
* pages have their ->index populated and are otherwise uninitialised.
* The page at @pages->prev has the lowest file offset, and reads should be
* issued in @pages->prev to @pages->next order.
* @nr_pages: The number of pages at *@pages
* @get_block: The filesystem's block mapper function.
*
* This function walks the pages and the blocks within each page, building and
* emitting large BIOs.
*
* If anything unusual happens, such as:
*
* - encountering a page which has buffers
* - encountering a page which has a non-hole after a hole
* - encountering a page with non-contiguous blocks
*
* then this code just gives up and calls the buffer_head-based read function.
* It does handle a page which has holes at the end - that is a common case:
* the end-of-file on blocksize < PAGE_CACHE_SIZE setups.
*
* BH_Boundary explanation:
*
* There is a problem. The mpage read code assembles several pages, gets all
* their disk mappings, and then submits them all. That's fine, but obtaining
* the disk mappings may require I/O. Reads of indirect blocks, for example.
*
* So an mpage read of the first 16 blocks of an ext2 file will cause I/O to be
* submitted in the following order:
* 12 0 1 2 3 4 5 6 7 8 9 10 11 13 14 15 16
*
* because the indirect block has to be read to get the mappings of blocks
* 13,14,15,16. Obviously, this impacts performance.
*
* So what we do it to allow the filesystem's get_block() function to set
* BH_Boundary when it maps block 11. BH_Boundary says: mapping of the block
* after this one will require I/O against a block which is probably close to
* this one. So you should push what I/O you have currently accumulated.
*
* This all causes the disk requests to be issued in the correct order.
*/
int
mpage_readpages(struct address_space *mapping, struct list_head *pages,
unsigned nr_pages, get_block_t get_block)
{
struct bio *bio = NULL;
unsigned page_idx;
sector_t last_block_in_bio = 0;
struct buffer_head map_bh;
unsigned long first_logical_block = 0;
gfp_t gfp = mapping_gfp_constraint(mapping, GFP_KERNEL);
map_bh.b_state = 0;
map_bh.b_size = 0;
for (page_idx = 0; page_idx < nr_pages; page_idx++) {
struct page *page = lru_to_page(pages);
prefetchw(&page->flags);
list_del(&page->lru);
if (!add_to_page_cache_lru(page, mapping,
mm, fs: obey gfp_mapping for add_to_page_cache() Commit 6afdb859b710 ("mm: do not ignore mapping_gfp_mask in page cache allocation paths") has caught some users of hardcoded GFP_KERNEL used in the page cache allocation paths. This, however, wasn't complete and there were others which went unnoticed. Dave Chinner has reported the following deadlock for xfs on loop device: : With the recent merge of the loop device changes, I'm now seeing : XFS deadlock on my single CPU, 1GB RAM VM running xfs/073. : : The deadlocked is as follows: : : kloopd1: loop_queue_read_work : xfs_file_iter_read : lock XFS inode XFS_IOLOCK_SHARED (on image file) : page cache read (GFP_KERNEL) : radix tree alloc : memory reclaim : reclaim XFS inodes : log force to unpin inodes : <wait for log IO completion> : : xfs-cil/loop1: <does log force IO work> : xlog_cil_push : xlog_write : <loop issuing log writes> : xlog_state_get_iclog_space() : <blocks due to all log buffers under write io> : <waits for IO completion> : : kloopd1: loop_queue_write_work : xfs_file_write_iter : lock XFS inode XFS_IOLOCK_EXCL (on image file) : <wait for inode to be unlocked> : : i.e. the kloopd, with it's split read and write work queues, has : introduced a dependency through memory reclaim. i.e. that writes : need to be able to progress for reads make progress. : : The problem, fundamentally, is that mpage_readpages() does a : GFP_KERNEL allocation, rather than paying attention to the inode's : mapping gfp mask, which is set to GFP_NOFS. : : The didn't used to happen, because the loop device used to issue : reads through the splice path and that does: : : error = add_to_page_cache_lru(page, mapping, index, : GFP_KERNEL & mapping_gfp_mask(mapping)); This has changed by commit aa4d86163e4 ("block: loop: switch to VFS ITER_BVEC"). This patch changes mpage_readpage{s} to follow gfp mask set for the mapping. There are, however, other places which are doing basically the same. lustre:ll_dir_filler is doing GFP_KERNEL from the function which apparently uses GFP_NOFS for other allocations so let's make this