linux/fs/f2fs/data.c

4256 lines
103 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
/*
* fs/f2fs/data.c
*
* Copyright (c) 2012 Samsung Electronics Co., Ltd.
* http://www.samsung.com/
*/
#include <linux/fs.h>
#include <linux/f2fs_fs.h>
#include <linux/buffer_head.h>
mm: introduce memalloc_retry_wait() Various places in the kernel - largely in filesystems - respond to a memory allocation failure by looping around and re-trying. Some of these cannot conveniently use __GFP_NOFAIL, for reasons such as: - a GFP_ATOMIC allocation, which __GFP_NOFAIL doesn't work on - a need to check for the process being signalled between failures - the possibility that other recovery actions could be performed - the allocation is quite deep in support code, and passing down an extra flag to say if __GFP_NOFAIL is wanted would be clumsy. Many of these currently use congestion_wait() which (in almost all cases) simply waits the given timeout - congestion isn't tracked for most devices. It isn't clear what the best delay is for loops, but it is clear that the various filesystems shouldn't be responsible for choosing a timeout. This patch introduces memalloc_retry_wait() with takes on that responsibility. Code that wants to retry a memory allocation can call this function passing the GFP flags that were used. It will wait however is appropriate. For now, it only considers __GFP_NORETRY and whatever gfpflags_allow_blocking() tests. If blocking is allowed without __GFP_NORETRY, then alloc_page either made some reclaim progress, or waited for a while, before failing. So there is no need for much further waiting. memalloc_retry_wait() will wait until the current jiffie ends. If this condition is not met, then alloc_page() won't have waited much if at all. In that case memalloc_retry_wait() waits about 200ms. This is the delay that most current loops uses. linux/sched/mm.h needs to be included in some files now, but linux/backing-dev.h does not. Link: https://lkml.kernel.org/r/163754371968.13692.1277530886009912421@noble.neil.brown.name Signed-off-by: NeilBrown <neilb@suse.de> Cc: Dave Chinner <david@fromorbit.com> Cc: Michal Hocko <mhocko@suse.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Jaegeuk Kim <jaegeuk@kernel.org> Cc: Chao Yu <chao@kernel.org> Cc: Darrick J. Wong <djwong@kernel.org> Cc: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-01-14 22:07:14 +00:00
#include <linux/sched/mm.h>
#include <linux/mpage.h>
#include <linux/writeback.h>
#include <linux/pagevec.h>
#include <linux/blkdev.h>
#include <linux/bio.h>
#include <linux/blk-crypto.h>
#include <linux/swap.h>
#include <linux/prefetch.h>
#include <linux/uio.h>
#include <linux/sched/signal.h>
#include <linux/fiemap.h>
#include <linux/iomap.h>
#include "f2fs.h"
#include "node.h"
#include "segment.h"
#include "iostat.h"
#include <trace/events/f2fs.h>
#define NUM_PREALLOC_POST_READ_CTXS 128
static struct kmem_cache *bio_post_read_ctx_cache;
static struct kmem_cache *bio_entry_slab;
static mempool_t *bio_post_read_ctx_pool;
static struct bio_set f2fs_bioset;
#define F2FS_BIO_POOL_SIZE NR_CURSEG_TYPE
int __init f2fs_init_bioset(void)
{
return bioset_init(&f2fs_bioset, F2FS_BIO_POOL_SIZE,
0, BIOSET_NEED_BVECS);
}
void f2fs_destroy_bioset(void)
{
bioset_exit(&f2fs_bioset);
}
bool f2fs_is_cp_guaranteed(struct page *page)
{
struct address_space *mapping = page->mapping;
struct inode *inode;
struct f2fs_sb_info *sbi;
if (!mapping)
return false;
inode = mapping->host;
sbi = F2FS_I_SB(inode);
if (inode->i_ino == F2FS_META_INO(sbi) ||
inode->i_ino == F2FS_NODE_INO(sbi) ||
f2fs: restructure f2fs page.private layout Restruct f2fs page private layout for below reasons: There are some cases that f2fs wants to set a flag in a page to indicate a specified status of page: a) page is in transaction list for atomic write b) page contains dummy data for aligned write c) page is migrating for GC d) page contains inline data for inline inode flush e) page belongs to merkle tree, and is verified for fsverity f) page is dirty and has filesystem/inode reference count for writeback g) page is temporary and has decompress io context reference for compression There are existed places in page structure we can use to store f2fs private status/data: - page.flags: PG_checked, PG_private - page.private However it was a mess when we using them, which may cause potential confliction: page.private PG_private PG_checked page._refcount (+1 at most) a) -1 set +1 b) -2 set c), d), e) set f) 0 set +1 g) pointer set The other problem is page.flags has no free slot, if we can avoid set zero to page.private and set PG_private flag, then we use non-zero value to indicate PG_private status, so that we may have chance to reclaim PG_private slot for other usage. [1] The other concern is f2fs has bad scalability in aspect of indicating more page status. So in this patch, let's restructure f2fs' page.private as below to solve above issues: Layout A: lowest bit should be 1 | bit0 = 1 | bit1 | bit2 | ... | bit MAX | private data .... | bit 0 PAGE_PRIVATE_NOT_POINTER bit 1 PAGE_PRIVATE_ATOMIC_WRITE bit 2 PAGE_PRIVATE_DUMMY_WRITE bit 3 PAGE_PRIVATE_ONGOING_MIGRATION bit 4 PAGE_PRIVATE_INLINE_INODE bit 5 PAGE_PRIVATE_REF_RESOURCE bit 6- f2fs private data Layout B: lowest bit should be 0 page.private is a wrapped pointer. After the change: page.private PG_private PG_checked page._refcount (+1 at most) a) 11 set +1 b) 101 set +1 c) 1001 set +1 d) 10001 set +1 e) set f) 100001 set +1 g) pointer set +1 [1] https://lore.kernel.org/linux-f2fs-devel/20210422154705.GO3596236@casper.infradead.org/T/#u Cc: Matthew Wilcox <willy@infradead.org> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2021-04-28 09:20:31 +00:00
S_ISDIR(inode->i_mode))
return true;
if ((S_ISREG(inode->i_mode) && IS_NOQUOTA(inode)) ||
f2fs: restructure f2fs page.private layout Restruct f2fs page private layout for below reasons: There are some cases that f2fs wants to set a flag in a page to indicate a specified status of page: a) page is in transaction list for atomic write b) page contains dummy data for aligned write c) page is migrating for GC d) page contains inline data for inline inode flush e) page belongs to merkle tree, and is verified for fsverity f) page is dirty and has filesystem/inode reference count for writeback g) page is temporary and has decompress io context reference for compression There are existed places in page structure we can use to store f2fs private status/data: - page.flags: PG_checked, PG_private - page.private However it was a mess when we using them, which may cause potential confliction: page.private PG_private PG_checked page._refcount (+1 at most) a) -1 set +1 b) -2 set c), d), e) set f) 0 set +1 g) pointer set The other problem is page.flags has no free slot, if we can avoid set zero to page.private and set PG_private flag, then we use non-zero value to indicate PG_private status, so that we may have chance to reclaim PG_private slot for other usage. [1] The other concern is f2fs has bad scalability in aspect of indicating more page status. So in this patch, let's restructure f2fs' page.private as below to solve above issues: Layout A: lowest bit should be 1 | bit0 = 1 | bit1 | bit2 | ... | bit MAX | private data .... | bit 0 PAGE_PRIVATE_NOT_POINTER bit 1 PAGE_PRIVATE_ATOMIC_WRITE bit 2 PAGE_PRIVATE_DUMMY_WRITE bit 3 PAGE_PRIVATE_ONGOING_MIGRATION bit 4 PAGE_PRIVATE_INLINE_INODE bit 5 PAGE_PRIVATE_REF_RESOURCE bit 6- f2fs private data Layout B: lowest bit should be 0 page.private is a wrapped pointer. After the change: page.private PG_private PG_checked page._refcount (+1 at most) a) 11 set +1 b) 101 set +1 c) 1001 set +1 d) 10001 set +1 e) set f) 100001 set +1 g) pointer set +1 [1] https://lore.kernel.org/linux-f2fs-devel/20210422154705.GO3596236@casper.infradead.org/T/#u Cc: Matthew Wilcox <willy@infradead.org> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2021-04-28 09:20:31 +00:00
page_private_gcing(page))
return true;
return false;
}
static enum count_type __read_io_type(struct page *page)
{
struct address_space *mapping = page_file_mapping(page);
if (mapping) {
struct inode *inode = mapping->host;
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
if (inode->i_ino == F2FS_META_INO(sbi))
return F2FS_RD_META;
if (inode->i_ino == F2FS_NODE_INO(sbi))
return F2FS_RD_NODE;
}
return F2FS_RD_DATA;
}
/* postprocessing steps for read bios */
enum bio_post_read_step {
#ifdef CONFIG_FS_ENCRYPTION
STEP_DECRYPT = BIT(0),
#else
STEP_DECRYPT = 0, /* compile out the decryption-related code */
#endif
#ifdef CONFIG_F2FS_FS_COMPRESSION
STEP_DECOMPRESS = BIT(1),
#else
STEP_DECOMPRESS = 0, /* compile out the decompression-related code */
#endif
#ifdef CONFIG_FS_VERITY
STEP_VERITY = BIT(2),
#else
STEP_VERITY = 0, /* compile out the verity-related code */
#endif
};
struct bio_post_read_ctx {
struct bio *bio;
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
struct f2fs_sb_info *sbi;
struct work_struct work;
unsigned int enabled_steps;
/*
* decompression_attempted keeps track of whether
* f2fs_end_read_compressed_page() has been called on the pages in the
* bio that belong to a compressed cluster yet.
*/
bool decompression_attempted;
block_t fs_blkaddr;
};
/*
* Update and unlock a bio's pages, and free the bio.
*
* This marks pages up-to-date only if there was no error in the bio (I/O error,
* decryption error, or verity error), as indicated by bio->bi_status.
*
* "Compressed pages" (pagecache pages backed by a compressed cluster on-disk)
* aren't marked up-to-date here, as decompression is done on a per-compression-
* cluster basis rather than a per-bio basis. Instead, we only must do two
* things for each compressed page here: call f2fs_end_read_compressed_page()
* with failed=true if an error occurred before it would have normally gotten
* called (i.e., I/O error or decryption error, but *not* verity error), and
* release the bio's reference to the decompress_io_ctx of the page's cluster.
*/
static void f2fs_finish_read_bio(struct bio *bio, bool in_task)
{
struct bio_vec *bv;
struct bvec_iter_all iter_all;
struct bio_post_read_ctx *ctx = bio->bi_private;
bio_for_each_segment_all(bv, bio, iter_all) {
struct page *page = bv->bv_page;
if (f2fs_is_compressed_page(page)) {
if (ctx && !ctx->decompression_attempted)
f2fs_end_read_compressed_page(page, true, 0,
in_task);
f2fs_put_page_dic(page, in_task);
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
continue;
}
if (bio->bi_status)
ClearPageUptodate(page);
else
SetPageUptodate(page);
dec_page_count(F2FS_P_SB(page), __read_io_type(page));
unlock_page(page);
}
if (ctx)
mempool_free(ctx, bio_post_read_ctx_pool);
bio_put(bio);
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
}
static void f2fs_verify_bio(struct work_struct *work)
{
struct bio_post_read_ctx *ctx =
container_of(work, struct bio_post_read_ctx, work);
struct bio *bio = ctx->bio;
bool may_have_compressed_pages = (ctx->enabled_steps & STEP_DECOMPRESS);
/*
* fsverity_verify_bio() may call readahead() again, and while verity
* will be disabled for this, decryption and/or decompression may still
* be needed, resulting in another bio_post_read_ctx being allocated.
* So to prevent deadlocks we need to release the current ctx to the
* mempool first. This assumes that verity is the last post-read step.
*/
mempool_free(ctx, bio_post_read_ctx_pool);
bio->bi_private = NULL;
/*
* Verify the bio's pages with fs-verity. Exclude compressed pages,
* as those were handled separately by f2fs_end_read_compressed_page().
*/
if (may_have_compressed_pages) {
struct bio_vec *bv;
struct bvec_iter_all iter_all;
bio_for_each_segment_all(bv, bio, iter_all) {
struct page *page = bv->bv_page;
if (!f2fs_is_compressed_page(page) &&
!fsverity_verify_page(page)) {
bio->bi_status = BLK_STS_IOERR;
break;
}
}
} else {
fsverity_verify_bio(bio);
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
}
f2fs_finish_read_bio(bio, true);
}
/*
* If the bio's data needs to be verified with fs-verity, then enqueue the
* verity work for the bio. Otherwise finish the bio now.
*
* Note that to avoid deadlocks, the verity work can't be done on the
* decryption/decompression workqueue. This is because verifying the data pages
* can involve reading verity metadata pages from the file, and these verity
* metadata pages may be encrypted and/or compressed.
*/
static void f2fs_verify_and_finish_bio(struct bio *bio, bool in_task)
f2fs: add fs-verity support Add fs-verity support to f2fs. fs-verity is a filesystem feature that enables transparent integrity protection and authentication of read-only files. It uses a dm-verity like mechanism at the file level: a Merkle tree is used to verify any block in the file in log(filesize) time. It is implemented mainly by helper functions in fs/verity/. See Documentation/filesystems/fsverity.rst for the full documentation. The f2fs support for fs-verity consists of: - Adding a filesystem feature flag and an inode flag for fs-verity. - Implementing the fsverity_operations to support enabling verity on an inode and reading/writing the verity metadata. - Updating ->readpages() to verify data as it's read from verity files and to support reading verity metadata pages. - Updating ->write_begin(), ->write_end(), and ->writepages() to support writing verity metadata pages. - Calling the fs-verity hooks for ->open(), ->setattr(), and ->ioctl(). Like ext4, f2fs stores the verity metadata (Merkle tree and fsverity_descriptor) past the end of the file, starting at the first 64K boundary beyond i_size. This approach works because (a) verity files are readonly, and (b) pages fully beyond i_size aren't visible to userspace but can be read/written internally by f2fs with only some relatively small changes to f2fs. Extended attributes cannot be used because (a) f2fs limits the total size of an inode's xattr entries to 4096 bytes, which wouldn't be enough for even a single Merkle tree block, and (b) f2fs encryption doesn't encrypt xattrs, yet the verity metadata *must* be encrypted when the file is because it contains hashes of the plaintext data. Acked-by: Jaegeuk Kim <jaegeuk@kernel.org> Acked-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Eric Biggers <ebiggers@google.com>
2019-07-22 16:26:24 +00:00
{
struct bio_post_read_ctx *ctx = bio->bi_private;
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
if (ctx && (ctx->enabled_steps & STEP_VERITY)) {
INIT_WORK(&ctx->work, f2fs_verify_bio);
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
fsverity_enqueue_verify_work(&ctx->work);
} else {
f2fs_finish_read_bio(bio, in_task);
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
}
}
f2fs: add fs-verity support Add fs-verity support to f2fs. fs-verity is a filesystem feature that enables transparent integrity protection and authentication of read-only files. It uses a dm-verity like mechanism at the file level: a Merkle tree is used to verify any block in the file in log(filesize) time. It is implemented mainly by helper functions in fs/verity/. See Documentation/filesystems/fsverity.rst for the full documentation. The f2fs support for fs-verity consists of: - Adding a filesystem feature flag and an inode flag for fs-verity. - Implementing the fsverity_operations to support enabling verity on an inode and reading/writing the verity metadata. - Updating ->readpages() to verify data as it's read from verity files and to support reading verity metadata pages. - Updating ->write_begin(), ->write_end(), and ->writepages() to support writing verity metadata pages. - Calling the fs-verity hooks for ->open(), ->setattr(), and ->ioctl(). Like ext4, f2fs stores the verity metadata (Merkle tree and fsverity_descriptor) past the end of the file, starting at the first 64K boundary beyond i_size. This approach works because (a) verity files are readonly, and (b) pages fully beyond i_size aren't visible to userspace but can be read/written internally by f2fs with only some relatively small changes to f2fs. Extended attributes cannot be used because (a) f2fs limits the total size of an inode's xattr entries to 4096 bytes, which wouldn't be enough for even a single Merkle tree block, and (b) f2fs encryption doesn't encrypt xattrs, yet the verity metadata *must* be encrypted when the file is because it contains hashes of the plaintext data. Acked-by: Jaegeuk Kim <jaegeuk@kernel.org> Acked-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Eric Biggers <ebiggers@google.com>
2019-07-22 16:26:24 +00:00
/*
* Handle STEP_DECOMPRESS by decompressing any compressed clusters whose last
* remaining page was read by @ctx->bio.
*
* Note that a bio may span clusters (even a mix of compressed and uncompressed
* clusters) or be for just part of a cluster. STEP_DECOMPRESS just indicates
* that the bio includes at least one compressed page. The actual decompression
* is done on a per-cluster basis, not a per-bio basis.
*/
static void f2fs_handle_step_decompress(struct bio_post_read_ctx *ctx,
bool in_task)
{
struct bio_vec *bv;
struct bvec_iter_all iter_all;
bool all_compressed = true;
block_t blkaddr = ctx->fs_blkaddr;
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
bio_for_each_segment_all(bv, ctx->bio, iter_all) {
struct page *page = bv->bv_page;
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
if (f2fs_is_compressed_page(page))
f2fs_end_read_compressed_page(page, false, blkaddr,
in_task);
else
all_compressed = false;
blkaddr++;
}
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
ctx->decompression_attempted = true;
/*
* Optimization: if all the bio's pages are compressed, then scheduling
* the per-bio verity work is unnecessary, as verity will be fully
* handled at the compression cluster level.
*/
if (all_compressed)
ctx->enabled_steps &= ~STEP_VERITY;
}
static void f2fs_post_read_work(struct work_struct *work)
{
struct bio_post_read_ctx *ctx =
container_of(work, struct bio_post_read_ctx, work);
struct bio *bio = ctx->bio;
if ((ctx->enabled_steps & STEP_DECRYPT) && !fscrypt_decrypt_bio(bio)) {
f2fs_finish_read_bio(bio, true);
return;
}
if (ctx->enabled_steps & STEP_DECOMPRESS)
f2fs_handle_step_decompress(ctx, true);
f2fs_verify_and_finish_bio(bio, true);
}
static void f2fs_read_end_io(struct bio *bio)
{
struct f2fs_sb_info *sbi = F2FS_P_SB(bio_first_page_all(bio));
f2fs: introduce periodic iostat io latency traces Whenever we notice some sluggish issues on our machines, we are always curious about how well all types of I/O in the f2fs filesystem are handled. But, it's hard to get this kind of real data. First of all, we need to reproduce the issue while turning on the profiling tool like blktrace, but the issue doesn't happen again easily. Second, with the intervention of any tools, the overall timing of the issue will be slightly changed and it sometimes makes us hard to figure it out. So, I added the feature printing out IO latency statistics tracepoint events, which are minimal things to understand filesystem's I/O related behaviors, into F2FS_IOSTAT kernel config. With "iostat_enable" sysfs node on, we can get this statistics info in a periodic way and it would cause the least overhead. [samples] f2fs_ckpt-254:1-507 [003] .... 2842.439683: f2fs_iostat_latency: dev = (254,11), iotype [peak lat.(ms)/avg lat.(ms)/count], rd_data [136/1/801], rd_node [136/1/1704], rd_meta [4/2/4], wr_sync_data [164/16/3331], wr_sync_node [152/3/648], wr_sync_meta [160/2/4243], wr_async_data [24/13/15], wr_async_node [0/0/0], wr_async_meta [0/0/0] f2fs_ckpt-254:1-507 [002] .... 2845.450514: f2fs_iostat_latency: dev = (254,11), iotype [peak lat.(ms)/avg lat.(ms)/count], rd_data [60/3/456], rd_node [60/3/1258], rd_meta [0/0/1], wr_sync_data [120/12/2285], wr_sync_node [88/5/428], wr_sync_meta [52/6/2990], wr_async_data [4/1/3], wr_async_node [0/0/0], wr_async_meta [0/0/0] Signed-off-by: Daeho Jeong <daehojeong@google.com> Reviewed-by: Chao Yu <chao@kernel.org> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2021-08-20 22:29:09 +00:00
struct bio_post_read_ctx *ctx;
bool intask = in_task();
f2fs: introduce periodic iostat io latency traces Whenever we notice some sluggish issues on our machines, we are always curious about how well all types of I/O in the f2fs filesystem are handled. But, it's hard to get this kind of real data. First of all, we need to reproduce the issue while turning on the profiling tool like blktrace, but the issue doesn't happen again easily. Second, with the intervention of any tools, the overall timing of the issue will be slightly changed and it sometimes makes us hard to figure it out. So, I added the feature printing out IO latency statistics tracepoint events, which are minimal things to understand filesystem's I/O related behaviors, into F2FS_IOSTAT kernel config. With "iostat_enable" sysfs node on, we can get this statistics info in a periodic way and it would cause the least overhead. [samples] f2fs_ckpt-254:1-507 [003] .... 2842.439683: f2fs_iostat_latency: dev = (254,11), iotype [peak lat.(ms)/avg lat.(ms)/count], rd_data [136/1/801], rd_node [136/1/1704], rd_meta [4/2/4], wr_sync_data [164/16/3331], wr_sync_node [152/3/648], wr_sync_meta [160/2/4243], wr_async_data [24/13/15], wr_async_node [0/0/0], wr_async_meta [0/0/0] f2fs_ckpt-254:1-507 [002] .... 2845.450514: f2fs_iostat_latency: dev = (254,11), iotype [peak lat.(ms)/avg lat.(ms)/count], rd_data [60/3/456], rd_node [60/3/1258], rd_meta [0/0/1], wr_sync_data [120/12/2285], wr_sync_node [88/5/428], wr_sync_meta [52/6/2990], wr_async_data [4/1/3], wr_async_node [0/0/0], wr_async_meta [0/0/0] Signed-off-by: Daeho Jeong <daehojeong@google.com> Reviewed-by: Chao Yu <chao@kernel.org> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2021-08-20 22:29:09 +00:00
iostat_update_and_unbind_ctx(bio);
f2fs: introduce periodic iostat io latency traces Whenever we notice some sluggish issues on our machines, we are always curious about how well all types of I/O in the f2fs filesystem are handled. But, it's hard to get this kind of real data. First of all, we need to reproduce the issue while turning on the profiling tool like blktrace, but the issue doesn't happen again easily. Second, with the intervention of any tools, the overall timing of the issue will be slightly changed and it sometimes makes us hard to figure it out. So, I added the feature printing out IO latency statistics tracepoint events, which are minimal things to understand filesystem's I/O related behaviors, into F2FS_IOSTAT kernel config. With "iostat_enable" sysfs node on, we can get this statistics info in a periodic way and it would cause the least overhead. [samples] f2fs_ckpt-254:1-507 [003] .... 2842.439683: f2fs_iostat_latency: dev = (254,11), iotype [peak lat.(ms)/avg lat.(ms)/count], rd_data [136/1/801], rd_node [136/1/1704], rd_meta [4/2/4], wr_sync_data [164/16/3331], wr_sync_node [152/3/648], wr_sync_meta [160/2/4243], wr_async_data [24/13/15], wr_async_node [0/0/0], wr_async_meta [0/0/0] f2fs_ckpt-254:1-507 [002] .... 2845.450514: f2fs_iostat_latency: dev = (254,11), iotype [peak lat.(ms)/avg lat.(ms)/count], rd_data [60/3/456], rd_node [60/3/1258], rd_meta [0/0/1], wr_sync_data [120/12/2285], wr_sync_node [88/5/428], wr_sync_meta [52/6/2990], wr_async_data [4/1/3], wr_async_node [0/0/0], wr_async_meta [0/0/0] Signed-off-by: Daeho Jeong <daehojeong@google.com> Reviewed-by: Chao Yu <chao@kernel.org> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2021-08-20 22:29:09 +00:00
ctx = bio->bi_private;
if (time_to_inject(sbi, FAULT_READ_IO))
bio->bi_status = BLK_STS_IOERR;
if (bio->bi_status) {
f2fs_finish_read_bio(bio, intask);
return;
}
if (ctx) {
unsigned int enabled_steps = ctx->enabled_steps &
(STEP_DECRYPT | STEP_DECOMPRESS);
/*
* If we have only decompression step between decompression and
* decrypt, we don't need post processing for this.
*/
if (enabled_steps == STEP_DECOMPRESS &&
!f2fs_low_mem_mode(sbi)) {
f2fs_handle_step_decompress(ctx, intask);
} else if (enabled_steps) {
INIT_WORK(&ctx->work, f2fs_post_read_work);
queue_work(ctx->sbi->post_read_wq, &ctx->work);
return;
}
}
f2fs_verify_and_finish_bio(bio, intask);
}
static void f2fs_write_end_io(struct bio *bio)
{
f2fs: introduce periodic iostat io latency traces Whenever we notice some sluggish issues on our machines, we are always curious about how well all types of I/O in the f2fs filesystem are handled. But, it's hard to get this kind of real data. First of all, we need to reproduce the issue while turning on the profiling tool like blktrace, but the issue doesn't happen again easily. Second, with the intervention of any tools, the overall timing of the issue will be slightly changed and it sometimes makes us hard to figure it out. So, I added the feature printing out IO latency statistics tracepoint events, which are minimal things to understand filesystem's I/O related behaviors, into F2FS_IOSTAT kernel config. With "iostat_enable" sysfs node on, we can get this statistics info in a periodic way and it would cause the least overhead. [samples] f2fs_ckpt-254:1-507 [003] .... 2842.439683: f2fs_iostat_latency: dev = (254,11), iotype [peak lat.(ms)/avg lat.(ms)/count], rd_data [136/1/801], rd_node [136/1/1704], rd_meta [4/2/4], wr_sync_data [164/16/3331], wr_sync_node [152/3/648], wr_sync_meta [160/2/4243], wr_async_data [24/13/15], wr_async_node [0/0/0], wr_async_meta [0/0/0] f2fs_ckpt-254:1-507 [002] .... 2845.450514: f2fs_iostat_latency: dev = (254,11), iotype [peak lat.(ms)/avg lat.(ms)/count], rd_data [60/3/456], rd_node [60/3/1258], rd_meta [0/0/1], wr_sync_data [120/12/2285], wr_sync_node [88/5/428], wr_sync_meta [52/6/2990], wr_async_data [4/1/3], wr_async_node [0/0/0], wr_async_meta [0/0/0] Signed-off-by: Daeho Jeong <daehojeong@google.com> Reviewed-by: Chao Yu <chao@kernel.org> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2021-08-20 22:29:09 +00:00
struct f2fs_sb_info *sbi;
Merge branch 'for-3.14/core' of git://git.kernel.dk/linux-block Pull core block IO changes from Jens Axboe: "The major piece in here is the immutable bio_ve series from Kent, the rest is fairly minor. It was supposed to go in last round, but various issues pushed it to this release instead. The pull request contains: - Various smaller blk-mq fixes from different folks. Nothing major here, just minor fixes and cleanups. - Fix for a memory leak in the error path in the block ioctl code from Christian Engelmayer. - Header export fix from CaiZhiyong. - Finally the immutable biovec changes from Kent Overstreet. This enables some nice future work on making arbitrarily sized bios possible, and splitting more efficient. Related fixes to immutable bio_vecs: - dm-cache immutable fixup from Mike Snitzer. - btrfs immutable fixup from Muthu Kumar. - bio-integrity fix from Nic Bellinger, which is also going to stable" * 'for-3.14/core' of git://git.kernel.dk/linux-block: (44 commits) xtensa: fixup simdisk driver to work with immutable bio_vecs block/blk-mq-cpu.c: use hotcpu_notifier() blk-mq: for_each_* macro correctness block: Fix memory leak in rw_copy_check_uvector() handling bio-integrity: Fix bio_integrity_verify segment start bug block: remove unrelated header files and export symbol blk-mq: uses page->list incorrectly blk-mq: use __smp_call_function_single directly btrfs: fix missing increment of bi_remaining Revert "block: Warn and free bio if bi_end_io is not set" block: Warn and free bio if bi_end_io is not set blk-mq: fix initializing request's start time block: blk-mq: don't export blk_mq_free_queue() block: blk-mq: make blk_sync_queue support mq block: blk-mq: support draining mq queue dm cache: increment bi_remaining when bi_end_io is restored block: fixup for generic bio chaining block: Really silence spurious compiler warnings block: Silence spurious compiler warnings block: Kill bio_pair_split() ...
2014-01-30 19:19:05 +00:00
struct bio_vec *bvec;
struct bvec_iter_all iter_all;
iostat_update_and_unbind_ctx(bio);
f2fs: introduce periodic iostat io latency traces Whenever we notice some sluggish issues on our machines, we are always curious about how well all types of I/O in the f2fs filesystem are handled. But, it's hard to get this kind of real data. First of all, we need to reproduce the issue while turning on the profiling tool like blktrace, but the issue doesn't happen again easily. Second, with the intervention of any tools, the overall timing of the issue will be slightly changed and it sometimes makes us hard to figure it out. So, I added the feature printing out IO latency statistics tracepoint events, which are minimal things to understand filesystem's I/O related behaviors, into F2FS_IOSTAT kernel config. With "iostat_enable" sysfs node on, we can get this statistics info in a periodic way and it would cause the least overhead. [samples] f2fs_ckpt-254:1-507 [003] .... 2842.439683: f2fs_iostat_latency: dev = (254,11), iotype [peak lat.(ms)/avg lat.(ms)/count], rd_data [136/1/801], rd_node [136/1/1704], rd_meta [4/2/4], wr_sync_data [164/16/3331], wr_sync_node [152/3/648], wr_sync_meta [160/2/4243], wr_async_data [24/13/15], wr_async_node [0/0/0], wr_async_meta [0/0/0] f2fs_ckpt-254:1-507 [002] .... 2845.450514: f2fs_iostat_latency: dev = (254,11), iotype [peak lat.(ms)/avg lat.(ms)/count], rd_data [60/3/456], rd_node [60/3/1258], rd_meta [0/0/1], wr_sync_data [120/12/2285], wr_sync_node [88/5/428], wr_sync_meta [52/6/2990], wr_async_data [4/1/3], wr_async_node [0/0/0], wr_async_meta [0/0/0] Signed-off-by: Daeho Jeong <daehojeong@google.com> Reviewed-by: Chao Yu <chao@kernel.org> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2021-08-20 22:29:09 +00:00
sbi = bio->bi_private;
if (time_to_inject(sbi, FAULT_WRITE_IO))
bio->bi_status = BLK_STS_IOERR;
bio_for_each_segment_all(bvec, bio, iter_all) {
struct page *page = bvec->bv_page;
enum count_type type = WB_DATA_TYPE(page, false);
fscrypt_finalize_bounce_page(&page);
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
#ifdef CONFIG_F2FS_FS_COMPRESSION
if (f2fs_is_compressed_page(page)) {
f2fs_compress_write_end_io(bio, page);
continue;
}
#endif
if (unlikely(bio->bi_status)) {
mapping_set_error(page->mapping, -EIO);
if (type == F2FS_WB_CP_DATA)
f2fs_stop_checkpoint(sbi, true,
STOP_CP_REASON_WRITE_FAIL);
}
f2fs_bug_on(sbi, page->mapping == NODE_MAPPING(sbi) &&
page->index != nid_of_node(page));
dec_page_count(sbi, type);
f2fs: fix to avoid broken of dnode block list f2fs recovery flow is relying on dnode block link list, it means fsynced file recovery depends on previous dnode's persistence in the list, so during fsync() we should wait on all regular inode's dnode writebacked before issuing flush. By this way, we can avoid dnode block list being broken by out-of-order IO submission due to IO scheduler or driver. Sheng Yong helps to do the test with this patch: Target:/data (f2fs, -) 64MB / 32768KB / 4KB / 8 1 / PERSIST / Index Base: SEQ-RD(MB/s) SEQ-WR(MB/s) RND-RD(IOPS) RND-WR(IOPS) Insert(TPS) Update(TPS) Delete(TPS) 1 867.82 204.15 41440.03 41370.54 680.8 1025.94 1031.08 2 871.87 205.87 41370.3 40275.2 791.14 1065.84 1101.7 3 866.52 205.69 41795.67 40596.16 694.69 1037.16 1031.48 Avg 868.7366667 205.2366667 41535.33333 40747.3 722.21 1042.98 1054.753333 After: SEQ-RD(MB/s) SEQ-WR(MB/s) RND-RD(IOPS) RND-WR(IOPS) Insert(TPS) Update(TPS) Delete(TPS) 1 798.81 202.5 41143 40613.87 602.71 838.08 913.83 2 805.79 206.47 40297.2 41291.46 604.44 840.75 924.27 3 814.83 206.17 41209.57 40453.62 602.85 834.66 927.91 Avg 806.4766667 205.0466667 40883.25667 40786.31667 603.3333333 837.83 922.0033333 Patched/Original: 0.928332713 0.999074239 0.984300676 1.000957528 0.835398753 0.803303994 0.874141189 It looks like atomic write will suffer performance regression. I suspect that the criminal is that we forcing to wait all dnode being in storage cache before we issue PREFLUSH+FUA. BTW, will commit ("f2fs: don't need to wait for node writes for atomic write") cause the problem: we will lose data of last transaction after SPO, even if atomic write return no error: - atomic_open(); - write() P1, P2, P3; - atomic_commit(); - writeback data: P1, P2, P3; - writeback node: N1, N2, N3; <--- If N1, N2 is not writebacked, N3 with fsync_mark is writebacked, In SPOR, we won't find N3 since node chain is broken, turns out that losing last transaction. - preflush + fua; - power-cut If we don't wait dnode writeback for atomic_write: SEQ-RD(MB/s) SEQ-WR(MB/s) RND-RD(IOPS) RND-WR(IOPS) Insert(TPS) Update(TPS) Delete(TPS) 1 779.91 206.03 41621.5 40333.16 716.9 1038.21 1034.85 2 848.51 204.35 40082.44 39486.17 791.83 1119.96 1083.77 3 772.12 206.27 41335.25 41599.65 723.29 1055.07 971.92 Avg 800.18 205.55 41013.06333 40472.99333 744.0066667 1071.08 1030.18 Patched/Original: 0.92108464 1.001526693 0.987425886 0.993268102 1.030180511 1.026942031 0.976702294 SQLite's performance recovers. Jaegeuk: "Practically, I don't see db corruption becase of this. We can excuse to lose the last transaction." Finally, we decide to keep original implementation of atomic write interface sematics that we don't wait all dnode writeback before preflush+fua submission. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-08-02 15:03:19 +00:00
if (f2fs_in_warm_node_list(sbi, page))
f2fs_del_fsync_node_entry(sbi, page);
f2fs: restructure f2fs page.private layout Restruct f2fs page private layout for below reasons: There are some cases that f2fs wants to set a flag in a page to indicate a specified status of page: a) page is in transaction list for atomic write b) page contains dummy data for aligned write c) page is migrating for GC d) page contains inline data for inline inode flush e) page belongs to merkle tree, and is verified for fsverity f) page is dirty and has filesystem/inode reference count for writeback g) page is temporary and has decompress io context reference for compression There are existed places in page structure we can use to store f2fs private status/data: - page.flags: PG_checked, PG_private - page.private However it was a mess when we using them, which may cause potential confliction: page.private PG_private PG_checked page._refcount (+1 at most) a) -1 set +1 b) -2 set c), d), e) set f) 0 set +1 g) pointer set The other problem is page.flags has no free slot, if we can avoid set zero to page.private and set PG_private flag, then we use non-zero value to indicate PG_private status, so that we may have chance to reclaim PG_private slot for other usage. [1] The other concern is f2fs has bad scalability in aspect of indicating more page status. So in this patch, let's restructure f2fs' page.private as below to solve above issues: Layout A: lowest bit should be 1 | bit0 = 1 | bit1 | bit2 | ... | bit MAX | private data .... | bit 0 PAGE_PRIVATE_NOT_POINTER bit 1 PAGE_PRIVATE_ATOMIC_WRITE bit 2 PAGE_PRIVATE_DUMMY_WRITE bit 3 PAGE_PRIVATE_ONGOING_MIGRATION bit 4 PAGE_PRIVATE_INLINE_INODE bit 5 PAGE_PRIVATE_REF_RESOURCE bit 6- f2fs private data Layout B: lowest bit should be 0 page.private is a wrapped pointer. After the change: page.private PG_private PG_checked page._refcount (+1 at most) a) 11 set +1 b) 101 set +1 c) 1001 set +1 d) 10001 set +1 e) set f) 100001 set +1 g) pointer set +1 [1] https://lore.kernel.org/linux-f2fs-devel/20210422154705.GO3596236@casper.infradead.org/T/#u Cc: Matthew Wilcox <willy@infradead.org> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2021-04-28 09:20:31 +00:00
clear_page_private_gcing(page);
end_page_writeback(page);
Merge branch 'for-3.14/core' of git://git.kernel.dk/linux-block Pull core block IO changes from Jens Axboe: "The major piece in here is the immutable bio_ve series from Kent, the rest is fairly minor. It was supposed to go in last round, but various issues pushed it to this release instead. The pull request contains: - Various smaller blk-mq fixes from different folks. Nothing major here, just minor fixes and cleanups. - Fix for a memory leak in the error path in the block ioctl code from Christian Engelmayer. - Header export fix from CaiZhiyong. - Finally the immutable biovec changes from Kent Overstreet. This enables some nice future work on making arbitrarily sized bios possible, and splitting more efficient. Related fixes to immutable bio_vecs: - dm-cache immutable fixup from Mike Snitzer. - btrfs immutable fixup from Muthu Kumar. - bio-integrity fix from Nic Bellinger, which is also going to stable" * 'for-3.14/core' of git://git.kernel.dk/linux-block: (44 commits) xtensa: fixup simdisk driver to work with immutable bio_vecs block/blk-mq-cpu.c: use hotcpu_notifier() blk-mq: for_each_* macro correctness block: Fix memory leak in rw_copy_check_uvector() handling bio-integrity: Fix bio_integrity_verify segment start bug block: remove unrelated header files and export symbol blk-mq: uses page->list incorrectly blk-mq: use __smp_call_function_single directly btrfs: fix missing increment of bi_remaining Revert "block: Warn and free bio if bi_end_io is not set" block: Warn and free bio if bi_end_io is not set blk-mq: fix initializing request's start time block: blk-mq: don't export blk_mq_free_queue() block: blk-mq: make blk_sync_queue support mq block: blk-mq: support draining mq queue dm cache: increment bi_remaining when bi_end_io is restored block: fixup for generic bio chaining block: Really silence spurious compiler warnings block: Silence spurious compiler warnings block: Kill bio_pair_split() ...
2014-01-30 19:19:05 +00:00
}
if (!get_pages(sbi, F2FS_WB_CP_DATA) &&
wq_has_sleeper(&sbi->cp_wait))
wake_up(&sbi->cp_wait);
bio_put(bio);
}
#ifdef CONFIG_BLK_DEV_ZONED
static void f2fs_zone_write_end_io(struct bio *bio)
{
struct f2fs_bio_info *io = (struct f2fs_bio_info *)bio->bi_private;
bio->bi_private = io->bi_private;
complete(&io->zone_wait);
f2fs_write_end_io(bio);
}
#endif
struct block_device *f2fs_target_device(struct f2fs_sb_info *sbi,
block_t blk_addr, sector_t *sector)
{
struct block_device *bdev = sbi->sb->s_bdev;
int i;
if (f2fs_is_multi_device(sbi)) {
for (i = 0; i < sbi->s_ndevs; i++) {
if (FDEV(i).start_blk <= blk_addr &&
FDEV(i).end_blk >= blk_addr) {
blk_addr -= FDEV(i).start_blk;
bdev = FDEV(i).bdev;
break;
}
}
}
if (sector)
*sector = SECTOR_FROM_BLOCK(blk_addr);
return bdev;
}
int f2fs_target_device_index(struct f2fs_sb_info *sbi, block_t blkaddr)
{
int i;
if (!f2fs_is_multi_device(sbi))
return 0;
for (i = 0; i < sbi->s_ndevs; i++)
if (FDEV(i).start_blk <= blkaddr && FDEV(i).end_blk >= blkaddr)
return i;
return 0;
}
static blk_opf_t f2fs_io_flags(struct f2fs_io_info *fio)
{
unsigned int temp_mask = GENMASK(NR_TEMP_TYPE - 1, 0);
unsigned int fua_flag, meta_flag, io_flag;
blk_opf_t op_flags = 0;
if (fio->op != REQ_OP_WRITE)
return 0;
if (fio->type == DATA)
io_flag = fio->sbi->data_io_flag;
else if (fio->type == NODE)
io_flag = fio->sbi->node_io_flag;
else
return 0;
fua_flag = io_flag & temp_mask;
meta_flag = (io_flag >> NR_TEMP_TYPE) & temp_mask;
/*
* data/node io flag bits per temp:
* REQ_META | REQ_FUA |
* 5 | 4 | 3 | 2 | 1 | 0 |
* Cold | Warm | Hot | Cold | Warm | Hot |
*/
if (BIT(fio->temp) & meta_flag)
op_flags |= REQ_META;
if (BIT(fio->temp) & fua_flag)
op_flags |= REQ_FUA;
return op_flags;
}
static struct bio *__bio_alloc(struct f2fs_io_info *fio, int npages)
{
struct f2fs_sb_info *sbi = fio->sbi;
struct block_device *bdev;
sector_t sector;
struct bio *bio;
bdev = f2fs_target_device(sbi, fio->new_blkaddr, &sector);
bio = bio_alloc_bioset(bdev, npages,
fio->op | fio->op_flags | f2fs_io_flags(fio),
GFP_NOIO, &f2fs_bioset);
bio->bi_iter.bi_sector = sector;
if (is_read_io(fio->op)) {
bio->bi_end_io = f2fs_read_end_io;
bio->bi_private = NULL;
} else {
bio->bi_end_io = f2fs_write_end_io;
bio->bi_private = sbi;
bio->bi_write_hint = f2fs_io_type_to_rw_hint(sbi,
fio->type, fio->temp);
}
f2fs: introduce periodic iostat io latency traces Whenever we notice some sluggish issues on our machines, we are always curious about how well all types of I/O in the f2fs filesystem are handled. But, it's hard to get this kind of real data. First of all, we need to reproduce the issue while turning on the profiling tool like blktrace, but the issue doesn't happen again easily. Second, with the intervention of any tools, the overall timing of the issue will be slightly changed and it sometimes makes us hard to figure it out. So, I added the feature printing out IO latency statistics tracepoint events, which are minimal things to understand filesystem's I/O related behaviors, into F2FS_IOSTAT kernel config. With "iostat_enable" sysfs node on, we can get this statistics info in a periodic way and it would cause the least overhead. [samples] f2fs_ckpt-254:1-507 [003] .... 2842.439683: f2fs_iostat_latency: dev = (254,11), iotype [peak lat.(ms)/avg lat.(ms)/count], rd_data [136/1/801], rd_node [136/1/1704], rd_meta [4/2/4], wr_sync_data [164/16/3331], wr_sync_node [152/3/648], wr_sync_meta [160/2/4243], wr_async_data [24/13/15], wr_async_node [0/0/0], wr_async_meta [0/0/0] f2fs_ckpt-254:1-507 [002] .... 2845.450514: f2fs_iostat_latency: dev = (254,11), iotype [peak lat.(ms)/avg lat.(ms)/count], rd_data [60/3/456], rd_node [60/3/1258], rd_meta [0/0/1], wr_sync_data [120/12/2285], wr_sync_node [88/5/428], wr_sync_meta [52/6/2990], wr_async_data [4/1/3], wr_async_node [0/0/0], wr_async_meta [0/0/0] Signed-off-by: Daeho Jeong <daehojeong@google.com> Reviewed-by: Chao Yu <chao@kernel.org> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2021-08-20 22:29:09 +00:00
iostat_alloc_and_bind_ctx(sbi, bio, NULL);
if (fio->io_wbc)
wbc_init_bio(fio->io_wbc, bio);
return bio;
}
static void f2fs_set_bio_crypt_ctx(struct bio *bio, const struct inode *inode,
pgoff_t first_idx,
const struct f2fs_io_info *fio,
gfp_t gfp_mask)
{
/*
* The f2fs garbage collector sets ->encrypted_page when it wants to
* read/write raw data without encryption.
*/
if (!fio || !fio->encrypted_page)
fscrypt_set_bio_crypt_ctx(bio, inode, first_idx, gfp_mask);
}
static bool f2fs_crypt_mergeable_bio(struct bio *bio, const struct inode *inode,
pgoff_t next_idx,
const struct f2fs_io_info *fio)
{
/*
* The f2fs garbage collector sets ->encrypted_page when it wants to
* read/write raw data without encryption.