consistent. cifs:readpages_get_pages is called from cifs_readpages and __cifs_readpages_from_fscache called from the same path obeys mapping gfp. ramfs_nommu_expand_for_mapping is hardcoding GFP_KERNEL as well regardless it uses mapping_gfp_mask for the page allocation. ext4_mpage_readpages is the called from the page cache allocation path same as read_pages and read_cache_pages As I've noticed in my previous post I cannot say I would be happy about sprinkling mapping_gfp_mask all over the place and it sounds like we should drop gfp_mask argument altogether and use it internally in __add_to_page_cache_locked that would require all the filesystems to use mapping gfp consistently which I am not sure is the case here. From a quick glance it seems that some file system use it all the time while others are selective. Signed-off-by: Michal Hocko <mhocko@suse.com> Reported-by: Dave Chinner <david@fromorbit.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Ming Lei <ming.lei@canonical.com> Cc: Andreas Dilger <andreas.dilger@intel.com> Cc: Oleg Drokin <oleg.drokin@intel.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Christoph Hellwig <hch@lst.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-10-15 22:28:24 +00:00
page->index,
gfp)) {
bio = do_mpage_readpage(bio, page,
nr_pages - page_idx,
&last_block_in_bio, &map_bh,
&first_logical_block,
mm, fs: obey gfp_mapping for add_to_page_cache() Commit 6afdb859b710 ("mm: do not ignore mapping_gfp_mask in page cache allocation paths") has caught some users of hardcoded GFP_KERNEL used in the page cache allocation paths. This, however, wasn't complete and there were others which went unnoticed. Dave Chinner has reported the following deadlock for xfs on loop device: : With the recent merge of the loop device changes, I'm now seeing : XFS deadlock on my single CPU, 1GB RAM VM running xfs/073. : : The deadlocked is as follows: : : kloopd1: loop_queue_read_work : xfs_file_iter_read : lock XFS inode XFS_IOLOCK_SHARED (on image file) : page cache read (GFP_KERNEL) : radix tree alloc : memory reclaim : reclaim XFS inodes : log force to unpin inodes : <wait for log IO completion> : : xfs-cil/loop1: <does log force IO work> : xlog_cil_push : xlog_write : <loop issuing log writes> : xlog_state_get_iclog_space() : <blocks due to all log buffers under write io> : <waits for IO completion> : : kloopd1: loop_queue_write_work : xfs_file_write_iter : lock XFS inode XFS_IOLOCK_EXCL (on image file) : <wait for inode to be unlocked> : : i.e. the kloopd, with it's split read and write work queues, has : introduced a dependency through memory reclaim. i.e. that writes : need to be able to progress for reads make progress. : : The problem, fundamentally, is that mpage_readpages() does a : GFP_KERNEL allocation, rather than paying attention to the inode's : mapping gfp mask, which is set to GFP_NOFS. : : The didn't used to happen, because the loop device used to issue : reads through the splice path and that does: : : error = add_to_page_cache_lru(page, mapping, index, : GFP_KERNEL & mapping_gfp_mask(mapping)); This has changed by commit aa4d86163e4 ("block: loop: switch to VFS ITER_BVEC"). This patch changes mpage_readpage{s} to follow gfp mask set for the mapping. There are, however, other places which are doing basically the same. lustre:ll_dir_filler is doing GFP_KERNEL from the function which apparently uses GFP_NOFS for other allocations so let's make this consistent. cifs:readpages_get_pages is called from cifs_readpages and __cifs_readpages_from_fscache called from the same path obeys mapping gfp. ramfs_nommu_expand_for_mapping is hardcoding GFP_KERNEL as well regardless it uses mapping_gfp_mask for the page allocation. ext4_mpage_readpages is the called from the page cache allocation path same as read_pages and read_cache_pages As I've noticed in my previous post I cannot say I would be happy about sprinkling mapping_gfp_mask all over the place and it sounds like we should drop gfp_mask argument altogether and use it internally in __add_to_page_cache_locked that would require all the filesystems to use mapping gfp consistently which I am not sure is the case here. From a quick glance it seems that some file system use it all the time while others are selective. Signed-off-by: Michal Hocko <mhocko@suse.com> Reported-by: Dave Chinner <david@fromorbit.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Ming Lei <ming.lei@canonical.com> Cc: Andreas Dilger <andreas.dilger@intel.com> Cc: Oleg Drokin <oleg.drokin@intel.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Christoph Hellwig <hch@lst.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-10-15 22:28:24 +00:00
get_block, gfp);
}
page_cache_release(page);
}
BUG_ON(!list_empty(pages));
if (bio)
mpage_bio_submit(READ, bio);
return 0;
}
EXPORT_SYMBOL(mpage_readpages);
/*
* This isn't called much at all
*/
int mpage_readpage(struct page *page, get_block_t get_block)
{
struct bio *bio = NULL;
sector_t last_block_in_bio = 0;
struct buffer_head map_bh;
unsigned long first_logical_block = 0;
gfp_t gfp = mapping_gfp_constraint(page->mapping, GFP_KERNEL);
map_bh.b_state = 0;
map_bh.b_size = 0;
bio = do_mpage_readpage(bio, page, 1, &last_block_in_bio,
mm, fs: obey gfp_mapping for add_to_page_cache() Commit 6afdb859b710 ("mm: do not ignore mapping_gfp_mask in page cache allocation paths") has caught some users of hardcoded GFP_KERNEL used in the page cache allocation paths. This, however, wasn't complete and there were others which went unnoticed. Dave Chinner has reported the following deadlock for xfs on loop device: : With the recent merge of the loop device changes, I'm now seeing : XFS deadlock on my single CPU, 1GB RAM VM running xfs/073. : : The deadlocked is as follows: : : kloopd1: loop_queue_read_work : xfs_file_iter_read : lock XFS inode XFS_IOLOCK_SHARED (on image file) : page cache read (GFP_KERNEL) : radix tree alloc : memory reclaim : reclaim XFS inodes : log force to unpin inodes : <wait for log IO completion> : : xfs-cil/loop1: <does log force IO work> : xlog_cil_push : xlog_write : <loop issuing log writes> : xlog_state_get_iclog_space() : <blocks due to all log buffers under write io> : <waits for IO completion> : : kloopd1: loop_queue_write_work : xfs_file_write_iter : lock XFS inode XFS_IOLOCK_EXCL (on image file) : <wait for inode to be unlocked> : : i.e. the kloopd, with it's split read and write work queues, has : introduced a dependency through memory reclaim. i.e. that writes : need to be able to progress for reads make progress. : : The problem, fundamentally, is that mpage_readpages() does a : GFP_KERNEL allocation, rather than paying attention to the inode's : mapping gfp mask, which is set to GFP_NOFS. : : The didn't used to happen, because the loop device used to issue : reads through the splice path and that does: : : error = add_to_page_cache_lru(page, mapping, index, : GFP_KERNEL & mapping_gfp_mask(mapping)); This has changed by commit aa4d86163e4 ("block: loop: switch to VFS ITER_BVEC"). This patch changes mpage_readpage{s} to follow gfp mask set for the mapping. There are, however, other places which are doing basically the same. lustre:ll_dir_filler is doing GFP_KERNEL from the function which apparently uses GFP_NOFS for other allocations so let's make this consistent. cifs:readpages_get_pages is called from cifs_readpages and __cifs_readpages_from_fscache called from the same path obeys mapping gfp. ramfs_nommu_expand_for_mapping is hardcoding GFP_KERNEL as well regardless it uses mapping_gfp_mask for the page allocation. ext4_mpage_readpages is the called from the page cache allocation path same as read_pages and read_cache_pages As I've noticed in my previous post I cannot say I would be happy about sprinkling mapping_gfp_mask all over the place and it sounds like we should drop gfp_mask argument altogether and use it internally in __add_to_page_cache_locked that would require all the filesystems to use mapping gfp consistently which I am not sure is the case here. From a quick glance it seems that some file system use it all the time while others are selective. Signed-off-by: Michal Hocko <mhocko@suse.com> Reported-by: Dave Chinner <david@fromorbit.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Ming Lei <ming.lei@canonical.com> Cc: Andreas Dilger <andreas.dilger@intel.com> Cc: Oleg Drokin <oleg.drokin@intel.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Christoph Hellwig <hch@lst.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-10-15 22:28:24 +00:00
&map_bh, &first_logical_block, get_block, gfp);
if (bio)
mpage_bio_submit(READ, bio);
return 0;
}
EXPORT_SYMBOL(mpage_readpage);
/*
* Writing is not so simple.