*/
if (fio && fio->encrypted_page)
return !bio_has_crypt_ctx(bio);
return fscrypt_mergeable_bio(bio, inode, next_idx);
}
void f2fs_submit_read_bio(struct f2fs_sb_info *sbi, struct bio *bio,
enum page_type type)
{
WARN_ON_ONCE(!is_read_io(bio_op(bio)));
trace_f2fs_submit_read_bio(sbi->sb, type, bio);
iostat_update_submit_ctx(bio, type);
submit_bio(bio);
}
static void f2fs_submit_write_bio(struct f2fs_sb_info *sbi, struct bio *bio,
enum page_type type)
{
WARN_ON_ONCE(is_read_io(bio_op(bio)));
f2fs: restructure f2fs page.private layout Restruct f2fs page private layout for below reasons: There are some cases that f2fs wants to set a flag in a page to indicate a specified status of page: a) page is in transaction list for atomic write b) page contains dummy data for aligned write c) page is migrating for GC d) page contains inline data for inline inode flush e) page belongs to merkle tree, and is verified for fsverity f) page is dirty and has filesystem/inode reference count for writeback g) page is temporary and has decompress io context reference for compression There are existed places in page structure we can use to store f2fs private status/data: - page.flags: PG_checked, PG_private - page.private However it was a mess when we using them, which may cause potential confliction: page.private PG_private PG_checked page._refcount (+1 at most) a) -1 set +1 b) -2 set c), d), e) set f) 0 set +1 g) pointer set The other problem is page.flags has no free slot, if we can avoid set zero to page.private and set PG_private flag, then we use non-zero value to indicate PG_private status, so that we may have chance to reclaim PG_private slot for other usage. [1] The other concern is f2fs has bad scalability in aspect of indicating more page status. So in this patch, let's restructure f2fs' page.private as below to solve above issues: Layout A: lowest bit should be 1 | bit0 = 1 | bit1 | bit2 | ... | bit MAX | private data .... | bit 0 PAGE_PRIVATE_NOT_POINTER bit 1 PAGE_PRIVATE_ATOMIC_WRITE bit 2 PAGE_PRIVATE_DUMMY_WRITE bit 3 PAGE_PRIVATE_ONGOING_MIGRATION bit 4 PAGE_PRIVATE_INLINE_INODE bit 5 PAGE_PRIVATE_REF_RESOURCE bit 6- f2fs private data Layout B: lowest bit should be 0 page.private is a wrapped pointer. After the change: page.private PG_private PG_checked page._refcount (+1 at most) a) 11 set +1 b) 101 set +1 c) 1001 set +1 d) 10001 set +1 e) set f) 100001 set +1 g) pointer set +1 [1] https://lore.kernel.org/linux-f2fs-devel/20210422154705.GO3596236@casper.infradead.org/T/#u Cc: Matthew Wilcox <willy@infradead.org> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2021-04-28 09:20:31 +00:00
if (f2fs_lfs_mode(sbi) && current->plug && PAGE_TYPE_ON_MAIN(type))
blk_finish_plug(current->plug);
f2fs: introduce periodic iostat io latency traces Whenever we notice some sluggish issues on our machines, we are always curious about how well all types of I/O in the f2fs filesystem are handled. But, it's hard to get this kind of real data. First of all, we need to reproduce the issue while turning on the profiling tool like blktrace, but the issue doesn't happen again easily. Second, with the intervention of any tools, the overall timing of the issue will be slightly changed and it sometimes makes us hard to figure it out. So, I added the feature printing out IO latency statistics tracepoint events, which are minimal things to understand filesystem's I/O related behaviors, into F2FS_IOSTAT kernel config. With "iostat_enable" sysfs node on, we can get this statistics info in a periodic way and it would cause the least overhead. [samples] f2fs_ckpt-254:1-507 [003] .... 2842.439683: f2fs_iostat_latency: dev = (254,11), iotype [peak lat.(ms)/avg lat.(ms)/count], rd_data [136/1/801], rd_node [136/1/1704], rd_meta [4/2/4], wr_sync_data [164/16/3331], wr_sync_node [152/3/648], wr_sync_meta [160/2/4243], wr_async_data [24/13/15], wr_async_node [0/0/0], wr_async_meta [0/0/0] f2fs_ckpt-254:1-507 [002] .... 2845.450514: f2fs_iostat_latency: dev = (254,11), iotype [peak lat.(ms)/avg lat.(ms)/count], rd_data [60/3/456], rd_node [60/3/1258], rd_meta [0/0/1], wr_sync_data [120/12/2285], wr_sync_node [88/5/428], wr_sync_meta [52/6/2990], wr_async_data [4/1/3], wr_async_node [0/0/0], wr_async_meta [0/0/0] Signed-off-by: Daeho Jeong <daehojeong@google.com> Reviewed-by: Chao Yu <chao@kernel.org> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2021-08-20 22:29:09 +00:00
trace_f2fs_submit_write_bio(sbi->sb, type, bio);
f2fs: introduce periodic iostat io latency traces Whenever we notice some sluggish issues on our machines, we are always curious about how well all types of I/O in the f2fs filesystem are handled. But, it's hard to get this kind of real data. First of all, we need to reproduce the issue while turning on the profiling tool like blktrace, but the issue doesn't happen again easily. Second, with the intervention of any tools, the overall timing of the issue will be slightly changed and it sometimes makes us hard to figure it out. So, I added the feature printing out IO latency statistics tracepoint events, which are minimal things to understand filesystem's I/O related behaviors, into F2FS_IOSTAT kernel config. With "iostat_enable" sysfs node on, we can get this statistics info in a periodic way and it would cause the least overhead. [samples] f2fs_ckpt-254:1-507 [003] .... 2842.439683: f2fs_iostat_latency: dev = (254,11), iotype [peak lat.(ms)/avg lat.(ms)/count], rd_data [136/1/801], rd_node [136/1/1704], rd_meta [4/2/4], wr_sync_data [164/16/3331], wr_sync_node [152/3/648], wr_sync_meta [160/2/4243], wr_async_data [24/13/15], wr_async_node [0/0/0], wr_async_meta [0/0/0] f2fs_ckpt-254:1-507 [002] .... 2845.450514: f2fs_iostat_latency: dev = (254,11), iotype [peak lat.(ms)/avg lat.(ms)/count], rd_data [60/3/456], rd_node [60/3/1258], rd_meta [0/0/1], wr_sync_data [120/12/2285], wr_sync_node [88/5/428], wr_sync_meta [52/6/2990], wr_async_data [4/1/3], wr_async_node [0/0/0], wr_async_meta [0/0/0] Signed-off-by: Daeho Jeong <daehojeong@google.com> Reviewed-by: Chao Yu <chao@kernel.org> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2021-08-20 22:29:09 +00:00
iostat_update_submit_ctx(bio, type);
submit_bio(bio);
}
static void __submit_merged_bio(struct f2fs_bio_info *io)
{
struct f2fs_io_info *fio = &io->fio;
if (!io->bio)
return;
if (is_read_io(fio->op)) {
trace_f2fs_prepare_read_bio(io->sbi->sb, fio->type, io->bio);
f2fs_submit_read_bio(io->sbi, io->bio, fio->type);
} else {
trace_f2fs_prepare_write_bio(io->sbi->sb, fio->type, io->bio);
f2fs_submit_write_bio(io->sbi, io->bio, fio->type);
}
io->bio = NULL;
}
f2fs: add bio cache for IPU SQLite in Wal mode may trigger sequential IPU write in db-wal file, after commit d1b3e72d5490 ("f2fs: submit bio of in-place-update pages"), we lost the chance of merging page in inner managed bio cache, result in submitting more small-sized IO. So let's add temporary bio in writepages() to cache mergeable write IO as much as possible. Test case: 1. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" 2. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" Before: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65552, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65560, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65568, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65576, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65584, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65592, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65600, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65608, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65616, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65624, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65632, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65640, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65648, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65656, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65664, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57352, size = 4096 After: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 65536 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57368, size = 4096 Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-02-19 08:15:29 +00:00
static bool __has_merged_page(struct bio *bio, struct inode *inode,
struct page *page, nid_t ino)
{
struct bio_vec *bvec;
struct bvec_iter_all iter_all;
f2fs: add bio cache for IPU SQLite in Wal mode may trigger sequential IPU write in db-wal file, after commit d1b3e72d5490 ("f2fs: submit bio of in-place-update pages"), we lost the chance of merging page in inner managed bio cache, result in submitting more small-sized IO. So let's add temporary bio in writepages() to cache mergeable write IO as much as possible. Test case: 1. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" 2. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" Before: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65552, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65560, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65568, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65576, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65584, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65592, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65600, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65608, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65616, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65624, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65632, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65640, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65648, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65656, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65664, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57352, size = 4096 After: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 65536 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57368, size = 4096 Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-02-19 08:15:29 +00:00
if (!bio)
return false;
if (!inode && !page && !ino)
return true;
f2fs: add bio cache for IPU SQLite in Wal mode may trigger sequential IPU write in db-wal file, after commit d1b3e72d5490 ("f2fs: submit bio of in-place-update pages"), we lost the chance of merging page in inner managed bio cache, result in submitting more small-sized IO. So let's add temporary bio in writepages() to cache mergeable write IO as much as possible. Test case: 1. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" 2. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" Before: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65552, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65560, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65568, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65576, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65584, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65592, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65600, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65608, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65616, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65624, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65632, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65640, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65648, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65656, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65664, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57352, size = 4096 After: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 65536 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57368, size = 4096 Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-02-19 08:15:29 +00:00
bio_for_each_segment_all(bvec, bio, iter_all) {
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
struct page *target = bvec->bv_page;
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
if (fscrypt_is_bounce_page(target)) {
target = fscrypt_pagecache_page(target);
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
if (IS_ERR(target))
continue;
}
if (f2fs_is_compressed_page(target)) {
target = f2fs_compress_control_page(target);
if (IS_ERR(target))
continue;
}
if (inode && inode == target->mapping->host)
return true;
if (page && page == target)
return true;
if (ino && ino == ino_of_node(target))
return true;
}
return false;
}
int f2fs_init_write_merge_io(struct f2fs_sb_info *sbi)
{
int i;
for (i = 0; i < NR_PAGE_TYPE; i++) {
int n = (i == META) ? 1 : NR_TEMP_TYPE;
int j;
sbi->write_io[i] = f2fs_kmalloc(sbi,
array_size(n, sizeof(struct f2fs_bio_info)),
GFP_KERNEL);
if (!sbi->write_io[i])
return -ENOMEM;
for (j = HOT; j < n; j++) {
struct f2fs_bio_info *io = &sbi->write_io[i][j];
init_f2fs_rwsem(&io->io_rwsem);
io->sbi = sbi;
io->bio = NULL;
io->last_block_in_bio = 0;
spin_lock_init(&io->io_lock);
INIT_LIST_HEAD(&io->io_list);
INIT_LIST_HEAD(&io->bio_list);
init_f2fs_rwsem(&io->bio_list_lock);
#ifdef CONFIG_BLK_DEV_ZONED
init_completion(&io->zone_wait);
io->zone_pending_bio = NULL;
io->bi_private = NULL;
#endif
}
}
return 0;
}
static void __f2fs_submit_merged_write(struct f2fs_sb_info *sbi,
enum page_type type, enum temp_type temp)
{
enum page_type btype = PAGE_TYPE_OF_BIO(type);
struct f2fs_bio_info *io = sbi->write_io[btype] + temp;
f2fs_down_write(&io->io_rwsem);
if (!io->bio)
goto unlock_out;
/* change META to META_FLUSH in the checkpoint procedure */
if (type >= META_FLUSH) {
io->fio.type = META_FLUSH;
io->bio->bi_opf |= REQ_META | REQ_PRIO | REQ_SYNC;
if (!test_opt(sbi, NOBARRIER))
io->bio->bi_opf |= REQ_PREFLUSH | REQ_FUA;
}
__submit_merged_bio(io);
unlock_out:
f2fs_up_write(&io->io_rwsem);
}
static void __submit_merged_write_cond(struct f2fs_sb_info *sbi,
struct inode *inode, struct page *page,
nid_t ino, enum page_type type, bool force)
{
enum temp_type temp;
bool ret = true;
for (temp = HOT; temp < NR_TEMP_TYPE; temp++) {
if (!force) {
enum page_type btype = PAGE_TYPE_OF_BIO(type);
struct f2fs_bio_info *io = sbi->write_io[btype] + temp;
f2fs_down_read(&io->io_rwsem);
f2fs: add bio cache for IPU SQLite in Wal mode may trigger sequential IPU write in db-wal file, after commit d1b3e72d5490 ("f2fs: submit bio of in-place-update pages"), we lost the chance of merging page in inner managed bio cache, result in submitting more small-sized IO. So let's add temporary bio in writepages() to cache mergeable write IO as much as possible. Test case: 1. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" 2. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" Before: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65552, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65560, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65568, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65576, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65584, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65592, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65600, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65608, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65616, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65624, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65632, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65640, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65648, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65656, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65664, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57352, size = 4096 After: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 65536 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57368, size = 4096 Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-02-19 08:15:29 +00:00
ret = __has_merged_page(io->bio, inode, page, ino);
f2fs_up_read(&io->io_rwsem);
}
if (ret)
__f2fs_submit_merged_write(sbi, type, temp);
/* TODO: use HOT temp only for meta pages now. */
if (type >= META)
break;
}
}
void f2fs_submit_merged_write(struct f2fs_sb_info *sbi, enum page_type type)
{
__submit_merged_write_cond(sbi, NULL, NULL, 0, type, true);
}
void f2fs_submit_merged_write_cond(struct f2fs_sb_info *sbi,
struct inode *inode, struct page *page,
nid_t ino, enum page_type type)
{
__submit_merged_write_cond(sbi, inode, page, ino, type, false);
}
void f2fs_flush_merged_writes(struct f2fs_sb_info *sbi)
{
f2fs_submit_merged_write(sbi, DATA);
f2fs_submit_merged_write(sbi, NODE);
f2fs_submit_merged_write(sbi, META);
}
/*
* Fill the locked page with data located in the block address.
* A caller needs to unlock the page on failure.
*/
int f2fs_submit_page_bio(struct f2fs_io_info *fio)
{
struct bio *bio;
struct page *page = fio->encrypted_page ?
fio->encrypted_page : fio->page;
f2fs: fix to do sanity check with block address in main area This patch add to do sanity check with below field: - cp_pack_total_block_count - blkaddr of data/node - extent info - Overview BUG() in verify_block_addr() when writing to a corrupted f2fs image - Reproduce (4.18 upstream kernel) - POC (poc.c) static void activity(char *mpoint) { char *foo_bar_baz; int err; static int buf[8192]; memset(buf, 0, sizeof(buf)); err = asprintf(&foo_bar_baz, "%s/foo/bar/baz", mpoint); int fd = open(foo_bar_baz, O_RDWR | O_TRUNC, 0777); if (fd >= 0) { write(fd, (char *)buf, sizeof(buf)); fdatasync(fd); close(fd); } } int main(int argc, char *argv[]) { activity(argv[1]); return 0; } - Kernel message [ 689.349473] F2FS-fs (loop0): Mounted with checkpoint version = 3 [ 699.728662] WARNING: CPU: 0 PID: 1309 at fs/f2fs/segment.c:2860 f2fs_inplace_write_data+0x232/0x240 [ 699.728670] Modules linked in: snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_pcm snd_timer snd mac_hid i2c_piix4 soundcore ib_iser rdma_cm iw_cm ib_cm ib_core iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx raid1 raid0 multipath linear 8139too crct10dif_pclmul crc32_pclmul qxl drm_kms_helper syscopyarea aesni_intel sysfillrect sysimgblt fb_sys_fops ttm drm aes_x86_64 crypto_simd cryptd 8139cp glue_helper mii pata_acpi floppy [ 699.729056] CPU: 0 PID: 1309 Comm: a.out Not tainted 4.18.0-rc1+ #4 [ 699.729064] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.729074] RIP: 0010:f2fs_inplace_write_data+0x232/0x240 [ 699.729076] Code: ff e9 cf fe ff ff 49 8d 7d 10 e8 39 45 ad ff 4d 8b 7d 10 be 04 00 00 00 49 8d 7f 48 e8 07 49 ad ff 45 8b 7f 48 e9 fb fe ff ff <0f> 0b f0 41 80 4d 48 04 e9 65 fe ff ff 90 66 66 66 66 90 55 48 8d [ 699.729130] RSP: 0018:ffff8801f43af568 EFLAGS: 00010202 [ 699.729139] RAX: 000000000000003f RBX: ffff8801f43af7b8 RCX: ffffffffb88c9113 [ 699.729142] RDX: 0000000000000003 RSI: dffffc0000000000 RDI: ffff8802024e5540 [ 699.729144] RBP: ffff8801f43af590 R08: 0000000000000009 R09: ffffffffffffffe8 [ 699.729147] R10: 0000000000000001 R11: ffffed0039b0596a R12: ffff8802024e5540 [ 699.729149] R13: ffff8801f0335500 R14: ffff8801e3e7a700 R15: ffff8801e1ee4450 [ 699.729154] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.729156] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.729159] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.729171] Call Trace: [ 699.729192] f2fs_do_write_data_page+0x2e2/0xe00 [ 699.729203] ? f2fs_should_update_outplace+0xd0/0xd0 [ 699.729238] ? memcg_drain_all_list_lrus+0x280/0x280 [ 699.729269] ? __radix_tree_replace+0xa3/0x120 [ 699.729276] __write_data_page+0x5c7/0xe30 [ 699.729291] ? kasan_check_read+0x11/0x20 [ 699.729310] ? page_mapped+0x8a/0x110 [ 699.729321] ? page_mkclean+0xe9/0x160 [ 699.729327] ? f2fs_do_write_data_page+0xe00/0xe00 [ 699.729331] ? invalid_page_referenced_vma+0x130/0x130 [ 699.729345] ? clear_page_dirty_for_io+0x332/0x450 [ 699.729351] f2fs_write_cache_pages+0x4ca/0x860 [ 699.729358] ? __write_data_page+0xe30/0xe30 [ 699.729374] ? percpu_counter_add_batch+0x22/0xa0 [ 699.729380] ? kasan_check_write+0x14/0x20 [ 699.729391] ? _raw_spin_lock+0x17/0x40 [ 699.729403] ? f2fs_mark_inode_dirty_sync.part.18+0x16/0x30 [ 699.729413] ? iov_iter_advance+0x113/0x640 [ 699.729418] ? f2fs_write_end+0x133/0x2e0 [ 699.729423] ? balance_dirty_pages_ratelimited+0x239/0x640 [ 699.729428] f2fs_write_data_pages+0x329/0x520 [ 699.729433] ? generic_perform_write+0x250/0x320 [ 699.729438] ? f2fs_write_cache_pages+0x860/0x860 [ 699.729454] ? current_time+0x110/0x110 [ 699.729459] ? f2fs_preallocate_blocks+0x1ef/0x370 [ 699.729464] do_writepages+0x37/0xb0 [ 699.729468] ? f2fs_write_cache_pages+0x860/0x860 [ 699.729472] ? do_writepages+0x37/0xb0 [ 699.729478] __filemap_fdatawrite_range+0x19a/0x1f0 [ 699.729483] ? delete_from_page_cache_batch+0x4e0/0x4e0 [ 699.729496] ? __vfs_write+0x2b2/0x410 [ 699.729501] file_write_and_wait_range+0x66/0xb0 [ 699.729506] f2fs_do_sync_file+0x1f9/0xd90 [ 699.729511] ? truncate_partial_data_page+0x290/0x290 [ 699.729521] ? __sb_end_write+0x30/0x50 [ 699.729526] ? vfs_write+0x20f/0x260 [ 699.729530] f2fs_sync_file+0x9a/0xb0 [ 699.729534] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.729548] vfs_fsync_range+0x68/0x100 [ 699.729554] ? __fget_light+0xc9/0xe0 [ 699.729558] do_fsync+0x3d/0x70 [ 699.729562] __x64_sys_fdatasync+0x24/0x30 [ 699.729585] do_syscall_64+0x78/0x170 [ 699.729595] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 699.729613] RIP: 0033:0x7f9bf930d800 [ 699.729615] Code: 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 83 3d 49 bf 2c 00 00 75 10 b8 4b 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 be 78 01 00 48 89 04 24 [ 699.729668] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.729673] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.729675] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.729678] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.729680] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.729683] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000 [ 699.729687] ---[ end trace 4ce02f25ff7d3df5 ]--- [ 699.729782] ------------[ cut here ]------------ [ 699.729785] kernel BUG at fs/f2fs/segment.h:654! [ 699.731055] invalid opcode: 0000 [#1] SMP KASAN PTI [ 699.732104] CPU: 0 PID: 1309 Comm: a.out Tainted: G W 4.18.0-rc1+ #4 [ 699.733684] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.735611] RIP: 0010:f2fs_submit_page_bio+0x29b/0x730 [ 699.736649] Code: 54 49 8d bd 18 04 00 00 e8 b2 59 af ff 41 8b 8d 18 04 00 00 8b 45 b8 41 d3 e6 44 01 f0 4c 8d 73 14 41 39 c7 0f 82 37 fe ff ff <0f> 0b 65 8b 05 2c 04 77 47 89 c0 48 0f a3 05 52 c1 d5 01 0f 92 c0 [ 699.740524] RSP: 0018:ffff8801f43af508 EFLAGS: 00010283 [ 699.741573] RAX: 0000000000000000 RBX: ffff8801f43af7b8 RCX: ffffffffb88a7cef [ 699.743006] RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff8801e3e7a64c [ 699.744426] RBP: ffff8801f43af558 R08: ffffed003e066b55 R09: ffffed003e066b55 [ 699.745833] R10: 0000000000000001 R11: ffffed003e066b54 R12: ffffea0007876940 [ 699.747256] R13: ffff8801f0335500 R14: ffff8801e3e7a600 R15: 0000000000000001 [ 699.748683] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.750293] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.751462] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.752874] Call Trace: [ 699.753386] ? f2fs_inplace_write_data+0x93/0x240 [ 699.754341] f2fs_inplace_write_data+0xd2/0x240 [ 699.755271] f2fs_do_write_data_page+0x2e2/0xe00 [ 699.756214] ? f2fs_should_update_outplace+0xd0/0xd0 [ 699.757215] ? memcg_drain_all_list_lrus+0x280/0x280 [ 699.758209] ? __radix_tree_replace+0xa3/0x120 [ 699.759164] __write_data_page+0x5c7/0xe30 [ 699.760002] ? kasan_check_read+0x11/0x20 [ 699.760823] ? page_mapped+0x8a/0x110 [ 699.761573] ? page_mkclean+0xe9/0x160 [ 699.762345] ? f2fs_do_write_data_page+0xe00/0xe00 [ 699.763332] ? invalid_page_referenced_vma+0x130/0x130 [ 699.764374] ? clear_page_dirty_for_io+0x332/0x450 [ 699.765347] f2fs_write_cache_pages+0x4ca/0x860 [ 699.766276] ? __write_data_page+0xe30/0xe30 [ 699.767161] ? percpu_counter_add_batch+0x22/0xa0 [ 699.768112] ? kasan_check_write+0x14/0x20 [ 699.768951] ? _raw_spin_lock+0x17/0x40 [ 699.769739] ? f2fs_mark_inode_dirty_sync.part.18+0x16/0x30 [ 699.770885] ? iov_iter_advance+0x113/0x640 [ 699.771743] ? f2fs_write_end+0x133/0x2e0 [ 699.772569] ? balance_dirty_pages_ratelimited+0x239/0x640 [ 699.773680] f2fs_write_data_pages+0x329/0x520 [ 699.774603] ? generic_perform_write+0x250/0x320 [ 699.775544] ? f2fs_write_cache_pages+0x860/0x860 [ 699.776510] ? current_time+0x110/0x110 [ 699.777299] ? f2fs_preallocate_blocks+0x1ef/0x370 [ 699.778279] do_writepages+0x37/0xb0 [ 699.779026] ? f2fs_write_cache_pages+0x860/0x860 [ 699.779978] ? do_writepages+0x37/0xb0 [ 699.780755] __filemap_fdatawrite_range+0x19a/0x1f0 [ 699.781746] ? delete_from_page_cache_batch+0x4e0/0x4e0 [ 699.782820] ? __vfs_write+0x2b2/0x410 [ 699.783597] file_write_and_wait_range+0x66/0xb0 [ 699.784540] f2fs_do_sync_file+0x1f9/0xd90 [ 699.785381] ? truncate_partial_data_page+0x290/0x290 [ 699.786415] ? __sb_end_write+0x30/0x50 [ 699.787204] ? vfs_write+0x20f/0x260 [ 699.787941] f2fs_sync_file+0x9a/0xb0 [ 699.788694] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.789572] vfs_fsync_range+0x68/0x100 [ 699.790360] ? __fget_light+0xc9/0xe0 [ 699.791128] do_fsync+0x3d/0x70 [ 699.791779] __x64_sys_fdatasync+0x24/0x30 [ 699.792614] do_syscall_64+0x78/0x170 [ 699.793371] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 699.794406] RIP: 0033:0x7f9bf930d800 [ 699.795134] Code: 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 83 3d 49 bf 2c 00 00 75 10 b8 4b 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 be 78 01 00 48 89 04 24 [ 699.798960] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.800483] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.801923] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.803373] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.804798] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.806233] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000 [ 699.807667] Modules linked in: snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_pcm snd_timer snd mac_hid i2c_piix4 soundcore ib_iser rdma_cm iw_cm ib_cm ib_core iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx raid1 raid0 multipath linear 8139too crct10dif_pclmul crc32_pclmul qxl drm_kms_helper syscopyarea aesni_intel sysfillrect sysimgblt fb_sys_fops ttm drm aes_x86_64 crypto_simd cryptd 8139cp glue_helper mii pata_acpi floppy [ 699.817079] ---[ end trace 4ce02f25ff7d3df6 ]--- [ 699.818068] RIP: 0010:f2fs_submit_page_bio+0x29b/0x730 [ 699.819114] Code: 54 49 8d bd 18 04 00 00 e8 b2 59 af ff 41 8b 8d 18 04 00 00 8b 45 b8 41 d3 e6 44 01 f0 4c 8d 73 14 41 39 c7 0f 82 37 fe ff ff <0f> 0b 65 8b 05 2c 04 77 47 89 c0 48 0f a3 05 52 c1 d5 01 0f 92 c0 [ 699.822919] RSP: 0018:ffff8801f43af508 EFLAGS: 00010283 [ 699.823977] RAX: 0000000000000000 RBX: ffff8801f43af7b8 RCX: ffffffffb88a7cef [ 699.825436] RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff8801e3e7a64c [ 699.826881] RBP: ffff8801f43af558 R08: ffffed003e066b55 R09: ffffed003e066b55 [ 699.828292] R10: 0000000000000001 R11: ffffed003e066b54 R12: ffffea0007876940 [ 699.829750] R13: ffff8801f0335500 R14: ffff8801e3e7a600 R15: 0000000000000001 [ 699.831192] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.832793] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.833981] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.835556] ================================================================== [ 699.837029] BUG: KASAN: stack-out-of-bounds in update_stack_state+0x38c/0x3e0 [ 699.838462] Read of size 8 at addr ffff8801f43af970 by task a.out/1309 [ 699.840086] CPU: 0 PID: 1309 Comm: a.out Tainted: G D W 4.18.0-rc1+ #4 [ 699.841603] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.843475] Call Trace: [ 699.843982] dump_stack+0x7b/0xb5 [ 699.844661] print_address_description+0x70/0x290 [ 699.845607] kasan_report+0x291/0x390 [ 699.846351] ? update_stack_state+0x38c/0x3e0 [ 699.853831] __asan_load8+0x54/0x90 [ 699.854569] update_stack_state+0x38c/0x3e0 [ 699.855428] ? __read_once_size_nocheck.constprop.7+0x20/0x20 [ 699.856601] ? __save_stack_trace+0x5e/0x100 [ 699.857476] unwind_next_frame.part.5+0x18e/0x490 [ 699.858448] ? unwind_dump+0x290/0x290 [ 699.859217] ? clear_page_dirty_for_io+0x332/0x450 [ 699.860185] __unwind_start+0x106/0x190 [ 699.860974] __save_stack_trace+0x5e/0x100 [ 699.861808] ? __save_stack_trace+0x5e/0x100 [ 699.862691] ? unlink_anon_vmas+0xba/0x2c0 [ 699.863525] save_stack_trace+0x1f/0x30 [ 699.864312] save_stack+0x46/0xd0 [ 699.864993] ? __alloc_pages_slowpath+0x1420/0x1420 [ 699.865990] ? flush_tlb_mm_range+0x15e/0x220 [ 699.866889] ? kasan_check_write+0x14/0x20 [ 699.867724] ? __dec_node_state+0x92/0xb0 [ 699.868543] ? lock_page_memcg+0x85/0xf0 [ 699.869350] ? unlock_page_memcg+0x16/0x80 [ 699.870185] ? page_remove_rmap+0x198/0x520 [ 699.871048] ? mark_page_accessed+0x133/0x200 [ 699.871930] ? _cond_resched+0x1a/0x50 [ 699.872700] ? unmap_page_range+0xcd4/0xe50 [ 699.873551] ? rb_next+0x58/0x80 [ 699.874217] ? rb_next+0x58/0x80 [ 699.874895] __kasan_slab_free+0x13c/0x1a0 [ 699.875734] ? unlink_anon_vmas+0xba/0x2c0 [ 699.876563] kasan_slab_free+0xe/0x10 [ 699.877315] kmem_cache_free+0x89/0x1e0 [ 699.878095] unlink_anon_vmas+0xba/0x2c0 [ 699.878913] free_pgtables+0x101/0x1b0 [ 699.879677] exit_mmap+0x146/0x2a0 [ 699.880378] ? __ia32_sys_munmap+0x50/0x50 [ 699.881214] ? kasan_check_read+0x11/0x20 [ 699.882052] ? mm_update_next_owner+0x322/0x380 [ 699.882985] mmput+0x8b/0x1d0 [ 699.883602] do_exit+0x43a/0x1390 [ 699.884288] ? mm_update_next_owner+0x380/0x380 [ 699.885212] ? f2fs_sync_file+0x9a/0xb0 [ 699.885995] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.886877] ? vfs_fsync_range+0x68/0x100 [ 699.887694] ? __fget_light+0xc9/0xe0 [ 699.888442] ? do_fsync+0x3d/0x70 [ 699.889118] ? __x64_sys_fdatasync+0x24/0x30 [ 699.889996] rewind_stack_do_exit+0x17/0x20 [ 699.890860] RIP: 0033:0x7f9bf930d800 [ 699.891585] Code: Bad RIP value. [ 699.892268] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.893781] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.895220] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.896643] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.898069] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.899505] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000 [ 699.901241] The buggy address belongs to the page: [ 699.902215] page:ffffea0007d0ebc0 count:0 mapcount:0 mapping:0000000000000000 index:0x0 [ 699.903811] flags: 0x2ffff0000000000() [ 699.904585] raw: 02ffff0000000000 0000000000000000 ffffffff07d00101 0000000000000000 [ 699.906125] raw: 0000000000000000 0000000000240000 00000000ffffffff 0000000000000000 [ 699.907673] page dumped because: kasan: bad access detected [ 699.909108] Memory state around the buggy address: [ 699.910077] ffff8801f43af800: 00 f1 f1 f1 f1 00 f4 f4 f4 f3 f3 f3 f3 00 00 00 [ 699.911528] ffff8801f43af880: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 699.912953] >ffff8801f43af900: 00 00 00 00 00 00 00 00 f1 01 f4 f4 f4 f2 f2 f2 [ 699.914392] ^ [ 699.915758] ffff8801f43af980: f2 00 f4 f4 00 00 00 00 f2 00 00 00 00 00 00 00 [ 699.917193] ffff8801f43afa00: 00 00 00 00 00 00 00 00 00 f3 f3 f3 00 00 00 00 [ 699.918634] ================================================================== - Location https://elixir.bootlin.com/linux/v4.18-rc1/source/fs/f2fs/segment.h#L644 Reported-by Wen Xu <wen.xu@gatech.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-08-01 11:13:44 +00:00
if (!f2fs_is_valid_blkaddr(fio->sbi, fio->new_blkaddr,
f2fs: introduce DATA_GENERIC_ENHANCE Previously, f2fs_is_valid_blkaddr(, blkaddr, DATA_GENERIC) will check whether @blkaddr locates in main area or not. That check is weak, since the block address in range of main area can point to the address which is not valid in segment info table, and we can not detect such condition, we may suffer worse corruption as system continues running. So this patch introduce DATA_GENERIC_ENHANCE to enhance the sanity check which trigger SIT bitmap check rather than only range check. This patch did below changes as wel: - set SBI_NEED_FSCK in f2fs_is_valid_blkaddr(). - get rid of is_valid_data_blkaddr() to avoid panic if blkaddr is invalid. - introduce verify_fio_blkaddr() to wrap fio {new,old}_blkaddr validation check. - spread blkaddr check in: * f2fs_get_node_info() * __read_out_blkaddrs() * f2fs_submit_page_read() * ra_data_block() * do_recover_data() This patch can fix bug reported from bugzilla below: https://bugzilla.kernel.org/show_bug.cgi?id=203215 https://bugzilla.kernel.org/show_bug.cgi?id=203223 https://bugzilla.kernel.org/show_bug.cgi?id=203231 https://bugzilla.kernel.org/show_bug.cgi?id=203235 https://bugzilla.kernel.org/show_bug.cgi?id=203241 = Update by Jaegeuk Kim = DATA_GENERIC_ENHANCE enhanced to validate block addresses on read/write paths. But, xfstest/generic/446 compalins some generated kernel messages saying invalid bitmap was detected when reading a block. The reaons is, when we get the block addresses from extent_cache, there is no lock to synchronize it from truncating the blocks in parallel. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-04-15 07:26:32 +00:00
fio->is_por ? META_POR : (__is_meta_io(fio) ?
META_GENERIC : DATA_GENERIC_ENHANCE)))
return -EFSCORRUPTED;
f2fs: fix to do sanity check with block address in main area This patch add to do sanity check with below field: - cp_pack_total_block_count - blkaddr of data/node - extent info - Overview BUG() in verify_block_addr() when writing to a corrupted f2fs image - Reproduce (4.18 upstream kernel) - POC (poc.c) static void activity(char *mpoint) { char *foo_bar_baz; int err; static int buf[8192]; memset(buf, 0, sizeof(buf)); err = asprintf(&foo_bar_baz, "%s/foo/bar/baz", mpoint); int fd = open(foo_bar_baz, O_RDWR | O_TRUNC, 0777); if (fd >= 0) { write(fd, (char *)buf, sizeof(buf)); fdatasync(fd); close(fd); } } int main(int argc, char *argv[]) { activity(argv[1]); return 0; } - Kernel message [ 689.349473] F2FS-fs (loop0): Mounted with checkpoint version = 3 [ 699.728662] WARNING: CPU: 0 PID: 1309 at fs/f2fs/segment.c:2860 f2fs_inplace_write_data+0x232/0x240 [ 699.728670] Modules linked in: snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_pcm snd_timer snd mac_hid i2c_piix4 soundcore ib_iser rdma_cm iw_cm ib_cm ib_core iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx raid1 raid0 multipath linear 8139too crct10dif_pclmul crc32_pclmul qxl drm_kms_helper syscopyarea aesni_intel sysfillrect sysimgblt fb_sys_fops ttm drm aes_x86_64 crypto_simd cryptd 8139cp glue_helper mii pata_acpi floppy [ 699.729056] CPU: 0 PID: 1309 Comm: a.out Not tainted 4.18.0-rc1+ #4 [ 699.729064] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.729074] RIP: 0010:f2fs_inplace_write_data+0x232/0x240 [ 699.729076] Code: ff e9 cf fe ff ff 49 8d 7d 10 e8 39 45 ad ff 4d 8b 7d 10 be 04 00 00 00 49 8d 7f 48 e8 07 49 ad ff 45 8b 7f 48 e9 fb fe ff ff <0f> 0b f0 41 80 4d 48 04 e9 65 fe ff ff 90 66 66 66 66 90 55 48 8d [ 699.729130] RSP: 0018:ffff8801f43af568 EFLAGS: 00010202 [ 699.729139] RAX: 000000000000003f RBX: ffff8801f43af7b8 RCX: ffffffffb88c9113 [ 699.729142] RDX: 0000000000000003 RSI: dffffc0000000000 RDI: ffff8802024e5540 [ 699.729144] RBP: ffff8801f43af590 R08: 0000000000000009 R09: ffffffffffffffe8 [ 699.729147] R10: 0000000000000001 R11: ffffed0039b0596a R12: ffff8802024e5540 [ 699.729149] R13: ffff8801f0335500 R14: ffff8801e3e7a700 R15: ffff8801e1ee4450 [ 699.729154] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.729156] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.729159] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.729171] Call Trace: [ 699.729192] f2fs_do_write_data_page+0x2e2/0xe00 [ 699.729203] ? f2fs_should_update_outplace+0xd0/0xd0 [ 699.729238] ? memcg_drain_all_list_lrus+0x280/0x280 [ 699.729269] ? __radix_tree_replace+0xa3/0x120 [ 699.729276] __write_data_page+0x5c7/0xe30 [ 699.729291] ? kasan_check_read+0x11/0x20 [ 699.729310] ? page_mapped+0x8a/0x110 [ 699.729321] ? page_mkclean+0xe9/0x160 [ 699.729327] ? f2fs_do_write_data_page+0xe00/0xe00 [ 699.729331] ? invalid_page_referenced_vma+0x130/0x130 [ 699.729345] ? clear_page_dirty_for_io+0x332/0x450 [ 699.729351] f2fs_write_cache_pages+0x4ca/0x860 [ 699.729358] ? __write_data_page+0xe30/0xe30 [ 699.729374] ? percpu_counter_add_batch+0x22/0xa0 [ 699.729380] ? kasan_check_write+0x14/0x20 [ 699.729391] ? _raw_spin_lock+0x17/0x40 [ 699.729403] ? f2fs_mark_inode_dirty_sync.part.18+0x16/0x30 [ 699.729413] ? iov_iter_advance+0x113/0x640 [ 699.729418] ? f2fs_write_end+0x133/0x2e0 [ 699.729423] ? balance_dirty_pages_ratelimited+0x239/0x640 [ 699.729428] f2fs_write_data_pages+0x329/0x520 [ 699.729433] ? generic_perform_write+0x250/0x320 [ 699.729438] ? f2fs_write_cache_pages+0x860/0x860 [ 699.729454] ? current_time+0x110/0x110 [ 699.729459] ? f2fs_preallocate_blocks+0x1ef/0x370 [ 699.729464] do_writepages+0x37/0xb0 [ 699.729468] ? f2fs_write_cache_pages+0x860/0x860 [ 699.729472] ? do_writepages+0x37/0xb0 [ 699.729478] __filemap_fdatawrite_range+0x19a/0x1f0 [ 699.729483] ? delete_from_page_cache_batch+0x4e0/0x4e0 [ 699.729496] ? __vfs_write+0x2b2/0x410 [ 699.729501] file_write_and_wait_range+0x66/0xb0 [ 699.729506] f2fs_do_sync_file+0x1f9/0xd90 [ 699.729511] ? truncate_partial_data_page+0x290/0x290 [ 699.729521] ? __sb_end_write+0x30/0x50 [ 699.729526] ? vfs_write+0x20f/0x260 [ 699.729530] f2fs_sync_file+0x9a/0xb0 [ 699.729534] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.729548] vfs_fsync_range+0x68/0x100 [ 699.729554] ? __fget_light+0xc9/0xe0 [ 699.729558] do_fsync+0x3d/0x70 [ 699.729562] __x64_sys_fdatasync+0x24/0x30 [ 699.729585] do_syscall_64+0x78/0x170 [ 699.729595] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 699.729613] RIP: 0033:0x7f9bf930d800 [ 699.729615] Code: 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 83 3d 49 bf 2c 00 00 75 10 b8 4b 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 be 78 01 00 48 89 04 24 [ 699.729668] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.729673] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.729675] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.729678] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.729680] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.729683] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000 [ 699.729687] ---[ end trace 4ce02f25ff7d3df5 ]--- [ 699.729782] ------------[ cut here ]------------ [ 699.729785] kernel BUG at fs/f2fs/segment.h:654! [ 699.731055] invalid opcode: 0000 [#1] SMP KASAN PTI [ 699.732104] CPU: 0 PID: 1309 Comm: a.out Tainted: G W 4.18.0-rc1+ #4 [ 699.733684] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.735611] RIP: 0010:f2fs_submit_page_bio+0x29b/0x730 [ 699.736649] Code: 54 49 8d bd 18 04 00 00 e8 b2 59 af ff 41 8b 8d 18 04 00 00 8b 45 b8 41 d3 e6 44 01 f0 4c 8d 73 14 41 39 c7 0f 82 37 fe ff ff <0f> 0b 65 8b 05 2c 04 77 47 89 c0 48 0f a3 05 52 c1 d5 01 0f 92 c0 [ 699.740524] RSP: 0018:ffff8801f43af508 EFLAGS: 00010283 [ 699.741573] RAX: 0000000000000000 RBX: ffff8801f43af7b8 RCX: ffffffffb88a7cef [ 699.743006] RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff8801e3e7a64c [ 699.744426] RBP: ffff8801f43af558 R08: ffffed003e066b55 R09: ffffed003e066b55 [ 699.745833] R10: 0000000000000001 R11: ffffed003e066b54 R12: ffffea0007876940 [ 699.747256] R13: ffff8801f0335500 R14: ffff8801e3e7a600 R15: 0000000000000001 [ 699.748683] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.750293] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.751462] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.752874] Call Trace: [ 699.753386] ? f2fs_inplace_write_data+0x93/0x240 [ 699.754341] f2fs_inplace_write_data+0xd2/0x240 [ 699.755271] f2fs_do_write_data_page+0x2e2/0xe00 [ 699.756214] ? f2fs_should_update_outplace+0xd0/0xd0 [ 699.757215] ? memcg_drain_all_list_lrus+0x280/0x280 [ 699.758209] ? __radix_tree_replace+0xa3/0x120 [ 699.759164] __write_data_page+0x5c7/0xe30 [ 699.760002] ? kasan_check_read+0x11/0x20 [ 699.760823] ? page_mapped+0x8a/0x110 [ 699.761573] ? page_mkclean+0xe9/0x160 [ 699.762345] ? f2fs_do_write_data_page+0xe00/0xe00 [ 699.763332] ? invalid_page_referenced_vma+0x130/0x130 [ 699.764374] ? clear_page_dirty_for_io+0x332/0x450 [ 699.765347] f2fs_write_cache_pages+0x4ca/0x860 [ 699.766276] ? __write_data_page+0xe30/0xe30 [ 699.767161] ? percpu_counter_add_batch+0x22/0xa0 [ 699.768112] ? kasan_check_write+0x14/0x20 [ 699.768951] ? _raw_spin_lock+0x17/0x40 [ 699.769739] ? f2fs_mark_inode_dirty_sync.part.18+0x16/0x30 [ 699.770885] ? iov_iter_advance+0x113/0x640 [ 699.771743] ? f2fs_write_end+0x133/0x2e0 [ 699.772569] ? balance_dirty_pages_ratelimited+0x239/0x640 [ 699.773680] f2fs_write_data_pages+0x329/0x520 [ 699.774603] ? generic_perform_write+0x250/0x320 [ 699.775544] ? f2fs_write_cache_pages+0x860/0x860 [ 699.776510] ? current_time+0x110/0x110 [ 699.777299] ? f2fs_preallocate_blocks+0x1ef/0x370 [ 699.778279] do_writepages+0x37/0xb0 [ 699.779026] ? f2fs_write_cache_pages+0x860/0x860 [ 699.779978] ? do_writepages+0x37/0xb0 [ 699.780755] __filemap_fdatawrite_range+0x19a/0x1f0 [ 699.781746] ? delete_from_page_cache_batch+0x4e0/0x4e0 [ 699.782820] ? __vfs_write+0x2b2/0x410 [ 699.783597] file_write_and_wait_range+0x66/0xb0 [ 699.784540] f2fs_do_sync_file+0x1f9/0xd90 [ 699.785381] ? truncate_partial_data_page+0x290/0x290 [ 699.786415] ? __sb_end_write+0x30/0x50 [ 699.787204] ? vfs_write+0x20f/0x260 [ 699.787941] f2fs_sync_file+0x9a/0xb0 [ 699.788694] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.789572] vfs_fsync_range+0x68/0x100 [ 699.790360] ? __fget_light+0xc9/0xe0 [ 699.791128] do_fsync+0x3d/0x70 [ 699.791779] __x64_sys_fdatasync+0x24/0x30 [ 699.792614] do_syscall_64+0x78/0x170 [ 699.793371] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 699.794406] RIP: 0033:0x7f9bf930d800 [ 699.795134] Code: 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 83 3d 49 bf 2c 00 00 75 10 b8 4b 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 be 78 01 00 48 89 04 24 [ 699.798960] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.800483] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.801923] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.803373] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.804798] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.806233] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000 [ 699.807667] Modules linked in: snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_pcm snd_timer snd mac_hid i2c_piix4 soundcore ib_iser rdma_cm iw_cm ib_cm ib_core iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx raid1 raid0 multipath linear 8139too crct10dif_pclmul crc32_pclmul qxl drm_kms_helper syscopyarea aesni_intel sysfillrect sysimgblt fb_sys_fops ttm drm aes_x86_64 crypto_simd cryptd 8139cp glue_helper mii pata_acpi floppy [ 699.817079] ---[ end trace 4ce02f25ff7d3df6 ]--- [ 699.818068] RIP: 0010:f2fs_submit_page_bio+0x29b/0x730 [ 699.819114] Code: 54 49 8d bd 18 04 00 00 e8 b2 59 af ff 41 8b 8d 18 04 00 00 8b 45 b8 41 d3 e6 44 01 f0 4c 8d 73 14 41 39 c7 0f 82 37 fe ff ff <0f> 0b 65 8b 05 2c 04 77 47 89 c0 48 0f a3 05 52 c1 d5 01 0f 92 c0 [ 699.822919] RSP: 0018:ffff8801f43af508 EFLAGS: 00010283 [ 699.823977] RAX: 0000000000000000 RBX: ffff8801f43af7b8 RCX: ffffffffb88a7cef [ 699.825436] RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff8801e3e7a64c [ 699.826881] RBP: ffff8801f43af558 R08: ffffed003e066b55 R09: ffffed003e066b55 [ 699.828292] R10: 0000000000000001 R11: ffffed003e066b54 R12: ffffea0007876940 [ 699.829750] R13: ffff8801f0335500 R14: ffff8801e3e7a600 R15: 0000000000000001 [ 699.831192] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.832793] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.833981] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.835556] ================================================================== [ 699.837029] BUG: KASAN: stack-out-of-bounds in update_stack_state+0x38c/0x3e0 [ 699.838462] Read of size 8 at addr ffff8801f43af970 by task a.out/1309 [ 699.840086] CPU: 0 PID: 1309 Comm: a.out Tainted: G D W 4.18.0-rc1+ #4 [ 699.841603] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.843475] Call Trace: [ 699.843982] dump_stack+0x7b/0xb5 [ 699.844661] print_address_description+0x70/0x290 [ 699.845607] kasan_report+0x291/0x390 [ 699.846351] ? update_stack_state+0x38c/0x3e0 [ 699.853831] __asan_load8+0x54/0x90 [ 699.854569] update_stack_state+0x38c/0x3e0 [ 699.855428] ? __read_once_size_nocheck.constprop.7+0x20/0x20 [ 699.856601] ? __save_stack_trace+0x5e/0x100 [ 699.857476] unwind_next_frame.part.5+0x18e/0x490 [ 699.858448] ? unwind_dump+0x290/0x290 [ 699.859217] ? clear_page_dirty_for_io+0x332/0x450 [ 699.860185] __unwind_start+0x106/0x190 [ 699.860974] __save_stack_trace+0x5e/0x100 [ 699.861808] ? __save_stack_trace+0x5e/0x100 [ 699.862691] ? unlink_anon_vmas+0xba/0x2c0 [ 699.863525] save_stack_trace+0x1f/0x30 [ 699.864312] save_stack+0x46/0xd0 [ 699.864993] ? __alloc_pages_slowpath+0x1420/0x1420 [ 699.865990] ? flush_tlb_mm_range+0x15e/0x220 [ 699.866889] ? kasan_check_write+0x14/0x20 [ 699.867724] ? __dec_node_state+0x92/0xb0 [ 699.868543] ? lock_page_memcg+0x85/0xf0 [ 699.869350] ? unlock_page_memcg+0x16/0x80 [ 699.870185] ? page_remove_rmap+0x198/0x520 [ 699.871048] ? mark_page_accessed+0x133/0x200 [ 699.871930] ? _cond_resched+0x1a/0x50 [ 699.872700] ? unmap_page_range+0xcd4/0xe50 [ 699.873551] ? rb_next+0x58/0x80 [ 699.874217] ? rb_next+0x58/0x80 [ 699.874895] __kasan_slab_free+0x13c/0x1a0 [ 699.875734] ? unlink_anon_vmas+0xba/0x2c0 [ 699.876563] kasan_slab_free+0xe/0x10 [ 699.877315] kmem_cache_free+0x89/0x1e0 [ 699.878095] unlink_anon_vmas+0xba/0x2c0 [ 699.878913] free_pgtables+0x101/0x1b0 [ 699.879677] exit_mmap+0x146/0x2a0 [ 699.880378] ? __ia32_sys_munmap+0x50/0x50 [ 699.881214] ? kasan_check_read+0x11/0x20 [ 699.882052] ? mm_update_next_owner+0x322/0x380 [ 699.882985] mmput+0x8b/0x1d0 [ 699.883602] do_exit+0x43a/0x1390 [ 699.884288] ? mm_update_next_owner+0x380/0x380 [ 699.885212] ? f2fs_sync_file+0x9a/0xb0 [ 699.885995] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.886877] ? vfs_fsync_range+0x68/0x100 [ 699.887694] ? __fget_light+0xc9/0xe0 [ 699.888442] ? do_fsync+0x3d/0x70 [ 699.889118] ? __x64_sys_fdatasync+0x24/0x30 [ 699.889996] rewind_stack_do_exit+0x17/0x20 [ 699.890860] RIP: 0033:0x7f9bf930d800 [ 699.891585] Code: Bad RIP value. [ 699.892268] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.893781] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.895220] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.896643] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.898069] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.899505] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000 [ 699.901241] The buggy address belongs to the page: [ 699.902215] page:ffffea0007d0ebc0 count:0 mapcount:0 mapping:0000000000000000 index:0x0 [ 699.903811] flags: 0x2ffff0000000000() [ 699.904585] raw: 02ffff0000000000 0000000000000000 ffffffff07d00101 0000000000000000 [ 699.906125] raw: 0000000000000000 0000000000240000 00000000ffffffff 0000000000000000 [ 699.907673] page dumped because: kasan: bad access detected [ 699.909108] Memory state around the buggy address: [ 699.910077] ffff8801f43af800: 00 f1 f1 f1 f1 00 f4 f4 f4 f3 f3 f3 f3 00 00 00 [ 699.911528] ffff8801f43af880: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 699.912953] >ffff8801f43af900: 00 00 00 00 00 00 00 00 f1 01 f4 f4 f4 f2 f2 f2 [ 699.914392] ^ [ 699.915758] ffff8801f43af980: f2 00 f4 f4 00 00 00 00 f2 00 00 00 00 00 00 00 [ 699.917193] ffff8801f43afa00: 00 00 00 00 00 00 00 00 00 f3 f3 f3 00 00 00 00 [ 699.918634] ================================================================== - Location https://elixir.bootlin.com/linux/v4.18-rc1/source/fs/f2fs/segment.h#L644 Reported-by Wen Xu <wen.xu@gatech.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-08-01 11:13:44 +00:00
trace_f2fs_submit_page_bio(page, fio);
/* Allocate a new bio */
bio = __bio_alloc(fio, 1);
f2fs_set_bio_crypt_ctx(bio, fio->page->mapping->host,
fio->page->index, fio, GFP_NOIO);
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 12:29:47 +00:00
if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) {
bio_put(bio);
return -EFAULT;
}
if (fio->io_wbc && !is_read_io(fio->op))
wbc_account_cgroup_owner(fio->io_wbc, fio->page, PAGE_SIZE);
inc_page_count(fio->sbi, is_read_io(fio->op) ?