*
* If the page has buffers then they will be used for obtaining the disk
* mapping. We only support pages which are fully mapped-and-dirty, with a
* special case for pages which are unmapped at the end: end-of-file.
*
* If the page has no buffers (preferred) then the page is mapped here.
*
* If all blocks are found to be contiguous then the page can go into the
* BIO. Otherwise fall back to the mapping's writepage().
*
* FIXME: This code wants an estimate of how many pages are still to be
* written, so it can intelligently allocate a suitably-sized BIO. For now,
* just allocate full-size (16-page) BIOs.
*/
struct mpage_data {
struct bio *bio;
sector_t last_block_in_bio;
get_block_t *get_block;
unsigned use_writepage;
};
/*
* We have our BIO, so we can now mark the buffers clean. Make
* sure to only clean buffers which we know we'll be writing.
*/
static void clean_buffers(struct page *page, unsigned first_unmapped)
{
unsigned buffer_counter = 0;
struct buffer_head *bh, *head;
if (!page_has_buffers(page))
return;
head = page_buffers(page);
bh = head;
do {
if (buffer_counter++ == first_unmapped)
break;
clear_buffer_dirty(bh);
bh = bh->b_this_page;
} while (bh != head);
/*
* we cannot drop the bh if the page is not uptodate or a concurrent
* readpage would fail to serialize with the bh and it would read from
* disk before we reach the platter.
*/
if (buffer_heads_over_limit && PageUptodate(page))
try_to_free_buffers(page);
}
static int __mpage_writepage(struct page *page, struct writeback_control *wbc,
void *data)
{
struct mpage_data *mpd = data;
struct bio *bio = mpd->bio;
struct address_space *mapping = page->mapping;
struct inode *inode = page->mapping->host;
const unsigned blkbits = inode->i_blkbits;
unsigned long end_index;
const unsigned blocks_per_page = PAGE_CACHE_SIZE >> blkbits;
sector_t last_block;
sector_t block_in_file;
sector_t blocks[MAX_BUF_PER_PAGE];
unsigned page_block;
unsigned first_unmapped = blocks_per_page;
struct block_device *bdev = NULL;
int boundary = 0;
sector_t boundary_block = 0;
struct block_device *boundary_bdev = NULL;
int length;
struct buffer_head map_bh;
loff_t i_size = i_size_read(inode);
int ret = 0;
int wr = (wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC : WRITE);
if (page_has_buffers(page)) {
struct buffer_head *head = page_buffers(page);
struct buffer_head *bh = head;
/* If they're all mapped and dirty, do it */
page_block = 0;
do {
BUG_ON(buffer_locked(bh));
if (!buffer_mapped(bh)) {
/*
* unmapped dirty buffers are created by
* __set_page_dirty_buffers -> mmapped data
*/
if (buffer_dirty(bh))
goto confused;
if (first_unmapped == blocks_per_page)
first_unmapped = page_block;
continue;
}
if (first_unmapped != blocks_per_page)
goto confused; /* hole -> non-hole */
if (!buffer_dirty(bh) || !buffer_uptodate(bh))
goto confused;
if (page_block) {
if (bh->b_blocknr != blocks[page_block-1] + 1)
goto confused;
}
blocks[page_block++] = bh->b_blocknr;
boundary = buffer_boundary(bh);
if (boundary) {
boundary_block = bh->b_blocknr;
boundary_bdev = bh->b_bdev;
}
bdev = bh->b_bdev;
} while ((bh = bh->b_this_page) != head);
if (first_unmapped)
goto page_is_mapped;
/*
* Page has buffers, but they are all unmapped. The page was
* created by pagein or read over a hole which was handled by
* block_read_full_page(). If this address_space is also
* using mpage_readpages then this can rarely happen.