__read_io_type(page) : WB_DATA_TYPE(fio->page, false));
if (is_read_io(bio_op(bio)))
f2fs_submit_read_bio(fio->sbi, bio, fio->type);
else
f2fs_submit_write_bio(fio->sbi, bio, fio->type);
return 0;
}
static bool page_is_mergeable(struct f2fs_sb_info *sbi, struct bio *bio,
block_t last_blkaddr, block_t cur_blkaddr)
{
if (unlikely(sbi->max_io_bytes &&
bio->bi_iter.bi_size >= sbi->max_io_bytes))
return false;
if (last_blkaddr + 1 != cur_blkaddr)
return false;
return bio->bi_bdev == f2fs_target_device(sbi, cur_blkaddr, NULL);
}
static bool io_type_is_mergeable(struct f2fs_bio_info *io,
struct f2fs_io_info *fio)
{
if (io->fio.op != fio->op)
return false;
return io->fio.op_flags == fio->op_flags;
}
static bool io_is_mergeable(struct f2fs_sb_info *sbi, struct bio *bio,
struct f2fs_bio_info *io,
struct f2fs_io_info *fio,
block_t last_blkaddr,
block_t cur_blkaddr)
{
if (!page_is_mergeable(sbi, bio, last_blkaddr, cur_blkaddr))
return false;
return io_type_is_mergeable(io, fio);
}
static void add_bio_entry(struct f2fs_sb_info *sbi, struct bio *bio,
struct page *page, enum temp_type temp)
{
struct f2fs_bio_info *io = sbi->write_io[DATA] + temp;
struct bio_entry *be;
be = f2fs_kmem_cache_alloc(bio_entry_slab, GFP_NOFS, true, NULL);
be->bio = bio;
bio_get(bio);
if (bio_add_page(bio, page, PAGE_SIZE, 0) != PAGE_SIZE)
f2fs_bug_on(sbi, 1);
f2fs_down_write(&io->bio_list_lock);
list_add_tail(&be->list, &io->bio_list);
f2fs_up_write(&io->bio_list_lock);
}
static void del_bio_entry(struct bio_entry *be)
{
list_del(&be->list);
kmem_cache_free(bio_entry_slab, be);
}
static int add_ipu_page(struct f2fs_io_info *fio, struct bio **bio,
struct page *page)
{
struct f2fs_sb_info *sbi = fio->sbi;
enum temp_type temp;
bool found = false;
int ret = -EAGAIN;
for (temp = HOT; temp < NR_TEMP_TYPE && !found; temp++) {
struct f2fs_bio_info *io = sbi->write_io[DATA] + temp;
struct list_head *head = &io->bio_list;
struct bio_entry *be;
f2fs_down_write(&io->bio_list_lock);
list_for_each_entry(be, head, list) {
if (be->bio != *bio)
continue;
found = true;
f2fs_bug_on(sbi, !page_is_mergeable(sbi, *bio,
*fio->last_block,
fio->new_blkaddr));
if (f2fs_crypt_mergeable_bio(*bio,
fio->page->mapping->host,
fio->page->index, fio) &&
bio_add_page(*bio, page, PAGE_SIZE, 0) ==
PAGE_SIZE) {
ret = 0;
break;
}
/* page can't be merged into bio; submit the bio */
del_bio_entry(be);
f2fs_submit_write_bio(sbi, *bio, DATA);
break;
}
f2fs_up_write(&io->bio_list_lock);
}
if (ret) {
bio_put(*bio);
*bio = NULL;
}
return ret;
}
void f2fs_submit_merged_ipu_write(struct f2fs_sb_info *sbi,
struct bio **bio, struct page *page)
{
enum temp_type temp;
bool found = false;
struct bio *target = bio ? *bio : NULL;
f2fs_bug_on(sbi, !target && !page);
for (temp = HOT; temp < NR_TEMP_TYPE && !found; temp++) {
struct f2fs_bio_info *io = sbi->write_io[DATA] + temp;
struct list_head *head = &io->bio_list;
struct bio_entry *be;
if (list_empty(head))
continue;
f2fs_down_read(&io->bio_list_lock);
list_for_each_entry(be, head, list) {
if (target)
found = (target == be->bio);
else
found = __has_merged_page(be->bio, NULL,
page, 0);
if (found)
break;
}
f2fs_up_read(&io->bio_list_lock);
if (!found)
continue;
found = false;
f2fs_down_write(&io->bio_list_lock);
list_for_each_entry(be, head, list) {
if (target)
found = (target == be->bio);
else
found = __has_merged_page(be->bio, NULL,
page, 0);
if (found) {
target = be->bio;
del_bio_entry(be);
break;
}
}
f2fs_up_write(&io->bio_list_lock);
}
if (found)
f2fs_submit_write_bio(sbi, target, DATA);
if (bio && *bio) {
bio_put(*bio);
*bio = NULL;
}
}
f2fs: add bio cache for IPU SQLite in Wal mode may trigger sequential IPU write in db-wal file, after commit d1b3e72d5490 ("f2fs: submit bio of in-place-update pages"), we lost the chance of merging page in inner managed bio cache, result in submitting more small-sized IO. So let's add temporary bio in writepages() to cache mergeable write IO as much as possible. Test case: 1. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" 2. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" Before: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65552, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65560, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65568, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65576, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65584, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65592, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65600, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65608, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65616, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65624, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65632, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65640, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65648, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65656, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65664, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57352, size = 4096 After: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 65536 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57368, size = 4096 Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-02-19 08:15:29 +00:00
int f2fs_merge_page_bio(struct f2fs_io_info *fio)
{
struct bio *bio = *fio->bio;
struct page *page = fio->encrypted_page ?
fio->encrypted_page : fio->page;
if (!f2fs_is_valid_blkaddr(fio->sbi, fio->new_blkaddr,
__is_meta_io(fio) ? META_GENERIC : DATA_GENERIC))
return -EFSCORRUPTED;
f2fs: add bio cache for IPU SQLite in Wal mode may trigger sequential IPU write in db-wal file, after commit d1b3e72d5490 ("f2fs: submit bio of in-place-update pages"), we lost the chance of merging page in inner managed bio cache, result in submitting more small-sized IO. So let's add temporary bio in writepages() to cache mergeable write IO as much as possible. Test case: 1. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" 2. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" Before: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65552, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65560, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65568, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65576, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65584, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65592, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65600, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65608, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65616, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65624, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65632, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65640, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65648, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65656, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65664, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57352, size = 4096 After: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 65536 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57368, size = 4096 Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-02-19 08:15:29 +00:00
trace_f2fs_submit_page_bio(page, fio);
if (bio && !page_is_mergeable(fio->sbi, bio, *fio->last_block,
fio->new_blkaddr))
f2fs_submit_merged_ipu_write(fio->sbi, &bio, NULL);
f2fs: add bio cache for IPU SQLite in Wal mode may trigger sequential IPU write in db-wal file, after commit d1b3e72d5490 ("f2fs: submit bio of in-place-update pages"), we lost the chance of merging page in inner managed bio cache, result in submitting more small-sized IO. So let's add temporary bio in writepages() to cache mergeable write IO as much as possible. Test case: 1. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" 2. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" Before: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65552, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65560, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65568, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65576, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65584, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65592, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65600, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65608, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65616, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65624, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65632, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65640, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65648, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65656, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65664, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57352, size = 4096 After: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 65536 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57368, size = 4096 Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-02-19 08:15:29 +00:00
alloc_new:
if (!bio) {
bio = __bio_alloc(fio, BIO_MAX_VECS);
f2fs_set_bio_crypt_ctx(bio, fio->page->mapping->host,
fio->page->index, fio, GFP_NOIO);
f2fs: add bio cache for IPU SQLite in Wal mode may trigger sequential IPU write in db-wal file, after commit d1b3e72d5490 ("f2fs: submit bio of in-place-update pages"), we lost the chance of merging page in inner managed bio cache, result in submitting more small-sized IO. So let's add temporary bio in writepages() to cache mergeable write IO as much as possible. Test case: 1. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" 2. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" Before: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65552, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65560, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65568, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65576, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65584, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65592, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65600, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65608, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65616, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65624, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65632, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65640, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65648, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65656, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65664, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57352, size = 4096 After: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 65536 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57368, size = 4096 Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-02-19 08:15:29 +00:00
add_bio_entry(fio->sbi, bio, page, fio->temp);
} else {
if (add_ipu_page(fio, &bio, page))
goto alloc_new;
f2fs: add bio cache for IPU SQLite in Wal mode may trigger sequential IPU write in db-wal file, after commit d1b3e72d5490 ("f2fs: submit bio of in-place-update pages"), we lost the chance of merging page in inner managed bio cache, result in submitting more small-sized IO. So let's add temporary bio in writepages() to cache mergeable write IO as much as possible. Test case: 1. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" 2. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" Before: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65552, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65560, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65568, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65576, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65584, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65592, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65600, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65608, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65616, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65624, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65632, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65640, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65648, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65656, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65664, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57352, size = 4096 After: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 65536 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57368, size = 4096 Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-02-19 08:15:29 +00:00
}
if (fio->io_wbc)
wbc_account_cgroup_owner(fio->io_wbc, fio->page, PAGE_SIZE);
f2fs: add bio cache for IPU SQLite in Wal mode may trigger sequential IPU write in db-wal file, after commit d1b3e72d5490 ("f2fs: submit bio of in-place-update pages"), we lost the chance of merging page in inner managed bio cache, result in submitting more small-sized IO. So let's add temporary bio in writepages() to cache mergeable write IO as much as possible. Test case: 1. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" 2. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" Before: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65552, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65560, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65568, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65576, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65584, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65592, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65600, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65608, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65616, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65624, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65632, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65640, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65648, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65656, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65664, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57352, size = 4096 After: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 65536 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57368, size = 4096 Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-02-19 08:15:29 +00:00
inc_page_count(fio->sbi, WB_DATA_TYPE(page, false));
f2fs: add bio cache for IPU SQLite in Wal mode may trigger sequential IPU write in db-wal file, after commit d1b3e72d5490 ("f2fs: submit bio of in-place-update pages"), we lost the chance of merging page in inner managed bio cache, result in submitting more small-sized IO. So let's add temporary bio in writepages() to cache mergeable write IO as much as possible. Test case: 1. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" 2. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" Before: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65552, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65560, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65568, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65576, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65584, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65592, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65600, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65608, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65616, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65624, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65632, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65640, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65648, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65656, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65664, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57352, size = 4096 After: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 65536 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57368, size = 4096 Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-02-19 08:15:29 +00:00
*fio->last_block = fio->new_blkaddr;
*fio->bio = bio;
return 0;
}
#ifdef CONFIG_BLK_DEV_ZONED
static bool is_end_zone_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr)
{
struct block_device *bdev = sbi->sb->s_bdev;
int devi = 0;
if (f2fs_is_multi_device(sbi)) {
devi = f2fs_target_device_index(sbi, blkaddr);
if (blkaddr < FDEV(devi).start_blk ||
blkaddr > FDEV(devi).end_blk) {
f2fs_err(sbi, "Invalid block %x", blkaddr);
return false;
}
blkaddr -= FDEV(devi).start_blk;
bdev = FDEV(devi).bdev;
}
return bdev_is_zoned(bdev) &&
f2fs_blkz_is_seq(sbi, devi, blkaddr) &&
(blkaddr % sbi->blocks_per_blkz == sbi->blocks_per_blkz - 1);
}
#endif
f2fs: fix to let caller retry allocating block address Configure io_bits with 2 and enable LFS mode, generic/013 reports below dmesg: BUG: unable to handle kernel NULL pointer dereference at 00000104 *pdpt = 0000000029b7b001 *pde = 0000000000000000 Oops: 0002 [#1] PREEMPT SMP Modules linked in: crc32_generic zram f2fs(O) rfcomm bnep bluetooth ecdh_generic snd_intel8x0 snd_ac97_codec ac97_bus snd_pcm snd_seq_midi snd_seq_midi_event snd_rawmidi snd_seq pcbc joydev snd_seq_device aesni_intel snd_timer aes_i586 snd crypto_simd cryptd soundcore i2c_piix4 serio_raw mac_hid video parport_pc ppdev lp parport hid_generic psmouse usbhid hid e1000 CPU: 0 PID: 11161 Comm: fsstress Tainted: G O 4.17.0-rc2 #38 Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 EIP: f2fs_submit_page_write+0x28d/0x550 [f2fs] EFLAGS: 00010206 CPU: 0 EAX: e863dcd8 EBX: 00000000 ECX: 00000100 EDX: 00000200 ESI: e863dcf4 EDI: f6f82768 EBP: e863dbb0 ESP: e863db74 DS: 007b ES: 007b FS: 00d8 GS: 0033 SS: 0068 CR0: 80050033 CR2: 00000104 CR3: 29a62020 CR4: 000406f0 Call Trace: do_write_page+0x6f/0xc0 [f2fs] write_data_page+0x4a/0xd0 [f2fs] do_write_data_page+0x327/0x630 [f2fs] __write_data_page+0x34b/0x820 [f2fs] __f2fs_write_data_pages+0x42d/0x8c0 [f2fs] f2fs_write_data_pages+0x27/0x30 [f2fs] do_writepages+0x1a/0x70 __filemap_fdatawrite_range+0x94/0xd0 filemap_write_and_wait_range+0x3d/0xa0 __generic_file_write_iter+0x11a/0x1f0 f2fs_file_write_iter+0xdd/0x3b0 [f2fs] __vfs_write+0xd2/0x150 vfs_write+0x9b/0x190 ksys_write+0x45/0x90 sys_write+0x16/0x20 do_fast_syscall_32+0xaa/0x22c entry_SYSENTER_32+0x4c/0x7b EIP: 0xb7fc8c51 EFLAGS: 00000246 CPU: 0 EAX: ffffffda EBX: 00000003 ECX: 09cde000 EDX: 00001000 ESI: 00000003 EDI: 00001000 EBP: 00000000 ESP: bfbded38 DS: 007b ES: 007b FS: 0000 GS: 0033 SS: 007b Code: e8 f9 77 34 c9 8b 45 e0 8b 80 b8 00 00 00 39 45 d8 0f 84 bb 02 00 00 8b 45 e0 8b 80 b8 00 00 00 8d 50 d8 8b 08 89 55 f0 8b 50 04 <89> 51 04 89 0a c7 00 00 01 00 00 c7 40 04 00 02 00 00 8b 45 dc EIP: f2fs_submit_page_write+0x28d/0x550 [f2fs] SS:ESP: 0068:e863db74 CR2: 0000000000000104 ---[ end trace 4cac79c0d1305ee6 ]--- allocate_data_block will submit all sequential pending IOs sorted by a FIFO list, If we failed to submit other user's IO due to unaligned write, we will retry to allocate new block address for current IO, then it will initialize fio.list again, if fio was in the list before, it can break FIFO list, result in above panic. Thread A Thread B - do_write_page - allocate_data_block - list_add_tail : fioA cached in FIFO list. - do_write_page - allocate_data_block - list_add_tail : fioB cached in FIFO list. - f2fs_submit_page_write : fail to submit IO - allocate_data_block - INIT_LIST_HEAD - f2fs_submit_page_write - list_del <-- NULL pointer dereference This patch adds fio.retry parameter to indicate failure status for each IO, and avoid bailing out if there is still pending IO in FIFO list for fixing. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-28 15:47:18 +00:00
void f2fs_submit_page_write(struct f2fs_io_info *fio)
{
struct f2fs_sb_info *sbi = fio->sbi;
enum page_type btype = PAGE_TYPE_OF_BIO(fio->type);
struct f2fs_bio_info *io = sbi->write_io[btype] + fio->temp;
struct page *bio_page;
enum count_type type;
f2fs_bug_on(sbi, is_read_io(fio->op));
f2fs_down_write(&io->io_rwsem);
next:
#ifdef CONFIG_BLK_DEV_ZONED
if (f2fs_sb_has_blkzoned(sbi) && btype < META && io->zone_pending_bio) {
wait_for_completion_io(&io->zone_wait);
bio_put(io->zone_pending_bio);
io->zone_pending_bio = NULL;
io->bi_private = NULL;
}
#endif
if (fio->in_list) {
spin_lock(&io->io_lock);
if (list_empty(&io->io_list)) {
spin_unlock(&io->io_lock);
f2fs: fix to let caller retry allocating block address Configure io_bits with 2 and enable LFS mode, generic/013 reports below dmesg: BUG: unable to handle kernel NULL pointer dereference at 00000104 *pdpt = 0000000029b7b001 *pde = 0000000000000000 Oops: 0002 [#1] PREEMPT SMP Modules linked in: crc32_generic zram f2fs(O) rfcomm bnep bluetooth ecdh_generic snd_intel8x0 snd_ac97_codec ac97_bus snd_pcm snd_seq_midi snd_seq_midi_event snd_rawmidi snd_seq pcbc joydev snd_seq_device aesni_intel snd_timer aes_i586 snd crypto_simd cryptd soundcore i2c_piix4 serio_raw mac_hid video parport_pc ppdev lp parport hid_generic psmouse usbhid hid e1000 CPU: 0 PID: 11161 Comm: fsstress Tainted: G O 4.17.0-rc2 #38 Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 EIP: f2fs_submit_page_write+0x28d/0x550 [f2fs] EFLAGS: 00010206 CPU: 0 EAX: e863dcd8 EBX: 00000000 ECX: 00000100 EDX: 00000200 ESI: e863dcf4 EDI: f6f82768 EBP: e863dbb0 ESP: e863db74 DS: 007b ES: 007b FS: 00d8 GS: 0033 SS: 0068 CR0: 80050033 CR2: 00000104 CR3: 29a62020 CR4: 000406f0 Call Trace: do_write_page+0x6f/0xc0 [f2fs] write_data_page+0x4a/0xd0 [f2fs] do_write_data_page+0x327/0x630 [f2fs] __write_data_page+0x34b/0x820 [f2fs] __f2fs_write_data_pages+0x42d/0x8c0 [f2fs] f2fs_write_data_pages+0x27/0x30 [f2fs] do_writepages+0x1a/0x70 __filemap_fdatawrite_range+0x94/0xd0 filemap_write_and_wait_range+0x3d/0xa0 __generic_file_write_iter+0x11a/0x1f0 f2fs_file_write_iter+0xdd/0x3b0 [f2fs] __vfs_write+0xd2/0x150 vfs_write+0x9b/0x190 ksys_write+0x45/0x90 sys_write+0x16/0x20 do_fast_syscall_32+0xaa/0x22c entry_SYSENTER_32+0x4c/0x7b EIP: 0xb7fc8c51 EFLAGS: 00000246 CPU: 0 EAX: ffffffda EBX: 00000003 ECX: 09cde000 EDX: 00001000 ESI: 00000003 EDI: 00001000 EBP: 00000000 ESP: bfbded38 DS: 007b ES: 007b FS: 0000 GS: 0033 SS: 007b Code: e8 f9 77 34 c9 8b 45 e0 8b 80 b8 00 00 00 39 45 d8 0f 84 bb 02 00 00 8b 45 e0 8b 80 b8 00 00 00 8d 50 d8 8b 08 89 55 f0 8b 50 04 <89> 51 04 89 0a c7 00 00 01 00 00 c7 40 04 00 02 00 00 8b 45 dc EIP: f2fs_submit_page_write+0x28d/0x550 [f2fs] SS:ESP: 0068:e863db74 CR2: 0000000000000104 ---[ end trace 4cac79c0d1305ee6 ]--- allocate_data_block will submit all sequential pending IOs sorted by a FIFO list, If we failed to submit other user's IO due to unaligned write, we will retry to allocate new block address for current IO, then it will initialize fio.list again, if fio was in the list before, it can break FIFO list, result in above panic. Thread A Thread B - do_write_page - allocate_data_block - list_add_tail : fioA cached in FIFO list. - do_write_page - allocate_data_block - list_add_tail : fioB cached in FIFO list. - f2fs_submit_page_write : fail to submit IO - allocate_data_block - INIT_LIST_HEAD - f2fs_submit_page_write - list_del <-- NULL pointer dereference This patch adds fio.retry parameter to indicate failure status for each IO, and avoid bailing out if there is still pending IO in FIFO list for fixing. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-28 15:47:18 +00:00
goto out;
}
fio = list_first_entry(&io->io_list,
struct f2fs_io_info, list);
list_del(&fio->list);
spin_unlock(&io->io_lock);
}
f2fs: introduce DATA_GENERIC_ENHANCE Previously, f2fs_is_valid_blkaddr(, blkaddr, DATA_GENERIC) will check whether @blkaddr locates in main area or not. That check is weak, since the block address in range of main area can point to the address which is not valid in segment info table, and we can not detect such condition, we may suffer worse corruption as system continues running. So this patch introduce DATA_GENERIC_ENHANCE to enhance the sanity check which trigger SIT bitmap check rather than only range check. This patch did below changes as wel: - set SBI_NEED_FSCK in f2fs_is_valid_blkaddr(). - get rid of is_valid_data_blkaddr() to avoid panic if blkaddr is invalid. - introduce verify_fio_blkaddr() to wrap fio {new,old}_blkaddr validation check. - spread blkaddr check in: * f2fs_get_node_info() * __read_out_blkaddrs() * f2fs_submit_page_read() * ra_data_block() * do_recover_data() This patch can fix bug reported from bugzilla below: https://bugzilla.kernel.org/show_bug.cgi?id=203215 https://bugzilla.kernel.org/show_bug.cgi?id=203223 https://bugzilla.kernel.org/show_bug.cgi?id=203231 https://bugzilla.kernel.org/show_bug.cgi?id=203235 https://bugzilla.kernel.org/show_bug.cgi?id=203241 = Update by Jaegeuk Kim = DATA_GENERIC_ENHANCE enhanced to validate block addresses on read/write paths. But, xfstest/generic/446 compalins some generated kernel messages saying invalid bitmap was detected when reading a block. The reaons is, when we get the block addresses from extent_cache, there is no lock to synchronize it from truncating the blocks in parallel. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-04-15 07:26:32 +00:00
verify_fio_blkaddr(fio);
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
if (fio->encrypted_page)
bio_page = fio->encrypted_page;
else if (fio->compressed_page)
bio_page = fio->compressed_page;
else
bio_page = fio->page;
/* set submitted = true as a return value */
fio->submitted = 1;
type = WB_DATA_TYPE(bio_page, fio->compressed_page);
inc_page_count(sbi, type);
if (io->bio &&
(!io_is_mergeable(sbi, io->bio, io, fio, io->last_block_in_bio,
fio->new_blkaddr) ||
!f2fs_crypt_mergeable_bio(io->bio, fio->page->mapping->host,
bio_page->index, fio)))
__submit_merged_bio(io);
alloc_new:
if (io->bio == NULL) {
io->bio = __bio_alloc(fio, BIO_MAX_VECS);
f2fs_set_bio_crypt_ctx(io->bio, fio->page->mapping->host,
bio_page->index, fio, GFP_NOIO);
io->fio = *fio;
}
if (bio_add_page(io->bio, bio_page, PAGE_SIZE, 0) < PAGE_SIZE) {
__submit_merged_bio(io);
goto alloc_new;
}
if (fio->io_wbc)
wbc_account_cgroup_owner(fio->io_wbc, fio->page, PAGE_SIZE);
io->last_block_in_bio = fio->new_blkaddr;
trace_f2fs_submit_page_write(fio->page, fio);
#ifdef CONFIG_BLK_DEV_ZONED
if (f2fs_sb_has_blkzoned(sbi) && btype < META &&
is_end_zone_blkaddr(sbi, fio->new_blkaddr)) {
bio_get(io->bio);
reinit_completion(&io->zone_wait);
io->bi_private = io->bio->bi_private;
io->bio->bi_private = io;
io->bio->bi_end_io = f2fs_zone_write_end_io;
io->zone_pending_bio = io->bio;
__submit_merged_bio(io);
}
#endif
if (fio->in_list)
goto next;
out:
if (is_sbi_flag_set(sbi, SBI_IS_SHUTDOWN) ||
!f2fs_is_checkpoint_ready(sbi))
__submit_merged_bio(io);
f2fs_up_write(&io->io_rwsem);
}
static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr,
unsigned nr_pages, blk_opf_t op_flag,
pgoff_t first_idx, bool for_write)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct bio *bio;
f2fs: introduce periodic iostat io latency traces Whenever we notice some sluggish issues on our machines, we are always curious about how well all types of I/O in the f2fs filesystem are handled. But, it's hard to get this kind of real data. First of all, we need to reproduce the issue while turning on the profiling tool like blktrace, but the issue doesn't happen again easily. Second, with the intervention of any tools, the overall timing of the issue will be slightly changed and it sometimes makes us hard to figure it out. So, I added the feature printing out IO latency statistics tracepoint events, which are minimal things to understand filesystem's I/O related behaviors, into F2FS_IOSTAT kernel config. With "iostat_enable" sysfs node on, we can get this statistics info in a periodic way and it would cause the least overhead. [samples] f2fs_ckpt-254:1-507 [003] .... 2842.439683: f2fs_iostat_latency: dev = (254,11), iotype [peak lat.(ms)/avg lat.(ms)/count], rd_data [136/1/801], rd_node [136/1/1704], rd_meta [4/2/4], wr_sync_data [164/16/3331], wr_sync_node [152/3/648], wr_sync_meta [160/2/4243], wr_async_data [24/13/15], wr_async_node [0/0/0], wr_async_meta [0/0/0] f2fs_ckpt-254:1-507 [002] .... 2845.450514: f2fs_iostat_latency: dev = (254,11), iotype [peak lat.(ms)/avg lat.(ms)/count], rd_data [60/3/456], rd_node [60/3/1258], rd_meta [0/0/1], wr_sync_data [120/12/2285], wr_sync_node [88/5/428], wr_sync_meta [52/6/2990], wr_async_data [4/1/3], wr_async_node [0/0/0], wr_async_meta [0/0/0] Signed-off-by: Daeho Jeong <daehojeong@google.com> Reviewed-by: Chao Yu <chao@kernel.org> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2021-08-20 22:29:09 +00:00
struct bio_post_read_ctx *ctx = NULL;
unsigned int post_read_steps = 0;
sector_t sector;
struct block_device *bdev = f2fs_target_device(sbi, blkaddr, &sector);
bio = bio_alloc_bioset(bdev, bio_max_segs(nr_pages),
REQ_OP_READ | op_flag,
for_write ? GFP_NOIO : GFP_KERNEL, &f2fs_bioset);
if (!bio)
return ERR_PTR(-ENOMEM);
bio->bi_iter.bi_sector = sector;
f2fs_set_bio_crypt_ctx(bio, inode, first_idx, NULL, GFP_NOFS);
bio->bi_end_io = f2fs_read_end_io;
if (fscrypt_inode_uses_fs_layer_crypto(inode))
post_read_steps |= STEP_DECRYPT;
f2fs: add fs-verity support Add fs-verity support to f2fs. fs-verity is a filesystem feature that enables transparent integrity protection and authentication of read-only files. It uses a dm-verity like mechanism at the file level: a Merkle tree is used to verify any block in the file in log(filesize) time. It is implemented mainly by helper functions in fs/verity/. See Documentation/filesystems/fsverity.rst for the full documentation. The f2fs support for fs-verity consists of: - Adding a filesystem feature flag and an inode flag for fs-verity. - Implementing the fsverity_operations to support enabling verity on an inode and reading/writing the verity metadata. - Updating ->readpages() to verify data as it's read from verity files and to support reading verity metadata pages. - Updating ->write_begin(), ->write_end(), and ->writepages() to support writing verity metadata pages. - Calling the fs-verity hooks for ->open(), ->setattr(), and ->ioctl(). Like ext4, f2fs stores the verity metadata (Merkle tree and fsverity_descriptor) past the end of the file, starting at the first 64K boundary beyond i_size. This approach works because (a) verity files are readonly, and (b) pages fully beyond i_size aren't visible to userspace but can be read/written internally by f2fs with only some relatively small changes to f2fs. Extended attributes cannot be used because (a) f2fs limits the total size of an inode's xattr entries to 4096 bytes, which wouldn't be enough for even a single Merkle tree block, and (b) f2fs encryption doesn't encrypt xattrs, yet the verity metadata *must* be encrypted when the file is because it contains hashes of the plaintext data. Acked-by: Jaegeuk Kim <jaegeuk@kernel.org> Acked-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Eric Biggers <ebiggers@google.com>
2019-07-22 16:26:24 +00:00
if (f2fs_need_verity(inode, first_idx))
post_read_steps |= STEP_VERITY;
/*
* STEP_DECOMPRESS is handled specially, since a compressed file might
* contain both compressed and uncompressed clusters. We'll allocate a
* bio_post_read_ctx if the file is compressed, but the caller is
* responsible for enabling STEP_DECOMPRESS if it's actually needed.
*/
if (post_read_steps || f2fs_compressed_file(inode)) {
/* Due to the mempool, this never fails. */
ctx = mempool_alloc(bio_post_read_ctx_pool, GFP_NOFS);
ctx->bio = bio;
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
ctx->sbi = sbi;
ctx->enabled_steps = post_read_steps;
ctx->fs_blkaddr = blkaddr;
ctx->decompression_attempted = false;
bio->bi_private = ctx;
}
f2fs: introduce periodic iostat io latency traces Whenever we notice some sluggish issues on our machines, we are always curious about how well all types of I/O in the f2fs filesystem are handled. But, it's hard to get this kind of real data. First of all, we need to reproduce the issue while turning on the profiling tool like blktrace, but the issue doesn't happen again easily. Second, with the intervention of any tools, the overall timing of the issue will be slightly changed and it sometimes makes us hard to figure it out. So, I added the feature printing out IO latency statistics tracepoint events, which are minimal things to understand filesystem's I/O related behaviors, into F2FS_IOSTAT kernel config. With "iostat_enable" sysfs node on, we can get this statistics info in a periodic way and it would cause the least overhead. [samples] f2fs_ckpt-254:1-507 [003] .... 2842.439683: f2fs_iostat_latency: dev = (254,11), iotype [peak lat.(ms)/avg lat.(ms)/count], rd_data [136/1/801], rd_node [136/1/1704], rd_meta [4/2/4], wr_sync_data [164/16/3331], wr_sync_node [152/3/648], wr_sync_meta [160/2/4243], wr_async_data [24/13/15], wr_async_node [0/0/0], wr_async_meta [0/0/0] f2fs_ckpt-254:1-507 [002] .... 2845.450514: f2fs_iostat_latency: dev = (254,11), iotype [peak lat.(ms)/avg lat.(ms)/count], rd_data [60/3/456], rd_node [60/3/1258], rd_meta [0/0/1], wr_sync_data [120/12/2285], wr_sync_node [88/5/428], wr_sync_meta [52/6/2990], wr_async_data [4/1/3], wr_async_node [0/0/0], wr_async_meta [0/0/0] Signed-off-by: Daeho Jeong <daehojeong@google.com> Reviewed-by: Chao Yu <chao@kernel.org> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2021-08-20 22:29:09 +00:00
iostat_alloc_and_bind_ctx(sbi, bio, ctx);
return bio;
}
/* This can handle encryption stuffs */
static int f2fs_submit_page_read(struct inode *inode, struct page *page,
block_t blkaddr, blk_opf_t op_flags,
bool for_write)
{
f2fs: introduce DATA_GENERIC_ENHANCE Previously, f2fs_is_valid_blkaddr(, blkaddr, DATA_GENERIC) will check whether @blkaddr locates in main area or not. That check is weak, since the block address in range of main area can point to the address which is not valid in segment info table, and we can not detect such condition, we may suffer worse corruption as system continues running. So this patch introduce DATA_GENERIC_ENHANCE to enhance the sanity check which trigger SIT bitmap check rather than only range check. This patch did below changes as wel: - set SBI_NEED_FSCK in f2fs_is_valid_blkaddr(). - get rid of is_valid_data_blkaddr() to avoid panic if blkaddr is invalid. - introduce verify_fio_blkaddr() to wrap fio {new,old}_blkaddr validation check. - spread blkaddr check in: * f2fs_get_node_info() * __read_out_blkaddrs() * f2fs_submit_page_read() * ra_data_block() * do_recover_data() This patch can fix bug reported from bugzilla below: https://bugzilla.kernel.org/show_bug.cgi?id=203215 https://bugzilla.kernel.org/show_bug.cgi?id=203223 https://bugzilla.kernel.org/show_bug.cgi?id=203231 https://bugzilla.kernel.org/show_bug.cgi?id=203235 https://bugzilla.kernel.org/show_bug.cgi?id=203241 = Update by Jaegeuk Kim = DATA_GENERIC_ENHANCE enhanced to validate block addresses on read/write paths. But, xfstest/generic/446 compalins some generated kernel messages saying invalid bitmap was detected when reading a block. The reaons is, when we get the block addresses from extent_cache, there is no lock to synchronize it from truncating the blocks in parallel. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-04-15 07:26:32 +00:00
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct bio *bio;
bio = f2fs_grab_read_bio(inode, blkaddr, 1, op_flags,
page->index, for_write);
if (IS_ERR(bio))
return PTR_ERR(bio);
/* wait for GCed page writeback via META_MAPPING */
f2fs_wait_on_block_writeback(inode, blkaddr);
if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) {
iostat_update_and_unbind_ctx(bio);
if (bio->bi_private)
mempool_free(bio->bi_private, bio_post_read_ctx_pool);
bio_put(bio);
return -EFAULT;
}
f2fs: introduce DATA_GENERIC_ENHANCE Previously, f2fs_is_valid_blkaddr(, blkaddr, DATA_GENERIC) will check whether @blkaddr locates in main area or not. That check is weak, since the block address in range of main area can point to the address which is not valid in segment info table, and we can not detect such condition, we may suffer worse corruption as system continues running. So this patch introduce DATA_GENERIC_ENHANCE to enhance the sanity check which trigger SIT bitmap check rather than only range check. This patch did below changes as wel: - set SBI_NEED_FSCK in f2fs_is_valid_blkaddr(). - get rid of is_valid_data_blkaddr() to avoid panic if blkaddr is invalid. - introduce verify_fio_blkaddr() to wrap fio {new,old}_blkaddr validation check. - spread blkaddr check in: * f2fs_get_node_info() * __read_out_blkaddrs() * f2fs_submit_page_read() * ra_data_block() * do_recover_data() This patch can fix bug reported from bugzilla below: https://bugzilla.kernel.org/show_bug.cgi?id=203215 https://bugzilla.kernel.org/show_bug.cgi?id=203223 https://bugzilla.kernel.org/show_bug.cgi?id=203231 https://bugzilla.kernel.org/show_bug.cgi?id=203235 https://bugzilla.kernel.org/show_bug.cgi?id=203241 = Update by Jaegeuk Kim = DATA_GENERIC_ENHANCE enhanced to validate block addresses on read/write paths. But, xfstest/generic/446 compalins some generated kernel messages saying invalid bitmap was detected when reading a block. The reaons is, when we get the block addresses from extent_cache, there is no lock to synchronize it from truncating the blocks in parallel. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-04-15 07:26:32 +00:00
inc_page_count(sbi, F2FS_RD_DATA);
f2fs_update_iostat(sbi, NULL, FS_DATA_READ_IO, F2FS_BLKSIZE);
f2fs_submit_read_bio(sbi, bio, DATA);
return 0;
}
static void __set_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr)
{
__le32 *addr = get_dnode_addr(dn->inode, dn->node_page);
f2fs: enhance on-disk inode structure scalability This patch add new flag F2FS_EXTRA_ATTR storing in inode.i_inline to indicate that on-disk structure of current inode is extended. In order to extend, we changed the inode structure a bit: Original one: struct f2fs_inode { ... struct f2fs_extent i_ext; __le32 i_addr[DEF_ADDRS_PER_INODE]; __le32 i_nid[DEF_NIDS_PER_INODE]; } Extended one: struct f2fs_inode { ... struct f2fs_extent i_ext; union { struct { __le16 i_extra_isize; __le16 i_padding; __le32 i_extra_end[0]; }; __le32 i_addr[DEF_ADDRS_PER_INODE]; }; __le32 i_nid[DEF_NIDS_PER_INODE]; } Once F2FS_EXTRA_ATTR is set, we will steal four bytes in the head of i_addr field for storing i_extra_isize and i_padding. with i_extra_isize, we can calculate actual size of reserved space in i_addr, available attribute fields included in total extra attribute fields for current inode can be described as below: +--------------------+ | .i_mode | | ... | | .i_ext | +--------------------+ | .i_extra_isize |-----+ | .i_padding | | | .i_prjid | | | .i_atime_extra | | | .i_ctime_extra | | | .i_mtime_extra |<----+ | .i_inode_cs |<----- store blkaddr/inline from here | .i_xattr_cs | | ... | +--------------------+ | | | block address | | | +--------------------+ | .i_nid | +--------------------+ | node_footer | | (nid, ino, offset) | +--------------------+ Hence, with this patch, we would enhance scalability of f2fs inode for storing more newly added attribute. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2017-07-18 16:19:06 +00:00
dn->data_blkaddr = blkaddr;
addr[dn->ofs_in_node] = cpu_to_le32(dn->data_blkaddr);
}
/*
* Lock ordering for the change of data block address:
* ->data_page
* ->node_page
* update block addresses in the node page
*/
void f2fs_set_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr)
{
f2fs_wait_on_page_writeback(dn->node_page, NODE, true, true);
__set_data_blkaddr(dn, blkaddr);
if (set_page_dirty(dn->node_page))
dn->node_changed = true;
}
void f2fs_update_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr)
{
f2fs_set_data_blkaddr(dn, blkaddr);
f2fs_update_read_extent_cache(dn);
}
/* dn->ofs_in_node will be returned with up-to-date last block pointer */
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
int f2fs_reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
int err;
if (!count)
return 0;
if (unlikely(is_inode_flag_set(dn->inode, FI_NO_ALLOC)))
return -EPERM;
err = inc_valid_block_count(sbi, dn->inode, &count, true);
if (unlikely(err))
return err;
trace_f2fs_reserve_new_blocks(dn->inode, dn->nid,
dn->ofs_in_node, count);
f2fs_wait_on_page_writeback(dn->node_page, NODE, true, true);
for (; count > 0; dn->ofs_in_node++) {
block_t blkaddr = f2fs_data_blkaddr(dn);
if (blkaddr == NULL_ADDR) {
__set_data_blkaddr(dn, NEW_ADDR);
count--;
}
}
if (set_page_dirty(dn->node_page))
dn->node_changed = true;
return 0;
}
/* Should keep dn->ofs_in_node unchanged */
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
int f2fs_reserve_new_block(struct dnode_of_data *dn)
{
unsigned int ofs_in_node = dn->ofs_in_node;
int ret;
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
ret = f2fs_reserve_new_blocks(dn, 1);
dn->ofs_in_node = ofs_in_node;
return ret;
}
int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index)
{
bool need_put = dn->inode_page ? false : true;
int err;
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
err = f2fs_get_dnode_of_data(dn, index, ALLOC_NODE);
if (err)
return err;
if (dn->data_blkaddr == NULL_ADDR)
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
err = f2fs_reserve_new_block(dn);
if (err || need_put)
f2fs_put_dnode(dn);
return err;
}
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index,
f2fs: optimize iteration over sparse directories Wei Chen reports a kernel bug as blew: INFO: task syz-executor.0:29056 blocked for more than 143 seconds. Not tainted 5.15.0-rc5 #1 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. task:syz-executor.0 state:D stack:14632 pid:29056 ppid: 6574 flags:0x00000004 Call Trace: __schedule+0x4a1/0x1720 schedule+0x36/0xe0 rwsem_down_write_slowpath+0x322/0x7a0 fscrypt_ioctl_set_policy+0x11f/0x2a0 __f2fs_ioctl+0x1a9f/0x5780 f2fs_ioctl+0x89/0x3a0 __x64_sys_ioctl+0xe8/0x140 do_syscall_64+0x34/0xb0 entry_SYSCALL_64_after_hwframe+0x44/0xae Eric did some investigation on this issue, quoted from reply of Eric: "Well, the quality of this bug report has a lot to be desired (not on upstream kernel, reproducer is full of totally irrelevant stuff, not sent to the mailing list of the filesystem whose disk image is being fuzzed, etc.). But what is going on is that f2fs_empty_dir() doesn't consider the case of a directory with an extremely large i_size on a malicious disk image. Specifically, the reproducer mounts an f2fs image with a directory that has an i_size of 14814520042850357248, then calls FS_IOC_SET_ENCRYPTION_POLICY on it. That results in a call to f2fs_empty_dir() to check whether the directory is empty. f2fs_empty_dir() then iterates through all 3616826182336513 blocks the directory allegedly contains to check whether any contain anything. i_rwsem is held during this, so anything else that tries to take it will hang." In order to solve this issue, let's use f2fs_get_next_page_offset() to speed up iteration by skipping holes for all below functions: - f2fs_empty_dir - f2fs_readdir - find_in_level The way why we can speed up iteration was described in 'commit 3cf4574705b4 ("f2fs: introduce get_next_page_offset to speed up SEEK_DATA")'. Meanwhile, in f2fs_empty_dir(), let's use f2fs_find_data_page() instead f2fs_get_lock_data_page(), due to i_rwsem was held in caller of f2fs_empty_dir(), there shouldn't be any races, so it's fine to not lock dentry page during lookuping dirents in the page. Link: https://lore.kernel.org/lkml/536944df-a0ae-1dd8-148f-510b476e1347@kernel.org/T/ Reported-by: Wei Chen <harperchen1110@gmail.com> Cc: Eric Biggers <ebiggers@google.com> Signed-off-by: Chao Yu <chao@kernel.org> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2022-11-08 14:33:21 +00:00
blk_opf_t op_flags, bool for_write,
pgoff_t *next_pgofs)
{
struct address_space *mapping = inode->i_mapping;
struct dnode_of_data dn;
struct page *page;
int err;
page = f2fs_grab_cache_page(mapping, index, for_write);
if (!page)
return ERR_PTR(-ENOMEM);
if (f2fs_lookup_read_extent_cache_block(inode, index,
&dn.data_blkaddr)) {
f2fs: introduce DATA_GENERIC_ENHANCE Previously, f2fs_is_valid_blkaddr(, blkaddr, DATA_GENERIC) will check whether @blkaddr locates in main area or not. That check is weak, since the block address in range of main area can point to the address which is not valid in segment info table, and we can not detect such condition, we may suffer worse corruption as system continues running. So this patch introduce DATA_GENERIC_ENHANCE to enhance the sanity check which trigger SIT bitmap check rather than only range check. This patch did below changes as wel: - set SBI_NEED_FSCK in f2fs_is_valid_blkaddr(). - get rid of is_valid_data_blkaddr() to avoid panic if blkaddr is invalid. - introduce verify_fio_blkaddr() to wrap fio {new,old}_blkaddr validation check. - spread blkaddr check in: * f2fs_get_node_info() * __read_out_blkaddrs() * f2fs_submit_page_read() * ra_data_block() * do_recover_data() This patch can fix bug reported from bugzilla below: https://bugzilla.kernel.org/show_bug.cgi?id=203215 https://bugzilla.kernel.org/show_bug.cgi?id=203223 https://bugzilla.kernel.org/show_bug.cgi?id=203231 https://bugzilla.kernel.org/show_bug.cgi?id=203235 https://bugzilla.kernel.org/show_bug.cgi?id=203241 = Update by Jaegeuk Kim = DATA_GENERIC_ENHANCE enhanced to validate block addresses on read/write paths. But, xfstest/generic/446 compalins some generated kernel messages saying invalid bitmap was detected when reading a block. The reaons is, when we get the block addresses from extent_cache, there is no lock to synchronize it from truncating the blocks in parallel. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-04-15 07:26:32 +00:00
if (!f2fs_is_valid_blkaddr(F2FS_I_SB(inode), dn.data_blkaddr,
DATA_GENERIC_ENHANCE_READ)) {
err = -EFSCORRUPTED;
f2fs: introduce DATA_GENERIC_ENHANCE Previously, f2fs_is_valid_blkaddr(, blkaddr, DATA_GENERIC) will check whether @blkaddr locates in main area or not. That check is weak, since the block address in range of main area can point to the address which is not valid in segment info table, and we can not detect such condition, we may suffer worse corruption as system continues running. So this patch introduce DATA_GENERIC_ENHANCE to enhance the sanity check which trigger SIT bitmap check rather than only range check. This patch did below changes as wel: - set SBI_NEED_FSCK in f2fs_is_valid_blkaddr(). - get rid of is_valid_data_blkaddr() to avoid panic if blkaddr is invalid. - introduce verify_fio_blkaddr() to wrap fio {new,old}_blkaddr validation check. - spread blkaddr check in: * f2fs_get_node_info() * __read_out_blkaddrs() * f2fs_submit_page_read() * ra_data_block() * do_recover_data() This patch can fix bug reported from bugzilla below: https://bugzilla.kernel.org/show_bug.cgi?id=203215 https://bugzilla.kernel.org/show_bug.cgi?id=203223 https://bugzilla.kernel.org/show_bug.cgi?id=203231 https://bugzilla.kernel.org/show_bug.cgi?id=203235 https://bugzilla.kernel.org/show_bug.cgi?id=203241 = Update by Jaegeuk Kim = DATA_GENERIC_ENHANCE enhanced to validate block addresses on read/write paths. But, xfstest/generic/446 compalins some generated kernel messages saying invalid bitmap was detected when reading a block. The reaons is, when we get the block addresses from extent_cache, there is no lock to synchronize it from truncating the blocks in parallel. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-04-15 07:26:32 +00:00
goto put_err;
}
goto got_it;
}
set_new_dnode(&dn, inode, NULL, NULL, 0);
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
err = f2fs_get_dnode_of_data(&dn, index, LOOKUP_NODE);
f2fs: optimize iteration over sparse directories Wei Chen reports a kernel bug as blew: INFO: task syz-executor.0:29056 blocked for more than 143 seconds. Not tainted 5.15.0-rc5 #1 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. task:syz-executor.0 state:D stack:14632 pid:29056 ppid: 6574 flags:0x00000004 Call Trace: __schedule+0x4a1/0x1720 schedule+0x36/0xe0 rwsem_down_write_slowpath+0x322/0x7a0 fscrypt_ioctl_set_policy+0x11f/0x2a0 __f2fs_ioctl+0x1a9f/0x5780 f2fs_ioctl+0x89/0x3a0 __x64_sys_ioctl+0xe8/0x140 do_syscall_64+0x34/0xb0 entry_SYSCALL_64_after_hwframe+0x44/0xae Eric did some investigation on this issue, quoted from reply of Eric: "Well, the quality of this bug report has a lot to be desired (not on upstream kernel, reproducer is full of totally irrelevant stuff, not sent to the mailing list of the filesystem whose disk image is being fuzzed, etc.). But what is going on is that f2fs_empty_dir() doesn't consider the case of a directory with an extremely large i_size on a malicious disk image. Specifically, the reproducer mounts an f2fs image with a directory that has an i_size of 14814520042850357248, then calls FS_IOC_SET_ENCRYPTION_POLICY on it. That results in a call to f2fs_empty_dir() to check whether the directory is empty. f2fs_empty_dir() then iterates through all 3616826182336513 blocks the directory allegedly contains to check whether any contain anything. i_rwsem is held during this, so anything else that tries to take it will hang." In order to solve this issue, let's use f2fs_get_next_page_offset() to speed up iteration by skipping holes for all below functions: - f2fs_empty_dir - f2fs_readdir - find_in_level The way why we can speed up iteration was described in 'commit 3cf4574705b4 ("f2fs: introduce get_next_page_offset to speed up SEEK_DATA")'. Meanwhile, in f2fs_empty_dir(), let's use f2fs_find_data_page() instead f2fs_get_lock_data_page(), due to i_rwsem was held in caller of f2fs_empty_dir(), there shouldn't be any races, so it's fine to not lock dentry page during lookuping dirents in the page. Link: https://lore.kernel.org/lkml/536944df-a0ae-1dd8-148f-510b476e1347@kernel.org/T/ Reported-by: Wei Chen <harperchen1110@gmail.com> Cc: Eric Biggers <ebiggers@google.com> Signed-off-by: Chao Yu <chao@kernel.org> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2022-11-08 14:33:21 +00:00
if (err) {
if (err == -ENOENT && next_pgofs)
*next_pgofs = f2fs_get_next_page_offset(&dn, index);
goto put_err;
f2fs: optimize iteration over sparse directories Wei Chen reports a kernel bug as blew: INFO: task syz-executor.0:29056 blocked for more than 143 seconds. Not tainted 5.15.0-rc5 #1 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. task:syz-executor.0 state:D stack:14632 pid:29056 ppid: 6574 flags:0x00000004 Call Trace: __schedule+0x4a1/0x1720 schedule+0x36/0xe0 rwsem_down_write_slowpath+0x322/0x7a0 fscrypt_ioctl_set_policy+0x11f/0x2a0 __f2fs_ioctl+0x1a9f/0x5780 f2fs_ioctl+0x89/0x3a0 __x64_sys_ioctl+0xe8/0x140 do_syscall_64+0x34/0xb0 entry_SYSCALL_64_after_hwframe+0x44/0xae Eric did some investigation on this issue, quoted from reply of Eric: "Well, the quality of this bug report has a lot to be desired (not on upstream kernel, reproducer is full of totally irrelevant stuff, not sent to the mailing list of the filesystem whose disk image is being fuzzed, etc.). But what is going on is that f2fs_empty_dir() doesn't consider the case of a directory with an extremely large i_size on a malicious disk image. Specifically, the reproducer mounts an f2fs image with a directory that has an i_size of 14814520042850357248, then calls FS_IOC_SET_ENCRYPTION_POLICY on it. That results in a call to f2fs_empty_dir() to check whether the directory is empty. f2fs_empty_dir() then iterates through all 3616826182336513 blocks the directory allegedly contains to check whether any contain anything. i_rwsem is held during this, so anything else that tries to take it will hang." In order to solve this issue, let's use f2fs_get_next_page_offset() to speed up iteration by skipping holes for all below functions: - f2fs_empty_dir - f2fs_readdir - find_in_level The way why we can speed up iteration was described in 'commit 3cf4574705b4 ("f2fs: introduce get_next_page_offset to speed up SEEK_DATA")'. Meanwhile, in f2fs_empty_dir(), let's use f2fs_find_data_page() instead f2fs_get_lock_data_page(), due to i_rwsem was held in caller of f2fs_empty_dir(), there shouldn't be any races, so it's fine to not lock dentry page during lookuping dirents in the page. Link: https://lore.kernel.org/lkml/536944df-a0ae-1dd8-148f-510b476e1347@kernel.org/T/ Reported-by: Wei Chen <harperchen1110@gmail.com> Cc: Eric Biggers <ebiggers@google.com> Signed-off-by: Chao Yu <chao@kernel.org> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2022-11-08 14:33:21 +00:00
}
f2fs_put_dnode(&dn);
if (unlikely(dn.data_blkaddr == NULL_ADDR)) {
err = -ENOENT;
f2fs: optimize iteration over sparse directories Wei Chen reports a kernel bug as blew: INFO: task syz-executor.0:29056 blocked for more than 143 seconds. Not tainted 5.15.0-rc5 #1 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. task:syz-executor.0 state:D stack:14632 pid:29056 ppid: 6574 flags:0x00000004 Call Trace: __schedule+0x4a1/0x1720 schedule+0x36/0xe0 rwsem_down_write_slowpath+0x322/0x7a0 fscrypt_ioctl_set_policy+0x11f/0x2a0 __f2fs_ioctl+0x1a9f/0x5780 f2fs_ioctl+0x89/0x3a0 __x64_sys_ioctl+0xe8/0x140 do_syscall_64+0x34/0xb0 entry_SYSCALL_64_after_hwframe+0x44/0xae Eric did some investigation on this issue, quoted from reply of Eric: "Well, the quality of this bug report has a lot to be desired (not on upstream kernel, reproducer is full of totally irrelevant stuff, not sent to the mailing list of the filesystem whose disk image is being fuzzed, etc.). But what is going on is that f2fs_empty_dir() doesn't consider the case of a directory with an extremely large i_size on a malicious disk image. Specifically, the reproducer mounts an f2fs image with a directory that has an i_size of 14814520042850357248, then calls FS_IOC_SET_ENCRYPTION_POLICY on it. That results in a call to f2fs_empty_dir() to check whether the directory is empty. f2fs_empty_dir() then iterates through all 3616826182336513 blocks the directory allegedly contains to check whether any contain anything. i_rwsem is held during this, so anything else that tries to take it will hang." In order to solve this issue, let's use f2fs_get_next_page_offset() to speed up iteration by skipping holes for all below functions: - f2fs_empty_dir - f2fs_readdir - find_in_level The way why we can speed up iteration was described in 'commit 3cf4574705b4 ("f2fs: introduce get_next_page_offset to speed up SEEK_DATA")'. Meanwhile, in f2fs_empty_dir(), let's use f2fs_find_data_page() instead f2fs_get_lock_data_page(), due to i_rwsem was held in caller of f2fs_empty_dir(), there shouldn't be any races, so it's fine to not lock dentry page during lookuping dirents in the page. Link: https://lore.kernel.org/lkml/536944df-a0ae-1dd8-148f-510b476e1347@kernel.org/T/ Reported-by: Wei Chen <harperchen1110@gmail.com> Cc: Eric Biggers <ebiggers@google.com> Signed-off-by: Chao Yu <chao@kernel.org> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2022-11-08 14:33:21 +00:00
if (next_pgofs)
*next_pgofs = index + 1;
goto put_err;
}
f2fs: introduce DATA_GENERIC_ENHANCE Previously, f2fs_is_valid_blkaddr(, blkaddr, DATA_GENERIC) will check whether @blkaddr locates in main area or not. That check is weak, since the block address in range of main area can point to the address which is not valid in segment info table, and we can not detect such condition, we may suffer worse corruption as system continues running. So this patch introduce DATA_GENERIC_ENHANCE to enhance the sanity check which trigger SIT bitmap check rather than only range check. This patch did below changes as wel: - set SBI_NEED_FSCK in f2fs_is_valid_blkaddr(). - get rid of is_valid_data_blkaddr() to avoid panic if blkaddr is invalid. - introduce verify_fio_blkaddr() to wrap fio {new,old}_blkaddr validation check. - spread blkaddr check in: * f2fs_get_node_info() * __read_out_blkaddrs() * f2fs_submit_page_read() * ra_data_block() * do_recover_data() This patch can fix bug reported from bugzilla below: https://bugzilla.kernel.org/show_bug.cgi?id=203215 https://bugzilla.kernel.org/show_bug.cgi?id=203223 https://bugzilla.kernel.org/show_bug.cgi?id=203231 https://bugzilla.kernel.org/show_bug.cgi?id=203235 https://bugzilla.kernel.org/show_bug.cgi?id=203241 = Update by Jaegeuk Kim = DATA_GENERIC_ENHANCE enhanced to validate block addresses on read/write paths. But, xfstest/generic/446 compalins some generated kernel messages saying invalid bitmap was detected when reading a block. The reaons is, when we get the block addresses from extent_cache, there is no lock to synchronize it from truncating the blocks in parallel. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-04-15 07:26:32 +00:00
if (dn.data_blkaddr != NEW_ADDR &&
!f2fs_is_valid_blkaddr(F2FS_I_SB(inode),
dn.data_blkaddr,
DATA_GENERIC_ENHANCE)) {
err = -EFSCORRUPTED;
f2fs: introduce DATA_GENERIC_ENHANCE Previously, f2fs_is_valid_blkaddr(, blkaddr, DATA_GENERIC) will check whether @blkaddr locates in main area or not. That check is weak, since the block address in range of main area can point to the address which is not valid in segment info table, and we can not detect such condition, we may suffer worse corruption as system continues running. So this patch introduce DATA_GENERIC_ENHANCE to enhance the sanity check which trigger SIT bitmap check rather than only range check. This patch did below changes as wel: - set SBI_NEED_FSCK in f2fs_is_valid_blkaddr(). - get rid of is_valid_data_blkaddr() to avoid panic if blkaddr is invalid. - introduce verify_fio_blkaddr() to wrap fio {new,old}_blkaddr validation check. - spread blkaddr check in: * f2fs_get_node_info() * __read_out_blkaddrs() * f2fs_submit_page_read() * ra_data_block() * do_recover_data() This patch can fix bug reported from bugzilla below: https://bugzilla.kernel.org/show_bug.cgi?id=203215 https://bugzilla.kernel.org/show_bug.cgi?id=203223 https://bugzilla.kernel.org/show_bug.cgi?id=203231 https://bugzilla.kernel.org/show_bug.cgi?id=203235 https://bugzilla.kernel.org/show_bug.cgi?id=203241 = Update by Jaegeuk Kim = DATA_GENERIC_ENHANCE enhanced to validate block addresses on read/write paths. But, xfstest/generic/446 compalins some generated kernel messages saying invalid bitmap was detected when reading a block. The reaons is, when we get the block addresses from extent_cache, there is no lock to synchronize it from truncating the blocks in parallel. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-04-15 07:26:32 +00:00
goto put_err;
}
got_it:
if (PageUptodate(page)) {
unlock_page(page);
return page;
}
/*
* A new dentry page is allocated but not able to be written, since its
* new inode page couldn't be allocated due to -ENOSPC.
* In such the case, its blkaddr can be remained as NEW_ADDR.
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
* see, f2fs_add_link -> f2fs_get_new_data_page ->
* f2fs_init_inode_metadata.
*/
if (dn.data_blkaddr == NEW_ADDR) {
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 12:29:47 +00:00
zero_user_segment(page, 0, PAGE_SIZE);
if (!PageUptodate(page))
SetPageUptodate(page);
unlock_page(page);
return page;
}
err = f2fs_submit_page_read(inode, page, dn.data_blkaddr,
op_flags, for_write);
if (err)
goto put_err;
return page;
put_err:
f2fs_put_page(page, 1);
return ERR_PTR(err);
}
f2fs: optimize iteration over sparse directories Wei Chen reports a kernel bug as blew: INFO: task syz-executor.0:29056 blocked for more than 143 seconds. Not tainted 5.15.0-rc5 #1 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. task:syz-executor.0 state:D stack:14632 pid:29056 ppid: 6574 flags:0x00000004 Call Trace: __schedule+0x4a1/0x1720 schedule+0x36/0xe0 rwsem_down_write_slowpath+0x322/0x7a0 fscrypt_ioctl_set_policy+0x11f/0x2a0 __f2fs_ioctl+0x1a9f/0x5780 f2fs_ioctl+0x89/0x3a0 __x64_sys_ioctl+0xe8/0x140 do_syscall_64+0x34/0xb0 entry_SYSCALL_64_after_hwframe+0x44/0xae Eric did some investigation on this issue, quoted from reply of Eric: "Well, the quality of this bug report has a lot to be desired (not on upstream kernel, reproducer is full of totally irrelevant stuff, not sent to the mailing list of the filesystem whose disk image is being fuzzed, etc.). But what is going on is that f2fs_empty_dir() doesn't consider the case of a directory with an extremely large i_size on a malicious disk image. Specifically, the reproducer mounts an f2fs image with a directory that has an i_size of 14814520042850357248, then calls FS_IOC_SET_ENCRYPTION_POLICY on it. That results in a call to f2fs_empty_dir() to check whether the directory is empty. f2fs_empty_dir() then iterates through all 3616826182336513 blocks the directory allegedly contains to check whether any contain anything. i_rwsem is held during this, so anything else that tries to take it will hang." In order to solve this issue, let's use f2fs_get_next_page_offset() to speed up iteration by skipping holes for all below functions: - f2fs_empty_dir - f2fs_readdir - find_in_level The way why we can speed up iteration was described in 'commit 3cf4574705b4 ("f2fs: introduce get_next_page_offset to speed up SEEK_DATA")'. Meanwhile, in f2fs_empty_dir(), let's use f2fs_find_data_page() instead f2fs_get_lock_data_page(), due to i_rwsem was held in caller of f2fs_empty_dir(), there shouldn't be any races, so it's fine to not lock dentry page during lookuping dirents in the page. Link: https://lore.kernel.org/lkml/536944df-a0ae-1dd8-148f-510b476e1347@kernel.org/T/ Reported-by: Wei Chen <harperchen1110@gmail.com> Cc: Eric Biggers <ebiggers@google.com> Signed-off-by: Chao Yu <chao@kernel.org> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2022-11-08 14:33:21 +00:00
struct page *f2fs_find_data_page(struct inode *inode, pgoff_t index,
pgoff_t *next_pgofs)
{
struct address_space *mapping = inode->i_mapping;
struct page *page;
page = find_get_page(mapping, index);
if (page && PageUptodate(page))
return page;
f2fs_put_page(page, 0);
f2fs: optimize iteration over sparse directories Wei Chen reports a kernel bug as blew: INFO: task syz-executor.0:29056 blocked for more than 143 seconds. Not tainted 5.15.0-rc5 #1 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. task:syz-executor.0 state:D stack:14632 pid:29056 ppid: 6574 flags:0x00000004 Call Trace: __schedule+0x4a1/0x1720 schedule+0x36/0xe0 rwsem_down_write_slowpath+0x322/0x7a0 fscrypt_ioctl_set_policy+0x11f/0x2a0 __f2fs_ioctl+0x1a9f/0x5780 f2fs_ioctl+0x89/0x3a0 __x64_sys_ioctl+0xe8/0x140 do_syscall_64+0x34/0xb0 entry_SYSCALL_64_after_hwframe+0x44/0xae Eric did some investigation on this issue, quoted from reply of Eric: "Well, the quality of this bug report has a lot to be desired (not on upstream kernel, reproducer is full of totally irrelevant stuff, not sent to the mailing list of the filesystem whose disk image is being fuzzed, etc.). But what is going on is that f2fs_empty_dir() doesn't consider the case of a directory with an extremely large i_size on a malicious disk image. Specifically, the reproducer mounts an f2fs image with a directory that has an i_size of 14814520042850357248, then calls FS_IOC_SET_ENCRYPTION_POLICY on it. That results in a call to f2fs_empty_dir() to check whether the directory is empty. f2fs_empty_dir() then iterates through all 3616826182336513 blocks the directory allegedly contains to check whether any contain anything. i_rwsem is held during this, so anything else that tries to take it will hang." In order to solve this issue, let's use f2fs_get_next_page_offset() to speed up iteration by skipping holes for all below functions: - f2fs_empty_dir - f2fs_readdir - find_in_level The way why we can speed up iteration was described in 'commit 3cf4574705b4 ("f2fs: introduce get_next_page_offset to speed up SEEK_DATA")'. Meanwhile, in f2fs_empty_dir(), let's use f2fs_find_data_page() instead f2fs_get_lock_data_page(), due to i_rwsem was held in caller of f2fs_empty_dir(), there shouldn't be any races, so it's fine to not lock dentry page during lookuping dirents in the page. Link: https://lore.kernel.org/lkml/536944df-a0ae-1dd8-148f-510b476e1347@kernel.org/T/ Reported-by: Wei Chen <harperchen1110@gmail.com> Cc: Eric Biggers <ebiggers@google.com> Signed-off-by: Chao Yu <chao@kernel.org> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2022-11-08 14:33:21 +00:00
page = f2fs_get_read_data_page(inode, index, 0, false, next_pgofs);
if (IS_ERR(page))
return page;
if (PageUptodate(page))
return page;
wait_on_page_locked(page);
if (unlikely(!PageUptodate(page))) {
f2fs_put_page(page, 0);
return ERR_PTR(-EIO);
}
return page;
}
/*
* If it tries to access a hole, return an error.
* Because, the callers, functions in dir.c and GC, should be able to know
* whether this page exists or not.
*/
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
struct page *f2fs_get_lock_data_page(struct inode *inode, pgoff_t index,
bool for_write)
{
struct address_space *mapping = inode->i_mapping;
struct page *page;
f2fs: optimize iteration over sparse directories Wei Chen reports a kernel bug as blew: INFO: task syz-executor.0:29056 blocked for more than 143 seconds. Not tainted 5.15.0-rc5 #1 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. task:syz-executor.0 state:D stack:14632 pid:29056 ppid: 6574 flags:0x00000004 Call Trace: __schedule+0x4a1/0x1720 schedule+0x36/0xe0 rwsem_down_write_slowpath+0x322/0x7a0 fscrypt_ioctl_set_policy+0x11f/0x2a0 __f2fs_ioctl+0x1a9f/0x5780 f2fs_ioctl+0x89/0x3a0 __x64_sys_ioctl+0xe8/0x140 do_syscall_64+0x34/0xb0 entry_SYSCALL_64_after_hwframe+0x44/0xae Eric did some investigation on this issue, quoted from reply of Eric: "Well, the quality of this bug report has a lot to be desired (not on upstream kernel, reproducer is full of totally irrelevant stuff, not sent to the mailing list of the filesystem whose disk image is being fuzzed, etc.). But what is going on is that f2fs_empty_dir() doesn't consider the case of a directory with an extremely large i_size on a malicious disk image. Specifically, the reproducer mounts an f2fs image with a directory that has an i_size of 14814520042850357248, then calls FS_IOC_SET_ENCRYPTION_POLICY on it. That results in a call to f2fs_empty_dir() to check whether the directory is empty. f2fs_empty_dir() then iterates through all 3616826182336513 blocks the directory allegedly contains to check whether any contain anything. i_rwsem is held during this, so anything else that tries to take it will hang." In order to solve this issue, let's use f2fs_get_next_page_offset() to speed up iteration by skipping holes for all below functions: - f2fs_empty_dir - f2fs_readdir - find_in_level The way why we can speed up iteration was described in 'commit 3cf4574705b4 ("f2fs: introduce get_next_page_offset to speed up SEEK_DATA")'. Meanwhile, in f2fs_empty_dir(), let's use f2fs_find_data_page() instead f2fs_get_lock_data_page(), due to i_rwsem was held in caller of f2fs_empty_dir(), there shouldn't be any races, so it's fine to not lock dentry page during lookuping dirents in the page. Link: https://lore.kernel.org/lkml/536944df-a0ae-1dd8-148f-510b476e1347@kernel.org/T/ Reported-by: Wei Chen <harperchen1110@gmail.com> Cc: Eric Biggers <ebiggers@google.com> Signed-off-by: Chao Yu <chao@kernel.org> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2022-11-08 14:33:21 +00:00
page = f2fs_get_read_data_page(inode, index, 0, for_write, NULL);
if (IS_ERR(page))
return page;
/* wait for read completion */
lock_page(page);
if (unlikely(page->mapping != mapping || !PageUptodate(page))) {
f2fs_put_page(page, 1);
return ERR_PTR(-EIO);
}
return page;
}
/*
* Caller ensures that this data page is never allocated.
* A new zero-filled data page is allocated in the page cache.
f2fs: introduce a new global lock scheme In the previous version, f2fs uses global locks according to the usage types, such as directory operations, block allocation, block write, and so on. Reference the following lock types in f2fs.h. enum lock_type { RENAME, /* for renaming operations */ DENTRY_OPS, /* for directory operations */ DATA_WRITE, /* for data write */ DATA_NEW, /* for data allocation */ DATA_TRUNC, /* for data truncate */ NODE_NEW, /* for node allocation */ NODE_TRUNC, /* for node truncate */ NODE_WRITE, /* for node write */ NR_LOCK_TYPE, }; In that case, we lose the performance under the multi-threading environment, since every types of operations must be conducted one at a time. In order to address the problem, let's share the locks globally with a mutex array regardless of any types. So, let users grab a mutex and perform their jobs in parallel as much as possbile. For this, I propose a new global lock scheme as follows. 0. Data structure - f2fs_sb_info -> mutex_lock[NR_GLOBAL_LOCKS] - f2fs_sb_info -> node_write 1. mutex_lock_op(sbi) - try to get an avaiable lock from the array. - returns the index of the gottern lock variable. 2. mutex_unlock_op(sbi, index of the lock) - unlock the given index of the lock. 3. mutex_lock_all(sbi) - grab all the locks in the array before the checkpoint. 4. mutex_unlock_all(sbi) - release all the locks in the array after checkpoint. 5. block_operations() - call mutex_lock_all() - sync_dirty_dir_inodes() - grab node_write - sync_node_pages() Note that, the pairs of mutex_lock_op()/mutex_unlock_op() and mutex_lock_all()/mutex_unlock_all() should be used together. Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
2012-11-22 07:21:29 +00:00
*
* Also, caller should grab and release a rwsem by calling f2fs_lock_op() and
* f2fs_unlock_op().
* Note that, ipage is set only by make_empty_dir, and if any error occur,
* ipage should be released by this function.
*/
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
struct page *f2fs_get_new_data_page(struct inode *inode,
struct page *ipage, pgoff_t index, bool new_i_size)
{
struct address_space *mapping = inode->i_mapping;
struct page *page;
struct dnode_of_data dn;
int err;
page = f2fs_grab_cache_page(mapping, index, true);
if (!page) {
/*
* before exiting, we should make sure ipage will be released
* if any error occur.
*/
f2fs_put_page(ipage, 1);
return ERR_PTR(-ENOMEM);
}
set_new_dnode(&dn, inode, ipage, NULL, 0);
err = f2fs_reserve_block(&dn, index);
if (err) {
f2fs_put_page(page, 1);
return ERR_PTR(err);
}
if (!ipage)
f2fs_put_dnode(&dn);
if (PageUptodate(page))
goto got_it;
if (dn.data_blkaddr == NEW_ADDR) {
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 12:29:47 +00:00
zero_user_segment(page, 0, PAGE_SIZE);
if (!PageUptodate(page))
SetPageUptodate(page);
} else {
f2fs_put_page(page, 1);
/* if ipage exists, blkaddr should be NEW_ADDR */
f2fs_bug_on(F2FS_I_SB(inode), ipage);
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
page = f2fs_get_lock_data_page(inode, index, true);
if (IS_ERR(page))
return page;
}
got_it:
if (new_i_size && i_size_read(inode) <
((loff_t)(index + 1) << PAGE_SHIFT))
f2fs_i_size_write(inode, ((loff_t)(index + 1) << PAGE_SHIFT));
return page;
}
static int __allocate_data_block(struct dnode_of_data *dn, int seg_type)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
struct f2fs_summary sum;
struct node_info ni;
f2fs: readahead encrypted block during GC During GC, for each encrypted block, we will read block synchronously into meta page, and then submit it into current cold data log area. So this block read model with 4k granularity can make poor performance, like migrating non-encrypted block, let's readahead encrypted block as well to improve migration performance. To implement this, we choose meta page that its index is old block address of the encrypted block, and readahead ciphertext into this page, later, if readaheaded page is still updated, we will load its data into target meta page, and submit the write IO. Note that for OPU, truncation, deletion, we need to invalid meta page after we invalid old block address, to make sure we won't load invalid data from target meta page during encrypted block migration. for ((i = 0; i < 1000; i++)) do { xfs_io -f /mnt/f2fs/dir/$i -c "pwrite 0 128k" -c "fsync"; } done for ((i = 0; i < 1000; i+=2)) do { rm /mnt/f2fs/dir/$i; } done ret = ioctl(fd, F2FS_IOC_GARBAGE_COLLECT, 0); Before: gc-6549 [001] d..1 214682.212797: block_rq_insert: 8,32 RA 32768 () 786400 + 64 [gc] gc-6549 [001] d..1 214682.212802: block_unplug: [gc] 1 gc-6549 [001] .... 214682.213892: block_bio_queue: 8,32 R 67494144 + 8 [gc] gc-6549 [001] .... 214682.213899: block_getrq: 8,32 R 67494144 + 8 [gc] gc-6549 [001] .... 214682.213902: block_plug: [gc] gc-6549 [001] d..1 214682.213905: block_rq_insert: 8,32 R 4096 () 67494144 + 8 [gc] gc-6549 [001] d..1 214682.213908: block_unplug: [gc] 1 gc-6549 [001] .... 214682.226405: block_bio_queue: 8,32 R 67494152 + 8 [gc] gc-6549 [001] .... 214682.226412: block_getrq: 8,32 R 67494152 + 8 [gc] gc-6549 [001] .... 214682.226414: block_plug: [gc] gc-6549 [001] d..1 214682.226417: block_rq_insert: 8,32 R 4096 () 67494152 + 8 [gc] gc-6549 [001] d..1 214682.226420: block_unplug: [gc] 1 gc-6549 [001] .... 214682.226904: block_bio_queue: 8,32 R 67494160 + 8 [gc] gc-6549 [001] .... 214682.226910: block_getrq: 8,32 R 67494160 + 8 [gc] gc-6549 [001] .... 214682.226911: block_plug: [gc] gc-6549 [001] d..1 214682.226914: block_rq_insert: 8,32 R 4096 () 67494160 + 8 [gc] gc-6549 [001] d..1 214682.226916: block_unplug: [gc] 1 After: gc-5678 [003] .... 214327.025906: block_bio_queue: 8,32 R 67493824 + 8 [gc] gc-5678 [003] .... 214327.025908: block_bio_backmerge: 8,32 R 67493824 + 8 [gc] gc-5678 [003] .... 214327.025915: block_bio_queue: 8,32 R 67493832 + 8 [gc] gc-5678 [003] .... 214327.025917: block_bio_backmerge: 8,32 R 67493832 + 8 [gc] gc-5678 [003] .... 214327.025923: block_bio_queue: 8,32 R 67493840 + 8 [gc] gc-5678 [003] .... 214327.025925: block_bio_backmerge: 8,32 R 67493840 + 8 [gc] gc-5678 [003] .... 214327.025932: block_bio_queue: 8,32 R 67493848 + 8 [gc] gc-5678 [003] .... 214327.025934: block_bio_backmerge: 8,32 R 67493848 + 8 [gc] gc-5678 [003] .... 214327.025941: block_bio_queue: 8,32 R 67493856 + 8 [gc] gc-5678 [003] .... 214327.025943: block_bio_backmerge: 8,32 R 67493856 + 8 [gc] gc-5678 [003] .... 214327.025953: block_bio_queue: 8,32 R 67493864 + 8 [gc] gc-5678 [003] .... 214327.025955: block_bio_backmerge: 8,32 R 67493864 + 8 [gc] gc-5678 [003] .... 214327.025962: block_bio_queue: 8,32 R 67493872 + 8 [gc] gc-5678 [003] .... 214327.025964: block_bio_backmerge: 8,32 R 67493872 + 8 [gc] gc-5678 [003] .... 214327.025970: block_bio_queue: 8,32 R 67493880 + 8 [gc] gc-5678 [003] .... 214327.025972: block_bio_backmerge: 8,32 R 67493880 + 8 [gc] gc-5678 [003] .... 214327.026000: block_bio_queue: 8,32 WS 34123776 + 2048 [gc] gc-5678 [003] .... 214327.026019: block_getrq: 8,32 WS 34123776 + 2048 [gc] gc-5678 [003] d..1 214327.026021: block_rq_insert: 8,32 R 131072 () 67493632 + 256 [gc] gc-5678 [003] d..1 214327.026023: block_unplug: [gc] 1 gc-5678 [003] d..1 214327.026026: block_rq_issue: 8,32 R 131072 () 67493632 + 256 [gc] gc-5678 [003] .... 214327.026046: block_plug: [gc] Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-08-14 14:37:25 +00:00
block_t old_blkaddr;
blkcnt_t count = 1;
int err;
if (unlikely(is_inode_flag_set(dn->inode, FI_NO_ALLOC)))
return -EPERM;
err = f2fs_get_node_info(sbi, dn->nid, &ni, false);
if (err)
return err;
dn->data_blkaddr = f2fs_data_blkaddr(dn);
if (dn->data_blkaddr == NULL_ADDR) {
err = inc_valid_block_count(sbi, dn->inode, &count, true);
if (unlikely(err))
return err;
}
set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version);
f2fs: readahead encrypted block during GC During GC, for each encrypted block, we will read block synchronously into meta page, and then submit it into current cold data log area. So this block read model with 4k granularity can make poor performance, like migrating non-encrypted block, let's readahead encrypted block as well to improve migration performance. To implement this, we choose meta page that its index is old block address of the encrypted block, and readahead ciphertext into this page, later, if readaheaded page is still updated, we will load its data into target meta page, and submit the write IO. Note that for OPU, truncation, deletion, we need to invalid meta page after we invalid old block address, to make sure we won't load invalid data from target meta page during encrypted block migration. for ((i = 0; i < 1000; i++)) do { xfs_io -f /mnt/f2fs/dir/$i -c "pwrite 0 128k" -c "fsync"; } done for ((i = 0; i < 1000; i+=2)) do { rm /mnt/f2fs/dir/$i; } done ret = ioctl(fd, F2FS_IOC_GARBAGE_COLLECT, 0); Before: gc-6549 [001] d..1 214682.212797: block_rq_insert: 8,32 RA 32768 () 786400 + 64 [gc] gc-6549 [001] d..1 214682.212802: block_unplug: [gc] 1 gc-6549 [001] .... 214682.213892: block_bio_queue: 8,32 R 67494144 + 8 [gc] gc-6549 [001] .... 214682.213899: block_getrq: 8,32 R 67494144 + 8 [gc] gc-6549 [001] .... 214682.213902: block_plug: [gc] gc-6549 [001] d..1 214682.213905: block_rq_insert: 8,32 R 4096 () 67494144 + 8 [gc] gc-6549 [001] d..1 214682.213908: block_unplug: [gc] 1 gc-6549 [001] .... 214682.226405: block_bio_queue: 8,32 R 67494152 + 8 [gc] gc-6549 [001] .... 214682.226412: block_getrq: 8,32 R 67494152 + 8 [gc] gc-6549 [001] .... 214682.226414: block_plug: [gc] gc-6549 [001] d..1 214682.226417: block_rq_insert: 8,32 R 4096 () 67494152 + 8 [gc] gc-6549 [001] d..1 214682.226420: block_unplug: [gc] 1 gc-6549 [001] .... 214682.226904: block_bio_queue: 8,32 R 67494160 + 8 [gc] gc-6549 [001] .... 214682.226910: block_getrq: 8,32 R 67494160 + 8 [gc] gc-6549 [001] .... 214682.226911: block_plug: [gc] gc-6549 [001] d..1 214682.226914: block_rq_insert: 8,32 R 4096 () 67494160 + 8 [gc] gc-6549 [001] d..1 214682.226916: block_unplug: [gc] 1 After: gc-5678 [003] .... 214327.025906: block_bio_queue: 8,32 R 67493824 + 8 [gc] gc-5678 [003] .... 214327.025908: block_bio_backmerge: 8,32 R 67493824 + 8 [gc] gc-5678 [003] .... 214327.025915: block_bio_queue: 8,32 R 67493832 + 8 [gc] gc-5678 [003] .... 214327.025917: block_bio_backmerge: 8,32 R 67493832 + 8 [gc] gc-5678 [003] .... 214327.025923: block_bio_queue: 8,32 R 67493840 + 8 [gc] gc-5678 [003] .... 214327.025925: block_bio_backmerge: 8,32 R 67493840 + 8 [gc] gc-5678 [003] .... 214327.025932: block_bio_queue: 8,32 R 67493848 + 8 [gc] gc-5678 [003] .... 214327.025934: block_bio_backmerge: 8,32 R 67493848 + 8 [gc] gc-5678 [003] .... 214327.025941: block_bio_queue: 8,32 R 67493856 + 8 [gc] gc-5678 [003] .... 214327.025943: block_bio_backmerge: 8,32 R 67493856 + 8 [gc] gc-5678 [003] .... 214327.025953: block_bio_queue: 8,32 R 67493864 + 8 [gc] gc-5678 [003] .... 214327.025955: block_bio_backmerge: 8,32 R 67493864 + 8 [gc] gc-5678 [003] .... 214327.025962: block_bio_queue: 8,32 R 67493872 + 8 [gc] gc-5678 [003] .... 214327.025964: block_bio_backmerge: 8,32 R 67493872 + 8 [gc] gc-5678 [003] .... 214327.025970: block_bio_queue: 8,32 R 67493880 + 8 [gc] gc-5678 [003] .... 214327.025972: block_bio_backmerge: 8,32 R 67493880 + 8 [gc] gc-5678 [003] .... 214327.026000: block_bio_queue: 8,32 WS 34123776 + 2048 [gc] gc-5678 [003] .... 214327.026019: block_getrq: 8,32 WS 34123776 + 2048 [gc] gc-5678 [003] d..1 214327.026021: block_rq_insert: 8,32 R 131072 () 67493632 + 256 [gc] gc-5678 [003] d..1 214327.026023: block_unplug: [gc] 1 gc-5678 [003] d..1 214327.026026: block_rq_issue: 8,32 R 131072 () 67493632 + 256 [gc] gc-5678 [003] .... 214327.026046: block_plug: [gc] Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-08-14 14:37:25 +00:00
old_blkaddr = dn->data_blkaddr;
err = f2fs_allocate_data_block(sbi, NULL, old_blkaddr,
&dn->data_blkaddr, &sum, seg_type, NULL);
if (err)
return err;
if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO)
f2fs_invalidate_internal_cache(sbi, old_blkaddr);
f2fs_update_data_blkaddr(dn, dn->data_blkaddr);
return 0;
}
static void f2fs_map_lock(struct f2fs_sb_info *sbi, int flag)
{
if (flag == F2FS_GET_BLOCK_PRE_AIO)
f2fs_down_read(&sbi->node_change);
else
f2fs_lock_op(sbi);
}
static void f2fs_map_unlock(struct f2fs_sb_info *sbi, int flag)
{
if (flag == F2FS_GET_BLOCK_PRE_AIO)
f2fs_up_read(&sbi->node_change);
else
f2fs_unlock_op(sbi);
}
int f2fs_get_block_locked(struct dnode_of_data *dn, pgoff_t index)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
int err = 0;
f2fs_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO);
if (!f2fs_lookup_read_extent_cache_block(dn->inode, index,
&dn->data_blkaddr))
err = f2fs_reserve_block(dn, index);
f2fs_map_unlock(sbi, F2FS_GET_BLOCK_PRE_AIO);
return err;
}
static int f2fs_map_no_dnode(struct inode *inode,
struct f2fs_map_blocks *map, struct dnode_of_data *dn,
pgoff_t pgoff)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
/*
* There is one exceptional case that read_node_page() may return
* -ENOENT due to filesystem has been shutdown or cp_error, return
* -EIO in that case.
*/
if (map->m_may_create &&
(is_sbi_flag_set(sbi, SBI_IS_SHUTDOWN) || f2fs_cp_error(sbi)))
return -EIO;
if (map->m_next_pgofs)
*map->m_next_pgofs = f2fs_get_next_page_offset(dn, pgoff);
if (map->m_next_extent)
*map->m_next_extent = f2fs_get_next_page_offset(dn, pgoff);
return 0;
}
static bool f2fs_map_blocks_cached(struct inode *inode,
struct f2fs_map_blocks *map, int flag)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
unsigned int maxblocks = map->m_len;
pgoff_t pgoff = (pgoff_t)map->m_lblk;
struct extent_info ei = {};
if (!f2fs_lookup_read_extent_cache(inode, pgoff, &ei))
return false;
map->m_pblk = ei.blk + pgoff - ei.fofs;
map->m_len = min((pgoff_t)maxblocks, ei.fofs + ei.len - pgoff);
map->m_flags = F2FS_MAP_MAPPED;
if (map->m_next_extent)
*map->m_next_extent = pgoff + map->m_len;
/* for hardware encryption, but to avoid potential issue in future */
if (flag == F2FS_GET_BLOCK_DIO)
f2fs_wait_on_block_writeback_range(inode,
map->m_pblk, map->m_len);
if (f2fs_allow_multi_device_dio(sbi, flag)) {
int bidx = f2fs_target_device_index(sbi, map->m_pblk);
struct f2fs_dev_info *dev = &sbi->devs[bidx];
map->m_bdev = dev->bdev;
map->m_pblk -= dev->start_blk;
map->m_len = min(map->m_len, dev->end_blk + 1 - map->m_pblk);
} else {
map->m_bdev = inode->i_sb->s_bdev;
}
return true;
}
static bool map_is_mergeable(struct f2fs_sb_info *sbi,
struct f2fs_map_blocks *map,
block_t blkaddr, int flag, int bidx,
int ofs)
{
if (map->m_multidev_dio && map->m_bdev != FDEV(bidx).bdev)
return false;
if (map->m_pblk != NEW_ADDR && blkaddr == (map->m_pblk + ofs))
return true;
if (map->m_pblk == NEW_ADDR && blkaddr == NEW_ADDR)
return true;
if (flag == F2FS_GET_BLOCK_PRE_DIO)
return true;
f2fs: support to map continuous holes or preallocated address This patch supports to map continuous holes or preallocated addresses to improve performace of lookuping mapping info during read DIO. [testcase 1] xfs_io -f /mnt/f2fs/hole -c "truncate 1m" -c "fsync" xfs_io -d /mnt/f2fs/hole -c "pread -b 1m 0 1m" [before] f2fs_direct_IO_enter: dev = (253,16), ino = 6 pos = 0 len = 1048576 ki_flags = 20000 ki_ioprio = 0 rw = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 0, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 1, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 2, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 3, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 4, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 5, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 6, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 7, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 8, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 9, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 10, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 11, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 12, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 13, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 14, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 15, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 16, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 ...... f2fs_direct_IO_exit: dev = (253,16), ino = 6 pos = 0 len = 1048576 rw = 0 ret = 1048576 [after] f2fs_direct_IO_enter: dev = (253,16), ino = 6 pos = 0 len = 1048576 ki_flags = 20000 ki_ioprio = 0 rw = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 0, start blkaddr = 0x0, len = 0x100, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_direct_IO_exit: dev = (253,16), ino = 6 pos = 0 len = 1048576 rw = 0 ret = 1048576 [testcase 2] xfs_io -f /mnt/f2fs/preallocated -c "falloc 0 1m" -c "fsync" xfs_io -d /mnt/f2fs/preallocated -c "pread -b 1m 0 1m" [before] f2fs_direct_IO_enter: dev = (253,16), ino = 11 pos = 0 len = 1048576 ki_flags = 20000 ki_ioprio = 0 rw = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 0, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 1, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 2, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 3, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 4, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 5, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 6, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 7, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 8, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 9, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 10, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 11, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 12, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 13, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 14, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 15, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 16, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 ...... f2fs_direct_IO_exit: dev = (253,16), ino = 11 pos = 0 len = 1048576 rw = 0 ret = 1048576 [after] f2fs_direct_IO_enter: dev = (253,16), ino = 11 pos = 0 len = 1048576 ki_flags = 20000 ki_ioprio = 0 rw = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 0, start blkaddr = 0xffffffff, len = 0x100, flags = 4, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_direct_IO_exit: dev = (253,16), ino = 11 pos = 0 len = 1048576 rw = 0 ret = 1048576 Signed-off-by: Chao Yu <chao@kernel.org> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2024-03-25 15:27:26 +00:00
if (flag == F2FS_GET_BLOCK_DIO &&
map->m_pblk == NULL_ADDR && blkaddr == NULL_ADDR)
return true;
return false;
}
/*
* f2fs_map_blocks() tries to find or build mapping relationship which
* maps continuous logical blocks to physical blocks, and return such
* info via f2fs_map_blocks structure.
*/
int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map, int flag)
{
unsigned int maxblocks = map->m_len;
struct dnode_of_data dn;
f2fs: fix to handle io error in ->direct_IO Here is a oops reported as following message when testing generic/019 of xfstest: ------------[ cut here ]------------ kernel BUG at /home/yuchao/git/f2fs-dev/segment.c:882! invalid opcode: 0000 [#1] SMP Modules linked in: zram lz4_compress lz4_decompress f2fs(O) ip6table_filter ip6_tables ebtable_nat ebtables nf_conntrack_ipv4 nf_def CPU: 2 PID: 25441 Comm: fio Tainted: G O 4.3.0-rc1+ #6 Hardware name: Hewlett-Packard HP Z220 CMT Workstation/1790, BIOS K51 v01.61 05/16/2013 task: ffff8803f4e85580 ti: ffff8803fd61c000 task.ti: ffff8803fd61c000 RIP: 0010:[<ffffffffa0784981>] [<ffffffffa0784981>] new_curseg+0x321/0x330 [f2fs] RSP: 0018:ffff8803fd61f918 EFLAGS: 00010246 RAX: 00000000000007ed RBX: 0000000000000224 RCX: 000000000000001f RDX: 0000000000000800 RSI: ffffffffffffffff RDI: ffff8803f56f4300 RBP: ffff8803fd61f978 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000024 R11: ffff8800d23bbd78 R12: ffff8800d0ef0000 R13: 0000000000000224 R14: 0000000000000000 R15: 0000000000000001 FS: 00007f827ff85700(0000) GS:ffff88041ea80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffffffffff600000 CR3: 00000003fef17000 CR4: 00000000001406e0 Stack: 000007ea00000002 0000000100000001 ffff8803f6456248 000007ed0000002b 0000000000000224 ffff880404d1aa20 ffff8803fd61f9c8 ffff8800d0ef0000 ffff8803f6456248 0000000000000001 00000000ffffffff ffffffffa078f358 Call Trace: [<ffffffffa0785b87>] allocate_segment_by_default+0x1a7/0x1f0 [f2fs] [<ffffffffa078322c>] allocate_data_block+0x17c/0x360 [f2fs] [<ffffffffa0779521>] __allocate_data_block+0x131/0x1d0 [f2fs] [<ffffffffa077a995>] f2fs_direct_IO+0x4b5/0x580 [f2fs] [<ffffffff811510ae>] generic_file_direct_write+0xae/0x160 [<ffffffff811518f5>] __generic_file_write_iter+0xd5/0x1f0 [<ffffffff81151e07>] generic_file_write_iter+0xf7/0x200 [<ffffffff81319e38>] ? apparmor_file_permission+0x18/0x20 [<ffffffffa0768480>] ? f2fs_fallocate+0x1190/0x1190 [f2fs] [<ffffffffa07684c6>] f2fs_file_write_iter+0x46/0x90 [f2fs] [<ffffffff8120b4fe>] aio_run_iocb+0x1ee/0x290 [<ffffffff81700f7e>] ? mutex_lock+0x1e/0x50 [<ffffffff8120a1d7>] ? aio_read_events+0x207/0x2b0 [<ffffffff8120b913>] do_io_submit+0x373/0x630 [<ffffffff8120a4f6>] ? SyS_io_getevents+0x56/0xb0 [<ffffffff8120bbe0>] SyS_io_submit+0x10/0x20 [<ffffffff81703857>] entry_SYSCALL_64_fastpath+0x12/0x6a Code: 45 c8 48 8b 78 10 e8 9f 23 bf e0 41 8b 8c 24 cc 03 00 00 89 c7 31 d2 89 c6 89 d8 29 df f7 f1 29 d1 39 cf 0f 83 be fd ff ff eb RIP [<ffffffffa0784981>] new_curseg+0x321/0x330 [f2fs] RSP <ffff8803fd61f918> ---[ end trace 2e577d7f711ddb86 ]--- The reason is that: in the test of generic/019, we will trigger a manmade IO error in block layer through debugfs, after that, prefree segment will no longer be freed, because we always skip doing gc or checkpoint when there occurs an IO error. Meanwhile fio with aio engine generated a large number of direct IOs, which continue allocating spaces in free segment until we run out of them, eventually, results in panic in new_curseg as no more free segment was found. So, this patch changes to return EIO in direct_IO for this condition. Signed-off-by: Chao Yu <chao2.yu@samsung.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2015-09-21 12:17:52 +00:00
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
f2fs: fix out-place-update DIO write In get_more_blocks(), we may override @create as below code: create = dio->op == REQ_OP_WRITE; if (dio->flags & DIO_SKIP_HOLES) { if (fs_startblk <= ((i_size_read(dio->inode) - 1) >> i_blkbits)) create = 0; } But in f2fs_map_blocks(), we only trigger f2fs_balance_fs() if @create is 1, so in LFS mode, dio overwrite under LFS mode can easily run out of free segments, result in below panic. Call Trace: allocate_segment_by_default+0xa8/0x270 [f2fs] f2fs_allocate_data_block+0x1ea/0x5c0 [f2fs] __allocate_data_block+0x306/0x480 [f2fs] f2fs_map_blocks+0x6f6/0x920 [f2fs] __get_data_block+0x4f/0xb0 [f2fs] get_data_block_dio_write+0x50/0x60 [f2fs] do_blockdev_direct_IO+0xcd5/0x21e0 __blockdev_direct_IO+0x3a/0x3c f2fs_direct_IO+0x1ff/0x4a0 [f2fs] generic_file_direct_write+0xd9/0x160 __generic_file_write_iter+0xbb/0x1e0 f2fs_file_write_iter+0xaf/0x220 [f2fs] __vfs_write+0xd0/0x130 vfs_write+0xb2/0x1b0 SyS_pwrite64+0x69/0xa0 ? vtime_user_exit+0x29/0x70 do_syscall_64+0x6e/0x160 entry_SYSCALL64_slow_path+0x25/0x25 RIP: new_curseg+0x36f/0x380 [f2fs] RSP: ffffac570393f7a8 So this patch introduces a parameter map.m_may_create to indicate that f2fs_map_blocks() is called from write or read path, which can give the right hint to let f2fs_map_blocks() trigger OPU allocation and call f2fs_balanc_fs() correctly. BTW, it disables physical address preallocation for direct IO in f2fs_preallocate_blocks, which is redundant to OPU allocation of f2fs_map_blocks. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-11-13 06:33:45 +00:00
int mode = map->m_may_create ? ALLOC_NODE : LOOKUP_NODE;
pgoff_t pgofs, end_offset, end;
int err = 0, ofs = 1;
unsigned int ofs_in_node, last_ofs_in_node;
blkcnt_t prealloc;
block_t blkaddr;
unsigned int start_pgofs;
int bidx = 0;
bool is_hole;
if (!maxblocks)
return 0;
if (!map->m_may_create && f2fs_map_blocks_cached(inode, map, flag))
goto out;
map->m_bdev = inode->i_sb->s_bdev;
map->m_multidev_dio =
f2fs_allow_multi_device_dio(F2FS_I_SB(inode), flag);
map->m_len = 0;
map->m_flags = 0;
/* it only supports block size == page size */
pgofs = (pgoff_t)map->m_lblk;
end = pgofs + maxblocks;
next_dnode:
f2fs: fix out-place-update DIO write In get_more_blocks(), we may override @create as below code: create = dio->op == REQ_OP_WRITE; if (dio->flags & DIO_SKIP_HOLES) { if (fs_startblk <= ((i_size_read(dio->inode) - 1) >> i_blkbits)) create = 0; } But in f2fs_map_blocks(), we only trigger f2fs_balance_fs() if @create is 1, so in LFS mode, dio overwrite under LFS mode can easily run out of free segments, result in below panic. Call Trace: allocate_segment_by_default+0xa8/0x270 [f2fs] f2fs_allocate_data_block+0x1ea/0x5c0 [f2fs] __allocate_data_block+0x306/0x480 [f2fs] f2fs_map_blocks+0x6f6/0x920 [f2fs] __get_data_block+0x4f/0xb0 [f2fs] get_data_block_dio_write+0x50/0x60 [f2fs] do_blockdev_direct_IO+0xcd5/0x21e0 __blockdev_direct_IO+0x3a/0x3c f2fs_direct_IO+0x1ff/0x4a0 [f2fs] generic_file_direct_write+0xd9/0x160 __generic_file_write_iter+0xbb/0x1e0 f2fs_file_write_iter+0xaf/0x220 [f2fs] __vfs_write+0xd0/0x130 vfs_write+0xb2/0x1b0 SyS_pwrite64+0x69/0xa0 ? vtime_user_exit+0x29/0x70 do_syscall_64+0x6e/0x160 entry_SYSCALL64_slow_path+0x25/0x25 RIP: new_curseg+0x36f/0x380 [f2fs] RSP: ffffac570393f7a8 So this patch introduces a parameter map.m_may_create to indicate that f2fs_map_blocks() is called from write or read path, which can give the right hint to let f2fs_map_blocks() trigger OPU allocation and call f2fs_balanc_fs() correctly. BTW, it disables physical address preallocation for direct IO in f2fs_preallocate_blocks, which is redundant to OPU allocation of f2fs_map_blocks. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-11-13 06:33:45 +00:00
if (map->m_may_create)
f2fs_map_lock(sbi, flag);
/* When reading holes, we need its node page */
set_new_dnode(&dn, inode, NULL, NULL, 0);
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
err = f2fs_get_dnode_of_data(&dn, pgofs, mode);
if (err) {
if (flag == F2FS_GET_BLOCK_BMAP)
map->m_pblk = 0;
if (err == -ENOENT)
err = f2fs_map_no_dnode(inode, map, &dn, pgofs);
goto unlock_out;
}
start_pgofs = pgofs;
prealloc = 0;
last_ofs_in_node = ofs_in_node = dn.ofs_in_node;
end_offset = ADDRS_PER_PAGE(dn.node_page, inode);
next_block:
blkaddr = f2fs_data_blkaddr(&dn);
is_hole = !__is_valid_data_blkaddr(blkaddr);
if (!is_hole &&
!f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC_ENHANCE)) {
err = -EFSCORRUPTED;
f2fs: fix to do sanity check with block address in main area This patch add to do sanity check with below field: - cp_pack_total_block_count - blkaddr of data/node - extent info - Overview BUG() in verify_block_addr() when writing to a corrupted f2fs image - Reproduce (4.18 upstream kernel) - POC (poc.c) static void activity(char *mpoint) { char *foo_bar_baz; int err; static int buf[8192]; memset(buf, 0, sizeof(buf)); err = asprintf(&foo_bar_baz, "%s/foo/bar/baz", mpoint); int fd = open(foo_bar_baz, O_RDWR | O_TRUNC, 0777); if (fd >= 0) { write(fd, (char *)buf, sizeof(buf)); fdatasync(fd); close(fd); } } int main(int argc, char *argv[]) { activity(argv[1]); return 0; } - Kernel message [ 689.349473] F2FS-fs (loop0): Mounted with checkpoint version = 3 [ 699.728662] WARNING: CPU: 0 PID: 1309 at fs/f2fs/segment.c:2860 f2fs_inplace_write_data+0x232/0x240 [ 699.728670] Modules linked in: snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_pcm snd_timer snd mac_hid i2c_piix4 soundcore ib_iser rdma_cm iw_cm ib_cm ib_core iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx raid1 raid0 multipath linear 8139too crct10dif_pclmul crc32_pclmul qxl drm_kms_helper syscopyarea aesni_intel sysfillrect sysimgblt fb_sys_fops ttm drm aes_x86_64 crypto_simd cryptd 8139cp glue_helper mii pata_acpi floppy [ 699.729056] CPU: 0 PID: 1309 Comm: a.out Not tainted 4.18.0-rc1+ #4 [ 699.729064] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.729074] RIP: 0010:f2fs_inplace_write_data+0x232/0x240 [ 699.729076] Code: ff e9 cf fe ff ff 49 8d 7d 10 e8 39 45 ad ff 4d 8b 7d 10 be 04 00 00 00 49 8d 7f 48 e8 07 49 ad ff 45 8b 7f 48 e9 fb fe ff ff <0f> 0b f0 41 80 4d 48 04 e9 65 fe ff ff 90 66 66 66 66 90 55 48 8d [ 699.729130] RSP: 0018:ffff8801f43af568 EFLAGS: 00010202 [ 699.729139] RAX: 000000000000003f RBX: ffff8801f43af7b8 RCX: ffffffffb88c9113 [ 699.729142] RDX: 0000000000000003 RSI: dffffc0000000000 RDI: ffff8802024e5540 [ 699.729144] RBP: ffff8801f43af590 R08: 0000000000000009 R09: ffffffffffffffe8 [ 699.729147] R10: 0000000000000001 R11: ffffed0039b0596a R12: ffff8802024e5540 [ 699.729149] R13: ffff8801f0335500 R14: ffff8801e3e7a700 R15: ffff8801e1ee4450 [ 699.729154] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.729156] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.729159] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.729171] Call Trace: [ 699.729192] f2fs_do_write_data_page+0x2e2/0xe00 [ 699.729203] ? f2fs_should_update_outplace+0xd0/0xd0 [ 699.729238] ? memcg_drain_all_list_lrus+0x280/0x280 [ 699.729269] ? __radix_tree_replace+0xa3/0x120 [ 699.729276] __write_data_page+0x5c7/0xe30 [ 699.729291] ? kasan_check_read+0x11/0x20 [ 699.729310] ? page_mapped+0x8a/0x110 [ 699.729321] ? page_mkclean+0xe9/0x160 [ 699.729327] ? f2fs_do_write_data_page+0xe00/0xe00 [ 699.729331] ? invalid_page_referenced_vma+0x130/0x130 [ 699.729345] ? clear_page_dirty_for_io+0x332/0x450 [ 699.729351] f2fs_write_cache_pages+0x4ca/0x860 [ 699.729358] ? __write_data_page+0xe30/0xe30 [ 699.729374] ? percpu_counter_add_batch+0x22/0xa0 [ 699.729380] ? kasan_check_write+0x14/0x20 [ 699.729391] ? _raw_spin_lock+0x17/0x40 [ 699.729403] ? f2fs_mark_inode_dirty_sync.part.18+0x16/0x30 [ 699.729413] ? iov_iter_advance+0x113/0x640 [ 699.729418] ? f2fs_write_end+0x133/0x2e0 [ 699.729423] ? balance_dirty_pages_ratelimited+0x239/0x640 [ 699.729428] f2fs_write_data_pages+0x329/0x520 [ 699.729433] ? generic_perform_write+0x250/0x320 [ 699.729438] ? f2fs_write_cache_pages+0x860/0x860 [ 699.729454] ? current_time+0x110/0x110 [ 699.729459] ? f2fs_preallocate_blocks+0x1ef/0x370 [ 699.729464] do_writepages+0x37/0xb0 [ 699.729468] ? f2fs_write_cache_pages+0x860/0x860 [ 699.729472] ? do_writepages+0x37/0xb0 [ 699.729478] __filemap_fdatawrite_range+0x19a/0x1f0 [ 699.729483] ? delete_from_page_cache_batch+0x4e0/0x4e0 [ 699.729496] ? __vfs_write+0x2b2/0x410 [ 699.729501] file_write_and_wait_range+0x66/0xb0 [ 699.729506] f2fs_do_sync_file+0x1f9/0xd90 [ 699.729511] ? truncate_partial_data_page+0x290/0x290 [ 699.729521] ? __sb_end_write+0x30/0x50 [ 699.729526] ? vfs_write+0x20f/0x260 [ 699.729530] f2fs_sync_file+0x9a/0xb0 [ 699.729534] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.729548] vfs_fsync_range+0x68/0x100 [ 699.729554] ? __fget_light+0xc9/0xe0 [ 699.729558] do_fsync+0x3d/0x70 [ 699.729562] __x64_sys_fdatasync+0x24/0x30 [ 699.729585] do_syscall_64+0x78/0x170 [ 699.729595] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 699.729613] RIP: 0033:0x7f9bf930d800 [ 699.729615] Code: 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 83 3d 49 bf 2c 00 00 75 10 b8 4b 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 be 78 01 00 48 89 04 24 [ 699.729668] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.729673] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.729675] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.729678] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.729680] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.729683] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000 [ 699.729687] ---[ end trace 4ce02f25ff7d3df5 ]--- [ 699.729782] ------------[ cut here ]------------ [ 699.729785] kernel BUG at fs/f2fs/segment.h:654! [ 699.731055] invalid opcode: 0000 [#1] SMP KASAN PTI [ 699.732104] CPU: 0 PID: 1309 Comm: a.out Tainted: G W 4.18.0-rc1+ #4 [ 699.733684] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.735611] RIP: 0010:f2fs_submit_page_bio+0x29b/0x730 [ 699.736649] Code: 54 49 8d bd 18 04 00 00 e8 b2 59 af ff 41 8b 8d 18 04 00 00 8b 45 b8 41 d3 e6 44 01 f0 4c 8d 73 14 41 39 c7 0f 82 37 fe ff ff <0f> 0b 65 8b 05 2c 04 77 47 89 c0 48 0f a3 05 52 c1 d5 01 0f 92 c0 [ 699.740524] RSP: 0018:ffff8801f43af508 EFLAGS: 00010283 [ 699.741573] RAX: 0000000000000000 RBX: ffff8801f43af7b8 RCX: ffffffffb88a7cef [ 699.743006] RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff8801e3e7a64c [ 699.744426] RBP: ffff8801f43af558 R08: ffffed003e066b55 R09: ffffed003e066b55 [ 699.745833] R10: 0000000000000001 R11: ffffed003e066b54 R12: ffffea0007876940 [ 699.747256] R13: ffff8801f0335500 R14: ffff8801e3e7a600 R15: 0000000000000001 [ 699.748683] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.750293] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.751462] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.752874] Call Trace: [ 699.753386] ? f2fs_inplace_write_data+0x93/0x240 [ 699.754341] f2fs_inplace_write_data+0xd2/0x240 [ 699.755271] f2fs_do_write_data_page+0x2e2/0xe00 [ 699.756214] ? f2fs_should_update_outplace+0xd0/0xd0 [ 699.757215] ? memcg_drain_all_list_lrus+0x280/0x280 [ 699.758209] ? __radix_tree_replace+0xa3/0x120 [ 699.759164] __write_data_page+0x5c7/0xe30 [ 699.760002] ? kasan_check_read+0x11/0x20 [ 699.760823] ? page_mapped+0x8a/0x110 [ 699.761573] ? page_mkclean+0xe9/0x160 [ 699.762345] ? f2fs_do_write_data_page+0xe00/0xe00 [ 699.763332] ? invalid_page_referenced_vma+0x130/0x130 [ 699.764374] ? clear_page_dirty_for_io+0x332/0x450 [ 699.765347] f2fs_write_cache_pages+0x4ca/0x860 [ 699.766276] ? __write_data_page+0xe30/0xe30 [ 699.767161] ? percpu_counter_add_batch+0x22/0xa0 [ 699.768112] ? kasan_check_write+0x14/0x20 [ 699.768951] ? _raw_spin_lock+0x17/0x40 [ 699.769739] ? f2fs_mark_inode_dirty_sync.part.18+0x16/0x30 [ 699.770885] ? iov_iter_advance+0x113/0x640 [ 699.771743] ? f2fs_write_end+0x133/0x2e0 [ 699.772569] ? balance_dirty_pages_ratelimited+0x239/0x640 [ 699.773680] f2fs_write_data_pages+0x329/0x520 [ 699.774603] ? generic_perform_write+0x250/0x320 [ 699.775544] ? f2fs_write_cache_pages+0x860/0x860 [ 699.776510] ? current_time+0x110/0x110 [ 699.777299] ? f2fs_preallocate_blocks+0x1ef/0x370 [ 699.778279] do_writepages+0x37/0xb0 [ 699.779026] ? f2fs_write_cache_pages+0x860/0x860 [ 699.779978] ? do_writepages+0x37/0xb0 [ 699.780755] __filemap_fdatawrite_range+0x19a/0x1f0 [ 699.781746] ? delete_from_page_cache_batch+0x4e0/0x4e0 [ 699.782820] ? __vfs_write+0x2b2/0x410 [ 699.783597] file_write_and_wait_range+0x66/0xb0 [ 