*/
goto confused;
}
/*
* The page has no buffers: map it to disk
*/
BUG_ON(!PageUptodate(page));
[PATCH] fix possible PAGE_CACHE_SHIFT overflows We've had two instances recently of overflows when doing 64_bit_value = (32_bit_value << PAGE_CACHE_SHIFT) I did a tree-wide grep of `<<.*PAGE_CACHE_SHIFT' and this is the result. - afs_rxfs_fetch_descriptor.offset is of type off_t, which seems broken. - jfs and jffs are limited to 4GB anyway. - reiserfs map_block_for_writepage() takes an unsigned long for the block - it should take sector_t. (It'll fail for huge filesystems with blocksize<PAGE_CACHE_SIZE) - cramfs_read() needs to use sector_t (I think cramsfs is busted on large filesystems anyway) - affs is limited in file size anyway. - I generally didn't fix 32-bit overflows in directory operations. - arm's __flush_dcache_page() is peculiar. What if the page lies beyond 4G? - gss_wrap_req_priv() needs checking (snd_buf->page_base) Cc: Oleg Drokin <green@linuxhacker.ru> Cc: David Howells <dhowells@redhat.com> Cc: David Woodhouse <dwmw2@infradead.org> Cc: <reiserfs-dev@namesys.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Anton Altaparmakov <aia21@cantab.net> Cc: Jeff Dike <jdike@addtoit.com> Cc: Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it> Cc: Roman Zippel <zippel@linux-m68k.org> Cc: <linux-fsdevel@vger.kernel.org> Cc: Miklos Szeredi <miklos@szeredi.hu> Cc: Russell King <rmk@arm.linux.org.uk> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Cc: Neil Brown <neilb@cse.unsw.edu.au> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 09:03:05 +00:00
block_in_file = (sector_t)page->index << (PAGE_CACHE_SHIFT - blkbits);
last_block = (i_size - 1) >> blkbits;
map_bh.b_page = page;
for (page_block = 0; page_block < blocks_per_page; ) {
map_bh.b_state = 0;
map_bh.b_size = 1 << blkbits;
if (mpd->get_block(inode, block_in_file, &map_bh, 1))
goto confused;
if (buffer_new(&map_bh))
unmap_underlying_metadata(map_bh.b_bdev,
map_bh.b_blocknr);
if (buffer_boundary(&map_bh)) {
boundary_block = map_bh.b_blocknr;
boundary_bdev = map_bh.b_bdev;
}
if (page_block) {
if (map_bh.b_blocknr != blocks[page_block-1] + 1)
goto confused;
}
blocks[page_block++] = map_bh.b_blocknr;
boundary = buffer_boundary(&map_bh);
bdev = map_bh.b_bdev;
if (block_in_file == last_block)
break;
block_in_file++;
}
BUG_ON(page_block == 0);
first_unmapped = page_block;
page_is_mapped:
end_index = i_size >> PAGE_CACHE_SHIFT;
if (page->index >= end_index) {
/*
* The page straddles i_size. It must be zeroed out on each
* and every writepage invocation because it may be mmapped.
* "A file is mapped in multiples of the page size. For a file
* that is not a multiple of the page size, the remaining memory
* is zeroed when mapped, and writes to that region are not
* written out to the file."