699.784540] f2fs_do_sync_file+0x1f9/0xd90 [ 699.785381] ? truncate_partial_data_page+0x290/0x290 [ 699.786415] ? __sb_end_write+0x30/0x50 [ 699.787204] ? vfs_write+0x20f/0x260 [ 699.787941] f2fs_sync_file+0x9a/0xb0 [ 699.788694] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.789572] vfs_fsync_range+0x68/0x100 [ 699.790360] ? __fget_light+0xc9/0xe0 [ 699.791128] do_fsync+0x3d/0x70 [ 699.791779] __x64_sys_fdatasync+0x24/0x30 [ 699.792614] do_syscall_64+0x78/0x170 [ 699.793371] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 699.794406] RIP: 0033:0x7f9bf930d800 [ 699.795134] Code: 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 83 3d 49 bf 2c 00 00 75 10 b8 4b 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 be 78 01 00 48 89 04 24 [ 699.798960] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.800483] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.801923] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.803373] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.804798] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.806233] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000 [ 699.807667] Modules linked in: snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_pcm snd_timer snd mac_hid i2c_piix4 soundcore ib_iser rdma_cm iw_cm ib_cm ib_core iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx raid1 raid0 multipath linear 8139too crct10dif_pclmul crc32_pclmul qxl drm_kms_helper syscopyarea aesni_intel sysfillrect sysimgblt fb_sys_fops ttm drm aes_x86_64 crypto_simd cryptd 8139cp glue_helper mii pata_acpi floppy [ 699.817079] ---[ end trace 4ce02f25ff7d3df6 ]--- [ 699.818068] RIP: 0010:f2fs_submit_page_bio+0x29b/0x730 [ 699.819114] Code: 54 49 8d bd 18 04 00 00 e8 b2 59 af ff 41 8b 8d 18 04 00 00 8b 45 b8 41 d3 e6 44 01 f0 4c 8d 73 14 41 39 c7 0f 82 37 fe ff ff <0f> 0b 65 8b 05 2c 04 77 47 89 c0 48 0f a3 05 52 c1 d5 01 0f 92 c0 [ 699.822919] RSP: 0018:ffff8801f43af508 EFLAGS: 00010283 [ 699.823977] RAX: 0000000000000000 RBX: ffff8801f43af7b8 RCX: ffffffffb88a7cef [ 699.825436] RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff8801e3e7a64c [ 699.826881] RBP: ffff8801f43af558 R08: ffffed003e066b55 R09: ffffed003e066b55 [ 699.828292] R10: 0000000000000001 R11: ffffed003e066b54 R12: ffffea0007876940 [ 699.829750] R13: ffff8801f0335500 R14: ffff8801e3e7a600 R15: 0000000000000001 [ 699.831192] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.832793] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.833981] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.835556] ================================================================== [ 699.837029] BUG: KASAN: stack-out-of-bounds in update_stack_state+0x38c/0x3e0 [ 699.838462] Read of size 8 at addr ffff8801f43af970 by task a.out/1309 [ 699.840086] CPU: 0 PID: 1309 Comm: a.out Tainted: G D W 4.18.0-rc1+ #4 [ 699.841603] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.843475] Call Trace: [ 699.843982] dump_stack+0x7b/0xb5 [ 699.844661] print_address_description+0x70/0x290 [ 699.845607] kasan_report+0x291/0x390 [ 699.846351] ? update_stack_state+0x38c/0x3e0 [ 699.853831] __asan_load8+0x54/0x90 [ 699.854569] update_stack_state+0x38c/0x3e0 [ 699.855428] ? __read_once_size_nocheck.constprop.7+0x20/0x20 [ 699.856601] ? __save_stack_trace+0x5e/0x100 [ 699.857476] unwind_next_frame.part.5+0x18e/0x490 [ 699.858448] ? unwind_dump+0x290/0x290 [ 699.859217] ? clear_page_dirty_for_io+0x332/0x450 [ 699.860185] __unwind_start+0x106/0x190 [ 699.860974] __save_stack_trace+0x5e/0x100 [ 699.861808] ? __save_stack_trace+0x5e/0x100 [ 699.862691] ? unlink_anon_vmas+0xba/0x2c0 [ 699.863525] save_stack_trace+0x1f/0x30 [ 699.864312] save_stack+0x46/0xd0 [ 699.864993] ? __alloc_pages_slowpath+0x1420/0x1420 [ 699.865990] ? flush_tlb_mm_range+0x15e/0x220 [ 699.866889] ? kasan_check_write+0x14/0x20 [ 699.867724] ? __dec_node_state+0x92/0xb0 [ 699.868543] ? lock_page_memcg+0x85/0xf0 [ 699.869350] ? unlock_page_memcg+0x16/0x80 [ 699.870185] ? page_remove_rmap+0x198/0x520 [ 699.871048] ? mark_page_accessed+0x133/0x200 [ 699.871930] ? _cond_resched+0x1a/0x50 [ 699.872700] ? unmap_page_range+0xcd4/0xe50 [ 699.873551] ? rb_next+0x58/0x80 [ 699.874217] ? rb_next+0x58/0x80 [ 699.874895] __kasan_slab_free+0x13c/0x1a0 [ 699.875734] ? unlink_anon_vmas+0xba/0x2c0 [ 699.876563] kasan_slab_free+0xe/0x10 [ 699.877315] kmem_cache_free+0x89/0x1e0 [ 699.878095] unlink_anon_vmas+0xba/0x2c0 [ 699.878913] free_pgtables+0x101/0x1b0 [ 699.879677] exit_mmap+0x146/0x2a0 [ 699.880378] ? __ia32_sys_munmap+0x50/0x50 [ 699.881214] ? kasan_check_read+0x11/0x20 [ 699.882052] ? mm_update_next_owner+0x322/0x380 [ 699.882985] mmput+0x8b/0x1d0 [ 699.883602] do_exit+0x43a/0x1390 [ 699.884288] ? mm_update_next_owner+0x380/0x380 [ 699.885212] ? f2fs_sync_file+0x9a/0xb0 [ 699.885995] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.886877] ? vfs_fsync_range+0x68/0x100 [ 699.887694] ? __fget_light+0xc9/0xe0 [ 699.888442] ? do_fsync+0x3d/0x70 [ 699.889118] ? __x64_sys_fdatasync+0x24/0x30 [ 699.889996] rewind_stack_do_exit+0x17/0x20 [ 699.890860] RIP: 0033:0x7f9bf930d800 [ 699.891585] Code: Bad RIP value. [ 699.892268] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.893781] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.895220] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.896643] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.898069] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.899505] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000 [ 699.901241] The buggy address belongs to the page: [ 699.902215] page:ffffea0007d0ebc0 count:0 mapcount:0 mapping:0000000000000000 index:0x0 [ 699.903811] flags: 0x2ffff0000000000() [ 699.904585] raw: 02ffff0000000000 0000000000000000 ffffffff07d00101 0000000000000000 [ 699.906125] raw: 0000000000000000 0000000000240000 00000000ffffffff 0000000000000000 [ 699.907673] page dumped because: kasan: bad access detected [ 699.909108] Memory state around the buggy address: [ 699.910077] ffff8801f43af800: 00 f1 f1 f1 f1 00 f4 f4 f4 f3 f3 f3 f3 00 00 00 [ 699.911528] ffff8801f43af880: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 699.912953] >ffff8801f43af900: 00 00 00 00 00 00 00 00 f1 01 f4 f4 f4 f2 f2 f2 [ 699.914392] ^ [ 699.915758] ffff8801f43af980: f2 00 f4 f4 00 00 00 00 f2 00 00 00 00 00 00 00 [ 699.917193] ffff8801f43afa00: 00 00 00 00 00 00 00 00 00 f3 f3 f3 00 00 00 00 [ 699.918634] ================================================================== - Location https://elixir.bootlin.com/linux/v4.18-rc1/source/fs/f2fs/segment.h#L644 Reported-by Wen Xu <wen.xu@gatech.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-08-01 11:13:44 +00:00
goto sync_out;
}
/* use out-place-update for direct IO under LFS mode */
if (map->m_may_create && (is_hole ||
(flag == F2FS_GET_BLOCK_DIO && f2fs_lfs_mode(sbi) &&
!f2fs_is_pinned_file(inode)))) {
if (unlikely(f2fs_cp_error(sbi))) {
err = -EIO;
goto sync_out;
}
switch (flag) {
case F2FS_GET_BLOCK_PRE_AIO:
if (blkaddr == NULL_ADDR) {
prealloc++;
last_ofs_in_node = dn.ofs_in_node;
}
break;
case F2FS_GET_BLOCK_PRE_DIO:
case F2FS_GET_BLOCK_DIO:
err = __allocate_data_block(&dn, map->m_seg_type);
if (err)
goto sync_out;
if (flag == F2FS_GET_BLOCK_PRE_DIO)
file_need_truncate(inode);
set_inode_flag(inode, FI_APPEND_WRITE);
break;
default:
WARN_ON_ONCE(1);
err = -EIO;
goto sync_out;
}
blkaddr = dn.data_blkaddr;
if (is_hole)
map->m_flags |= F2FS_MAP_NEW;
} else if (is_hole) {
if (f2fs_compressed_file(inode) &&
f2fs_sanity_check_cluster(&dn)) {
err = -EFSCORRUPTED;
f2fs_handle_error(sbi,
ERROR_CORRUPTED_CLUSTER);
goto sync_out;
}
switch (flag) {
case F2FS_GET_BLOCK_PRECACHE:
goto sync_out;
case F2FS_GET_BLOCK_BMAP:
map->m_pblk = 0;
goto sync_out;
case F2FS_GET_BLOCK_FIEMAP:
if (blkaddr == NULL_ADDR) {
if (map->m_next_pgofs)
*map->m_next_pgofs = pgofs + 1;
goto sync_out;
}
break;
f2fs: support to map continuous holes or preallocated address This patch supports to map continuous holes or preallocated addresses to improve performace of lookuping mapping info during read DIO. [testcase 1] xfs_io -f /mnt/f2fs/hole -c "truncate 1m" -c "fsync" xfs_io -d /mnt/f2fs/hole -c "pread -b 1m 0 1m" [before] f2fs_direct_IO_enter: dev = (253,16), ino = 6 pos = 0 len = 1048576 ki_flags = 20000 ki_ioprio = 0 rw = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 0, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 1, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 2, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 3, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 4, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 5, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 6, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 7, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 8, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 9, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 10, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 11, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 12, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 13, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 14, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 15, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 16, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 ...... f2fs_direct_IO_exit: dev = (253,16), ino = 6 pos = 0 len = 1048576 rw = 0 ret = 1048576 [after] f2fs_direct_IO_enter: dev = (253,16), ino = 6 pos = 0 len = 1048576 ki_flags = 20000 ki_ioprio = 0 rw = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 0, start blkaddr = 0x0, len = 0x100, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_direct_IO_exit: dev = (253,16), ino = 6 pos = 0 len = 1048576 rw = 0 ret = 1048576 [testcase 2] xfs_io -f /mnt/f2fs/preallocated -c "falloc 0 1m" -c "fsync" xfs_io -d /mnt/f2fs/preallocated -c "pread -b 1m 0 1m" [before] f2fs_direct_IO_enter: dev = (253,16), ino = 11 pos = 0 len = 1048576 ki_flags = 20000 ki_ioprio = 0 rw = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 0, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 1, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 2, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 3, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 4, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 5, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 6, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 7, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 8, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 9, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 10, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 11, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 12, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 13, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 14, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 15, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 16, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 ...... f2fs_direct_IO_exit: dev = (253,16), ino = 11 pos = 0 len = 1048576 rw = 0 ret = 1048576 [after] f2fs_direct_IO_enter: dev = (253,16), ino = 11 pos = 0 len = 1048576 ki_flags = 20000 ki_ioprio = 0 rw = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 0, start blkaddr = 0xffffffff, len = 0x100, flags = 4, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_direct_IO_exit: dev = (253,16), ino = 11 pos = 0 len = 1048576 rw = 0 ret = 1048576 Signed-off-by: Chao Yu <chao@kernel.org> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2024-03-25 15:27:26 +00:00
case F2FS_GET_BLOCK_DIO:
if (map->m_next_pgofs)
*map->m_next_pgofs = pgofs + 1;
break;
default:
/* for defragment case */
if (map->m_next_pgofs)
*map->m_next_pgofs = pgofs + 1;
goto sync_out;
}
}
if (flag == F2FS_GET_BLOCK_PRE_AIO)
goto skip;
if (map->m_multidev_dio)
bidx = f2fs_target_device_index(sbi, blkaddr);
if (map->m_len == 0) {
/* reserved delalloc block should be mapped for fiemap. */
if (blkaddr == NEW_ADDR)
map->m_flags |= F2FS_MAP_DELALLOC;
f2fs: support to map continuous holes or preallocated address This patch supports to map continuous holes or preallocated addresses to improve performace of lookuping mapping info during read DIO. [testcase 1] xfs_io -f /mnt/f2fs/hole -c "truncate 1m" -c "fsync" xfs_io -d /mnt/f2fs/hole -c "pread -b 1m 0 1m" [before] f2fs_direct_IO_enter: dev = (253,16), ino = 6 pos = 0 len = 1048576 ki_flags = 20000 ki_ioprio = 0 rw = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 0, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 1, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 2, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 3, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 4, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 5, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 6, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 7, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 8, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 9, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 10, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 11, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 12, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 13, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 14, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 15, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 16, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 ...... f2fs_direct_IO_exit: dev = (253,16), ino = 6 pos = 0 len = 1048576 rw = 0 ret = 1048576 [after] f2fs_direct_IO_enter: dev = (253,16), ino = 6 pos = 0 len = 1048576 ki_flags = 20000 ki_ioprio = 0 rw = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 0, start blkaddr = 0x0, len = 0x100, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_direct_IO_exit: dev = (253,16), ino = 6 pos = 0 len = 1048576 rw = 0 ret = 1048576 [testcase 2] xfs_io -f /mnt/f2fs/preallocated -c "falloc 0 1m" -c "fsync" xfs_io -d /mnt/f2fs/preallocated -c "pread -b 1m 0 1m" [before] f2fs_direct_IO_enter: dev = (253,16), ino = 11 pos = 0 len = 1048576 ki_flags = 20000 ki_ioprio = 0 rw = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 0, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 1, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 2, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 3, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 4, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 5, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 6, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 7, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 8, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 9, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 10, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 11, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 12, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 13, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 14, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 15, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 16, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 ...... f2fs_direct_IO_exit: dev = (253,16), ino = 11 pos = 0 len = 1048576 rw = 0 ret = 1048576 [after] f2fs_direct_IO_enter: dev = (253,16), ino = 11 pos = 0 len = 1048576 ki_flags = 20000 ki_ioprio = 0 rw = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 0, start blkaddr = 0xffffffff, len = 0x100, flags = 4, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_direct_IO_exit: dev = (253,16), ino = 11 pos = 0 len = 1048576 rw = 0 ret = 1048576 Signed-off-by: Chao Yu <chao@kernel.org> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2024-03-25 15:27:26 +00:00
if (flag != F2FS_GET_BLOCK_DIO || !is_hole)
map->m_flags |= F2FS_MAP_MAPPED;
map->m_pblk = blkaddr;
map->m_len = 1;
if (map->m_multidev_dio)
map->m_bdev = FDEV(bidx).bdev;
} else if (map_is_mergeable(sbi, map, blkaddr, flag, bidx, ofs)) {
ofs++;
map->m_len++;
} else {
goto sync_out;
}
skip:
dn.ofs_in_node++;
pgofs++;
/* preallocate blocks in batch for one dnode page */
if (flag == F2FS_GET_BLOCK_PRE_AIO &&
(pgofs == end || dn.ofs_in_node == end_offset)) {
dn.ofs_in_node = ofs_in_node;
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
err = f2fs_reserve_new_blocks(&dn, prealloc);
if (err)
goto sync_out;
map->m_len += dn.ofs_in_node - ofs_in_node;
if (prealloc && dn.ofs_in_node != last_ofs_in_node + 1) {
err = -ENOSPC;
goto sync_out;
}
dn.ofs_in_node = end_offset;
}
if (pgofs >= end)
goto sync_out;
else if (dn.ofs_in_node < end_offset)
goto next_block;
if (flag == F2FS_GET_BLOCK_PRECACHE) {
if (map->m_flags & F2FS_MAP_MAPPED) {
unsigned int ofs = start_pgofs - map->m_lblk;
f2fs_update_read_extent_cache_range(&dn,
start_pgofs, map->m_pblk + ofs,
map->m_len - ofs);
}
}
f2fs_put_dnode(&dn);
f2fs: fix out-place-update DIO write In get_more_blocks(), we may override @create as below code: create = dio->op == REQ_OP_WRITE; if (dio->flags & DIO_SKIP_HOLES) { if (fs_startblk <= ((i_size_read(dio->inode) - 1) >> i_blkbits)) create = 0; } But in f2fs_map_blocks(), we only trigger f2fs_balance_fs() if @create is 1, so in LFS mode, dio overwrite under LFS mode can easily run out of free segments, result in below panic. Call Trace: allocate_segment_by_default+0xa8/0x270 [f2fs] f2fs_allocate_data_block+0x1ea/0x5c0 [f2fs] __allocate_data_block+0x306/0x480 [f2fs] f2fs_map_blocks+0x6f6/0x920 [f2fs] __get_data_block+0x4f/0xb0 [f2fs] get_data_block_dio_write+0x50/0x60 [f2fs] do_blockdev_direct_IO+0xcd5/0x21e0 __blockdev_direct_IO+0x3a/0x3c f2fs_direct_IO+0x1ff/0x4a0 [f2fs] generic_file_direct_write+0xd9/0x160 __generic_file_write_iter+0xbb/0x1e0 f2fs_file_write_iter+0xaf/0x220 [f2fs] __vfs_write+0xd0/0x130 vfs_write+0xb2/0x1b0 SyS_pwrite64+0x69/0xa0 ? vtime_user_exit+0x29/0x70 do_syscall_64+0x6e/0x160 entry_SYSCALL64_slow_path+0x25/0x25 RIP: new_curseg+0x36f/0x380 [f2fs] RSP: ffffac570393f7a8 So this patch introduces a parameter map.m_may_create to indicate that f2fs_map_blocks() is called from write or read path, which can give the right hint to let f2fs_map_blocks() trigger OPU allocation and call f2fs_balanc_fs() correctly. BTW, it disables physical address preallocation for direct IO in f2fs_preallocate_blocks, which is redundant to OPU allocation of f2fs_map_blocks. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-11-13 06:33:45 +00:00
if (map->m_may_create) {
f2fs_map_unlock(sbi, flag);
f2fs_balance_fs(sbi, dn.node_changed);
}
goto next_dnode;
sync_out:
if (flag == F2FS_GET_BLOCK_DIO && map->m_flags & F2FS_MAP_MAPPED) {
/*
* for hardware encryption, but to avoid potential issue
* in future
*/
f2fs_wait_on_block_writeback_range(inode,
map->m_pblk, map->m_len);
if (map->m_multidev_dio) {
block_t blk_addr = map->m_pblk;
bidx = f2fs_target_device_index(sbi, map->m_pblk);
map->m_bdev = FDEV(bidx).bdev;
map->m_pblk -= FDEV(bidx).start_blk;
if (map->m_may_create)
f2fs_update_device_state(sbi, inode->i_ino,
blk_addr, map->m_len);
f2fs_bug_on(sbi, blk_addr + map->m_len >
FDEV(bidx).end_blk + 1);
}
}
if (flag == F2FS_GET_BLOCK_PRECACHE) {
if (map->m_flags & F2FS_MAP_MAPPED) {
unsigned int ofs = start_pgofs - map->m_lblk;
f2fs_update_read_extent_cache_range(&dn,
start_pgofs, map->m_pblk + ofs,
map->m_len - ofs);
}
if (map->m_next_extent)
*map->m_next_extent = pgofs + 1;
}
f2fs_put_dnode(&dn);
unlock_out:
f2fs: fix out-place-update DIO write In get_more_blocks(), we may override @create as below code: create = dio->op == REQ_OP_WRITE; if (dio->flags & DIO_SKIP_HOLES) { if (fs_startblk <= ((i_size_read(dio->inode) - 1) >> i_blkbits)) create = 0; } But in f2fs_map_blocks(), we only trigger f2fs_balance_fs() if @create is 1, so in LFS mode, dio overwrite under LFS mode can easily run out of free segments, result in below panic. Call Trace: allocate_segment_by_default+0xa8/0x270 [f2fs] f2fs_allocate_data_block+0x1ea/0x5c0 [f2fs] __allocate_data_block+0x306/0x480 [f2fs] f2fs_map_blocks+0x6f6/0x920 [f2fs] __get_data_block+0x4f/0xb0 [f2fs] get_data_block_dio_write+0x50/0x60 [f2fs] do_blockdev_direct_IO+0xcd5/0x21e0 __blockdev_direct_IO+0x3a/0x3c f2fs_direct_IO+0x1ff/0x4a0 [f2fs] generic_file_direct_write+0xd9/0x160 __generic_file_write_iter+0xbb/0x1e0 f2fs_file_write_iter+0xaf/0x220 [f2fs] __vfs_write+0xd0/0x130 vfs_write+0xb2/0x1b0 SyS_pwrite64+0x69/0xa0 ? vtime_user_exit+0x29/0x70 do_syscall_64+0x6e/0x160 entry_SYSCALL64_slow_path+0x25/0x25 RIP: new_curseg+0x36f/0x380 [f2fs] RSP: ffffac570393f7a8 So this patch introduces a parameter map.m_may_create to indicate that f2fs_map_blocks() is called from write or read path, which can give the right hint to let f2fs_map_blocks() trigger OPU allocation and call f2fs_balanc_fs() correctly. BTW, it disables physical address preallocation for direct IO in f2fs_preallocate_blocks, which is redundant to OPU allocation of f2fs_map_blocks. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-11-13 06:33:45 +00:00
if (map->m_may_create) {
f2fs_map_unlock(sbi, flag);
f2fs_balance_fs(sbi, dn.node_changed);
}
out:
trace_f2fs_map_blocks(inode, map, flag, err);
return err;
}
bool f2fs_overwrite_io(struct inode *inode, loff_t pos, size_t len)
{
struct f2fs_map_blocks map;
block_t last_lblk;
int err;
if (pos + len > i_size_read(inode))
return false;
map.m_lblk = F2FS_BYTES_TO_BLK(pos);
map.m_next_pgofs = NULL;
map.m_next_extent = NULL;
map.m_seg_type = NO_CHECK_TYPE;
map.m_may_create = false;
last_lblk = F2FS_BLK_ALIGN(pos + len);
while (map.m_lblk < last_lblk) {
map.m_len = last_lblk - map.m_lblk;
err = f2fs_map_blocks(inode, &map, F2FS_GET_BLOCK_DEFAULT);
if (err || map.m_len == 0)
return false;
map.m_lblk += map.m_len;
}
return true;
}
static inline u64 bytes_to_blks(struct inode *inode, u64 bytes)
{
return (bytes >> inode->i_blkbits);
}
static inline u64 blks_to_bytes(struct inode *inode, u64 blks)
{
return (blks << inode->i_blkbits);
}
static int f2fs_xattr_fiemap(struct inode *inode,
struct fiemap_extent_info *fieinfo)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct page *page;
struct node_info ni;
__u64 phys = 0, len;
__u32 flags;
nid_t xnid = F2FS_I(inode)->i_xattr_nid;
int err = 0;
if (f2fs_has_inline_xattr(inode)) {
int offset;
page = f2fs_grab_cache_page(NODE_MAPPING(sbi),
inode->i_ino, false);
if (!page)
return -ENOMEM;
err = f2fs_get_node_info(sbi, inode->i_ino, &ni, false);
if (err) {
f2fs_put_page(page, 1);
return err;
}
phys = blks_to_bytes(inode, ni.blk_addr);
offset = offsetof(struct f2fs_inode, i_addr) +
sizeof(__le32) * (DEF_ADDRS_PER_INODE -
get_inline_xattr_addrs(inode));
phys += offset;
len = inline_xattr_size(inode);
f2fs_put_page(page, 1);
flags = FIEMAP_EXTENT_DATA_INLINE | FIEMAP_EXTENT_NOT_ALIGNED;
if (!xnid)
flags |= FIEMAP_EXTENT_LAST;
err = fiemap_fill_next_extent(fieinfo, 0, phys, len, flags);
trace_f2fs_fiemap(inode, 0, phys, len, flags, err);
if (err)
return err;
}
if (xnid) {
page = f2fs_grab_cache_page(NODE_MAPPING(sbi), xnid, false);
if (!page)
return -ENOMEM;
err = f2fs_get_node_info(sbi, xnid, &ni, false);
if (err) {
f2fs_put_page(page, 1);
return err;
}
phys = blks_to_bytes(inode, ni.blk_addr);
len = inode->i_sb->s_blocksize;
f2fs_put_page(page, 1);
flags = FIEMAP_EXTENT_LAST;
}
if (phys) {
err = fiemap_fill_next_extent(fieinfo, 0, phys, len, flags);
trace_f2fs_fiemap(inode, 0, phys, len, flags, err);
}
return (err < 0 ? err : 0);
}
static loff_t max_inode_blocks(struct inode *inode)
{
loff_t result = ADDRS_PER_INODE(inode);
loff_t leaf_count = ADDRS_PER_BLOCK(inode);
/* two direct node blocks */
result += (leaf_count * 2);
/* two indirect node blocks */
leaf_count *= NIDS_PER_BLOCK;
result += (leaf_count * 2);
/* one double indirect node block */
leaf_count *= NIDS_PER_BLOCK;
result += leaf_count;
return result;
}
int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
u64 start, u64 len)
{
struct f2fs_map_blocks map;
sector_t start_blk, last_blk;
pgoff_t next_pgofs;
u64 logical = 0, phys = 0, size = 0;
u32 flags = 0;
int ret = 0;
bool compr_cluster = false, compr_appended;
unsigned int cluster_size = F2FS_I(inode)->i_cluster_size;
unsigned int count_in_cluster = 0;
loff_t maxbytes;
if (fieinfo->fi_flags & FIEMAP_FLAG_CACHE) {
ret = f2fs_precache_extents(inode);
if (ret)
return ret;
}
ret = fiemap_prep(inode, fieinfo, start, &len, FIEMAP_FLAG_XATTR);
if (ret)
return ret;
inode_lock_shared(inode);
maxbytes = max_file_blocks(inode) << F2FS_BLKSIZE_BITS;
if (start > maxbytes) {
ret = -EFBIG;
goto out;
}
if (len > maxbytes || (maxbytes - len) < start)
len = maxbytes - start;
if (fieinfo->fi_flags & FIEMAP_FLAG_XATTR) {
ret = f2fs_xattr_fiemap(inode, fieinfo);
goto out;
}
if (f2fs_has_inline_data(inode) || f2fs_has_inline_dentry(inode)) {
ret = f2fs_inline_data_fiemap(inode, fieinfo, start, len);
if (ret != -EAGAIN)
goto out;
}
if (bytes_to_blks(inode, len) == 0)
len = blks_to_bytes(inode, 1);
start_blk = bytes_to_blks(inode, start);
last_blk = bytes_to_blks(inode, start + len - 1);
next:
memset(&map, 0, sizeof(map));
map.m_lblk = start_blk;
map.m_len = bytes_to_blks(inode, len);
map.m_next_pgofs = &next_pgofs;
map.m_seg_type = NO_CHECK_TYPE;
if (compr_cluster) {
map.m_lblk += 1;
map.m_len = cluster_size - count_in_cluster;
}
ret = f2fs_map_blocks(inode, &map, F2FS_GET_BLOCK_FIEMAP);
if (ret)
goto out;
/* HOLE */
if (!compr_cluster && !(map.m_flags & F2FS_MAP_FLAGS)) {
start_blk = next_pgofs;
if (blks_to_bytes(inode, start_blk) < blks_to_bytes(inode,
max_inode_blocks(inode)))
goto prep_next;
flags |= FIEMAP_EXTENT_LAST;
}
compr_appended = false;
/* In a case of compressed cluster, append this to the last extent */
if (compr_cluster && ((map.m_flags & F2FS_MAP_DELALLOC) ||
!(map.m_flags & F2FS_MAP_FLAGS))) {
compr_appended = true;
goto skip_fill;
}
if (size) {
flags |= FIEMAP_EXTENT_MERGED;
if (IS_ENCRYPTED(inode))
flags |= FIEMAP_EXTENT_DATA_ENCRYPTED;
ret = fiemap_fill_next_extent(fieinfo, logical,
phys, size, flags);
trace_f2fs_fiemap(inode, logical, phys, size, flags, ret);
if (ret)
goto out;
size = 0;
}
if (start_blk > last_blk)
goto out;
skip_fill:
if (map.m_pblk == COMPRESS_ADDR) {
compr_cluster = true;
count_in_cluster = 1;
} else if (compr_appended) {
unsigned int appended_blks = cluster_size -
count_in_cluster + 1;
size += blks_to_bytes(inode, appended_blks);
start_blk += appended_blks;
compr_cluster = false;
} else {
logical = blks_to_bytes(inode, start_blk);
phys = __is_valid_data_blkaddr(map.m_pblk) ?
blks_to_bytes(inode, map.m_pblk) : 0;
size = blks_to_bytes(inode, map.m_len);
flags = 0;
if (compr_cluster) {
flags = FIEMAP_EXTENT_ENCODED;
count_in_cluster += map.m_len;
if (count_in_cluster == cluster_size) {
compr_cluster = false;
size += blks_to_bytes(inode, 1);
}
} else if (map.m_flags & F2FS_MAP_DELALLOC) {
flags = FIEMAP_EXTENT_UNWRITTEN;
}
start_blk += bytes_to_blks(inode, size);
}
prep_next:
cond_resched();
if (fatal_signal_pending(current))
ret = -EINTR;
else
goto next;
out:
if (ret == 1)
ret = 0;
inode_unlock_shared(inode);
return ret;
}
f2fs: add fs-verity support Add fs-verity support to f2fs. fs-verity is a filesystem feature that enables transparent integrity protection and authentication of read-only files. It uses a dm-verity like mechanism at the file level: a Merkle tree is used to verify any block in the file in log(filesize) time. It is implemented mainly by helper functions in fs/verity/. See Documentation/filesystems/fsverity.rst for the full documentation. The f2fs support for fs-verity consists of: - Adding a filesystem feature flag and an inode flag for fs-verity. - Implementing the fsverity_operations to support enabling verity on an inode and reading/writing the verity metadata. - Updating ->readpages() to verify data as it's read from verity files and to support reading verity metadata pages. - Updating ->write_begin(), ->write_end(), and ->writepages() to support writing verity metadata pages. - Calling the fs-verity hooks for ->open(), ->setattr(), and ->ioctl(). Like ext4, f2fs stores the verity metadata (Merkle tree and fsverity_descriptor) past the end of the file, starting at the first 64K boundary beyond i_size. This approach works because (a) verity files are readonly, and (b) pages fully beyond i_size aren't visible to userspace but can be read/written internally by f2fs with only some relatively small changes to f2fs. Extended attributes cannot be used because (a) f2fs limits the total size of an inode's xattr entries to 4096 bytes, which wouldn't be enough for even a single Merkle tree block, and (b) f2fs encryption doesn't encrypt xattrs, yet the verity metadata *must* be encrypted when the file is because it contains hashes of the plaintext data. Acked-by: Jaegeuk Kim <jaegeuk@kernel.org> Acked-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Eric Biggers <ebiggers@google.com>
2019-07-22 16:26:24 +00:00
static inline loff_t f2fs_readpage_limit(struct inode *inode)
{
if (IS_ENABLED(CONFIG_FS_VERITY) && IS_VERITY(inode))
f2fs: add fs-verity support Add fs-verity support to f2fs. fs-verity is a filesystem feature that enables transparent integrity protection and authentication of read-only files. It uses a dm-verity like mechanism at the file level: a Merkle tree is used to verify any block in the file in log(filesize) time. It is implemented mainly by helper functions in fs/verity/. See Documentation/filesystems/fsverity.rst for the full documentation. The f2fs support for fs-verity consists of: - Adding a filesystem feature flag and an inode flag for fs-verity. - Implementing the fsverity_operations to support enabling verity on an inode and reading/writing the verity metadata. - Updating ->readpages() to verify data as it's read from verity files and to support reading verity metadata pages. - Updating ->write_begin(), ->write_end(), and ->writepages() to support writing verity metadata pages. - Calling the fs-verity hooks for ->open(), ->setattr(), and ->ioctl(). Like ext4, f2fs stores the verity metadata (Merkle tree and fsverity_descriptor) past the end of the file, starting at the first 64K boundary beyond i_size. This approach works because (a) verity files are readonly, and (b) pages fully beyond i_size aren't visible to userspace but can be read/written internally by f2fs with only some relatively small changes to f2fs. Extended attributes cannot be used because (a) f2fs limits the total size of an inode's xattr entries to 4096 bytes, which wouldn't be enough for even a single Merkle tree block, and (b) f2fs encryption doesn't encrypt xattrs, yet the verity metadata *must* be encrypted when the file is because it contains hashes of the plaintext data. Acked-by: Jaegeuk Kim <jaegeuk@kernel.org> Acked-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Eric Biggers <ebiggers@google.com>
2019-07-22 16:26:24 +00:00
return inode->i_sb->s_maxbytes;
return i_size_read(inode);
}
static inline blk_opf_t f2fs_ra_op_flags(struct readahead_control *rac)
{
return rac ? REQ_RAHEAD : 0;
}
static int f2fs_read_single_page(struct inode *inode, struct folio *folio,
unsigned nr_pages,
struct f2fs_map_blocks *map,
struct bio **bio_ret,
sector_t *last_block_in_bio,
struct readahead_control *rac)
{
struct bio *bio = *bio_ret;
const unsigned blocksize = blks_to_bytes(inode, 1);
sector_t block_in_file;
sector_t last_block;
sector_t last_block_in_file;
sector_t block_nr;
pgoff_t index = folio_index(folio);
int ret = 0;
block_in_file = (sector_t)index;
last_block = block_in_file + nr_pages;
last_block_in_file = bytes_to_blks(inode,
f2fs_readpage_limit(inode) + blocksize - 1);
if (last_block > last_block_in_file)
last_block = last_block_in_file;
/* just zeroing out page which is beyond EOF */
if (block_in_file >= last_block)
goto zero_out;
/*
* Map blocks using the previous result first.
*/
if ((map->m_flags & F2FS_MAP_MAPPED) &&
block_in_file > map->m_lblk &&
block_in_file < (map->m_lblk + map->m_len))
goto got_it;
/*
* Then do more f2fs_map_blocks() calls until we are
* done with this page.
*/
map->m_lblk = block_in_file;
map->m_len = last_block - block_in_file;
ret = f2fs_map_blocks(inode, map, F2FS_GET_BLOCK_DEFAULT);
if (ret)
goto out;
got_it:
if ((map->m_flags & F2FS_MAP_MAPPED)) {
block_nr = map->m_pblk + block_in_file - map->m_lblk;
folio_set_mappedtodisk(folio);
if (!f2fs_is_valid_blkaddr(F2FS_I_SB(inode), block_nr,
f2fs: introduce DATA_GENERIC_ENHANCE Previously, f2fs_is_valid_blkaddr(, blkaddr, DATA_GENERIC) will check whether @blkaddr locates in main area or not. That check is weak, since the block address in range of main area can point to the address which is not valid in segment info table, and we can not detect such condition, we may suffer worse corruption as system continues running. So this patch introduce DATA_GENERIC_ENHANCE to enhance the sanity check which trigger SIT bitmap check rather than only range check. This patch did below changes as wel: - set SBI_NEED_FSCK in f2fs_is_valid_blkaddr(). - get rid of is_valid_data_blkaddr() to avoid panic if blkaddr is invalid. - introduce verify_fio_blkaddr() to wrap fio {new,old}_blkaddr validation check. - spread blkaddr check in: * f2fs_get_node_info() * __read_out_blkaddrs() * f2fs_submit_page_read() * ra_data_block() * do_recover_data() This patch can fix bug reported from bugzilla below: https://bugzilla.kernel.org/show_bug.cgi?id=203215 https://bugzilla.kernel.org/show_bug.cgi?id=203223 https://bugzilla.kernel.org/show_bug.cgi?id=203231 https://bugzilla.kernel.org/show_bug.cgi?id=203235 https://bugzilla.kernel.org/show_bug.cgi?id=203241 = Update by Jaegeuk Kim = DATA_GENERIC_ENHANCE enhanced to validate block addresses on read/write paths. But, xfstest/generic/446 compalins some generated kernel messages saying invalid bitmap was detected when reading a block. The reaons is, when we get the block addresses from extent_cache, there is no lock to synchronize it from truncating the blocks in parallel. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-04-15 07:26:32 +00:00
DATA_GENERIC_ENHANCE_READ)) {
ret = -EFSCORRUPTED;
goto out;
}
} else {
zero_out:
folio_zero_segment(folio, 0, folio_size(folio));
if (f2fs_need_verity(inode, index) &&
!fsverity_verify_folio(folio)) {
f2fs: add fs-verity support Add fs-verity support to f2fs. fs-verity is a filesystem feature that enables transparent integrity protection and authentication of read-only files. It uses a dm-verity like mechanism at the file level: a Merkle tree is used to verify any block in the file in log(filesize) time. It is implemented mainly by helper functions in fs/verity/. See Documentation/filesystems/fsverity.rst for the full documentation. The f2fs support for fs-verity consists of: - Adding a filesystem feature flag and an inode flag for fs-verity. - Implementing the fsverity_operations to support enabling verity on an inode and reading/writing the verity metadata. - Updating ->readpages() to verify data as it's read from verity files and to support reading verity metadata pages. - Updating ->write_begin(), ->write_end(), and ->writepages() to support writing verity metadata pages. - Calling the fs-verity hooks for ->open(), ->setattr(), and ->ioctl(). Like ext4, f2fs stores the verity metadata (Merkle tree and fsverity_descriptor) past the end of the file, starting at the first 64K boundary beyond i_size. This approach works because (a) verity files are readonly, and (b) pages fully beyond i_size aren't visible to userspace but can be read/written internally by f2fs with only some relatively small changes to f2fs. Extended attributes cannot be used because (a) f2fs limits the total size of an inode's xattr entries to 4096 bytes, which wouldn't be enough for even a single Merkle tree block, and (b) f2fs encryption doesn't encrypt xattrs, yet the verity metadata *must* be encrypted when the file is because it contains hashes of the plaintext data. Acked-by: Jaegeuk Kim <jaegeuk@kernel.org> Acked-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Eric Biggers <ebiggers@google.com>
2019-07-22 16:26:24 +00:00
ret = -EIO;
goto out;
}
if (!folio_test_uptodate(folio))
folio_mark_uptodate(folio);
folio_unlock(folio);
goto out;
}
/*
* This page will go to BIO. Do we need to send this
* BIO off first?
*/
if (bio && (!page_is_mergeable(F2FS_I_SB(inode), bio,
*last_block_in_bio, block_nr) ||
!f2fs_crypt_mergeable_bio(bio, inode, index, NULL))) {
submit_and_realloc:
f2fs_submit_read_bio(F2FS_I_SB(inode), bio, DATA);
bio = NULL;
}
if (bio == NULL) {
bio = f2fs_grab_read_bio(inode, block_nr, nr_pages,
f2fs_ra_op_flags(rac), index,
false);
if (IS_ERR(bio)) {
ret = PTR_ERR(bio);
bio = NULL;
goto out;
}
}
/*
* If the page is under writeback, we need to wait for
* its completion to see the correct decrypted data.
*/
f2fs_wait_on_block_writeback(inode, block_nr);
if (!bio_add_folio(bio, folio, blocksize, 0))
goto submit_and_realloc;
inc_page_count(F2FS_I_SB(inode), F2FS_RD_DATA);
f2fs_update_iostat(F2FS_I_SB(inode), NULL, FS_DATA_READ_IO,
F2FS_BLKSIZE);
*last_block_in_bio = block_nr;
out:
*bio_ret = bio;
return ret;
}
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
#ifdef CONFIG_F2FS_FS_COMPRESSION
int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret,
unsigned nr_pages, sector_t *last_block_in_bio,
struct readahead_control *rac, bool for_write)
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
{
struct dnode_of_data dn;
struct inode *inode = cc->inode;
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct bio *bio = *bio_ret;
unsigned int start_idx = cc->cluster_idx << cc->log_cluster_size;
sector_t last_block_in_file;
const unsigned blocksize = blks_to_bytes(inode, 1);
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
struct decompress_io_ctx *dic = NULL;
struct extent_info ei = {};
bool from_dnode = true;
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
int i;
int ret = 0;
f2fs_bug_on(sbi, f2fs_cluster_is_empty(cc));
last_block_in_file = bytes_to_blks(inode,
f2fs_readpage_limit(inode) + blocksize - 1);
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
/* get rid of pages beyond EOF */
for (i = 0; i < cc->cluster_size; i++) {
struct page *page = cc->rpages[i];
if (!page)
continue;
if ((sector_t)page->index >= last_block_in_file) {
zero_user_segment(page, 0, PAGE_SIZE);
if (!PageUptodate(page))
SetPageUptodate(page);
} else if (!PageUptodate(page)) {
continue;
}
unlock_page(page);
if (for_write)
put_page(page);
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
cc->rpages[i] = NULL;
cc->nr_rpages--;
}
/* we are done since all pages are beyond EOF */
if (f2fs_cluster_is_empty(cc))
goto out;
if (f2fs_lookup_read_extent_cache(inode, start_idx, &ei))
from_dnode = false;
if (!from_dnode)
goto skip_reading_dnode;
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
set_new_dnode(&dn, inode, NULL, NULL, 0);
ret = f2fs_get_dnode_of_data(&dn, start_idx, LOOKUP_NODE);
if (ret)
goto out;
if (unlikely(f2fs_cp_error(sbi))) {
ret = -EIO;
goto out_put_dnode;
}
f2fs_bug_on(sbi, dn.data_blkaddr != COMPRESS_ADDR);
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
skip_reading_dnode:
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
for (i = 1; i < cc->cluster_size; i++) {
block_t blkaddr;
blkaddr = from_dnode ? data_blkaddr(dn.inode, dn.node_page,
dn.ofs_in_node + i) :
ei.blk + i - 1;
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
if (!__is_valid_data_blkaddr(blkaddr))
break;
if (!f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC)) {
ret = -EFAULT;
goto out_put_dnode;
}
cc->nr_cpages++;
if (!from_dnode && i >= ei.c_len)
break;
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
}
/* nothing to decompress */
if (cc->nr_cpages == 0) {
ret = 0;
goto out_put_dnode;
}
dic = f2fs_alloc_dic(cc);
if (IS_ERR(dic)) {
ret = PTR_ERR(dic);
goto out_put_dnode;
}
for (i = 0; i < cc->nr_cpages; i++) {
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
struct page *page = dic->cpages[i];
block_t blkaddr;
struct bio_post_read_ctx *ctx;
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
blkaddr = from_dnode ? data_blkaddr(dn.inode, dn.node_page,
dn.ofs_in_node + i + 1) :
ei.blk + i;
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
f2fs_wait_on_block_writeback(inode, blkaddr);
if (f2fs_load_compressed_page(sbi, page, blkaddr)) {
if (atomic_dec_and_test(&dic->remaining_pages)) {
f2fs_decompress_cluster(dic, true);
break;
}
continue;
}
if (bio && (!page_is_mergeable(sbi, bio,
*last_block_in_bio, blkaddr) ||
!f2fs_crypt_mergeable_bio(bio, inode, page->index, NULL))) {
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
submit_and_realloc:
f2fs_submit_read_bio(sbi, bio, DATA);
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
bio = NULL;
}
if (!bio) {
bio = f2fs_grab_read_bio(inode, blkaddr, nr_pages,
f2fs_ra_op_flags(rac),
page->index, for_write);
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
if (IS_ERR(bio)) {
ret = PTR_ERR(bio);
f2fs_decompress_end_io(dic, ret, true);
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
f2fs_put_dnode(&dn);
*bio_ret = NULL;
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
return ret;
}
}
if (bio_add_page(bio, page, blocksize, 0) < blocksize)
goto submit_and_realloc;
f2fs: introduce periodic iostat io latency traces Whenever we notice some sluggish issues on our machines, we are always curious about how well all types of I/O in the f2fs filesystem are handled. But, it's hard to get this kind of real data. First of all, we need to reproduce the issue while turning on the profiling tool like blktrace, but the issue doesn't happen again easily. Second, with the intervention of any tools, the overall timing of the issue will be slightly changed and it sometimes makes us hard to figure it out. So, I added the feature printing out IO latency statistics tracepoint events, which are minimal things to understand filesystem's I/O related behaviors, into F2FS_IOSTAT kernel config. With "iostat_enable" sysfs node on, we can get this statistics info in a periodic way and it would cause the least overhead. [samples] f2fs_ckpt-254:1-507 [003] .... 2842.439683: f2fs_iostat_latency: dev = (254,11), iotype [peak lat.(ms)/avg lat.(ms)/count], rd_data [136/1/801], rd_node [136/1/1704], rd_meta [4/2/4], wr_sync_data [164/16/3331], wr_sync_node [152/3/648], wr_sync_meta [160/2/4243], wr_async_data [24/13/15], wr_async_node [0/0/0], wr_async_meta [0/0/0] f2fs_ckpt-254:1-507 [002] .... 2845.450514: f2fs_iostat_latency: dev = (254,11), iotype [peak lat.(ms)/avg lat.(ms)/count], rd_data [60/3/456], rd_node [60/3/1258], rd_meta [0/0/1], wr_sync_data [120/12/2285], wr_sync_node [88/5/428], wr_sync_meta [52/6/2990], wr_async_data [4/1/3], wr_async_node [0/0/0], wr_async_meta [0/0/0] Signed-off-by: Daeho Jeong <daehojeong@google.com> Reviewed-by: Chao Yu <chao@kernel.org> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2021-08-20 22:29:09 +00:00
ctx = get_post_read_ctx(bio);
ctx->enabled_steps |= STEP_DECOMPRESS;
refcount_inc(&dic->refcnt);
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
inc_page_count(sbi, F2FS_RD_DATA);
f2fs_update_iostat(sbi, inode, FS_DATA_READ_IO, F2FS_BLKSIZE);
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
*last_block_in_bio = blkaddr;
}
if (from_dnode)
f2fs_put_dnode(&dn);
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
*bio_ret = bio;
return 0;
out_put_dnode:
if (from_dnode)
f2fs_put_dnode(&dn);
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
out:
for (i = 0; i < cc->cluster_size; i++) {
if (cc->rpages[i]) {
ClearPageUptodate(cc->rpages[i]);
unlock_page(cc->rpages[i]);
}
}
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
*bio_ret = bio;
return ret;
}
#endif
/*
* This function was originally taken from fs/mpage.c, and customized for f2fs.
* Major change was from block_size == page_size in f2fs by default.
*/
static int f2fs_mpage_readpages(struct inode *inode,
struct readahead_control *rac, struct folio *folio)
{
struct bio *bio = NULL;
sector_t last_block_in_bio = 0;
struct f2fs_map_blocks map;
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
#ifdef CONFIG_F2FS_FS_COMPRESSION
struct compress_ctx cc = {
.inode = inode,
.log_cluster_size = F2FS_I(inode)->i_log_cluster_size,
.cluster_size = F2FS_I(inode)->i_cluster_size,
.cluster_idx = NULL_CLUSTER,
.rpages = NULL,
.cpages = NULL,
.nr_rpages = 0,
.nr_cpages = 0,
};
pgoff_t nc_cluster_idx = NULL_CLUSTER;
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
#endif
unsigned nr_pages = rac ? readahead_count(rac) : 1;
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
unsigned max_nr_pages = nr_pages;
pgoff_t index;
int ret = 0;
map.m_pblk = 0;
map.m_lblk = 0;
map.m_len = 0;
map.m_flags = 0;
map.m_next_pgofs = NULL;
map.m_next_extent = NULL;
map.m_seg_type = NO_CHECK_TYPE;
f2fs: fix out-place-update DIO write In get_more_blocks(), we may override @create as below code: create = dio->op == REQ_OP_WRITE; if (dio->flags & DIO_SKIP_HOLES) { if (fs_startblk <= ((i_size_read(dio->inode) - 1) >> i_blkbits)) create = 0; } But in f2fs_map_blocks(), we only trigger f2fs_balance_fs() if @create is 1, so in LFS mode, dio overwrite under LFS mode can easily run out of free segments, result in below panic. Call Trace: allocate_segment_by_default+0xa8/0x270 [f2fs] f2fs_allocate_data_block+0x1ea/0x5c0 [f2fs] __allocate_data_block+0x306/0x480 [f2fs] f2fs_map_blocks+0x6f6/0x920 [f2fs] __get_data_block+0x4f/0xb0 [f2fs] get_data_block_dio_write+0x50/0x60 [f2fs] do_blockdev_direct_IO+0xcd5/0x21e0 __blockdev_direct_IO+0x3a/0x3c f2fs_direct_IO+0x1ff/0x4a0 [f2fs] generic_file_direct_write+0xd9/0x160 __generic_file_write_iter+0xbb/0x1e0 f2fs_file_write_iter+0xaf/0x220 [f2fs] __vfs_write+0xd0/0x130 vfs_write+0xb2/0x1b0 SyS_pwrite64+0x69/0xa0 ? vtime_user_exit+0x29/0x70 do_syscall_64+0x6e/0x160 entry_SYSCALL64_slow_path+0x25/0x25 RIP: new_curseg+0x36f/0x380 [f2fs] RSP: ffffac570393f7a8 So this patch introduces a parameter map.m_may_create to indicate that f2fs_map_blocks() is called from write or read path, which can give the right hint to let f2fs_map_blocks() trigger OPU allocation and call f2fs_balanc_fs() correctly. BTW, it disables physical address preallocation for direct IO in f2fs_preallocate_blocks, which is redundant to OPU allocation of f2fs_map_blocks. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-11-13 06:33:45 +00:00
map.m_may_create = false;
for (; nr_pages; nr_pages--) {
if (rac) {
folio = readahead_folio(rac);
prefetchw(&folio->flags);
}
index = folio_index(folio);
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
#ifdef CONFIG_F2FS_FS_COMPRESSION
if (!f2fs_compressed_file(inode))
goto read_single_page;
/* there are remained compressed pages, submit them */
if (!f2fs_cluster_can_merge_page(&cc, index)) {
ret = f2fs_read_multi_pages(&cc, &bio,
max_nr_pages,
&last_block_in_bio,
rac, false);
f2fs_destroy_compress_ctx(&cc, false);
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
if (ret)
goto set_error_page;
}
if (cc.cluster_idx == NULL_CLUSTER) {
if (nc_cluster_idx == index >> cc.log_cluster_size)
goto read_single_page;
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
ret = f2fs_is_compressed_cluster(inode, index);
if (ret < 0)
goto set_error_page;
else if (!ret) {
nc_cluster_idx =
index >> cc.log_cluster_size;
goto read_single_page;
}
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
nc_cluster_idx = NULL_CLUSTER;
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
}
ret = f2fs_init_compress_ctx(&cc);
if (ret)
goto set_error_page;
f2fs_compress_ctx_add_page(&cc, &folio->page);
goto next_page;
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
read_single_page:
#endif
ret = f2fs_read_single_page(inode, folio, max_nr_pages, &map,
&bio, &last_block_in_bio, rac);
if (ret) {
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
#ifdef CONFIG_F2FS_FS_COMPRESSION
set_error_page:
#endif
folio_zero_segment(folio, 0, folio_size(folio));
folio_unlock(folio);
}
#ifdef CONFIG_F2FS_FS_COMPRESSION
next_page:
#endif
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
#ifdef CONFIG_F2FS_FS_COMPRESSION
if (f2fs_compressed_file(inode)) {
/* last page */
if (nr_pages == 1 && !f2fs_cluster_is_empty(&cc)) {
ret = f2fs_read_multi_pages(&cc, &bio,
max_nr_pages,
&last_block_in_bio,
rac, false);
f2fs_destroy_compress_ctx(&cc, false);
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
}
}
#endif
}
if (bio)
f2fs_submit_read_bio(F2FS_I_SB(inode), bio, DATA);
return ret;
}
static int f2fs_read_data_folio(struct file *file, struct folio *folio)
{
struct inode *inode = folio_file_mapping(folio)->host;
int ret = -EAGAIN;
trace_f2fs_readpage(folio, DATA);
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
if (!f2fs_is_compress_backend_ready(inode)) {
folio_unlock(folio);
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
return -EOPNOTSUPP;
}
/* If the file has inline data, try to read it directly */
if (f2fs_has_inline_data(inode))
ret = f2fs_read_inline_data(inode, folio);
if (ret == -EAGAIN)
ret = f2fs_mpage_readpages(inode, NULL, folio);
return ret;
}
static void f2fs_readahead(struct readahead_control *rac)
{
struct inode *inode = rac->mapping->host;
trace_f2fs_readpages(inode, readahead_index(rac), readahead_count(rac));
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
if (!f2fs_is_compress_backend_ready(inode))
return;
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
/* If the file has inline data, skip readahead */
if (f2fs_has_inline_data(inode))
return;
f2fs_mpage_readpages(inode, rac, NULL);
}
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
int f2fs_encrypt_one_page(struct f2fs_io_info *fio)
{
struct inode *inode = fio->page->mapping->host;
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
struct page *mpage, *page;
gfp_t gfp_flags = GFP_NOFS;
if (!f2fs_encrypted_file(inode))
return 0;
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
page = fio->compressed_page ? fio->compressed_page : fio->page;
if (fscrypt_inode_uses_inline_crypto(inode))
return 0;
retry_encrypt:
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
fio->encrypted_page = fscrypt_encrypt_pagecache_blocks(page,
PAGE_SIZE, 0, gfp_flags);
f2fs: readahead encrypted block during GC During GC, for each encrypted block, we will read block synchronously into meta page, and then submit it into current cold data log area. So this block read model with 4k granularity can make poor performance, like migrating non-encrypted block, let's readahead encrypted block as well to improve migration performance. To implement this, we choose meta page that its index is old block address of the encrypted block, and readahead ciphertext into this page, later, if readaheaded page is still updated, we will load its data into target meta page, and submit the write IO. Note that for OPU, truncation, deletion, we need to invalid meta page after we invalid old block address, to make sure we won't load invalid data from target meta page during encrypted block migration. for ((i = 0; i < 1000; i++)) do { xfs_io -f /mnt/f2fs/dir/$i -c "pwrite 0 128k" -c "fsync"; } done for ((i = 0; i < 1000; i+=2)) do { rm /mnt/f2fs/dir/$i; } done ret = ioctl(fd, F2FS_IOC_GARBAGE_COLLECT, 0); Before: gc-6549 [001] d..1 214682.212797: block_rq_insert: 8,32 RA 32768 () 786400 + 64 [gc] gc-6549 [001] d..1 214682.212802: block_unplug: [gc] 1 gc-6549 [001] .... 214682.213892: block_bio_queue: 8,32 R 67494144 + 8 [gc] gc-6549 [001] .... 214682.213899: block_getrq: 8,32 R 67494144 + 8 [gc] gc-6549 [001] .... 214682.213902: block_plug: [gc] gc-6549 [001] d..1 214682.213905: block_rq_insert: 8,32 R 4096 () 67494144 + 8 [gc] gc-6549 [001] d..1 214682.213908: block_unplug: [gc] 1 gc-6549 [001] .... 214682.226405: block_bio_queue: 8,32 R 67494152 + 8 [gc] gc-6549 [001] .... 214682.226412: block_getrq: 8,32 R 67494152 + 8 [gc] gc-6549 [001] .... 214682.226414: block_plug: [gc] gc-6549 [001] d..1 214682.226417: block_rq_insert: 8,32 R 4096 () 67494152 + 8 [gc] gc-6549 [001] d..1 214682.226420: block_unplug: [gc] 1 gc-6549 [001] .... 214682.226904: block_bio_queue: 8,32 R 67494160 + 8 [gc] gc-6549 [001] .... 214682.226910: block_getrq: 8,32 R 67494160 + 8 [gc] gc-6549 [001] .... 214682.226911: block_plug: [gc] gc-6549 [001] d..1 214682.226914: block_rq_insert: 8,32 R 4096 () 67494160 + 8 [gc] gc-6549 [001] d..1 214682.226916: block_unplug: [gc] 1 After: gc-5678 [003] .... 214327.025906: block_bio_queue: 8,32 R 67493824 + 8 [gc] gc-5678 [003] .... 214327.025908: block_bio_backmerge: 8,32 R 67493824 + 8 [gc] gc-5678 [003] .... 214327.025915: block_bio_queue: 8,32 R 67493832 + 8 [gc] gc-5678 [003] .... 214327.025917: block_bio_backmerge: 8,32 R 67493832 + 8 [gc] gc-5678 [003] .... 214327.025923: block_bio_queue: 8,32 R 67493840 + 8 [gc] gc-5678 [003] .... 214327.025925: block_bio_backmerge: 8,32 R 67493840 + 8 [gc] gc-5678 [003] .... 214327.025932: block_bio_queue: 8,32 R 67493848 + 8 [gc] gc-5678 [003] .... 214327.025934: block_bio_backmerge: 8,32 R 67493848 + 8 [gc] gc-5678 [003] .... 214327.025941: block_bio_queue: 8,32 R 67493856 + 8 [gc] gc-5678 [003] .... 214327.025943: block_bio_backmerge: 8,32 R 67493856 + 8 [gc] gc-5678 [003] .... 214327.025953: block_bio_queue: 8,32 R 67493864 + 8 [gc] gc-5678 [003] .... 214327.025955: block_bio_backmerge: 8,32 R 67493864 + 8 [gc] gc-5678 [003] .... 214327.025962: block_bio_queue: 8,32 R 67493872 + 8 [gc] gc-5678 [003] .... 214327.025964: block_bio_backmerge: 8,32 R 67493872 + 8 [gc] gc-5678 [003] .... 214327.025970: block_bio_queue: 8,32 R 67493880 + 8 [gc] gc-5678 [003] .... 214327.025972: block_bio_backmerge: 8,32 R 67493880 + 8 [gc] gc-5678 [003] .... 214327.026000: block_bio_queue: 8,32 WS 34123776 + 2048 [gc] gc-5678 [003] .... 214327.026019: block_getrq: 8,32 WS 34123776 + 2048 [gc] gc-5678 [003] d..1 214327.026021: block_rq_insert: 8,32 R 131072 () 67493632 + 256 [gc] gc-5678 [003] d..1 214327.026023: block_unplug: [gc] 1 gc-5678 [003] d..1 214327.026026: block_rq_issue: 8,32 R 131072 () 67493632 + 256 [gc] gc-5678 [003] .... 214327.026046: block_plug: [gc] Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-08-14 14:37:25 +00:00
if (IS_ERR(fio->encrypted_page)) {
/* flush pending IOs and wait for a while in the ENOMEM case */
if (PTR_ERR(fio->encrypted_page) == -ENOMEM) {
f2fs_flush_merged_writes(fio->sbi);
mm: introduce memalloc_retry_wait() Various places in the kernel - largely in filesystems - respond to a memory allocation failure by looping around and re-trying. Some of these cannot conveniently use __GFP_NOFAIL, for reasons such as: - a GFP_ATOMIC allocation, which __GFP_NOFAIL doesn't work on - a need to check for the process being signalled between failures - the possibility that other recovery actions could be performed - the allocation is quite deep in support code, and passing down an extra flag to say if __GFP_NOFAIL is wanted would be clumsy. Many of these currently use congestion_wait() which (in almost all cases) simply waits the given timeout - congestion isn't tracked for most devices. It isn't clear what the best delay is for loops, but it is clear that the various filesystems shouldn't be responsible for choosing a timeout. This patch introduces memalloc_retry_wait() with takes on that responsibility. Code that wants to retry a memory allocation can call this function passing the GFP flags that were used. It will wait however is appropriate. For now, it only considers __GFP_NORETRY and whatever gfpflags_allow_blocking() tests. If blocking is allowed without __GFP_NORETRY, then alloc_page either made some reclaim progress, or waited for a while, before failing. So there is no need for much further waiting. memalloc_retry_wait() will wait until the current jiffie ends. If this condition is not met, then alloc_page() won't have waited much if at all. In that case memalloc_retry_wait() waits about 200ms. This is the delay that most current loops uses. linux/sched/mm.h needs to be included in some files now, but linux/backing-dev.h does not. Link: https://lkml.kernel.org/r/163754371968.13692.1277530886009912421@noble.neil.brown.name Signed-off-by: NeilBrown <neilb@suse.de> Cc: Dave Chinner <david@fromorbit.com> Cc: Michal Hocko <mhocko@suse.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Jaegeuk Kim <jaegeuk@kernel.org> Cc: Chao Yu <chao@kernel.org> Cc: Darrick J. Wong <djwong@kernel.org> Cc: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-01-14 22:07:14 +00:00
memalloc_retry_wait(GFP_NOFS);
f2fs: readahead encrypted block during GC During GC, for each encrypted block, we will read block synchronously into meta page, and then submit it into current cold data log area. So this block read model with 4k granularity can make poor performance, like migrating non-encrypted block, let's readahead encrypted block as well to improve migration performance. To implement this, we choose meta page that its index is old block address of the encrypted block, and readahead ciphertext into this page, later, if readaheaded page is still updated, we will load its data into target meta page, and submit the write IO. Note that for OPU, truncation, deletion, we need to invalid meta page after we invalid old block address, to make sure we won't load invalid data from target meta page during encrypted block migration. for ((i = 0; i < 1000; i++)) do { xfs_io -f /mnt/f2fs/dir/$i -c "pwrite 0 128k" -c "fsync"; } done for ((i = 0; i < 1000; i+=2)) do { rm /mnt/f2fs/dir/$i; } done ret = ioctl(fd, F2FS_IOC_GARBAGE_COLLECT, 0); Before: gc-6549 [001] d..1 214682.212797: block_rq_insert: 8,32 RA 32768 () 786400 + 64 [gc] gc-6549 [001] d..1 214682.212802: block_unplug: [gc] 1 gc-6549 [001] .... 214682.213892: block_bio_queue: 8,32 R 67494144 + 8 [gc] gc-6549 [001] .... 214682.213899: block_getrq: 8,32 R 67494144 + 8 [gc] gc-6549 [001] .... 214682.213902: block_plug: [gc] gc-6549 [001] d..1 214682.213905: block_rq_insert: 8,32 R 4096 () 67494144 + 8 [gc] gc-6549 [001] d..1 214682.213908: block_unplug: [gc] 1 gc-6549 [001] .... 214682.226405: block_bio_queue: 8,32 R 67494152 + 8 [gc] gc-6549 [001] .... 214682.226412: block_getrq: 8,32 R 67494152 + 8 [gc] gc-6549 [001] .... 214682.226414: block_plug: [gc] gc-6549 [001] d..1 214682.226417: block_rq_insert: 8,32 R 4096 () 67494152 + 8 [gc] gc-6549 [001] d..1 214682.226420: block_unplug: [gc] 1 gc-6549 [001] .... 214682.226904: block_bio_queue: 8,32 R 67494160 + 8 [gc] gc-6549 [001] .... 214682.226910: block_getrq: 8,32 R 67494160 + 8 [gc] gc-6549 [001] .... 214682.226911: block_plug: [gc] gc-6549 [001] d..1 214682.226914: block_rq_insert: 8,32 R 4096 () 67494160 + 8 [gc] gc-6549 [001] d..1 214682.226916: block_unplug: [gc] 1 After: gc-5678 [003] .... 214327.025906: block_bio_queue: 8,32 R 67493824 + 8 [gc] gc-5678 [003] .... 214327.025908: block_bio_backmerge: 8,32 R 67493824 + 8 [gc] gc-5678 [003] .... 214327.025915: block_bio_queue: 8,32 R 67493832 + 8 [gc] gc-5678 [003] .... 214327.025917: block_bio_backmerge: 8,32 R 67493832 + 8 [gc] gc-5678 [003] .... 214327.025923: block_bio_queue: 8,32 R 67493840 + 8 [gc] gc-5678 [003] .... 214327.025925: block_bio_backmerge: 8,32 R 67493840 + 8 [gc] gc-5678 [003] .... 214327.025932: block_bio_queue: 8,32 R 67493848 + 8 [gc] gc-5678 [003] .... 214327.025934: block_bio_backmerge: 8,32 R 67493848 + 8 [gc] gc-5678 [003] .... 214327.025941: block_bio_queue: 8,32 R 67493856 + 8 [gc] gc-5678 [003] .... 214327.025943: block_bio_backmerge: 8,32 R 67493856 + 8 [gc] gc-5678 [003] .... 214327.025953: block_bio_queue: 8,32 R 67493864 + 8 [gc] gc-5678 [003] .... 214327.025955: block_bio_backmerge: 8,32 R 67493864 + 8 [gc] gc-5678 [003] .... 214327.025962: block_bio_queue: 8,32 R 67493872 + 8 [gc] gc-5678 [003] .... 214327.025964: block_bio_backmerge: 8,32 R 67493872 + 8 [gc] gc-5678 [003] .... 214327.025970: block_bio_queue: 8,32 R 67493880 + 8 [gc] gc-5678 [003] .... 214327.025972: block_bio_backmerge: 8,32 R 67493880 + 8 [gc] gc-5678 [003] .... 214327.026000: block_bio_queue: 8,32 WS 34123776 + 2048 [gc] gc-5678 [003] .... 214327.026019: block_getrq: 8,32 WS 34123776 + 2048 [gc] gc-5678 [003] d..1 214327.026021: block_rq_insert: 8,32 R 131072 () 67493632 + 256 [gc] gc-5678 [003] d..1 214327.026023: block_unplug: [gc] 1 gc-5678 [003] d..1 214327.026026: block_rq_issue: 8,32 R 131072 () 67493632 + 256 [gc] gc-5678 [003] .... 214327.026046: block_plug: [gc] Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-08-14 14:37:25 +00:00
gfp_flags |= __GFP_NOFAIL;
goto retry_encrypt;
}
return PTR_ERR(fio->encrypted_page);
}
f2fs: readahead encrypted block during GC During GC, for each encrypted block, we will read block synchronously into meta page, and then submit it into current cold data log area. So this block read model with 4k granularity can make poor performance, like migrating non-encrypted block, let's readahead encrypted block as well to improve migration performance. To implement this, we choose meta page that its index is old block address of the encrypted block, and readahead ciphertext into this page, later, if readaheaded page is still updated, we will load its data into target meta page, and submit the write IO. Note that for OPU, truncation, deletion, we need to invalid meta page after we invalid old block address, to make sure we won't load invalid data from target meta page during encrypted block migration. for ((i = 0; i < 1000; i++)) do { xfs_io -f /mnt/f2fs/dir/$i -c "pwrite 0 128k" -c "fsync"; } done for ((i = 0; i < 1000; i+=2)) do { rm /mnt/f2fs/dir/$i; } done ret = ioctl(fd, F2FS_IOC_GARBAGE_COLLECT, 0); Before: gc-6549 [001] d..1 214682.212797: block_rq_insert: 8,32 RA 32768 () 786400 + 64 [gc] gc-6549 [001] d..1 214682.212802: block_unplug: [gc] 1 gc-6549 [001] .... 214682.213892: block_bio_queue: 8,32 R 67494144 + 8 [gc] gc-6549 [001] .... 214682.213899: block_getrq: 8,32 R 67494144 + 8 [gc] gc-6549 [001] .... 214682.213902: block_plug: [gc] gc-6549 [001] d..1 214682.213905: block_rq_insert: 8,32 R 4096 () 67494144 + 8 [gc] gc-6549 [001] d..1 214682.213908: block_unplug: [gc] 1 gc-6549 [001] .... 214682.226405: block_bio_queue: 8,32 R 67494152 + 8 [gc] gc-6549 [001] .... 214682.226412: block_getrq: 8,32 R 67494152 + 8 [gc] gc-6549 [001] .... 214682.226414: block_plug: [gc] gc-6549 [001] d..1 214682.226417: block_rq_insert: 8,32 R 4096 () 67494152 + 8 [gc] gc-6549 [001] d..1 214682.226420: block_unplug: [gc] 1 gc-6549 [001] .... 214682.226904: block_bio_queue: 8,32 R 67494160 + 8 [gc] gc-6549 [001] .... 214682.226910: block_getrq: 8,32 R 67494160 + 8 [gc] gc-6549 [001] .... 214682.226911: block_plug: [gc] gc-6549 [001] d..1 214682.226914: block_rq_insert: 8,32 R 4096 () 67494160 + 8 [gc] gc-6549 [001] d..1 214682.226916: block_unplug: [gc] 1 After: gc-5678 [003] .... 214327.025906: block_bio_queue: 8,32 R 67493824 + 8 [gc] gc-5678 [003] .... 214327.025908: block_bio_backmerge: 8,32 R 67493824 + 8 [gc] gc-5678 [003] .... 214327.025915: block_bio_queue: 8,32 R 67493832 + 8 [gc] gc-5678 [003] .... 214327.025917: block_bio_backmerge: 8,32 R 67493832 + 8 [gc] gc-5678 [003] .... 214327.025923: block_bio_queue: 8,32 R 67493840 + 8 [gc] gc-5678 [003] .... 214327.025925: block_bio_backmerge: 8,32 R 67493840 + 8 [gc] gc-5678 [003] .... 214327.025932: block_bio_queue: 8,32 R 67493848 + 8 [gc] gc-5678 [003] .... 214327.025934: block_bio_backmerge: 8,32 R 67493848 + 8 [gc] gc-5678 [003] .... 214327.025941: block_bio_queue: 8,32 R 67493856 + 8 [gc] gc-5678 [003] .... 214327.025943: block_bio_backmerge: 8,32 R 67493856 + 8 [gc] gc-5678 [003] .... 214327.025953: block_bio_queue: 8,32 R 67493864 + 8 [gc] gc-5678 [003] .... 214327.025955: block_bio_backmerge: 8,32 R 67493864 + 8 [gc] gc-5678 [003] .... 214327.025962: block_bio_queue: 8,32 R 67493872 + 8 [gc] gc-5678 [003] .... 214327.025964: block_bio_backmerge: 8,32 R 67493872 + 8 [gc] gc-5678 [003] .... 214327.025970: block_bio_queue: 8,32 R 67493880 + 8 [gc] gc-5678 [003] .... 214327.025972: block_bio_backmerge: 8,32 R 67493880 + 8 [gc] gc-5678 [003] .... 214327.026000: block_bio_queue: 8,32 WS 34123776 + 2048 [gc] gc-5678 [003] .... 214327.026019: block_getrq: 8,32 WS 34123776 + 2048 [gc] gc-5678 [003] d..1 214327.026021: block_rq_insert: 8,32 R 131072 () 67493632 + 256 [gc] gc-5678 [003] d..1 214327.026023: block_unplug: [gc] 1 gc-5678 [003] d..1 214327.026026: block_rq_issue: 8,32 R 131072 () 67493632 + 256 [gc] gc-5678 [003] .... 214327.026046: block_plug: [gc] Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-08-14 14:37:25 +00:00
mpage = find_lock_page(META_MAPPING(fio->sbi), fio->old_blkaddr);
if (mpage) {
if (PageUptodate(mpage))
memcpy(page_address(mpage),
page_address(fio->encrypted_page), PAGE_SIZE);
f2fs_put_page(mpage, 1);
}
f2fs: readahead encrypted block during GC During GC, for each encrypted block, we will read block synchronously into meta page, and then submit it into current cold data log area. So this block read model with 4k granularity can make poor performance, like migrating non-encrypted block, let's readahead encrypted block as well to improve migration performance. To implement this, we choose meta page that its index is old block address of the encrypted block, and readahead ciphertext into this page, later, if readaheaded page is still updated, we will load its data into target meta page, and submit the write IO. Note that for OPU, truncation, deletion, we need to invalid meta page after we invalid old block address, to make sure we won't load invalid data from target meta page during encrypted block migration. for ((i = 0; i < 1000; i++)) do { xfs_io -f /mnt/f2fs/dir/$i -c "pwrite 0 128k" -c "fsync"; } done for ((i = 0; i < 1000; i+=2)) do { rm /mnt/f2fs/dir/$i; } done ret = ioctl(fd, F2FS_IOC_GARBAGE_COLLECT, 0); Before: gc-6549 [001] d..1 214682.212797: block_rq_insert: 8,32 RA 32768 () 786400 + 64 [gc] gc-6549 [001] d..1 214682.212802: block_unplug: [gc] 1 gc-6549 [001] .... 214682.213892: block_bio_queue: 8,32 R 67494144 + 8 [gc] gc-6549 [001] .... 214682.213899: block_getrq: 8,32 R 67494144 + 8 [gc] gc-6549 [001] .... 214682.213902: block_plug: [gc] gc-6549 [001] d..1 214682.213905: block_rq_insert: 8,32 R 4096 () 67494144 + 8 [gc] gc-6549 [001] d..1 214682.213908: block_unplug: [gc] 1 gc-6549 [001] .... 214682.226405: block_bio_queue: 8,32 R 67494152 + 8 [gc] gc-6549 [001] .... 214682.226412: block_getrq: 8,32 R 67494152 + 8 [gc] gc-6549 [001] .... 214682.226414: block_plug: [gc] gc-6549 [001] d..1 214682.226417: block_rq_insert: 8,32 R 4096 () 67494152 + 8 [gc] gc-6549 [001] d..1 214682.226420: block_unplug: [gc] 1 gc-6549 [001] .... 214682.226904: block_bio_queue: 8,32 R 67494160 + 8 [gc] gc-6549 [001] .... 214682.226910: block_getrq: 8,32 R 67494160 + 8 [gc] gc-6549 [001] .... 214682.226911: block_plug: [gc] gc-6549 [001] d..1 214682.226914: block_rq_insert: 8,32 R 4096 () 67494160 + 8 [gc] gc-6549 [001] d..1 214682.226916: block_unplug: [gc] 1 After: gc-5678 [003] .... 214327.025906: block_bio_queue: 8,32 R 67493824 + 8 [gc] gc-5678 [003] .... 214327.025908: block_bio_backmerge: 8,32 R 67493824 + 8 [gc] gc-5678 [003] .... 214327.025915: block_bio_queue: 8,32 R 67493832 + 8 [gc] gc-5678 [003] .... 214327.025917: block_bio_backmerge: 8,32 R 67493832 + 8 [gc] gc-5678 [003] .... 214327.025923: block_bio_queue: 8,32 R 67493840 + 8 [gc] gc-5678 [003] .... 214327.025925: block_bio_backmerge: 8,32 R 67493840 + 8 [gc] gc-5678 [003] .... 214327.025932: block_bio_queue: 8,32 R 67493848 + 8 [gc] gc-5678 [003] .... 214327.025934: block_bio_backmerge: 8,32 R 67493848 + 8 [gc] gc-5678 [003] .... 214327.025941: block_bio_queue: 8,32 R 67493856 + 8 [gc] gc-5678 [003] .... 214327.025943: block_bio_backmerge: 8,32 R 67493856 + 8 [gc] gc-5678 [003] .... 214327.025953: block_bio_queue: 8,32 R 67493864 + 8 [gc] gc-5678 [003] .... 214327.025955: block_bio_backmerge: 8,32 R 67493864 + 8 [gc] gc-5678 [003] .... 214327.025962: block_bio_queue: 8,32 R 67493872 + 8 [gc] gc-5678 [003] .... 214327.025964: block_bio_backmerge: 8,32 R 67493872 + 8 [gc] gc-5678 [003] .... 214327.025970: block_bio_queue: 8,32 R 67493880 + 8 [gc] gc-5678 [003] .... 214327.025972: block_bio_backmerge: 8,32 R 67493880 + 8 [gc] gc-5678 [003] .... 214327.026000: block_bio_queue: 8,32 WS 34123776 + 2048 [gc] gc-5678 [003] .... 214327.026019: block_getrq: 8,32 WS 34123776 + 2048 [gc] gc-5678 [003] d..1 214327.026021: block_rq_insert: 8,32 R 131072 () 67493632 + 256 [gc] gc-5678 [003] d..1 214327.026023: block_unplug: [gc] 1 gc-5678 [003] d..1 214327.026026: block_rq_issue: 8,32 R 131072 () 67493632 + 256 [gc] gc-5678 [003] .... 214327.026046: block_plug: [gc] Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-08-14 14:37:25 +00:00
return 0;
}
static inline bool check_inplace_update_policy(struct inode *inode,
struct f2fs_io_info *fio)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
if (IS_F2FS_IPU_HONOR_OPU_WRITE(sbi) &&
is_inode_flag_set(inode, FI_OPU_WRITE))
return false;
if (IS_F2FS_IPU_FORCE(sbi))
return true;
if (IS_F2FS_IPU_SSR(sbi) && f2fs_need_SSR(sbi))
return true;
if (IS_F2FS_IPU_UTIL(sbi) && utilization(sbi) > SM_I(sbi)->min_ipu_util)
return true;
if (IS_F2FS_IPU_SSR_UTIL(sbi) && f2fs_need_SSR(sbi) &&
utilization(sbi) > SM_I(sbi)->min_ipu_util)
return true;
/*
* IPU for rewrite async pages
*/
if (IS_F2FS_IPU_ASYNC(sbi) && fio && fio->op == REQ_OP_WRITE &&
!(fio->op_flags & REQ_SYNC) && !IS_ENCRYPTED(inode))
return true;
/* this is only set during fdatasync */
if (IS_F2FS_IPU_FSYNC(sbi) && is_inode_flag_set(inode, FI_NEED_IPU))
return true;
if (unlikely(fio && is_sbi_flag_set(sbi, SBI_CP_DISABLED) &&
!f2fs_is_checkpointed_data(sbi, fio->old_blkaddr)))
return true;
return false;
}
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
bool f2fs_should_update_inplace(struct inode *inode, struct f2fs_io_info *fio)
{
f2fs: swap: support migrating swapfile in aligned write mode This patch supports to migrate swapfile in aligned write mode during swapon in order to keep swapfile being aligned to section as much as possible, then pinned swapfile will locates fully filled section which may not affected by GC. However, for the case that swapfile's size is not aligned to section size, it will still leave last extent in file's tail as unaligned due to its size is smaller than section size, like case #2. case #1 xfs_io -f /mnt/f2fs/file -c "pwrite 0 4M" -c "fsync" Before swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..3047]: 1123352..1126399 3048 0x1000 1: [3048..7143]: 237568..241663 4096 0x1000 2: [7144..8191]: 245760..246807 1048 0x1001 After swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..8191]: 249856..258047 8192 0x1001 Kmsg: F2FS-fs (zram0): Swapfile (2) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(2097152 * n) case #2 xfs_io -f /mnt/f2fs/file -c "pwrite 0 3M" -c "fsync" Before swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..3047]: 246808..249855 3048 0x1000 1: [3048..6143]: 237568..240663 3096 0x1001 After swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..4095]: 258048..262143 4096 0x1000 1: [4096..6143]: 238616..240663 2048 0x1001 Kmsg: F2FS-fs (zram0): Swapfile: last extent is not aligned to section F2FS-fs (zram0): Swapfile (2) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(2097152 * n) Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2021-05-26 06:29:27 +00:00
/* swap file is migrating in aligned write mode */
if (is_inode_flag_set(inode, FI_ALIGNED_WRITE))
return false;
if (f2fs_is_pinned_file(inode))
return true;
/* if this is cold file, we should overwrite to avoid fragmentation */
if (file_is_cold(inode) && !is_inode_flag_set(inode, FI_OPU_WRITE))
return true;
return check_inplace_update_policy(inode, fio);
}
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
bool f2fs_should_update_outplace(struct inode *inode, struct f2fs_io_info *fio)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
/* The below cases were checked when setting it. */
if (f2fs_is_pinned_file(inode))
return false;
if (fio && is_sbi_flag_set(sbi, SBI_NEED_FSCK))
return true;
if (f2fs_lfs_mode(sbi))
return true;
if (S_ISDIR(inode->i_mode))
return true;
if (IS_NOQUOTA(inode))
return true;
if (f2fs_used_in_atomic_write(inode))
return true;
/* rewrite low ratio compress data w/ OPU mode to avoid fragmentation */
if (f2fs_compressed_file(inode) &&
F2FS_OPTION(sbi).compress_mode == COMPR_MODE_USER &&
is_inode_flag_set(inode, FI_ENABLE_COMPRESS))
return true;
f2fs: swap: support migrating swapfile in aligned write mode This patch supports to migrate swapfile in aligned write mode during swapon in order to keep swapfile being aligned to section as much as possible, then pinned swapfile will locates fully filled section which may not affected by GC. However, for the case that swapfile's size is not aligned to section size, it will still leave last extent in file's tail as unaligned due to its size is smaller than section size, like case #2. case #1 xfs_io -f /mnt/f2fs/file -c "pwrite 0 4M" -c "fsync" Before swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..3047]: 1123352..1126399 3048 0x1000 1: [3048..7143]: 237568..241663 4096 0x1000 2: [7144..8191]: 245760..246807 1048 0x1001 After swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..8191]: 249856..258047 8192 0x1001 Kmsg: F2FS-fs (zram0): Swapfile (2) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(2097152 * n) case #2 xfs_io -f /mnt/f2fs/file -c "pwrite 0 3M" -c "fsync" Before swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..3047]: 246808..249855 3048 0x1000 1: [3048..6143]: 237568..240663 3096 0x1001 After swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..4095]: 258048..262143 4096 0x1000 1: [4096..6143]: 238616..240663 2048 0x1001 Kmsg: F2FS-fs (zram0): Swapfile: last extent is not aligned to section F2FS-fs (zram0): Swapfile (2) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(2097152 * n) Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2021-05-26 06:29:27 +00:00
/* swap file is migrating in aligned write mode */
if (is_inode_flag_set(inode, FI_ALIGNED_WRITE))
return true;
if (is_inode_flag_set(inode, FI_OPU_WRITE))
return true;
if (fio) {
f2fs: restructure f2fs page.private layout Restruct f2fs page private layout for below reasons: There are some cases that f2fs wants to set a flag in a page to indicate a specified status of page: a) page is in transaction list for atomic write b) page contains dummy data for aligned write c) page is migrating for GC d) page contains inline data for inline inode flush e) page belongs to merkle tree, and is verified for fsverity f) page is dirty and has filesystem/inode reference count for writeback g) page is temporary and has decompress io context reference for compression There are existed places in page structure we can use to store f2fs private status/data: - page.flags: PG_checked, PG_private - page.private However it was a mess when we using them, which may cause potential confliction: page.private PG_private PG_checked page._refcount (+1 at most) a) -1 set +1 b) -2 set c), d), e) set f) 0 set +1 g) pointer set The other problem is page.flags has no free slot, if we can avoid set zero to page.private and set PG_private flag, then we use non-zero value to indicate PG_private status, so that we may have chance to reclaim PG_private slot for other usage. [1] The other concern is f2fs has bad scalability in aspect of indicating more page status. So in this patch, let's restructure f2fs' page.private as below to solve above issues: Layout A: lowest bit should be 1 | bit0 = 1 | bit1 | bit2 | ... | bit MAX | private data .... | bit 0 PAGE_PRIVATE_NOT_POINTER bit 1 PAGE_PRIVATE_ATOMIC_WRITE bit 2 PAGE_PRIVATE_DUMMY_WRITE bit 3 PAGE_PRIVATE_ONGOING_MIGRATION bit 4 PAGE_PRIVATE_INLINE_INODE bit 5 PAGE_PRIVATE_REF_RESOURCE bit 6- f2fs private data Layout B: lowest bit should be 0 page.private is a wrapped pointer. After the change: page.private PG_private PG_checked page._refcount (+1 at most) a) 11 set +1 b) 101 set +1 c) 1001 set +1 d) 10001 set +1 e) set f) 100001 set +1 g) pointer set +1 [1] https://lore.kernel.org/linux-f2fs-devel/20210422154705.GO3596236@casper.infradead.org/T/#u Cc: Matthew Wilcox <willy@infradead.org> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2021-04-28 09:20:31 +00:00
if (page_private_gcing(fio->page))
return true;
if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED) &&
f2fs_is_checkpointed_data(sbi, fio->old_blkaddr)))
return true;
}
return false;
}
static inline bool need_inplace_update(struct f2fs_io_info *fio)
{
struct inode *inode = fio->page->mapping->host;
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
if (f2fs_should_update_outplace(inode, fio))
return false;
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
return f2fs_should_update_inplace(inode, fio);
}
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
int f2fs_do_write_data_page(struct f2fs_io_info *fio)
{
struct page *page = fio->page;
struct inode *inode = page->mapping->host;
struct dnode_of_data dn;
struct node_info ni;
bool ipu_force = false;
int err = 0;
/* Use COW inode to make dnode_of_data for atomic write */
if (f2fs_is_atomic_file(inode))
set_new_dnode(&dn, F2FS_I(inode)->cow_inode, NULL, NULL, 0);
else
set_new_dnode(&dn, inode, NULL, NULL, 0);
if (need_inplace_update(fio) &&
f2fs_lookup_read_extent_cache_block(inode, page->index,
&fio->old_blkaddr)) {
f2fs: fix to do sanity check with block address in main area This patch add to do sanity check with below field: - cp_pack_total_block_count - blkaddr of data/node - extent info - Overview BUG() in verify_block_addr() when writing to a corrupted f2fs image - Reproduce (4.18 upstream kernel) - POC (poc.c) static void activity(char *mpoint) { char *foo_bar_baz; int err; static int buf[8192]; memset(buf, 0, sizeof(buf)); err = asprintf(&foo_bar_baz, "%s/foo/bar/baz", mpoint); int fd = open(foo_bar_baz, O_RDWR | O_TRUNC, 0777); if (fd >= 0) { write(fd, (char *)buf, sizeof(buf)); fdatasync(fd); close(fd); } } int main(int argc, char *argv[]) { activity(argv[1]); return 0; } - Kernel message [ 689.349473] F2FS-fs (loop0): Mounted with checkpoint version = 3 [ 699.728662] WARNING: CPU: 0 PID: 1309 at fs/f2fs/segment.c:2860 f2fs_inplace_write_data+0x232/0x240 [ 699.728670] Modules linked in: snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_pcm snd_timer snd mac_hid i2c_piix4 soundcore ib_iser rdma_cm iw_cm ib_cm ib_core iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx raid1 raid0 multipath linear 8139too crct10dif_pclmul crc32_pclmul qxl drm_kms_helper syscopyarea aesni_intel sysfillrect sysimgblt fb_sys_fops ttm drm aes_x86_64 crypto_simd cryptd 8139cp glue_helper mii pata_acpi floppy [ 699.729056] CPU: 0 PID: 1309 Comm: a.out Not tainted 4.18.0-rc1+ #4 [ 699.729064] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.729074] RIP: 0010:f2fs_inplace_write_data+0x232/0x240 [ 699.729076] Code: ff e9 cf fe ff ff 49 8d 7d 10 e8 39 45 ad ff 4d 8b 7d 10 be 04 00 00 00 49 8d 7f 48 e8 07 49 ad ff 45 8b 7f 48 e9 fb fe ff ff <0f> 0b f0 41 80 4d 48 04 e9 65 fe ff ff 90 66 66 66 66 90 55 48 8d [ 699.729130] RSP: 0018:ffff8801f43af568 EFLAGS: 00010202 [ 699.729139] RAX: 000000000000003f RBX: ffff8801f43af7b8 RCX: ffffffffb88c9113 [ 699.729142] RDX: 0000000000000003 RSI: dffffc0000000000 RDI: ffff8802024e5540 [ 699.729144] RBP: ffff8801f43af590 R08: 0000000000000009 R09: ffffffffffffffe8 [ 699.729147] R10: 0000000000000001 R11: ffffed0039b0596a R12: ffff8802024e5540 [ 699.729149] R13: ffff8801f0335500 R14: ffff8801e3e7a700 R15: ffff8801e1ee4450 [ 699.729154] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.729156] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.729159] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.729171] Call Trace: [ 699.729192] f2fs_do_write_data_page+0x2e2/0xe00 [ 699.729203] ? f2fs_should_update_outplace+0xd0/0xd0 [ 699.729238] ? memcg_drain_all_list_lrus+0x280/0x280 [ 699.729269] ? __radix_tree_replace+0xa3/0x120 [ 699.729276] __write_data_page+0x5c7/0xe30 [ 699.729291] ? kasan_check_read+0x11/0x20 [ 699.729310] ? page_mapped+0x8a/0x110 [ 699.729321] ? page_mkclean+0xe9/0x160 [ 699.729327] ? f2fs_do_write_data_page+0xe00/0xe00 [ 699.729331] ? invalid_page_referenced_vma+0x130/0x130 [ 699.729345] ? clear_page_dirty_for_io+0x332/0x450 [ 699.729351] f2fs_write_cache_pages+0x4ca/0x860 [ 699.729358] ? __write_data_page+0xe30/0xe30 [ 699.729374] ? percpu_counter_add_batch+0x22/0xa0 [ 699.729380] ? kasan_check_write+0x14/0x20 [ 699.729391] ? _raw_spin_lock+0x17/0x40 [ 699.729403] ? f2fs_mark_inode_dirty_sync.part.18+0x16/0x30 [ 699.729413] ? iov_iter_advance+0x113/0x640 [ 699.729418] ? f2fs_write_end+0x133/0x2e0 [ 699.729423] ? balance_dirty_pages_ratelimited+0x239/0x640 [ 699.729428] f2fs_write_data_pages+0x329/0x520 [ 699.729433] ? generic_perform_write+0x250/0x320 [ 699.729438] ? f2fs_write_cache_pages+0x860/0x860 [ 699.729454] ? current_time+0x110/0x110 [ 699.729459] ? f2fs_preallocate_blocks+0x1ef/0x370 [ 699.729464] do_writepages+0x37/0xb0 [ 699.729468] ? f2fs_write_cache_pages+0x860/0x860 [ 699.729472] ? do_writepages+0x37/0xb0 [ 699.729478] __filemap_fdatawrite_range+0x19a/0x1f0 [ 699.729483] ? delete_from_page_cache_batch+0x4e0/0x4e0 [ 699.729496] ? __vfs_write+0x2b2/0x410 [ 699.729501] file_write_and_wait_range+0x66/0xb0 [ 699.729506] f2fs_do_sync_file+0x1f9/0xd90 [ 699.729511] ? truncate_partial_data_page+0x290/0x290 [ 699.729521] ? __sb_end_write+0x30/0x50 [ 699.729526] ? vfs_write+0x20f/0x260 [ 699.729530] f2fs_sync_file+0x9a/0xb0 [ 699.729534] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.729548] vfs_fsync_range+0x68/0x100 [ 699.729554] ? __fget_light+0xc9/0xe0 [ 699.729558] do_fsync+0x3d/0x70 [ 699.729562] __x64_sys_fdatasync+0x24/0x30 [ 699.729585] do_syscall_64+0x78/0x170 [ 699.729595] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 699.729613] RIP: 0033:0x7f9bf930d800 [ 699.729615] Code: 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 83 3d 49 bf 2c 00 00 75 10 b8 4b 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 be 78 01 00 48 89 04 24 [ 699.729668] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.729673] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.729675] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.729678] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.729680] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.729683] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000 [ 699.729687] ---[ end trace 4ce02f25ff7d3df5 ]--- [ 699.729782] ------------[ cut here ]------------ [ 699.729785] kernel BUG at fs/f2fs/segment.h:654! [ 699.731055] invalid opcode: 0000 [#1] SMP KASAN PTI [ 699.732104] CPU: 0 PID: 1309 Comm: a.out Tainted: G W 4.18.0-rc1+ #4 [ 699.733684] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.735611] RIP: 0010:f2fs_submit_page_bio+0x29b/0x730 [ 699.736649] Code: 54 49 8d bd 18 04 00 00 e8 b2 59 af ff 41 8b 8d 18 04 00 00 8b 45 b8 41 d3 e6 44 01 f0 4c 8d 73 14 41 39 c7 0f 82 37 fe ff ff <0f> 0b 65 8b 05 2c 04 77 47 89 c0 48 0f a3 05 52 c1 d5 01 0f 92 c0 [ 699.740524] RSP: 0018:ffff8801f43af508 EFLAGS: 00010283 [ 699.741573] RAX: 0000000000000000 RBX: ffff8801f43af7b8 RCX: ffffffffb88a7cef [ 699.743006] RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff8801e3e7a64c [ 699.744426] RBP: ffff8801f43af558 R08: ffffed003e066b55 R09: ffffed003e066b55 [ 699.745833] R10: 0000000000000001 R11: ffffed003e066b54 R12: ffffea0007876940 [ 699.747256] R13: ffff8801f0335500 R14: ffff8801e3e7a600 R15: 0000000000000001 [ 699.748683] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.750293] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.751462] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.752874] Call Trace: [ 699.753386] ? f2fs_inplace_write_data+0x93/0x240 [ 699.754341] f2fs_inplace_write_data+0xd2/0x240 [ 699.755271] f2fs_do_write_data_page+0x2e2/0xe00 [ 699.756214] ? f2fs_should_update_outplace+0xd0/0xd0 [ 699.757215] ? memcg_drain_all_list_lrus+0x280/0x280 [ 699.758209] ? __radix_tree_replace+0xa3/0x120 [ 699.759164] __write_data_page+0x5c7/0xe30 [ 699.760002] ? kasan_check_read+0x11/0x20 [ 699.760823] ? page_mapped+0x8a/0x110 [ 699.761573] ? page_mkclean+0xe9/0x160 [ 699.762345] ? f2fs_do_write_data_page+0xe00/0xe00 [ 699.763332] ? invalid_page_referenced_vma+0x130/0x130 [ 699.764374] ? clear_page_dirty_for_io+0x332/0x450 [ 699.765347] f2fs_write_cache_pages+0x4ca/0x860 [ 699.766276] ? __write_data_page+0xe30/0xe30 [ 699.767161] ? percpu_counter_add_batch+0x22/0xa0 [ 699.768112] ? kasan_check_write+0x14/0x20 [ 699.768951] ? _raw_spin_lock+0x17/0x40 [ 699.769739] ? f2fs_mark_inode_dirty_sync.part.18+0x16/0x30 [ 699.770885] ? iov_iter_advance+0x113/0x640 [ 699.771743] ? f2fs_write_end+0x133/0x2e0 [ 699.772569] ? balance_dirty_pages_ratelimited+0x239/0x640 [ 699.773680] f2fs_write_data_pages+0x329/0x520 [ 699.774603] ? generic_perform_write+0x250/0x320 [ 699.775544] ? f2fs_write_cache_pages+0x860/0x860 [ 699.776510] ? current_time+0x110/0x110 [ 699.777299] ? f2fs_preallocate_blocks+0x1ef/0x370 [ 699.778279] do_writepages+0x37/0xb0 [ 699.779026] ? f2fs_write_cache_pages+0x860/0x860 [ 699.779978] ? do_writepages+0x37/0xb0 [ 699.780755] __filemap_fdatawrite_range+0x19a/0x1f0 [ 699.781746] ? delete_from_page_cache_batch+0x4e0/0x4e0 [ 699.782820] ? __vfs_write+0x2b2/0x410 [ 699.783597] file_write_and_wait_range+0x66/0xb0 [ 699.784540] f2fs_do_sync_file+0x1f9/0xd90 [ 699.785381] ? truncate_partial_data_page+0x290/0x290 [ 699.786415] ? __sb_end_write+0x30/0x50 [ 699.787204] ? vfs_write+0x20f/0x260 [ 699.787941] f2fs_sync_file+0x9a/0xb0 [ 699.788694] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.789572] vfs_fsync_range+0x68/0x100 [ 699.790360] ? __fget_light+0xc9/0xe0 [ 699.791128] do_fsync+0x3d/0x70 [ 699.791779] __x64_sys_fdatasync+0x24/0x30 [ 699.792614] do_syscall_64+0x78/0x170 [ 699.793371] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 699.794406] RIP: 0033:0x7f9bf930d800 [ 699.795134] Code: 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 83 3d 49 bf 2c 00 00 75 10 b8 4b 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 be 78 01 00 48 89 04 24 [ 699.798960] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.800483] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.801923] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.803373] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.804798] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.806233] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000 [ 699.807667] Modules linked in: snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_pcm snd_timer snd mac_hid i2c_piix4 soundcore ib_iser rdma_cm iw_cm ib_cm ib_core iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx raid1 raid0 multipath linear 8139too crct10dif_pclmul crc32_pclmul qxl drm_kms_helper syscopyarea aesni_intel sysfillrect sysimgblt fb_sys_fops ttm drm aes_x86_64 crypto_simd cryptd 8139cp glue_helper mii pata_acpi floppy [ 699.817079] ---[ end trace 4ce02f25ff7d3df6 ]--- [ 699.818068] RIP: 0010:f2fs_submit_page_bio+0x29b/0x730 [ 699.819114] Code: 54 49 8d bd 18 04 00 00 e8 b2 59 af ff 41 8b 8d 18 04 00 00 8b 45 b8 41 d3 e6 44 01 f0 4c 8d 73 14 41 39 c7 0f 82 37 fe ff ff <0f> 0b 65 8b 05 2c 04 77 47 89 c0 48 0f a3 05 52 c1 d5 01 0f 92 c0 [ 699.822919] RSP: 0018:ffff8801f43af508 EFLAGS: 00010283 [ 699.823977] RAX: 0000000000000000 RBX: ffff8801f43af7b8 RCX: ffffffffb88a7cef [ 699.825436] RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff8801e3e7a64c [ 699.826881] RBP: ffff8801f43af558 R08: ffffed003e066b55 R09: ffffed003e066b55 [ 699.828292] R10: 0000000000000001 R11: ffffed003e066b54 R12: ffffea0007876940 [ 699.829750] R13: ffff8801f0335500 R14: ffff8801e3e7a600 R15: 0000000000000001 [ 699.831192] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.832793] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.833981] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.835556] ================================================================== [ 699.837029] BUG: KASAN: stack-out-of-bounds in update_stack_state+0x38c/0x3e0 [ 699.838462] Read of size 8 at addr ffff8801f43af970 by task a.out/1309 [ 699.840086] CPU: 0 PID: 1309 Comm: a.out Tainted: G D W 4.18.0-rc1+ #4 [ 699.841603] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.843475] Call Trace: [ 699.843982] dump_stack+0x7b/0xb5 [ 699.844661] print_address_description+0x70/0x290 [ 699.845607] kasan_report+0x291/0x390 [ 699.846351] ? update_stack_state+0x38c/0x3e0 [ 699.853831] __asan_load8+0x54/0x90 [ 699.854569] update_stack_state+0x38c/0x3e0 [ 699.855428] ? __read_once_size_nocheck.constprop.7+0x20/0x20 [ 699.856601] ? __save_stack_trace+0x5e/0x100 [ 699.857476] unwind_next_frame.part.5+0x18e/0x490 [ 699.858448] ? unwind_dump+0x290/0x290 [ 699.859217] ? clear_page_dirty_for_io+0x332/0x450 [ 699.860185] __unwind_start+0x106/0x190 [ 699.860974] __save_stack_trace+0x5e/0x100 [ 699.861808] ? __save_stack_trace+0x5e/0x100 [ 699.862691] ? unlink_anon_vmas+0xba/0x2c0 [ 699.863525] save_stack_trace+0x1f/0x30 [ 699.864312] save_stack+0x46/0xd0 [ 699.864993] ? __alloc_pages_slowpath+0x1420/0x1420 [ 699.865990] ? flush_tlb_mm_range+0x15e/0x220 [ 699.866889] ? kasan_check_write+0x14/0x20 [ 699.867724] ? __dec_node_state+0x92/0xb0 [ 699.868543] ? lock_page_memcg+0x85/0xf0 [ 699.869350] ? unlock_page_memcg+0x16/0x80 [ 699.870185] ? page_remove_rmap+0x198/0x520 [ 699.871048] ? mark_page_accessed+0x133/0x200 [ 699.871930] ? _cond_resched+0x1a/0x50 [ 699.872700] ? unmap_page_range+0xcd4/0xe50 [ 699.873551] ? rb_next+0x58/0x80 [ 699.874217] ? rb_next+0x58/0x80 [ 699.874895] __kasan_slab_free+0x13c/0x1a0 [ 699.875734] ? unlink_anon_vmas+0xba/0x2c0 [ 699.876563] kasan_slab_free+0xe/0x10 [ 699.877315] kmem_cache_free+0x89/0x1e0 [ 699.878095] unlink_anon_vmas+0xba/0x2c0 [ 699.878913] free_pgtables+0x101/0x1b0 [ 699.879677] exit_mmap+0x146/0x2a0 [ 699.880378] ? __ia32_sys_munmap+0x50/0x50 [ 699.881214] ? kasan_check_read+0x11/0x20 [ 699.882052] ? mm_update_next_owner+0x322/0x380 [ 699.882985] mmput+0x8b/0x1d0 [ 699.883602] do_exit+0x43a/0x1390 [ 699.884288] ? mm_update_next_owner+0x380/0x380 [ 699.885212] ? f2fs_sync_file+0x9a/0xb0 [ 699.885995] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.886877] ? vfs_fsync_range+0x68/0x100 [ 699.887694] ? __fget_light+0xc9/0xe0 [ 699.888442] ? do_fsync+0x3d/0x70 [ 699.889118] ? __x64_sys_fdatasync+0x24/0x30 [ 699.889996] rewind_stack_do_exit+0x17/0x20 [ 699.890860] RIP: 0033:0x7f9bf930d800 [ 699.891585] Code: Bad RIP value. [ 699.892268] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.893781] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.895220] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.896643] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.898069] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.899505] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000 [ 699.901241] The buggy address belongs to the page: [ 699.902215] page:ffffea0007d0ebc0 count:0 mapcount:0 mapping:0000000000000000 index:0x0 [ 699.903811] flags: 0x2ffff0000000000() [ 699.904585] raw: 02ffff0000000000 0000000000000000 ffffffff07d00101 0000000000000000 [ 699.906125] raw: 0000000000000000 0000000000240000 00000000ffffffff 0000000000000000 [ 699.907673] page dumped because: kasan: bad access detected [ 699.909108] Memory state around the buggy address: [ 699.910077] ffff8801f43af800: 00 f1 f1 f1 f1 00 f4 f4 f4 f3 f3 f3 f3 00 00 00 [ 699.911528] ffff8801f43af880: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 699.912953] >ffff8801f43af900: 00 00 00 00 00 00 00 00 f1 01 f4 f4 f4 f2 f2 f2 [ 699.914392] ^ [ 699.915758] ffff8801f43af980: f2 00 f4 f4 00 00 00 00 f2 00 00 00 00 00 00 00 [ 699.917193] ffff8801f43afa00: 00 00 00 00 00 00 00 00 00 f3 f3 f3 00 00 00 00 [ 699.918634] ================================================================== - Location https://elixir.bootlin.com/linux/v4.18-rc1/source/fs/f2fs/segment.h#L644 Reported-by Wen Xu <wen.xu@gatech.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-08-01 11:13:44 +00:00
if (!f2fs_is_valid_blkaddr(fio->sbi, fio->old_blkaddr,
DATA_GENERIC_ENHANCE))
return -EFSCORRUPTED;