*/
unsigned offset = i_size & (PAGE_CACHE_SIZE - 1);
if (page->index > end_index || !offset)
goto confused;
Pagecache zeroing: zero_user_segment, zero_user_segments and zero_user Simplify page cache zeroing of segments of pages through 3 functions zero_user_segments(page, start1, end1, start2, end2) Zeros two segments of the page. It takes the position where to start and end the zeroing which avoids length calculations and makes code clearer. zero_user_segment(page, start, end) Same for a single segment. zero_user(page, start, length) Length variant for the case where we know the length. We remove the zero_user_page macro. Issues: 1. Its a macro. Inline functions are preferable. 2. The KM_USER0 macro is only defined for HIGHMEM. Having to treat this special case everywhere makes the code needlessly complex. The parameter for zeroing is always KM_USER0 except in one single case that we open code. Avoiding KM_USER0 makes a lot of code not having to be dealing with the special casing for HIGHMEM anymore. Dealing with kmap is only necessary for HIGHMEM configurations. In those configurations we use KM_USER0 like we do for a series of other functions defined in highmem.h. Since KM_USER0 is depends on HIGHMEM the existing zero_user_page function could not be a macro. zero_user_* functions introduced here can be be inline because that constant is not used when these functions are called. Also extract the flushing of the caches to be outside of the kmap. [akpm@linux-foundation.org: fix nfs and ntfs build] [akpm@linux-foundation.org: fix ntfs build some more] Signed-off-by: Christoph Lameter <clameter@sgi.com> Cc: Steven French <sfrench@us.ibm.com> Cc: Michael Halcrow <mhalcrow@us.ibm.com> Cc: <linux-ext4@vger.kernel.org> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Cc: "J. Bruce Fields" <bfields@fieldses.org> Cc: Anton Altaparmakov <aia21@cantab.net> Cc: Mark Fasheh <mark.fasheh@oracle.com> Cc: David Chinner <dgc@sgi.com> Cc: Michael Halcrow <mhalcrow@us.ibm.com> Cc: Steven French <sfrench@us.ibm.com> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 06:28:29 +00:00
zero_user_segment(page, offset, PAGE_CACHE_SIZE);
}
/*
* This page will go to BIO. Do we need to send this BIO off first?
*/
if (bio && mpd->last_block_in_bio != blocks[0] - 1)
bio = mpage_bio_submit(wr, bio);
alloc_new:
if (bio == NULL) {
if (first_unmapped == blocks_per_page) {
if (!bdev_write_page(bdev, blocks[0] << (blkbits - 9),
page, wbc)) {
clean_buffers(page, first_unmapped);
goto out;
}
}
bio = mpage_alloc(bdev, blocks[0] << (blkbits - 9),
BIO_MAX_PAGES, GFP_NOFS|__GFP_HIGH);
if (bio == NULL)
goto confused;
writeback: make writeback_control track the inode being written back Currently, for cgroup writeback, the IO submission paths directly associate the bio's with the blkcg from inode_to_wb_blkcg_css(); however, it'd be necessary to keep more writeback context to implement foreign inode writeback detection. wbc (writeback_control) is the natural fit for the extra context - it persists throughout the writeback of each inode and is passed all the way down to IO submission paths. This patch adds wbc_attach_and_unlock_inode(), wbc_detach_inode(), and wbc_attach_fdatawrite_inode() which are used to associate wbc with the inode being written back. IO submission paths now use wbc_init_bio() instead of directly associating bio's with blkcg themselves. This leaves inode_to_wb_blkcg_css() w/o any user. The function is removed. wbc currently only tracks the associated wb (bdi_writeback). Future patches will add more for foreign inode detection. The association is established under i_lock which will be depended upon when migrating foreign inodes to other wb's. As currently, once established, inode to wb association never changes, going through wbc when initializing bio's doesn't cause any behavior changes. v2: submit_blk_blkcg() now checks whether the wbc is associated with a wb before dereferencing it. This can happen when pageout() is writing pages directly without going through the usual writeback path. As pageout() path is single-threaded, we don't want it to be blocked behind a slow cgroup and ultimately want it to delegate actual writing to the usual writeback path. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Jens Axboe <axboe@kernel.dk> Cc: Jan Kara <jack@suse.cz> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Greg Thelen <gthelen@google.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2015-06-02 14:39:48 +00:00
wbc_init_bio(wbc, bio);
}
/*
* Must try to add the page before marking the buffer clean or
* the confused fail path above (OOM) will be very confused when
* it finds all bh marked clean (i.e. it will not write anything)
*/