f2fs: fix to do sanity check with block address in main area This patch add to do sanity check with below field: - cp_pack_total_block_count - blkaddr of data/node - extent info - Overview BUG() in verify_block_addr() when writing to a corrupted f2fs image - Reproduce (4.18 upstream kernel) - POC (poc.c) static void activity(char *mpoint) { char *foo_bar_baz; int err; static int buf[8192]; memset(buf, 0, sizeof(buf)); err = asprintf(&foo_bar_baz, "%s/foo/bar/baz", mpoint); int fd = open(foo_bar_baz, O_RDWR | O_TRUNC, 0777); if (fd >= 0) { write(fd, (char *)buf, sizeof(buf)); fdatasync(fd); close(fd); } } int main(int argc, char *argv[]) { activity(argv[1]); return 0; } - Kernel message [ 689.349473] F2FS-fs (loop0): Mounted with checkpoint version = 3 [ 699.728662] WARNING: CPU: 0 PID: 1309 at fs/f2fs/segment.c:2860 f2fs_inplace_write_data+0x232/0x240 [ 699.728670] Modules linked in: snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_pcm snd_timer snd mac_hid i2c_piix4 soundcore ib_iser rdma_cm iw_cm ib_cm ib_core iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx raid1 raid0 multipath linear 8139too crct10dif_pclmul crc32_pclmul qxl drm_kms_helper syscopyarea aesni_intel sysfillrect sysimgblt fb_sys_fops ttm drm aes_x86_64 crypto_simd cryptd 8139cp glue_helper mii pata_acpi floppy [ 699.729056] CPU: 0 PID: 1309 Comm: a.out Not tainted 4.18.0-rc1+ #4 [ 699.729064] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.729074] RIP: 0010:f2fs_inplace_write_data+0x232/0x240 [ 699.729076] Code: ff e9 cf fe ff ff 49 8d 7d 10 e8 39 45 ad ff 4d 8b 7d 10 be 04 00 00 00 49 8d 7f 48 e8 07 49 ad ff 45 8b 7f 48 e9 fb fe ff ff <0f> 0b f0 41 80 4d 48 04 e9 65 fe ff ff 90 66 66 66 66 90 55 48 8d [ 699.729130] RSP: 0018:ffff8801f43af568 EFLAGS: 00010202 [ 699.729139] RAX: 000000000000003f RBX: ffff8801f43af7b8 RCX: ffffffffb88c9113 [ 699.729142] RDX: 0000000000000003 RSI: dffffc0000000000 RDI: ffff8802024e5540 [ 699.729144] RBP: ffff8801f43af590 R08: 0000000000000009 R09: ffffffffffffffe8 [ 699.729147] R10: 0000000000000001 R11: ffffed0039b0596a R12: ffff8802024e5540 [ 699.729149] R13: ffff8801f0335500 R14: ffff8801e3e7a700 R15: ffff8801e1ee4450 [ 699.729154] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.729156] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.729159] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.729171] Call Trace: [ 699.729192] f2fs_do_write_data_page+0x2e2/0xe00 [ 699.729203] ? f2fs_should_update_outplace+0xd0/0xd0 [ 699.729238] ? memcg_drain_all_list_lrus+0x280/0x280 [ 699.729269] ? __radix_tree_replace+0xa3/0x120 [ 699.729276] __write_data_page+0x5c7/0xe30 [ 699.729291] ? kasan_check_read+0x11/0x20 [ 699.729310] ? page_mapped+0x8a/0x110 [ 699.729321] ? page_mkclean+0xe9/0x160 [ 699.729327] ? f2fs_do_write_data_page+0xe00/0xe00 [ 699.729331] ? invalid_page_referenced_vma+0x130/0x130 [ 699.729345] ? clear_page_dirty_for_io+0x332/0x450 [ 699.729351] f2fs_write_cache_pages+0x4ca/0x860 [ 699.729358] ? __write_data_page+0xe30/0xe30 [ 699.729374] ? percpu_counter_add_batch+0x22/0xa0 [ 699.729380] ? kasan_check_write+0x14/0x20 [ 699.729391] ? _raw_spin_lock+0x17/0x40 [ 699.729403] ? f2fs_mark_inode_dirty_sync.part.18+0x16/0x30 [ 699.729413] ? iov_iter_advance+0x113/0x640 [ 699.729418] ? f2fs_write_end+0x133/0x2e0 [ 699.729423] ? balance_dirty_pages_ratelimited+0x239/0x640 [ 699.729428] f2fs_write_data_pages+0x329/0x520 [ 699.729433] ? generic_perform_write+0x250/0x320 [ 699.729438] ? f2fs_write_cache_pages+0x860/0x860 [ 699.729454] ? current_time+0x110/0x110 [ 699.729459] ? f2fs_preallocate_blocks+0x1ef/0x370 [ 699.729464] do_writepages+0x37/0xb0 [ 699.729468] ? f2fs_write_cache_pages+0x860/0x860 [ 699.729472] ? do_writepages+0x37/0xb0 [ 699.729478] __filemap_fdatawrite_range+0x19a/0x1f0 [ 699.729483] ? delete_from_page_cache_batch+0x4e0/0x4e0 [ 699.729496] ? __vfs_write+0x2b2/0x410 [ 699.729501] file_write_and_wait_range+0x66/0xb0 [ 699.729506] f2fs_do_sync_file+0x1f9/0xd90 [ 699.729511] ? truncate_partial_data_page+0x290/0x290 [ 699.729521] ? __sb_end_write+0x30/0x50 [ 699.729526] ? vfs_write+0x20f/0x260 [ 699.729530] f2fs_sync_file+0x9a/0xb0 [ 699.729534] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.729548] vfs_fsync_range+0x68/0x100 [ 699.729554] ? __fget_light+0xc9/0xe0 [ 699.729558] do_fsync+0x3d/0x70 [ 699.729562] __x64_sys_fdatasync+0x24/0x30 [ 699.729585] do_syscall_64+0x78/0x170 [ 699.729595] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 699.729613] RIP: 0033:0x7f9bf930d800 [ 699.729615] Code: 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 83 3d 49 bf 2c 00 00 75 10 b8 4b 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 be 78 01 00 48 89 04 24 [ 699.729668] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.729673] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.729675] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.729678] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.729680] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.729683] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000 [ 699.729687] ---[ end trace 4ce02f25ff7d3df5 ]--- [ 699.729782] ------------[ cut here ]------------ [ 699.729785] kernel BUG at fs/f2fs/segment.h:654! [ 699.731055] invalid opcode: 0000 [#1] SMP KASAN PTI [ 699.732104] CPU: 0 PID: 1309 Comm: a.out Tainted: G W 4.18.0-rc1+ #4 [ 699.733684] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.735611] RIP: 0010:f2fs_submit_page_bio+0x29b/0x730 [ 699.736649] Code: 54 49 8d bd 18 04 00 00 e8 b2 59 af ff 41 8b 8d 18 04 00 00 8b 45 b8 41 d3 e6 44 01 f0 4c 8d 73 14 41 39 c7 0f 82 37 fe ff ff <0f> 0b 65 8b 05 2c 04 77 47 89 c0 48 0f a3 05 52 c1 d5 01 0f 92 c0 [ 699.740524] RSP: 0018:ffff8801f43af508 EFLAGS: 00010283 [ 699.741573] RAX: 0000000000000000 RBX: ffff8801f43af7b8 RCX: ffffffffb88a7cef [ 699.743006] RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff8801e3e7a64c [ 699.744426] RBP: ffff8801f43af558 R08: ffffed003e066b55 R09: ffffed003e066b55 [ 699.745833] R10: 0000000000000001 R11: ffffed003e066b54 R12: ffffea0007876940 [ 699.747256] R13: ffff8801f0335500 R14: ffff8801e3e7a600 R15: 0000000000000001 [ 699.748683] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.750293] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.751462] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.752874] Call Trace: [ 699.753386] ? f2fs_inplace_write_data+0x93/0x240 [ 699.754341] f2fs_inplace_write_data+0xd2/0x240 [ 699.755271] f2fs_do_write_data_page+0x2e2/0xe00 [ 699.756214] ? f2fs_should_update_outplace+0xd0/0xd0 [ 699.757215] ? memcg_drain_all_list_lrus+0x280/0x280 [ 699.758209] ? __radix_tree_replace+0xa3/0x120 [ 699.759164] __write_data_page+0x5c7/0xe30 [ 699.760002] ? kasan_check_read+0x11/0x20 [ 699.760823] ? page_mapped+0x8a/0x110 [ 699.761573] ? page_mkclean+0xe9/0x160 [ 699.762345] ? f2fs_do_write_data_page+0xe00/0xe00 [ 699.763332] ? invalid_page_referenced_vma+0x130/0x130 [ 699.764374] ? clear_page_dirty_for_io+0x332/0x450 [ 699.765347] f2fs_write_cache_pages+0x4ca/0x860 [ 699.766276] ? __write_data_page+0xe30/0xe30 [ 699.767161] ? percpu_counter_add_batch+0x22/0xa0 [ 699.768112] ? kasan_check_write+0x14/0x20 [ 699.768951] ? _raw_spin_lock+0x17/0x40 [ 699.769739] ? f2fs_mark_inode_dirty_sync.part.18+0x16/0x30 [ 699.770885] ? iov_iter_advance+0x113/0x640 [ 699.771743] ? f2fs_write_end+0x133/0x2e0 [ 699.772569] ? balance_dirty_pages_ratelimited+0x239/0x640 [ 699.773680] f2fs_write_data_pages+0x329/0x520 [ 699.774603] ? generic_perform_write+0x250/0x320 [ 699.775544] ? f2fs_write_cache_pages+0x860/0x860 [ 699.776510] ? current_time+0x110/0x110 [ 699.777299] ? f2fs_preallocate_blocks+0x1ef/0x370 [ 699.778279] do_writepages+0x37/0xb0 [ 699.779026] ? f2fs_write_cache_pages+0x860/0x860 [ 699.779978] ? do_writepages+0x37/0xb0 [ 699.780755] __filemap_fdatawrite_range+0x19a/0x1f0 [ 699.781746] ? delete_from_page_cache_batch+0x4e0/0x4e0 [ 699.782820] ? __vfs_write+0x2b2/0x410 [ 699.783597] file_write_and_wait_range+0x66/0xb0 [ 699.784540] f2fs_do_sync_file+0x1f9/0xd90 [ 699.785381] ? truncate_partial_data_page+0x290/0x290 [ 699.786415] ? __sb_end_write+0x30/0x50 [ 699.787204] ? vfs_write+0x20f/0x260 [ 699.787941] f2fs_sync_file+0x9a/0xb0 [ 699.788694] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.789572] vfs_fsync_range+0x68/0x100 [ 699.790360] ? __fget_light+0xc9/0xe0 [ 699.791128] do_fsync+0x3d/0x70 [ 699.791779] __x64_sys_fdatasync+0x24/0x30 [ 699.792614] do_syscall_64+0x78/0x170 [ 699.793371] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 699.794406] RIP: 0033:0x7f9bf930d800 [ 699.795134] Code: 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 83 3d 49 bf 2c 00 00 75 10 b8 4b 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 be 78 01 00 48 89 04 24 [ 699.798960] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.800483] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.801923] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.803373] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.804798] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.806233] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000 [ 699.807667] Modules linked in: snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_pcm snd_timer snd mac_hid i2c_piix4 soundcore ib_iser rdma_cm iw_cm ib_cm ib_core iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx raid1 raid0 multipath linear 8139too crct10dif_pclmul crc32_pclmul qxl drm_kms_helper syscopyarea aesni_intel sysfillrect sysimgblt fb_sys_fops ttm drm aes_x86_64 crypto_simd cryptd 8139cp glue_helper mii pata_acpi floppy [ 699.817079] ---[ end trace 4ce02f25ff7d3df6 ]--- [ 699.818068] RIP: 0010:f2fs_submit_page_bio+0x29b/0x730 [ 699.819114] Code: 54 49 8d bd 18 04 00 00 e8 b2 59 af ff 41 8b 8d 18 04 00 00 8b 45 b8 41 d3 e6 44 01 f0 4c 8d 73 14 41 39 c7 0f 82 37 fe ff ff <0f> 0b 65 8b 05 2c 04 77 47 89 c0 48 0f a3 05 52 c1 d5 01 0f 92 c0 [ 699.822919] RSP: 0018:ffff8801f43af508 EFLAGS: 00010283 [ 699.823977] RAX: 0000000000000000 RBX: ffff8801f43af7b8 RCX: ffffffffb88a7cef [ 699.825436] RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff8801e3e7a64c [ 699.826881] RBP: ffff8801f43af558 R08: ffffed003e066b55 R09: ffffed003e066b55 [ 699.828292] R10: 0000000000000001 R11: ffffed003e066b54 R12: ffffea0007876940 [ 699.829750] R13: ffff8801f0335500 R14: ffff8801e3e7a600 R15: 0000000000000001 [ 699.831192] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.832793] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.833981] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.835556] ================================================================== [ 699.837029] BUG: KASAN: stack-out-of-bounds in update_stack_state+0x38c/0x3e0 [ 699.838462] Read of size 8 at addr ffff8801f43af970 by task a.out/1309 [ 699.840086] CPU: 0 PID: 1309 Comm: a.out Tainted: G D W 4.18.0-rc1+ #4 [ 699.841603] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.843475] Call Trace: [ 699.843982] dump_stack+0x7b/0xb5 [ 699.844661] print_address_description+0x70/0x290 [ 699.845607] kasan_report+0x291/0x390 [ 699.846351] ? update_stack_state+0x38c/0x3e0 [ 699.853831] __asan_load8+0x54/0x90 [ 699.854569] update_stack_state+0x38c/0x3e0 [ 699.855428] ? __read_once_size_nocheck.constprop.7+0x20/0x20 [ 699.856601] ? __save_stack_trace+0x5e/0x100 [ 699.857476] unwind_next_frame.part.5+0x18e/0x490 [ 699.858448] ? unwind_dump+0x290/0x290 [ 699.859217] ? clear_page_dirty_for_io+0x332/0x450 [ 699.860185] __unwind_start+0x106/0x190 [ 699.860974] __save_stack_trace+0x5e/0x100 [ 699.861808] ? __save_stack_trace+0x5e/0x100 [ 699.862691] ? unlink_anon_vmas+0xba/0x2c0 [ 699.863525] save_stack_trace+0x1f/0x30 [ 699.864312] save_stack+0x46/0xd0 [ 699.864993] ? __alloc_pages_slowpath+0x1420/0x1420 [ 699.865990] ? flush_tlb_mm_range+0x15e/0x220 [ 699.866889] ? kasan_check_write+0x14/0x20 [ 699.867724] ? __dec_node_state+0x92/0xb0 [ 699.868543] ? lock_page_memcg+0x85/0xf0 [ 699.869350] ? unlock_page_memcg+0x16/0x80 [ 699.870185] ? page_remove_rmap+0x198/0x520 [ 699.871048] ? mark_page_accessed+0x133/0x200 [ 699.871930] ? _cond_resched+0x1a/0x50 [ 699.872700] ? unmap_page_range+0xcd4/0xe50 [ 699.873551] ? rb_next+0x58/0x80 [ 699.874217] ? rb_next+0x58/0x80 [ 699.874895] __kasan_slab_free+0x13c/0x1a0 [ 699.875734] ? unlink_anon_vmas+0xba/0x2c0 [ 699.876563] kasan_slab_free+0xe/0x10 [ 699.877315] kmem_cache_free+0x89/0x1e0 [ 699.878095] unlink_anon_vmas+0xba/0x2c0 [ 699.878913] free_pgtables+0x101/0x1b0 [ 699.879677] exit_mmap+0x146/0x2a0 [ 699.880378] ? __ia32_sys_munmap+0x50/0x50 [ 699.881214] ? kasan_check_read+0x11/0x20 [ 699.882052] ? mm_update_next_owner+0x322/0x380 [ 699.882985] mmput+0x8b/0x1d0 [ 699.883602] do_exit+0x43a/0x1390 [ 699.884288] ? mm_update_next_owner+0x380/0x380 [ 699.885212] ? f2fs_sync_file+0x9a/0xb0 [ 699.885995] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.886877] ? vfs_fsync_range+0x68/0x100 [ 699.887694] ? __fget_light+0xc9/0xe0 [ 699.888442] ? do_fsync+0x3d/0x70 [ 699.889118] ? __x64_sys_fdatasync+0x24/0x30 [ 699.889996] rewind_stack_do_exit+0x17/0x20 [ 699.890860] RIP: 0033:0x7f9bf930d800 [ 699.891585] Code: Bad RIP value. [ 699.892268] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.893781] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.895220] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.896643] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.898069] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.899505] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000 [ 699.901241] The buggy address belongs to the page: [ 699.902215] page:ffffea0007d0ebc0 count:0 mapcount:0 mapping:0000000000000000 index:0x0 [ 699.903811] flags: 0x2ffff0000000000() [ 699.904585] raw: 02ffff0000000000 0000000000000000 ffffffff07d00101 0000000000000000 [ 699.906125] raw: 0000000000000000 0000000000240000 00000000ffffffff 0000000000000000 [ 699.907673] page dumped because: kasan: bad access detected [ 699.909108] Memory state around the buggy address: [ 699.910077] ffff8801f43af800: 00 f1 f1 f1 f1 00 f4 f4 f4 f3 f3 f3 f3 00 00 00 [ 699.911528] ffff8801f43af880: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 699.912953] >ffff8801f43af900: 00 00 00 00 00 00 00 00 f1 01 f4 f4 f4 f2 f2 f2 [ 699.914392] ^ [ 699.915758] ffff8801f43af980: f2 00 f4 f4 00 00 00 00 f2 00 00 00 00 00 00 00 [ 699.917193] ffff8801f43afa00: 00 00 00 00 00 00 00 00 00 f3 f3 f3 00 00 00 00 [ 699.918634] ================================================================== - Location https://elixir.bootlin.com/linux/v4.18-rc1/source/fs/f2fs/segment.h#L644 Reported-by Wen Xu <wen.xu@gatech.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-08-01 11:13:44 +00:00
ipu_force = true;
fio->need_lock = LOCK_DONE;
goto got_it;
}
/* Deadlock due to between page->lock and f2fs_lock_op */
if (fio->need_lock == LOCK_REQ && !f2fs_trylock_op(fio->sbi))
return -EAGAIN;
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
err = f2fs_get_dnode_of_data(&dn, page->index, LOOKUP_NODE);
if (err)
goto out;
fio->old_blkaddr = dn.data_blkaddr;
/* This page is already truncated */
if (fio->old_blkaddr == NULL_ADDR) {
ClearPageUptodate(page);
f2fs: restructure f2fs page.private layout Restruct f2fs page private layout for below reasons: There are some cases that f2fs wants to set a flag in a page to indicate a specified status of page: a) page is in transaction list for atomic write b) page contains dummy data for aligned write c) page is migrating for GC d) page contains inline data for inline inode flush e) page belongs to merkle tree, and is verified for fsverity f) page is dirty and has filesystem/inode reference count for writeback g) page is temporary and has decompress io context reference for compression There are existed places in page structure we can use to store f2fs private status/data: - page.flags: PG_checked, PG_private - page.private However it was a mess when we using them, which may cause potential confliction: page.private PG_private PG_checked page._refcount (+1 at most) a) -1 set +1 b) -2 set c), d), e) set f) 0 set +1 g) pointer set The other problem is page.flags has no free slot, if we can avoid set zero to page.private and set PG_private flag, then we use non-zero value to indicate PG_private status, so that we may have chance to reclaim PG_private slot for other usage. [1] The other concern is f2fs has bad scalability in aspect of indicating more page status. So in this patch, let's restructure f2fs' page.private as below to solve above issues: Layout A: lowest bit should be 1 | bit0 = 1 | bit1 | bit2 | ... | bit MAX | private data .... | bit 0 PAGE_PRIVATE_NOT_POINTER bit 1 PAGE_PRIVATE_ATOMIC_WRITE bit 2 PAGE_PRIVATE_DUMMY_WRITE bit 3 PAGE_PRIVATE_ONGOING_MIGRATION bit 4 PAGE_PRIVATE_INLINE_INODE bit 5 PAGE_PRIVATE_REF_RESOURCE bit 6- f2fs private data Layout B: lowest bit should be 0 page.private is a wrapped pointer. After the change: page.private PG_private PG_checked page._refcount (+1 at most) a) 11 set +1 b) 101 set +1 c) 1001 set +1 d) 10001 set +1 e) set f) 100001 set +1 g) pointer set +1 [1] https://lore.kernel.org/linux-f2fs-devel/20210422154705.GO3596236@casper.infradead.org/T/#u Cc: Matthew Wilcox <willy@infradead.org> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2021-04-28 09:20:31 +00:00
clear_page_private_gcing(page);
goto out_writepage;
}
got_it:
f2fs: fix to do sanity check with block address in main area This patch add to do sanity check with below field: - cp_pack_total_block_count - blkaddr of data/node - extent info - Overview BUG() in verify_block_addr() when writing to a corrupted f2fs image - Reproduce (4.18 upstream kernel) - POC (poc.c) static void activity(char *mpoint) { char *foo_bar_baz; int err; static int buf[8192]; memset(buf, 0, sizeof(buf)); err = asprintf(&foo_bar_baz, "%s/foo/bar/baz", mpoint); int fd = open(foo_bar_baz, O_RDWR | O_TRUNC, 0777); if (fd >= 0) { write(fd, (char *)buf, sizeof(buf)); fdatasync(fd); close(fd); } } int main(int argc, char *argv[]) { activity(argv[1]); return 0; } - Kernel message [ 689.349473] F2FS-fs (loop0): Mounted with checkpoint version = 3 [ 699.728662] WARNING: CPU: 0 PID: 1309 at fs/f2fs/segment.c:2860 f2fs_inplace_write_data+0x232/0x240 [ 699.728670] Modules linked in: snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_pcm snd_timer snd mac_hid i2c_piix4 soundcore ib_iser rdma_cm iw_cm ib_cm ib_core iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx raid1 raid0 multipath linear 8139too crct10dif_pclmul crc32_pclmul qxl drm_kms_helper syscopyarea aesni_intel sysfillrect sysimgblt fb_sys_fops ttm drm aes_x86_64 crypto_simd cryptd 8139cp glue_helper mii pata_acpi floppy [ 699.729056] CPU: 0 PID: 1309 Comm: a.out Not tainted 4.18.0-rc1+ #4 [ 699.729064] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.729074] RIP: 0010:f2fs_inplace_write_data+0x232/0x240 [ 699.729076] Code: ff e9 cf fe ff ff 49 8d 7d 10 e8 39 45 ad ff 4d 8b 7d 10 be 04 00 00 00 49 8d 7f 48 e8 07 49 ad ff 45 8b 7f 48 e9 fb fe ff ff <0f> 0b f0 41 80 4d 48 04 e9 65 fe ff ff 90 66 66 66 66 90 55 48 8d [ 699.729130] RSP: 0018:ffff8801f43af568 EFLAGS: 00010202 [ 699.729139] RAX: 000000000000003f RBX: ffff8801f43af7b8 RCX: ffffffffb88c9113 [ 699.729142] RDX: 0000000000000003 RSI: dffffc0000000000 RDI: ffff8802024e5540 [ 699.729144] RBP: ffff8801f43af590 R08: 0000000000000009 R09: ffffffffffffffe8 [ 699.729147] R10: 0000000000000001 R11: ffffed0039b0596a R12: ffff8802024e5540 [ 699.729149] R13: ffff8801f0335500 R14: ffff8801e3e7a700 R15: ffff8801e1ee4450 [ 699.729154] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.729156] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.729159] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.729171] Call Trace: [ 699.729192] f2fs_do_write_data_page+0x2e2/0xe00 [ 699.729203] ? f2fs_should_update_outplace+0xd0/0xd0 [ 699.729238] ? memcg_drain_all_list_lrus+0x280/0x280 [ 699.729269] ? __radix_tree_replace+0xa3/0x120 [ 699.729276] __write_data_page+0x5c7/0xe30 [ 699.729291] ? kasan_check_read+0x11/0x20 [ 699.729310] ? page_mapped+0x8a/0x110 [ 699.729321] ? page_mkclean+0xe9/0x160 [ 699.729327] ? f2fs_do_write_data_page+0xe00/0xe00 [ 699.729331] ? invalid_page_referenced_vma+0x130/0x130 [ 699.729345] ? clear_page_dirty_for_io+0x332/0x450 [ 699.729351] f2fs_write_cache_pages+0x4ca/0x860 [ 699.729358] ? __write_data_page+0xe30/0xe30 [ 699.729374] ? percpu_counter_add_batch+0x22/0xa0 [ 699.729380] ? kasan_check_write+0x14/0x20 [ 699.729391] ? _raw_spin_lock+0x17/0x40 [ 699.729403] ? f2fs_mark_inode_dirty_sync.part.18+0x16/0x30 [ 699.729413] ? iov_iter_advance+0x113/0x640 [ 699.729418] ? f2fs_write_end+0x133/0x2e0 [ 699.729423] ? balance_dirty_pages_ratelimited+0x239/0x640 [ 699.729428] f2fs_write_data_pages+0x329/0x520 [ 699.729433] ? generic_perform_write+0x250/0x320 [ 699.729438] ? f2fs_write_cache_pages+0x860/0x860 [ 699.729454] ? current_time+0x110/0x110 [ 699.729459] ? f2fs_preallocate_blocks+0x1ef/0x370 [ 699.729464] do_writepages+0x37/0xb0 [ 699.729468] ? f2fs_write_cache_pages+0x860/0x860 [ 699.729472] ? do_writepages+0x37/0xb0 [ 699.729478] __filemap_fdatawrite_range+0x19a/0x1f0 [ 699.729483] ? delete_from_page_cache_batch+0x4e0/0x4e0 [ 699.729496] ? __vfs_write+0x2b2/0x410 [ 699.729501] file_write_and_wait_range+0x66/0xb0 [ 699.729506] f2fs_do_sync_file+0x1f9/0xd90 [ 699.729511] ? truncate_partial_data_page+0x290/0x290 [ 699.729521] ? __sb_end_write+0x30/0x50 [ 699.729526] ? vfs_write+0x20f/0x260 [ 699.729530] f2fs_sync_file+0x9a/0xb0 [ 699.729534] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.729548] vfs_fsync_range+0x68/0x100 [ 699.729554] ? __fget_light+0xc9/0xe0 [ 699.729558] do_fsync+0x3d/0x70 [ 699.729562] __x64_sys_fdatasync+0x24/0x30 [ 699.729585] do_syscall_64+0x78/0x170 [ 699.729595] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 699.729613] RIP: 0033:0x7f9bf930d800 [ 699.729615] Code: 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 83 3d 49 bf 2c 00 00 75 10 b8 4b 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 be 78 01 00 48 89 04 24 [ 699.729668] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.729673] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.729675] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.729678] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.729680] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.729683] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000 [ 699.729687] ---[ end trace 4ce02f25ff7d3df5 ]--- [ 699.729782] ------------[ cut here ]------------ [ 699.729785] kernel BUG at fs/f2fs/segment.h:654! [ 699.731055] invalid opcode: 0000 [#1] SMP KASAN PTI [ 699.732104] CPU: 0 PID: 1309 Comm: a.out Tainted: G W 4.18.0-rc1+ #4 [ 699.733684] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.735611] RIP: 0010:f2fs_submit_page_bio+0x29b/0x730 [ 699.736649] Code: 54 49 8d bd 18 04 00 00 e8 b2 59 af ff 41 8b 8d 18 04 00 00 8b 45 b8 41 d3 e6 44 01 f0 4c 8d 73 14 41 39 c7 0f 82 37 fe ff ff <0f> 0b 65 8b 05 2c 04 77 47 89 c0 48 0f a3 05 52 c1 d5 01 0f 92 c0 [ 699.740524] RSP: 0018:ffff8801f43af508 EFLAGS: 00010283 [ 699.741573] RAX: 0000000000000000 RBX: ffff8801f43af7b8 RCX: ffffffffb88a7cef [ 699.743006] RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff8801e3e7a64c [ 699.744426] RBP: ffff8801f43af558 R08: ffffed003e066b55 R09: ffffed003e066b55 [ 699.745833] R10: 0000000000000001 R11: ffffed003e066b54 R12: ffffea0007876940 [ 699.747256] R13: ffff8801f0335500 R14: ffff8801e3e7a600 R15: 0000000000000001 [ 699.748683] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.750293] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.751462] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.752874] Call Trace: [ 699.753386] ? f2fs_inplace_write_data+0x93/0x240 [ 699.754341] f2fs_inplace_write_data+0xd2/0x240 [ 699.755271] f2fs_do_write_data_page+0x2e2/0xe00 [ 699.756214] ? f2fs_should_update_outplace+0xd0/0xd0 [ 699.757215] ? memcg_drain_all_list_lrus+0x280/0x280 [ 699.758209] ? __radix_tree_replace+0xa3/0x120 [ 699.759164] __write_data_page+0x5c7/0xe30 [ 699.760002] ? kasan_check_read+0x11/0x20 [ 699.760823] ? page_mapped+0x8a/0x110 [ 699.761573] ? page_mkclean+0xe9/0x160 [ 699.762345] ? f2fs_do_write_data_page+0xe00/0xe00 [ 699.763332] ? invalid_page_referenced_vma+0x130/0x130 [ 699.764374] ? clear_page_dirty_for_io+0x332/0x450 [ 699.765347] f2fs_write_cache_pages+0x4ca/0x860 [ 699.766276] ? __write_data_page+0xe30/0xe30 [ 699.767161] ? percpu_counter_add_batch+0x22/0xa0 [ 699.768112] ? kasan_check_write+0x14/0x20 [ 699.768951] ? _raw_spin_lock+0x17/0x40 [ 699.769739] ? f2fs_mark_inode_dirty_sync.part.18+0x16/0x30 [ 699.770885] ? iov_iter_advance+0x113/0x640 [ 699.771743] ? f2fs_write_end+0x133/0x2e0 [ 699.772569] ? balance_dirty_pages_ratelimited+0x239/0x640 [ 699.773680] f2fs_write_data_pages+0x329/0x520 [ 699.774603] ? generic_perform_write+0x250/0x320 [ 699.775544] ? f2fs_write_cache_pages+0x860/0x860 [ 699.776510] ? current_time+0x110/0x110 [ 699.777299] ? f2fs_preallocate_blocks+0x1ef/0x370 [ 699.778279] do_writepages+0x37/0xb0 [ 699.779026] ? f2fs_write_cache_pages+0x860/0x860 [ 699.779978] ? do_writepages+0x37/0xb0 [ 699.780755] __filemap_fdatawrite_range+0x19a/0x1f0 [ 699.781746] ? delete_from_page_cache_batch+0x4e0/0x4e0 [ 699.782820] ? __vfs_write+0x2b2/0x410 [ 699.783597] file_write_and_wait_range+0x66/0xb0 [ 699.784540] f2fs_do_sync_file+0x1f9/0xd90 [ 699.785381] ? truncate_partial_data_page+0x290/0x290 [ 699.786415] ? __sb_end_write+0x30/0x50 [ 699.787204] ? vfs_write+0x20f/0x260 [ 699.787941] f2fs_sync_file+0x9a/0xb0 [ 699.788694] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.789572] vfs_fsync_range+0x68/0x100 [ 699.790360] ? __fget_light+0xc9/0xe0 [ 699.791128] do_fsync+0x3d/0x70 [ 699.791779] __x64_sys_fdatasync+0x24/0x30 [ 699.792614] do_syscall_64+0x78/0x170 [ 699.793371] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 699.794406] RIP: 0033:0x7f9bf930d800 [ 699.795134] Code: 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 83 3d 49 bf 2c 00 00 75 10 b8 4b 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 be 78 01 00 48 89 04 24 [ 699.798960] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.800483] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.801923] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.803373] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.804798] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.806233] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000 [ 699.807667] Modules linked in: snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_pcm snd_timer snd mac_hid i2c_piix4 soundcore ib_iser rdma_cm iw_cm ib_cm ib_core iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx raid1 raid0 multipath linear 8139too crct10dif_pclmul crc32_pclmul qxl drm_kms_helper syscopyarea aesni_intel sysfillrect sysimgblt fb_sys_fops ttm drm aes_x86_64 crypto_simd cryptd 8139cp glue_helper mii pata_acpi floppy [ 699.817079] ---[ end trace 4ce02f25ff7d3df6 ]--- [ 699.818068] RIP: 0010:f2fs_submit_page_bio+0x29b/0x730 [ 699.819114] Code: 54 49 8d bd 18 04 00 00 e8 b2 59 af ff 41 8b 8d 18 04 00 00 8b 45 b8 41 d3 e6 44 01 f0 4c 8d 73 14 41 39 c7 0f 82 37 fe ff ff <0f> 0b 65 8b 05 2c 04 77 47 89 c0 48 0f a3 05 52 c1 d5 01 0f 92 c0 [ 699.822919] RSP: 0018:ffff8801f43af508 EFLAGS: 00010283 [ 699.823977] RAX: 0000000000000000 RBX: ffff8801f43af7b8 RCX: ffffffffb88a7cef [ 699.825436] RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff8801e3e7a64c [ 699.826881] RBP: ffff8801f43af558 R08: ffffed003e066b55 R09: ffffed003e066b55 [ 699.828292] R10: 0000000000000001 R11: ffffed003e066b54 R12: ffffea0007876940 [ 699.829750] R13: ffff8801f0335500 R14: ffff8801e3e7a600 R15: 0000000000000001 [ 699.831192] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.832793] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.833981] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.835556] ================================================================== [ 699.837029] BUG: KASAN: stack-out-of-bounds in update_stack_state+0x38c/0x3e0 [ 699.838462] Read of size 8 at addr ffff8801f43af970 by task a.out/1309 [ 699.840086] CPU: 0 PID: 1309 Comm: a.out Tainted: G D W 4.18.0-rc1+ #4 [ 699.841603] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.843475] Call Trace: [ 699.843982] dump_stack+0x7b/0xb5 [ 699.844661] print_address_description+0x70/0x290 [ 699.845607] kasan_report+0x291/0x390 [ 699.846351] ? update_stack_state+0x38c/0x3e0 [ 699.853831] __asan_load8+0x54/0x90 [ 699.854569] update_stack_state+0x38c/0x3e0 [ 699.855428] ? __read_once_size_nocheck.constprop.7+0x20/0x20 [ 699.856601] ? __save_stack_trace+0x5e/0x100 [ 699.857476] unwind_next_frame.part.5+0x18e/0x490 [ 699.858448] ? unwind_dump+0x290/0x290 [ 699.859217] ? clear_page_dirty_for_io+0x332/0x450 [ 699.860185] __unwind_start+0x106/0x190 [ 699.860974] __save_stack_trace+0x5e/0x100 [ 699.861808] ? __save_stack_trace+0x5e/0x100 [ 699.862691] ? unlink_anon_vmas+0xba/0x2c0 [ 699.863525] save_stack_trace+0x1f/0x30 [ 699.864312] save_stack+0x46/0xd0 [ 699.864993] ? __alloc_pages_slowpath+0x1420/0x1420 [ 699.865990] ? flush_tlb_mm_range+0x15e/0x220 [ 699.866889] ? kasan_check_write+0x14/0x20 [ 699.867724] ? __dec_node_state+0x92/0xb0 [ 699.868543] ? lock_page_memcg+0x85/0xf0 [ 699.869350] ? unlock_page_memcg+0x16/0x80 [ 699.870185] ? page_remove_rmap+0x198/0x520 [ 699.871048] ? mark_page_accessed+0x133/0x200 [ 699.871930] ? _cond_resched+0x1a/0x50 [ 699.872700] ? unmap_page_range+0xcd4/0xe50 [ 699.873551] ? rb_next+0x58/0x80 [ 699.874217] ? rb_next+0x58/0x80 [ 699.874895] __kasan_slab_free+0x13c/0x1a0 [ 699.875734] ? unlink_anon_vmas+0xba/0x2c0 [ 699.876563] kasan_slab_free+0xe/0x10 [ 699.877315] kmem_cache_free+0x89/0x1e0 [ 699.878095] unlink_anon_vmas+0xba/0x2c0 [ 699.878913] free_pgtables+0x101/0x1b0 [ 699.879677] exit_mmap+0x146/0x2a0 [ 699.880378] ? __ia32_sys_munmap+0x50/0x50 [ 699.881214] ? kasan_check_read+0x11/0x20 [ 699.882052] ? mm_update_next_owner+0x322/0x380 [ 699.882985] mmput+0x8b/0x1d0 [ 699.883602] do_exit+0x43a/0x1390 [ 699.884288] ? mm_update_next_owner+0x380/0x380 [ 699.885212] ? f2fs_sync_file+0x9a/0xb0 [ 699.885995] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.886877] ? vfs_fsync_range+0x68/0x100 [ 699.887694] ? __fget_light+0xc9/0xe0 [ 699.888442] ? do_fsync+0x3d/0x70 [ 699.889118] ? __x64_sys_fdatasync+0x24/0x30 [ 699.889996] rewind_stack_do_exit+0x17/0x20 [ 699.890860] RIP: 0033:0x7f9bf930d800 [ 699.891585] Code: Bad RIP value. [ 699.892268] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.893781] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.895220] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.896643] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.898069] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.899505] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000 [ 699.901241] The buggy address belongs to the page: [ 699.902215] page:ffffea0007d0ebc0 count:0 mapcount:0 mapping:0000000000000000 index:0x0 [ 699.903811] flags: 0x2ffff0000000000() [ 699.904585] raw: 02ffff0000000000 0000000000000000 ffffffff07d00101 0000000000000000 [ 699.906125] raw: 0000000000000000 0000000000240000 00000000ffffffff 0000000000000000 [ 699.907673] page dumped because: kasan: bad access detected [ 699.909108] Memory state around the buggy address: [ 699.910077] ffff8801f43af800: 00 f1 f1 f1 f1 00 f4 f4 f4 f3 f3 f3 f3 00 00 00 [ 699.911528] ffff8801f43af880: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 699.912953] >ffff8801f43af900: 00 00 00 00 00 00 00 00 f1 01 f4 f4 f4 f2 f2 f2 [ 699.914392] ^ [ 699.915758] ffff8801f43af980: f2 00 f4 f4 00 00 00 00 f2 00 00 00 00 00 00 00 [ 699.917193] ffff8801f43afa00: 00 00 00 00 00 00 00 00 00 f3 f3 f3 00 00 00 00 [ 699.918634] ================================================================== - Location https://elixir.bootlin.com/linux/v4.18-rc1/source/fs/f2fs/segment.h#L644 Reported-by Wen Xu <wen.xu@gatech.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-08-01 11:13:44 +00:00
if (__is_valid_data_blkaddr(fio->old_blkaddr) &&
!f2fs_is_valid_blkaddr(fio->sbi, fio->old_blkaddr,
f2fs: introduce DATA_GENERIC_ENHANCE Previously, f2fs_is_valid_blkaddr(, blkaddr, DATA_GENERIC) will check whether @blkaddr locates in main area or not. That check is weak, since the block address in range of main area can point to the address which is not valid in segment info table, and we can not detect such condition, we may suffer worse corruption as system continues running. So this patch introduce DATA_GENERIC_ENHANCE to enhance the sanity check which trigger SIT bitmap check rather than only range check. This patch did below changes as wel: - set SBI_NEED_FSCK in f2fs_is_valid_blkaddr(). - get rid of is_valid_data_blkaddr() to avoid panic if blkaddr is invalid. - introduce verify_fio_blkaddr() to wrap fio {new,old}_blkaddr validation check. - spread blkaddr check in: * f2fs_get_node_info() * __read_out_blkaddrs() * f2fs_submit_page_read() * ra_data_block() * do_recover_data() This patch can fix bug reported from bugzilla below: https://bugzilla.kernel.org/show_bug.cgi?id=203215 https://bugzilla.kernel.org/show_bug.cgi?id=203223 https://bugzilla.kernel.org/show_bug.cgi?id=203231 https://bugzilla.kernel.org/show_bug.cgi?id=203235 https://bugzilla.kernel.org/show_bug.cgi?id=203241 = Update by Jaegeuk Kim = DATA_GENERIC_ENHANCE enhanced to validate block addresses on read/write paths. But, xfstest/generic/446 compalins some generated kernel messages saying invalid bitmap was detected when reading a block. The reaons is, when we get the block addresses from extent_cache, there is no lock to synchronize it from truncating the blocks in parallel. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-04-15 07:26:32 +00:00
DATA_GENERIC_ENHANCE)) {
err = -EFSCORRUPTED;
f2fs: fix to do sanity check with block address in main area This patch add to do sanity check with below field: - cp_pack_total_block_count - blkaddr of data/node - extent info - Overview BUG() in verify_block_addr() when writing to a corrupted f2fs image - Reproduce (4.18 upstream kernel) - POC (poc.c) static void activity(char *mpoint) { char *foo_bar_baz; int err; static int buf[8192]; memset(buf, 0, sizeof(buf)); err = asprintf(&foo_bar_baz, "%s/foo/bar/baz", mpoint); int fd = open(foo_bar_baz, O_RDWR | O_TRUNC, 0777); if (fd >= 0) { write(fd, (char *)buf, sizeof(buf)); fdatasync(fd); close(fd); } } int main(int argc, char *argv[]) { activity(argv[1]); return 0; } - Kernel message [ 689.349473] F2FS-fs (loop0): Mounted with checkpoint version = 3 [ 699.728662] WARNING: CPU: 0 PID: 1309 at fs/f2fs/segment.c:2860 f2fs_inplace_write_data+0x232/0x240 [ 699.728670] Modules linked in: snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_pcm snd_timer snd mac_hid i2c_piix4 soundcore ib_iser rdma_cm iw_cm ib_cm ib_core iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx raid1 raid0 multipath linear 8139too crct10dif_pclmul crc32_pclmul qxl drm_kms_helper syscopyarea aesni_intel sysfillrect sysimgblt fb_sys_fops ttm drm aes_x86_64 crypto_simd cryptd 8139cp glue_helper mii pata_acpi floppy [ 699.729056] CPU: 0 PID: 1309 Comm: a.out Not tainted 4.18.0-rc1+ #4 [ 699.729064] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.729074] RIP: 0010:f2fs_inplace_write_data+0x232/0x240 [ 699.729076] Code: ff e9 cf fe ff ff 49 8d 7d 10 e8 39 45 ad ff 4d 8b 7d 10 be 04 00 00 00 49 8d 7f 48 e8 07 49 ad ff 45 8b 7f 48 e9 fb fe ff ff <0f> 0b f0 41 80 4d 48 04 e9 65 fe ff ff 90 66 66 66 66 90 55 48 8d [ 699.729130] RSP: 0018:ffff8801f43af568 EFLAGS: 00010202 [ 699.729139] RAX: 000000000000003f RBX: ffff8801f43af7b8 RCX: ffffffffb88c9113 [ 699.729142] RDX: 0000000000000003 RSI: dffffc0000000000 RDI: ffff8802024e5540 [ 699.729144] RBP: ffff8801f43af590 R08: 0000000000000009 R09: ffffffffffffffe8 [ 699.729147] R10: 0000000000000001 R11: ffffed0039b0596a R12: ffff8802024e5540 [ 699.729149] R13: ffff8801f0335500 R14: ffff8801e3e7a700 R15: ffff8801e1ee4450 [ 699.729154] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.729156] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.729159] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.729171] Call Trace: [ 699.729192] f2fs_do_write_data_page+0x2e2/0xe00 [ 699.729203] ? f2fs_should_update_outplace+0xd0/0xd0 [ 699.729238] ? memcg_drain_all_list_lrus+0x280/0x280 [ 699.729269] ? __radix_tree_replace+0xa3/0x120 [ 699.729276] __write_data_page+0x5c7/0xe30 [ 699.729291] ? kasan_check_read+0x11/0x20 [ 699.729310] ? page_mapped+0x8a/0x110 [ 699.729321] ? page_mkclean+0xe9/0x160 [ 699.729327] ? f2fs_do_write_data_page+0xe00/0xe00 [ 699.729331] ? invalid_page_referenced_vma+0x130/0x130 [ 699.729345] ? clear_page_dirty_for_io+0x332/0x450 [ 699.729351] f2fs_write_cache_pages+0x4ca/0x860 [ 699.729358] ? __write_data_page+0xe30/0xe30 [ 699.729374] ? percpu_counter_add_batch+0x22/0xa0 [ 699.729380] ? kasan_check_write+0x14/0x20 [ 699.729391] ? _raw_spin_lock+0x17/0x40 [ 699.729403] ? f2fs_mark_inode_dirty_sync.part.18+0x16/0x30 [ 699.729413] ? iov_iter_advance+0x113/0x640 [ 699.729418] ? f2fs_write_end+0x133/0x2e0 [ 699.729423] ? balance_dirty_pages_ratelimited+0x239/0x640 [ 699.729428] f2fs_write_data_pages+0x329/0x520 [ 699.729433] ? generic_perform_write+0x250/0x320 [ 699.729438] ? f2fs_write_cache_pages+0x860/0x860 [ 699.729454] ? current_time+0x110/0x110 [ 699.729459] ? f2fs_preallocate_blocks+0x1ef/0x370 [ 699.729464] do_writepages+0x37/0xb0 [ 699.729468] ? f2fs_write_cache_pages+0x860/0x860 [ 699.729472] ? do_writepages+0x37/0xb0 [ 699.729478] __filemap_fdatawrite_range+0x19a/0x1f0 [ 699.729483] ? delete_from_page_cache_batch+0x4e0/0x4e0 [ 699.729496] ? __vfs_write+0x2b2/0x410 [ 699.729501] file_write_and_wait_range+0x66/0xb0 [ 699.729506] f2fs_do_sync_file+0x1f9/0xd90 [ 699.729511] ? truncate_partial_data_page+0x290/0x290 [ 699.729521] ? __sb_end_write+0x30/0x50 [ 699.729526] ? vfs_write+0x20f/0x260 [ 699.729530] f2fs_sync_file+0x9a/0xb0 [ 699.729534] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.729548] vfs_fsync_range+0x68/0x100 [ 699.729554] ? __fget_light+0xc9/0xe0 [ 699.729558] do_fsync+0x3d/0x70 [ 699.729562] __x64_sys_fdatasync+0x24/0x30 [ 699.729585] do_syscall_64+0x78/0x170 [ 699.729595] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 699.729613] RIP: 0033:0x7f9bf930d800 [ 699.729615] Code: 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 83 3d 49 bf 2c 00 00 75 10 b8 4b 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 be 78 01 00 48 89 04 24 [ 699.729668] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.729673] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.729675] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.729678] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.729680] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.729683] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000 [ 699.729687] ---[ end trace 4ce02f25ff7d3df5 ]--- [ 699.729782] ------------[ cut here ]------------ [ 699.729785] kernel BUG at fs/f2fs/segment.h:654! [ 699.731055] invalid opcode: 0000 [#1] SMP KASAN PTI [ 699.732104] CPU: 0 PID: 1309 Comm: a.out Tainted: G W 4.18.0-rc1+ #4 [ 699.733684] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.735611] RIP: 0010:f2fs_submit_page_bio+0x29b/0x730 [ 699.736649] Code: 54 49 8d bd 18 04 00 00 e8 b2 59 af ff 41 8b 8d 18 04 00 00 8b 45 b8 41 d3 e6 44 01 f0 4c 8d 73 14 41 39 c7 0f 82 37 fe ff ff <0f> 0b 65 8b 05 2c 04 77 47 89 c0 48 0f a3 05 52 c1 d5 01 0f 92 c0 [ 699.740524] RSP: 0018:ffff8801f43af508 EFLAGS: 00010283 [ 699.741573] RAX: 0000000000000000 RBX: ffff8801f43af7b8 RCX: ffffffffb88a7cef [ 699.743006] RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff8801e3e7a64c [ 699.744426] RBP: ffff8801f43af558 R08: ffffed003e066b55 R09: ffffed003e066b55 [ 699.745833] R10: 0000000000000001 R11: ffffed003e066b54 R12: ffffea0007876940 [ 699.747256] R13: ffff8801f0335500 R14: ffff8801e3e7a600 R15: 0000000000000001 [ 699.748683] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.750293] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.751462] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.752874] Call Trace: [ 699.753386] ? f2fs_inplace_write_data+0x93/0x240 [ 699.754341] f2fs_inplace_write_data+0xd2/0x240 [ 699.755271] f2fs_do_write_data_page+0x2e2/0xe00 [ 699.756214] ? f2fs_should_update_outplace+0xd0/0xd0 [ 699.757215] ? memcg_drain_all_list_lrus+0x280/0x280 [ 699.758209] ? __radix_tree_replace+0xa3/0x120 [ 699.759164] __write_data_page+0x5c7/0xe30 [ 699.760002] ? kasan_check_read+0x11/0x20 [ 699.760823] ? page_mapped+0x8a/0x110 [ 699.761573] ? page_mkclean+0xe9/0x160 [ 699.762345] ? f2fs_do_write_data_page+0xe00/0xe00 [ 699.763332] ? invalid_page_referenced_vma+0x130/0x130 [ 699.764374] ? clear_page_dirty_for_io+0x332/0x450 [ 699.765347] f2fs_write_cache_pages+0x4ca/0x860 [ 699.766276] ? __write_data_page+0xe30/0xe30 [ 699.767161] ? percpu_counter_add_batch+0x22/0xa0 [ 699.768112] ? kasan_check_write+0x14/0x20 [ 699.768951] ? _raw_spin_lock+0x17/0x40 [ 699.769739] ? f2fs_mark_inode_dirty_sync.part.18+0x16/0x30 [ 699.770885] ? iov_iter_advance+0x113/0x640 [ 699.771743] ? f2fs_write_end+0x133/0x2e0 [ 699.772569] ? balance_dirty_pages_ratelimited+0x239/0x640 [ 699.773680] f2fs_write_data_pages+0x329/0x520 [ 699.774603] ? generic_perform_write+0x250/0x320 [ 699.775544] ? f2fs_write_cache_pages+0x860/0x860 [ 699.776510] ? current_time+0x110/0x110 [ 699.777299] ? f2fs_preallocate_blocks+0x1ef/0x370 [ 699.778279] do_writepages+0x37/0xb0 [ 699.779026] ? f2fs_write_cache_pages+0x860/0x860 [ 699.779978] ? do_writepages+0x37/0xb0 [ 699.780755] __filemap_fdatawrite_range+0x19a/0x1f0 [ 699.781746] ? delete_from_page_cache_batch+0x4e0/0x4e0 [ 699.782820] ? __vfs_write+0x2b2/0x410 [ 699.783597] file_write_and_wait_range+0x66/0xb0 [ 699.784540] f2fs_do_sync_file+0x1f9/0xd90 [ 699.785381] ? truncate_partial_data_page+0x290/0x290 [ 699.786415] ? __sb_end_write+0x30/0x50 [ 699.787204] ? vfs_write+0x20f/0x260 [ 699.787941] f2fs_sync_file+0x9a/0xb0 [ 699.788694] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.789572] vfs_fsync_range+0x68/0x100 [ 699.790360] ? __fget_light+0xc9/0xe0 [ 699.791128] do_fsync+0x3d/0x70 [ 699.791779] __x64_sys_fdatasync+0x24/0x30 [ 699.792614] do_syscall_64+0x78/0x170 [ 699.793371] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 699.794406] RIP: 0033:0x7f9bf930d800 [ 699.795134] Code: 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 83 3d 49 bf 2c 00 00 75 10 b8 4b 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 be 78 01 00 48 89 04 24 [ 699.798960] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.800483] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.801923] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.803373] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.804798] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.806233] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000 [ 699.807667] Modules linked in: snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_pcm snd_timer snd mac_hid i2c_piix4 soundcore ib_iser rdma_cm iw_cm ib_cm ib_core iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx raid1 raid0 multipath linear 8139too crct10dif_pclmul crc32_pclmul qxl drm_kms_helper syscopyarea aesni_intel sysfillrect sysimgblt fb_sys_fops ttm drm aes_x86_64 crypto_simd cryptd 8139cp glue_helper mii pata_acpi floppy [ 699.817079] ---[ end trace 4ce02f25ff7d3df6 ]--- [ 699.818068] RIP: 0010:f2fs_submit_page_bio+0x29b/0x730 [ 699.819114] Code: 54 49 8d bd 18 04 00 00 e8 b2 59 af ff 41 8b 8d 18 04 00 00 8b 45 b8 41 d3 e6 44 01 f0 4c 8d 73 14 41 39 c7 0f 82 37 fe ff ff <0f> 0b 65 8b 05 2c 04 77 47 89 c0 48 0f a3 05 52 c1 d5 01 0f 92 c0 [ 699.822919] RSP: 0018:ffff8801f43af508 EFLAGS: 00010283 [ 699.823977] RAX: 0000000000000000 RBX: ffff8801f43af7b8 RCX: ffffffffb88a7cef [ 699.825436] RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff8801e3e7a64c [ 699.826881] RBP: ffff8801f43af558 R08: ffffed003e066b55 R09: ffffed003e066b55 [ 699.828292] R10: 0000000000000001 R11: ffffed003e066b54 R12: ffffea0007876940 [ 699.829750] R13: ffff8801f0335500 R14: ffff8801e3e7a600 R15: 0000000000000001 [ 699.831192] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.832793] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.833981] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.835556] ================================================================== [ 699.837029] BUG: KASAN: stack-out-of-bounds in update_stack_state+0x38c/0x3e0 [ 699.838462] Read of size 8 at addr ffff8801f43af970 by task a.out/1309 [ 699.840086] CPU: 0 PID: 1309 Comm: a.out Tainted: G D W 4.18.0-rc1+ #4 [ 699.841603] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.843475] Call Trace: [ 699.843982] dump_stack+0x7b/0xb5 [ 699.844661] print_address_description+0x70/0x290 [ 699.845607] kasan_report+0x291/0x390 [ 699.846351] ? update_stack_state+0x38c/0x3e0 [ 699.853831] __asan_load8+0x54/0x90 [ 699.854569] update_stack_state+0x38c/0x3e0 [ 699.855428] ? __read_once_size_nocheck.constprop.7+0x20/0x20 [ 699.856601] ? __save_stack_trace+0x5e/0x100 [ 699.857476] unwind_next_frame.part.5+0x18e/0x490 [ 699.858448] ? unwind_dump+0x290/0x290 [ 699.859217] ? clear_page_dirty_for_io+0x332/0x450 [ 699.860185] __unwind_start+0x106/0x190 [ 699.860974] __save_stack_trace+0x5e/0x100 [ 699.861808] ? __save_stack_trace+0x5e/0x100 [ 699.862691] ? unlink_anon_vmas+0xba/0x2c0 [ 699.863525] save_stack_trace+0x1f/0x30 [ 699.864312] save_stack+0x46/0xd0 [ 699.864993] ? __alloc_pages_slowpath+0x1420/0x1420 [ 699.865990] ? flush_tlb_mm_range+0x15e/0x220 [ 699.866889] ? kasan_check_write+0x14/0x20 [ 699.867724] ? __dec_node_state+0x92/0xb0 [ 699.868543] ? lock_page_memcg+0x85/0xf0 [ 699.869350] ? unlock_page_memcg+0x16/0x80 [ 699.870185] ? page_remove_rmap+0x198/0x520 [ 699.871048] ? mark_page_accessed+0x133/0x200 [ 699.871930] ? _cond_resched+0x1a/0x50 [ 699.872700] ? unmap_page_range+0xcd4/0xe50 [ 699.873551] ? rb_next+0x58/0x80 [ 699.874217] ? rb_next+0x58/0x80 [ 699.874895] __kasan_slab_free+0x13c/0x1a0 [ 699.875734] ? unlink_anon_vmas+0xba/0x2c0 [ 699.876563] kasan_slab_free+0xe/0x10 [ 699.877315] kmem_cache_free+0x89/0x1e0 [ 699.878095] unlink_anon_vmas+0xba/0x2c0 [ 699.878913] free_pgtables+0x101/0x1b0 [ 699.879677] exit_mmap+0x146/0x2a0 [ 699.880378] ? __ia32_sys_munmap+0x50/0x50 [ 699.881214] ? kasan_check_read+0x11/0x20 [ 699.882052] ? mm_update_next_owner+0x322/0x380 [ 699.882985] mmput+0x8b/0x1d0 [ 699.883602] do_exit+0x43a/0x1390 [ 699.884288] ? mm_update_next_owner+0x380/0x380 [ 699.885212] ? f2fs_sync_file+0x9a/0xb0 [ 699.885995] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.886877] ? vfs_fsync_range+0x68/0x100 [ 699.887694] ? __fget_light+0xc9/0xe0 [ 699.888442] ? do_fsync+0x3d/0x70 [ 699.889118] ? __x64_sys_fdatasync+0x24/0x30 [ 699.889996] rewind_stack_do_exit+0x17/0x20 [ 699.890860] RIP: 0033:0x7f9bf930d800 [ 699.891585] Code: Bad RIP value. [ 699.892268] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.893781] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.895220] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.896643] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.898069] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.899505] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000 [ 699.901241] The buggy address belongs to the page: [ 699.902215] page:ffffea0007d0ebc0 count:0 mapcount:0 mapping:0000000000000000 index:0x0 [ 699.903811] flags: 0x2ffff0000000000() [ 699.904585] raw: 02ffff0000000000 0000000000000000 ffffffff07d00101 0000000000000000 [ 699.906125] raw: 0000000000000000 0000000000240000 00000000ffffffff 0000000000000000 [ 699.907673] page dumped because: kasan: bad access detected [ 699.909108] Memory state around the buggy address: [ 699.910077] ffff8801f43af800: 00 f1 f1 f1 f1 00 f4 f4 f4 f3 f3 f3 f3 00 00 00 [ 699.911528] ffff8801f43af880: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 699.912953] >ffff8801f43af900: 00 00 00 00 00 00 00 00 f1 01 f4 f4 f4 f2 f2 f2 [ 699.914392] ^ [ 699.915758] ffff8801f43af980: f2 00 f4 f4 00 00 00 00 f2 00 00 00 00 00 00 00 [ 699.917193] ffff8801f43afa00: 00 00 00 00 00 00 00 00 00 f3 f3 f3 00 00 00 00 [ 699.918634] ================================================================== - Location https://elixir.bootlin.com/linux/v4.18-rc1/source/fs/f2fs/segment.h#L644 Reported-by Wen Xu <wen.xu@gatech.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-08-01 11:13:44 +00:00
goto out_writepage;
}
/* wait for GCed page writeback via META_MAPPING */
if (fio->meta_gc)
f2fs_wait_on_block_writeback(inode, fio->old_blkaddr);
/*
* If current allocation needs SSR,
* it had better in-place writes for updated data.