writeback: implement foreign cgroup inode detection As concurrent write sharing of an inode is expected to be very rare and memcg only tracks page ownership on first-use basis severely confining the usefulness of such sharing, cgroup writeback tracks ownership per-inode. While the support for concurrent write sharing of an inode is deemed unnecessary, an inode being written to by different cgroups at different points in time is a lot more common, and, more importantly, charging only by first-use can too readily lead to grossly incorrect behaviors (single foreign page can lead to gigabytes of writeback to be incorrectly attributed). To resolve this issue, cgroup writeback detects the majority dirtier of an inode and will transfer the ownership to it. To avoid unnnecessary oscillation, the detection mechanism keeps track of history and gives out the switch verdict only if the foreign usage pattern is stable over a certain amount of time and/or writeback attempts. The detection mechanism has fairly low space and computation overhead. It adds 8 bytes to struct inode (one int and two u16's) and minimal amount of calculation per IO. The detection mechanism converges to the correct answer usually in several seconds of IO time when there's a clear majority dirtier. Even when there isn't, it can reach an acceptable answer fairly quickly under most circumstances. Please see wb_detach_inode() for more details. This patch only implements detection. Following patches will implement actual switching. v2: wbc_account_io() now checks whether the wbc is associated with a wb before dereferencing it. This can happen when pageout() is writing pages directly without going through the usual writeback path. As pageout() path is single-threaded, we don't want it to be blocked behind a slow cgroup and ultimately want it to delegate actual writing to the usual writeback path. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Jens Axboe <axboe@kernel.dk> Cc: Jan Kara <jack@suse.cz> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Greg Thelen <gthelen@google.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2015-05-28 18:50:51 +00:00
wbc_account_io(wbc, page, PAGE_SIZE);
length = first_unmapped << blkbits;
if (bio_add_page(bio, page, length, 0) < length) {
bio = mpage_bio_submit(wr, bio);
goto alloc_new;
}
clean_buffers(page, first_unmapped);
BUG_ON(PageWriteback(page));
set_page_writeback(page);
unlock_page(page);
if (boundary || (first_unmapped != blocks_per_page)) {
bio = mpage_bio_submit(wr, bio);
if (boundary_block) {
write_boundary_block(boundary_bdev,
boundary_block, 1 << blkbits);
}
} else {
mpd->last_block_in_bio = blocks[blocks_per_page - 1];
}
goto out;
confused:
if (bio)
bio = mpage_bio_submit(wr, bio);
if (mpd->use_writepage) {
ret = mapping->a_ops->writepage(page, wbc);
} else {
ret = -EAGAIN;
goto out;
}
/*
* The caller has a ref on the inode, so *mapping is stable
*/
mapping_set_error(mapping, ret);
out:
mpd->bio = bio;
return ret;
}
/**
* mpage_writepages - walk the list of dirty pages of the given address space & writepage() all of them
* @mapping: address space structure to write
* @wbc: subtract the number of written pages from *@wbc->nr_to_write
* @get_block: the filesystem's block mapper function.
* If this is NULL then use a_ops->writepage. Otherwise, go
* direct-to-BIO.
*
* This is a library function, which implements the writepages()
* address_space_operation.
*
* If a page is already under I/O, generic_writepages() skips it, even
* if it's dirty. This is desirable behaviour for memory-cleaning writeback,
* but it is INCORRECT for data-integrity system calls such as fsync(). fsync()
* and msync() need to guarantee that all the data which was dirty at the time
* the call was made get new I/O started against them. If wbc->sync_mode is
* WB_SYNC_ALL then we were called for data integrity and we must wait for
* existing IO to complete.
*/
int
mpage_writepages(struct address_space *mapping,
struct writeback_control *wbc, get_block_t get_block)
{
struct blk_plug plug;
int ret;
blk_start_plug(&plug);
if (!get_block)
ret = generic_writepages(mapping, wbc);
else {
struct mpage_data mpd = {
.bio = NULL,
.last_block_in_bio = 0,
.get_block = get_block,
.use_writepage = 1,
};
ret = write_cache_pages(mapping, wbc, __mpage_writepage, &mpd);
if (mpd.bio) {
int wr = (wbc->sync_mode == WB_SYNC_ALL ?
WRITE_SYNC : WRITE);
mpage_bio_submit(wr, mpd.bio);
}
}
blk_finish_plug(&plug);
return ret;
}
EXPORT_SYMBOL(mpage_writepages);
int mpage_writepage(struct page *page, get_block_t get_block,
struct writeback_control *wbc)
{
struct mpage_data mpd = {
.bio = NULL,
.last_block_in_bio = 0,
.get_block = get_block,
.use_writepage = 0,
};
int ret = __mpage_writepage(page, wbc, &mpd);
if (mpd.bio) {
int wr = (wbc->sync_mode == WB_SYNC_ALL ?
WRITE_SYNC : WRITE);
mpage_bio_submit(wr, mpd.bio);
}
return ret;
}
EXPORT_SYMBOL(mpage_writepage);