*/
f2fs: introduce DATA_GENERIC_ENHANCE Previously, f2fs_is_valid_blkaddr(, blkaddr, DATA_GENERIC) will check whether @blkaddr locates in main area or not. That check is weak, since the block address in range of main area can point to the address which is not valid in segment info table, and we can not detect such condition, we may suffer worse corruption as system continues running. So this patch introduce DATA_GENERIC_ENHANCE to enhance the sanity check which trigger SIT bitmap check rather than only range check. This patch did below changes as wel: - set SBI_NEED_FSCK in f2fs_is_valid_blkaddr(). - get rid of is_valid_data_blkaddr() to avoid panic if blkaddr is invalid. - introduce verify_fio_blkaddr() to wrap fio {new,old}_blkaddr validation check. - spread blkaddr check in: * f2fs_get_node_info() * __read_out_blkaddrs() * f2fs_submit_page_read() * ra_data_block() * do_recover_data() This patch can fix bug reported from bugzilla below: https://bugzilla.kernel.org/show_bug.cgi?id=203215 https://bugzilla.kernel.org/show_bug.cgi?id=203223 https://bugzilla.kernel.org/show_bug.cgi?id=203231 https://bugzilla.kernel.org/show_bug.cgi?id=203235 https://bugzilla.kernel.org/show_bug.cgi?id=203241 = Update by Jaegeuk Kim = DATA_GENERIC_ENHANCE enhanced to validate block addresses on read/write paths. But, xfstest/generic/446 compalins some generated kernel messages saying invalid bitmap was detected when reading a block. The reaons is, when we get the block addresses from extent_cache, there is no lock to synchronize it from truncating the blocks in parallel. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-04-15 07:26:32 +00:00
if (ipu_force ||
(__is_valid_data_blkaddr(fio->old_blkaddr) &&
need_inplace_update(fio))) {
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
err = f2fs_encrypt_one_page(fio);
if (err)
goto out_writepage;
set_page_writeback(page);
f2fs_put_dnode(&dn);
if (fio->need_lock == LOCK_REQ)
f2fs_unlock_op(fio->sbi);
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
err = f2fs_inplace_write_data(fio);
if (err) {
if (fscrypt_inode_uses_fs_layer_crypto(inode))
fscrypt_finalize_bounce_page(&fio->encrypted_page);
end_page_writeback(page);
} else {
set_inode_flag(inode, FI_UPDATE_WRITE);
}
trace_f2fs_do_write_data_page(page_folio(page), IPU);
return err;
}
if (fio->need_lock == LOCK_RETRY) {
if (!f2fs_trylock_op(fio->sbi)) {
err = -EAGAIN;
goto out_writepage;
}
fio->need_lock = LOCK_REQ;
}
err = f2fs_get_node_info(fio->sbi, dn.nid, &ni, false);
if (err)
goto out_writepage;
fio->version = ni.version;
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
err = f2fs_encrypt_one_page(fio);
if (err)
goto out_writepage;
set_page_writeback(page);
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
if (fio->compr_blocks && fio->old_blkaddr == COMPRESS_ADDR)
f2fs_i_compr_blocks_update(inode, fio->compr_blocks - 1, false);
/* LFS mode write path */
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
f2fs_outplace_write_data(&dn, fio);
trace_f2fs_do_write_data_page(page_folio(page), OPU);
set_inode_flag(inode, FI_APPEND_WRITE);
out_writepage:
f2fs_put_dnode(&dn);
out:
if (fio->need_lock == LOCK_REQ)
f2fs_unlock_op(fio->sbi);
return err;
}
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
int f2fs_write_single_data_page(struct page *page, int *submitted,
f2fs: add bio cache for IPU SQLite in Wal mode may trigger sequential IPU write in db-wal file, after commit d1b3e72d5490 ("f2fs: submit bio of in-place-update pages"), we lost the chance of merging page in inner managed bio cache, result in submitting more small-sized IO. So let's add temporary bio in writepages() to cache mergeable write IO as much as possible. Test case: 1. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" 2. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" Before: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65552, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65560, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65568, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65576, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65584, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65592, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65600, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65608, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65616, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65624, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65632, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65640, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65648, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65656, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65664, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57352, size = 4096 After: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 65536 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57368, size = 4096 Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-02-19 08:15:29 +00:00
struct bio **bio,
sector_t *last_block,
struct writeback_control *wbc,
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
enum iostat_type io_type,
int compr_blocks,
bool allow_balance)
{
struct inode *inode = page->mapping->host;
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
loff_t i_size = i_size_read(inode);
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
const pgoff_t end_index = ((unsigned long long)i_size)
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 12:29:47 +00:00
>> PAGE_SHIFT;
loff_t psize = (loff_t)(page->index + 1) << PAGE_SHIFT;
unsigned offset = 0;
f2fs: introduce a new global lock scheme In the previous version, f2fs uses global locks according to the usage types, such as directory operations, block allocation, block write, and so on. Reference the following lock types in f2fs.h. enum lock_type { RENAME, /* for renaming operations */ DENTRY_OPS, /* for directory operations */ DATA_WRITE, /* for data write */ DATA_NEW, /* for data allocation */ DATA_TRUNC, /* for data truncate */ NODE_NEW, /* for node allocation */ NODE_TRUNC, /* for node truncate */ NODE_WRITE, /* for node write */ NR_LOCK_TYPE, }; In that case, we lose the performance under the multi-threading environment, since every types of operations must be conducted one at a time. In order to address the problem, let's share the locks globally with a mutex array regardless of any types. So, let users grab a mutex and perform their jobs in parallel as much as possbile. For this, I propose a new global lock scheme as follows. 0. Data structure - f2fs_sb_info -> mutex_lock[NR_GLOBAL_LOCKS] - f2fs_sb_info -> node_write 1. mutex_lock_op(sbi) - try to get an avaiable lock from the array. - returns the index of the gottern lock variable. 2. mutex_unlock_op(sbi, index of the lock) - unlock the given index of the lock. 3. mutex_lock_all(sbi) - grab all the locks in the array before the checkpoint. 4. mutex_unlock_all(sbi) - release all the locks in the array after checkpoint. 5. block_operations() - call mutex_lock_all() - sync_dirty_dir_inodes() - grab node_write - sync_node_pages() Note that, the pairs of mutex_lock_op()/mutex_unlock_op() and mutex_lock_all()/mutex_unlock_all() should be used together. Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
2012-11-22 07:21:29 +00:00
bool need_balance_fs = false;
bool quota_inode = IS_NOQUOTA(inode);
int err = 0;
struct f2fs_io_info fio = {
.sbi = sbi,
.ino = inode->i_ino,
.type = DATA,
.op = REQ_OP_WRITE,
.op_flags = wbc_to_write_flags(wbc),
.old_blkaddr = NULL_ADDR,
.page = page,
.encrypted_page = NULL,
.submitted = 0,
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
.compr_blocks = compr_blocks,
.need_lock = compr_blocks ? LOCK_DONE : LOCK_RETRY,
.meta_gc = f2fs_meta_inode_gc_required(inode) ? 1 : 0,
.io_type = io_type,
.io_wbc = wbc,
f2fs: add bio cache for IPU SQLite in Wal mode may trigger sequential IPU write in db-wal file, after commit d1b3e72d5490 ("f2fs: submit bio of in-place-update pages"), we lost the chance of merging page in inner managed bio cache, result in submitting more small-sized IO. So let's add temporary bio in writepages() to cache mergeable write IO as much as possible. Test case: 1. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" 2. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" Before: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65552, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65560, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65568, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65576, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65584, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65592, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65600, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65608, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65616, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65624, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65632, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65640, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65648, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65656, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65664, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57352, size = 4096 After: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 65536 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57368, size = 4096 Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-02-19 08:15:29 +00:00
.bio = bio,
.last_block = last_block,
};
trace_f2fs_writepage(page_folio(page), DATA);
/* we should bypass data pages to proceed the kworker jobs */
if (unlikely(f2fs_cp_error(sbi))) {
mapping_set_error(page->mapping, -EIO);
/*
* don't drop any dirty dentry pages for keeping lastest
* directory structure.
*/
if (S_ISDIR(inode->i_mode) &&
!is_sbi_flag_set(sbi, SBI_IS_CLOSE))
goto redirty_out;
/* keep data pages in remount-ro mode */
if (F2FS_OPTION(sbi).errors == MOUNT_ERRORS_READONLY)
goto redirty_out;
goto out;
}
if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
goto redirty_out;
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
if (page->index < end_index ||
f2fs_verity_in_progress(inode) ||
compr_blocks)
f2fs: introduce a new global lock scheme In the previous version, f2fs uses global locks according to the usage types, such as directory operations, block allocation, block write, and so on. Reference the following lock types in f2fs.h. enum lock_type { RENAME, /* for renaming operations */ DENTRY_OPS, /* for directory operations */ DATA_WRITE, /* for data write */ DATA_NEW, /* for data allocation */ DATA_TRUNC, /* for data truncate */ NODE_NEW, /* for node allocation */ NODE_TRUNC, /* for node truncate */ NODE_WRITE, /* for node write */ NR_LOCK_TYPE, }; In that case, we lose the performance under the multi-threading environment, since every types of operations must be conducted one at a time. In order to address the problem, let's share the locks globally with a mutex array regardless of any types. So, let users grab a mutex and perform their jobs in parallel as much as possbile. For this, I propose a new global lock scheme as follows. 0. Data structure - f2fs_sb_info -> mutex_lock[NR_GLOBAL_LOCKS] - f2fs_sb_info -> node_write 1. mutex_lock_op(sbi) - try to get an avaiable lock from the array. - returns the index of the gottern lock variable. 2. mutex_unlock_op(sbi, index of the lock) - unlock the given index of the lock. 3. mutex_lock_all(sbi) - grab all the locks in the array before the checkpoint. 4. mutex_unlock_all(sbi) - release all the locks in the array after checkpoint. 5. block_operations() - call mutex_lock_all() - sync_dirty_dir_inodes() - grab node_write - sync_node_pages() Note that, the pairs of mutex_lock_op()/mutex_unlock_op() and mutex_lock_all()/mutex_unlock_all() should be used together. Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
2012-11-22 07:21:29 +00:00
goto write;
/*
* If the offset is out-of-range of file size,
* this page does not have to be written to disk.
*/
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 12:29:47 +00:00
offset = i_size & (PAGE_SIZE - 1);
if ((page->index >= end_index + 1) || !offset)
f2fs: introduce a new global lock scheme In the previous version, f2fs uses global locks according to the usage types, such as directory operations, block allocation, block write, and so on. Reference the following lock types in f2fs.h. enum lock_type { RENAME, /* for renaming operations */ DENTRY_OPS, /* for directory operations */ DATA_WRITE, /* for data write */ DATA_NEW, /* for data allocation */ DATA_TRUNC, /* for data truncate */ NODE_NEW, /* for node allocation */ NODE_TRUNC, /* for node truncate */ NODE_WRITE, /* for node write */ NR_LOCK_TYPE, }; In that case, we lose the performance under the multi-threading environment, since every types of operations must be conducted one at a time. In order to address the problem, let's share the locks globally with a mutex array regardless of any types. So, let users grab a mutex and perform their jobs in parallel as much as possbile. For this, I propose a new global lock scheme as follows. 0. Data structure - f2fs_sb_info -> mutex_lock[NR_GLOBAL_LOCKS] - f2fs_sb_info -> node_write 1. mutex_lock_op(sbi) - try to get an avaiable lock from the array. - returns the index of the gottern lock variable. 2. mutex_unlock_op(sbi, index of the lock) - unlock the given index of the lock. 3. mutex_lock_all(sbi) - grab all the locks in the array before the checkpoint. 4. mutex_unlock_all(sbi) - release all the locks in the array after checkpoint. 5. block_operations() - call mutex_lock_all() - sync_dirty_dir_inodes() - grab node_write - sync_node_pages() Note that, the pairs of mutex_lock_op()/mutex_unlock_op() and mutex_lock_all()/mutex_unlock_all() should be used together. Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
2012-11-22 07:21:29 +00:00
goto out;
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 12:29:47 +00:00
zero_user_segment(page, offset, PAGE_SIZE);
f2fs: introduce a new global lock scheme In the previous version, f2fs uses global locks according to the usage types, such as directory operations, block allocation, block write, and so on. Reference the following lock types in f2fs.h. enum lock_type { RENAME, /* for renaming operations */ DENTRY_OPS, /* for directory operations */ DATA_WRITE, /* for data write */ DATA_NEW, /* for data allocation */ DATA_TRUNC, /* for data truncate */ NODE_NEW, /* for node allocation */ NODE_TRUNC, /* for node truncate */ NODE_WRITE, /* for node write */ NR_LOCK_TYPE, }; In that case, we lose the performance under the multi-threading environment, since every types of operations must be conducted one at a time. In order to address the problem, let's share the locks globally with a mutex array regardless of any types. So, let users grab a mutex and perform their jobs in parallel as much as possbile. For this, I propose a new global lock scheme as follows. 0. Data structure - f2fs_sb_info -> mutex_lock[NR_GLOBAL_LOCKS] - f2fs_sb_info -> node_write 1. mutex_lock_op(sbi) - try to get an avaiable lock from the array. - returns the index of the gottern lock variable. 2. mutex_unlock_op(sbi, index of the lock) - unlock the given index of the lock. 3. mutex_lock_all(sbi) - grab all the locks in the array before the checkpoint. 4. mutex_unlock_all(sbi) - release all the locks in the array after checkpoint. 5. block_operations() - call mutex_lock_all() - sync_dirty_dir_inodes() - grab node_write - sync_node_pages() Note that, the pairs of mutex_lock_op()/mutex_unlock_op() and mutex_lock_all()/mutex_unlock_all() should be used together. Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
2012-11-22 07:21:29 +00:00
write:
/* Dentry/quota blocks are controlled by checkpoint */
if (S_ISDIR(inode->i_mode) || quota_inode) {
/*
* We need to wait for node_write to avoid block allocation during
* checkpoint. This can only happen to quota writes which can cause
* the below discard race condition.
*/
if (quota_inode)
f2fs_down_read(&sbi->node_write);
fio.need_lock = LOCK_DONE;
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
err = f2fs_do_write_data_page(&fio);
if (quota_inode)
f2fs_up_read(&sbi->node_write);
goto done;
}
if (!wbc->for_reclaim)
f2fs: introduce a new global lock scheme In the previous version, f2fs uses global locks according to the usage types, such as directory operations, block allocation, block write, and so on. Reference the following lock types in f2fs.h. enum lock_type { RENAME, /* for renaming operations */ DENTRY_OPS, /* for directory operations */ DATA_WRITE, /* for data write */ DATA_NEW, /* for data allocation */ DATA_TRUNC, /* for data truncate */ NODE_NEW, /* for node allocation */ NODE_TRUNC, /* for node truncate */ NODE_WRITE, /* for node write */ NR_LOCK_TYPE, }; In that case, we lose the performance under the multi-threading environment, since every types of operations must be conducted one at a time. In order to address the problem, let's share the locks globally with a mutex array regardless of any types. So, let users grab a mutex and perform their jobs in parallel as much as possbile. For this, I propose a new global lock scheme as follows. 0. Data structure - f2fs_sb_info -> mutex_lock[NR_GLOBAL_LOCKS] - f2fs_sb_info -> node_write 1. mutex_lock_op(sbi) - try to get an avaiable lock from the array. - returns the index of the gottern lock variable. 2. mutex_unlock_op(sbi, index of the lock) - unlock the given index of the lock. 3. mutex_lock_all(sbi) - grab all the locks in the array before the checkpoint. 4. mutex_unlock_all(sbi) - release all the locks in the array after checkpoint. 5. block_operations() - call mutex_lock_all() - sync_dirty_dir_inodes() - grab node_write - sync_node_pages() Note that, the pairs of mutex_lock_op()/mutex_unlock_op() and mutex_lock_all()/mutex_unlock_all() should be used together. Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
2012-11-22 07:21:29 +00:00
need_balance_fs = true;
else if (has_not_enough_free_secs(sbi, 0, 0))
f2fs: introduce a new global lock scheme In the previous version, f2fs uses global locks according to the usage types, such as directory operations, block allocation, block write, and so on. Reference the following lock types in f2fs.h. enum lock_type { RENAME, /* for renaming operations */ DENTRY_OPS, /* for directory operations */ DATA_WRITE, /* for data write */ DATA_NEW, /* for data allocation */ DATA_TRUNC, /* for data truncate */ NODE_NEW, /* for node allocation */ NODE_TRUNC, /* for node truncate */ NODE_WRITE, /* for node write */ NR_LOCK_TYPE, }; In that case, we lose the performance under the multi-threading environment, since every types of operations must be conducted one at a time. In order to address the problem, let's share the locks globally with a mutex array regardless of any types. So, let users grab a mutex and perform their jobs in parallel as much as possbile. For this, I propose a new global lock scheme as follows. 0. Data structure - f2fs_sb_info -> mutex_lock[NR_GLOBAL_LOCKS] - f2fs_sb_info -> node_write 1. mutex_lock_op(sbi) - try to get an avaiable lock from the array. - returns the index of the gottern lock variable. 2. mutex_unlock_op(sbi, index of the lock) - unlock the given index of the lock. 3. mutex_lock_all(sbi) - grab all the locks in the array before the checkpoint. 4. mutex_unlock_all(sbi) - release all the locks in the array after checkpoint. 5. block_operations() - call mutex_lock_all() - sync_dirty_dir_inodes() - grab node_write - sync_node_pages() Note that, the pairs of mutex_lock_op()/mutex_unlock_op() and mutex_lock_all()/mutex_unlock_all() should be used together. Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
2012-11-22 07:21:29 +00:00
goto redirty_out;
else
set_inode_flag(inode, FI_HOT_DATA);
err = -EAGAIN;
if (f2fs_has_inline_data(inode)) {
err = f2fs_write_inline_data(inode, page);
if (!err)
goto out;
}
if (err == -EAGAIN) {
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
err = f2fs_do_write_data_page(&fio);
if (err == -EAGAIN) {
f2fs_bug_on(sbi, compr_blocks);
fio.need_lock = LOCK_REQ;
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
err = f2fs_do_write_data_page(&fio);
}
}
if (err) {
file_set_keep_isize(inode);
} else {
f2fs: cover last_disk_size update with spinlock This change solves below hangtask issue: INFO: task kworker/u16:1:58 blocked for more than 122 seconds. Not tainted 5.6.0-rc2-00590-g9983bdae4974e #11 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. kworker/u16:1 D 0 58 2 0x00000000 Workqueue: writeback wb_workfn (flush-179:0) Backtrace: (__schedule) from [<c0913234>] (schedule+0x78/0xf4) (schedule) from [<c017ec74>] (rwsem_down_write_slowpath+0x24c/0x4c0) (rwsem_down_write_slowpath) from [<c0915f2c>] (down_write+0x6c/0x70) (down_write) from [<c0435b80>] (f2fs_write_single_data_page+0x608/0x7ac) (f2fs_write_single_data_page) from [<c0435fd8>] (f2fs_write_cache_pages+0x2b4/0x7c4) (f2fs_write_cache_pages) from [<c043682c>] (f2fs_write_data_pages+0x344/0x35c) (f2fs_write_data_pages) from [<c0267ee8>] (do_writepages+0x3c/0xd4) (do_writepages) from [<c0310cbc>] (__writeback_single_inode+0x44/0x454) (__writeback_single_inode) from [<c03112d0>] (writeback_sb_inodes+0x204/0x4b0) (writeback_sb_inodes) from [<c03115cc>] (__writeback_inodes_wb+0x50/0xe4) (__writeback_inodes_wb) from [<c03118f4>] (wb_writeback+0x294/0x338) (wb_writeback) from [<c0312dac>] (wb_workfn+0x35c/0x54c) (wb_workfn) from [<c014f2b8>] (process_one_work+0x214/0x544) (process_one_work) from [<c014f634>] (worker_thread+0x4c/0x574) (worker_thread) from [<c01564fc>] (kthread+0x144/0x170) (kthread) from [<c01010e8>] (ret_from_fork+0x14/0x2c) Reported-and-tested-by: Ondřej Jirman <megi@xff.cz> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2020-02-27 11:30:03 +00:00
spin_lock(&F2FS_I(inode)->i_size_lock);
if (F2FS_I(inode)->last_disk_size < psize)
F2FS_I(inode)->last_disk_size = psize;
f2fs: cover last_disk_size update with spinlock This change solves below hangtask issue: INFO: task kworker/u16:1:58 blocked for more than 122 seconds. Not tainted 5.6.0-rc2-00590-g9983bdae4974e #11 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. kworker/u16:1 D 0 58 2 0x00000000 Workqueue: writeback wb_workfn (flush-179:0) Backtrace: (__schedule) from [<c0913234>] (schedule+0x78/0xf4) (schedule) from [<c017ec74>] (rwsem_down_write_slowpath+0x24c/0x4c0) (rwsem_down_write_slowpath) from [<c0915f2c>] (down_write+0x6c/0x70) (down_write) from [<c0435b80>] (f2fs_write_single_data_page+0x608/0x7ac) (f2fs_write_single_data_page) from [<c0435fd8>] (f2fs_write_cache_pages+0x2b4/0x7c4) (f2fs_write_cache_pages) from [<c043682c>] (f2fs_write_data_pages+0x344/0x35c) (f2fs_write_data_pages) from [<c0267ee8>] (do_writepages+0x3c/0xd4) (do_writepages) from [<c0310cbc>] (__writeback_single_inode+0x44/0x454) (__writeback_single_inode) from [<c03112d0>] (writeback_sb_inodes+0x204/0x4b0) (writeback_sb_inodes) from [<c03115cc>] (__writeback_inodes_wb+0x50/0xe4) (__writeback_inodes_wb) from [<c03118f4>] (wb_writeback+0x294/0x338) (wb_writeback) from [<c0312dac>] (wb_workfn+0x35c/0x54c) (wb_workfn) from [<c014f2b8>] (process_one_work+0x214/0x544) (process_one_work) from [<c014f634>] (worker_thread+0x4c/0x574) (worker_thread) from [<c01564fc>] (kthread+0x144/0x170) (kthread) from [<c01010e8>] (ret_from_fork+0x14/0x2c) Reported-and-tested-by: Ondřej Jirman <megi@xff.cz> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2020-02-27 11:30:03 +00:00
spin_unlock(&F2FS_I(inode)->i_size_lock);
}
done:
if (err && err != -ENOENT)
goto redirty_out;
f2fs: introduce a new global lock scheme In the previous version, f2fs uses global locks according to the usage types, such as directory operations, block allocation, block write, and so on. Reference the following lock types in f2fs.h. enum lock_type { RENAME, /* for renaming operations */ DENTRY_OPS, /* for directory operations */ DATA_WRITE, /* for data write */ DATA_NEW, /* for data allocation */ DATA_TRUNC, /* for data truncate */ NODE_NEW, /* for node allocation */ NODE_TRUNC, /* for node truncate */ NODE_WRITE, /* for node write */ NR_LOCK_TYPE, }; In that case, we lose the performance under the multi-threading environment, since every types of operations must be conducted one at a time. In order to address the problem, let's share the locks globally with a mutex array regardless of any types. So, let users grab a mutex and perform their jobs in parallel as much as possbile. For this, I propose a new global lock scheme as follows. 0. Data structure - f2fs_sb_info -> mutex_lock[NR_GLOBAL_LOCKS] - f2fs_sb_info -> node_write 1. mutex_lock_op(sbi) - try to get an avaiable lock from the array. - returns the index of the gottern lock variable. 2. mutex_unlock_op(sbi, index of the lock) - unlock the given index of the lock. 3. mutex_lock_all(sbi) - grab all the locks in the array before the checkpoint. 4. mutex_unlock_all(sbi) - release all the locks in the array after checkpoint. 5. block_operations() - call mutex_lock_all() - sync_dirty_dir_inodes() - grab node_write - sync_node_pages() Note that, the pairs of mutex_lock_op()/mutex_unlock_op() and mutex_lock_all()/mutex_unlock_all() should be used together. Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
2012-11-22 07:21:29 +00:00
out:
inode_dec_dirty_pages(inode);
if (err) {
ClearPageUptodate(page);
f2fs: restructure f2fs page.private layout Restruct f2fs page private layout for below reasons: There are some cases that f2fs wants to set a flag in a page to indicate a specified status of page: a) page is in transaction list for atomic write b) page contains dummy data for aligned write c) page is migrating for GC d) page contains inline data for inline inode flush e) page belongs to merkle tree, and is verified for fsverity f) page is dirty and has filesystem/inode reference count for writeback g) page is temporary and has decompress io context reference for compression There are existed places in page structure we can use to store f2fs private status/data: - page.flags: PG_checked, PG_private - page.private However it was a mess when we using them, which may cause potential confliction: page.private PG_private PG_checked page._refcount (+1 at most) a) -1 set +1 b) -2 set c), d), e) set f) 0 set +1 g) pointer set The other problem is page.flags has no free slot, if we can avoid set zero to page.private and set PG_private flag, then we use non-zero value to indicate PG_private status, so that we may have chance to reclaim PG_private slot for other usage. [1] The other concern is f2fs has bad scalability in aspect of indicating more page status. So in this patch, let's restructure f2fs' page.private as below to solve above issues: Layout A: lowest bit should be 1 | bit0 = 1 | bit1 | bit2 | ... | bit MAX | private data .... | bit 0 PAGE_PRIVATE_NOT_POINTER bit 1 PAGE_PRIVATE_ATOMIC_WRITE bit 2 PAGE_PRIVATE_DUMMY_WRITE bit 3 PAGE_PRIVATE_ONGOING_MIGRATION bit 4 PAGE_PRIVATE_INLINE_INODE bit 5 PAGE_PRIVATE_REF_RESOURCE bit 6- f2fs private data Layout B: lowest bit should be 0 page.private is a wrapped pointer. After the change: page.private PG_private PG_checked page._refcount (+1 at most) a) 11 set +1 b) 101 set +1 c) 1001 set +1 d) 10001 set +1 e) set f) 100001 set +1 g) pointer set +1 [1] https://lore.kernel.org/linux-f2fs-devel/20210422154705.GO3596236@casper.infradead.org/T/#u Cc: Matthew Wilcox <willy@infradead.org> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2021-04-28 09:20:31 +00:00
clear_page_private_gcing(page);
}
if (wbc->for_reclaim) {
f2fs_submit_merged_write_cond(sbi, NULL, page, 0, DATA);
clear_inode_flag(inode, FI_HOT_DATA);
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
f2fs_remove_dirty_inode(inode);
submitted = NULL;
}
unlock_page(page);
f2fs: fix potential recursive call when enabling data_flush As Hagbard Celine reported: Hi, this is a long standing bug that I've hit before on older kernels, but I was not able to get the syslog saved because of the nature of the bug. This time I had booted form a pen-drive, and was able to save the log to it's efi-partition. What i did to trigger it was to create a partition and format it f2fs, then mount it with options: "rw,relatime,lazytime,background_gc=on,disable_ext_identify,discard,heap,user_xattr,inline_xattr,acl,inline_data,inline_dentry,flush_merge,data_flush,extent_cache,mode=adaptive,active_logs=6,whint_mode=fs-based,alloc_mode=default,fsync_mode=strict". Then I unpacked a big .tar.xz to the partition (I used a gentoo-stage3-tarball as I was in process of installing Gentoo). Same options just without data_flush gives no problems. Mar 20 20:54:01 usbgentoo kernel: FAT-fs (nvme0n1p4): Volume was not properly unmounted. Some data may be corrupt. Please run fsck. Mar 20 21:05:23 usbgentoo kernel: kworker/dying (1588) used greatest stack depth: 12064 bytes left Mar 20 21:06:40 usbgentoo kernel: BUG: stack guard page was hit at 00000000a4b0733c (stack is 0000000056016422..0000000096e7463f) Mar 20 21:06:40 usbgentoo kernel: kernel stack overflow ...... Mar 20 21:06:40 usbgentoo kernel: Call Trace: Mar 20 21:06:40 usbgentoo kernel: read_node_page+0x71/0xf0 Mar 20 21:06:40 usbgentoo kernel: ? xas_load+0x8/0x50 Mar 20 21:06:40 usbgentoo kernel: __get_node_page+0x73/0x2a0 Mar 20 21:06:40 usbgentoo kernel: f2fs_get_dnode_of_data+0x34e/0x580 Mar 20 21:06:40 usbgentoo kernel: f2fs_write_inline_data+0x5e/0x2a0 Mar 20 21:06:40 usbgentoo kernel: __write_data_page+0x421/0x690 Mar 20 21:06:40 usbgentoo kernel: f2fs_write_cache_pages+0x1cf/0x460 Mar 20 21:06:40 usbgentoo kernel: f2fs_write_data_pages+0x2b3/0x2e0 Mar 20 21:06:40 usbgentoo kernel: ? f2fs_inode_chksum_verify+0x1d/0xc0 Mar 20 21:06:40 usbgentoo kernel: ? read_node_page+0x71/0xf0 Mar 20 21:06:40 usbgentoo kernel: do_writepages+0x3c/0xd0 Mar 20 21:06:40 usbgentoo kernel: __filemap_fdatawrite_range+0x7c/0xb0 Mar 20 21:06:40 usbgentoo kernel: f2fs_sync_dirty_inodes+0xf2/0x200 Mar 20 21:06:40 usbgentoo kernel: f2fs_balance_fs_bg+0x2a3/0x2c0 Mar 20 21:06:40 usbgentoo kernel: ? f2fs_inode_dirtied+0x21/0xc0 Mar 20 21:06:40 usbgentoo kernel: f2fs_balance_fs+0xd6/0x2b0 Mar 20 21:06:40 usbgentoo kernel: __write_data_page+0x4fb/0x690 ...... Mar 20 21:06:40 usbgentoo kernel: __writeback_single_inode+0x2a1/0x340 Mar 20 21:06:40 usbgentoo kernel: ? soft_cursor+0x1b4/0x220 Mar 20 21:06:40 usbgentoo kernel: writeback_sb_inodes+0x1d5/0x3e0 Mar 20 21:06:40 usbgentoo kernel: __writeback_inodes_wb+0x58/0xa0 Mar 20 21:06:40 usbgentoo kernel: wb_writeback+0x250/0x2e0 Mar 20 21:06:40 usbgentoo kernel: ? 0xffffffff8c000000 Mar 20 21:06:40 usbgentoo kernel: ? cpumask_next+0x16/0x20 Mar 20 21:06:40 usbgentoo kernel: wb_workfn+0x2f6/0x3b0 Mar 20 21:06:40 usbgentoo kernel: ? __switch_to_asm+0x40/0x70 Mar 20 21:06:40 usbgentoo kernel: process_one_work+0x1f5/0x3f0 Mar 20 21:06:40 usbgentoo kernel: worker_thread+0x28/0x3c0 Mar 20 21:06:40 usbgentoo kernel: ? rescuer_thread+0x330/0x330 Mar 20 21:06:40 usbgentoo kernel: kthread+0x10e/0x130 Mar 20 21:06:40 usbgentoo kernel: ? kthread_create_on_node+0x60/0x60 Mar 20 21:06:40 usbgentoo kernel: ret_from_fork+0x35/0x40 The root cause is that we run into an infinite recursive calling in between f2fs_balance_fs_bg and writepage() as described below: - f2fs_write_data_pages --- A - __write_data_page - f2fs_balance_fs - f2fs_balance_fs_bg --- B - f2fs_sync_dirty_inodes - filemap_fdatawrite - f2fs_write_data_pages --- A ... - f2fs_balance_fs_bg --- B ... In order to fix this issue, let's detect such condition in __write_data_page() and just skip calling f2fs_balance_fs() recursively. Reported-by: Hagbard Celine <hagbardcelin@gmail.com> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-04-02 10:52:19 +00:00
if (!S_ISDIR(inode->i_mode) && !IS_NOQUOTA(inode) &&
!F2FS_I(inode)->wb_task && allow_balance)
f2fs_balance_fs(sbi, need_balance_fs);
if (unlikely(f2fs_cp_error(sbi))) {
f2fs_submit_merged_write(sbi, DATA);
if (bio && *bio)
f2fs_submit_merged_ipu_write(sbi, bio, NULL);
submitted = NULL;
}
if (submitted)
*submitted = fio.submitted;
return 0;
redirty_out:
redirty_page_for_writepage(wbc, page);
/*
* pageout() in MM translates EAGAIN, so calls handle_write_error()
* -> mapping_set_error() -> set_bit(AS_EIO, ...).
* file_write_and_wait_range() will see EIO error, which is critical
* to return value of fsync() followed by atomic_write failure to user.
*/
if (!err || wbc->for_reclaim)
return AOP_WRITEPAGE_ACTIVATE;
unlock_page(page);
return err;
}
static int f2fs_write_data_page(struct page *page,
struct writeback_control *wbc)
{
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
#ifdef CONFIG_F2FS_FS_COMPRESSION
struct inode *inode = page->mapping->host;
if (unlikely(f2fs_cp_error(F2FS_I_SB(inode))))
goto out;
if (f2fs_compressed_file(inode)) {
if (f2fs_is_compressed_cluster(inode, page->index)) {
redirty_page_for_writepage(wbc, page);
return AOP_WRITEPAGE_ACTIVATE;
}
}
out:
#endif
return f2fs_write_single_data_page(page, NULL, NULL, NULL,
wbc, FS_DATA_IO, 0, true);
}
/*
* This function was copied from write_cache_pages from mm/page-writeback.c.
* The major change is making write step of cold data page separately from
* warm/hot data page.
*/
static int f2fs_write_cache_pages(struct address_space *mapping,
struct writeback_control *wbc,
enum iostat_type io_type)
{
int ret = 0;
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
int done = 0, retry = 0;
struct page *pages_local[F2FS_ONSTACK_PAGES];
struct page **pages = pages_local;
struct folio_batch fbatch;
struct f2fs_sb_info *sbi = F2FS_M_SB(mapping);
f2fs: add bio cache for IPU SQLite in Wal mode may trigger sequential IPU write in db-wal file, after commit d1b3e72d5490 ("f2fs: submit bio of in-place-update pages"), we lost the chance of merging page in inner managed bio cache, result in submitting more small-sized IO. So let's add temporary bio in writepages() to cache mergeable write IO as much as possible. Test case: 1. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" 2. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" Before: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65552, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65560, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65568, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65576, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65584, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65592, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65600, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65608, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65616, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65624, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65632, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65640, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65648, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65656, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65664, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57352, size = 4096 After: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 65536 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57368, size = 4096 Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-02-19 08:15:29 +00:00
struct bio *bio = NULL;
sector_t last_block;
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
#ifdef CONFIG_F2FS_FS_COMPRESSION
struct inode *inode = mapping->host;
struct compress_ctx cc = {
.inode = inode,
.log_cluster_size = F2FS_I(inode)->i_log_cluster_size,
.cluster_size = F2FS_I(inode)->i_cluster_size,
.cluster_idx = NULL_CLUSTER,
.rpages = NULL,
.nr_rpages = 0,
.cpages = NULL,
.valid_nr_cpages = 0,
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
.rbuf = NULL,
.cbuf = NULL,
.rlen = PAGE_SIZE * F2FS_I(inode)->i_cluster_size,
.private = NULL,
};
#endif
int nr_folios, p, idx;
int nr_pages;
unsigned int max_pages = F2FS_ONSTACK_PAGES;
pgoff_t index;
pgoff_t end; /* Inclusive */
pgoff_t done_index;
int range_whole = 0;
xa_mark_t tag;
int nwritten = 0;
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
int submitted = 0;
int i;
#ifdef CONFIG_F2FS_FS_COMPRESSION
if (f2fs_compressed_file(inode) &&
1 << cc.log_cluster_size > F2FS_ONSTACK_PAGES) {
pages = f2fs_kzalloc(sbi, sizeof(struct page *) <<
cc.log_cluster_size, GFP_NOFS | __GFP_NOFAIL);
max_pages = 1 << cc.log_cluster_size;
}
#endif
folio_batch_init(&fbatch);
if (get_dirty_pages(mapping->host) <=
SM_I(F2FS_M_SB(mapping))->min_hot_blocks)
set_inode_flag(mapping->host, FI_HOT_DATA);
else
clear_inode_flag(mapping->host, FI_HOT_DATA);
if (wbc->range_cyclic) {
index = mapping->writeback_index; /* prev offset */
end = -1;
} else {
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 12:29:47 +00:00
index = wbc->range_start >> PAGE_SHIFT;
end = wbc->range_end >> PAGE_SHIFT;
if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
range_whole = 1;
}
if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
tag = PAGECACHE_TAG_TOWRITE;
else
tag = PAGECACHE_TAG_DIRTY;
retry:
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
retry = 0;
if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
tag_pages_for_writeback(mapping, index, end);
done_index = index;
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
while (!done && !retry && (index <= end)) {
nr_pages = 0;
again:
nr_folios = filemap_get_folios_tag(mapping, &index, end,
tag, &fbatch);
if (nr_folios == 0) {
if (nr_pages)
goto write;
break;
}
for (i = 0; i < nr_folios; i++) {
struct folio *folio = fbatch.folios[i];
idx = 0;
p = folio_nr_pages(folio);
add_more:
pages[nr_pages] = folio_page(folio, idx);
folio_get(folio);
if (++nr_pages == max_pages) {
index = folio->index + idx + 1;
folio_batch_release(&fbatch);
goto write;
}
if (++idx < p)
goto add_more;
}
folio_batch_release(&fbatch);
goto again;
write:
for (i = 0; i < nr_pages; i++) {
struct page *page = pages[i];
struct folio *folio = page_folio(page);
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
bool need_readd;
readd:
need_readd = false;
#ifdef CONFIG_F2FS_FS_COMPRESSION
if (f2fs_compressed_file(inode)) {
void *fsdata = NULL;
struct page *pagep;
int ret2;
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
ret = f2fs_init_compress_ctx(&cc);
if (ret) {
done = 1;
break;
}
if (!f2fs_cluster_can_merge_page(&cc,
folio->index)) {
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
ret = f2fs_write_multi_pages(&cc,
&submitted, wbc, io_type);
if (!ret)
need_readd = true;
goto result;
}
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
if (unlikely(f2fs_cp_error(sbi)))
goto lock_folio;
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
if (!f2fs_cluster_is_empty(&cc))
goto lock_folio;
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
if (f2fs_all_cluster_page_ready(&cc,
pages, i, nr_pages, true))
goto lock_folio;
ret2 = f2fs_prepare_compress_overwrite(
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
inode, &pagep,
folio->index, &fsdata);
if (ret2 < 0) {
ret = ret2;
done = 1;
break;
} else if (ret2 &&
(!f2fs_compress_write_end(inode,
fsdata, folio->index, 1) ||
!f2fs_all_cluster_page_ready(&cc,
pages, i, nr_pages,
false))) {
retry = 1;
break;
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
}
}
#endif
/* give a priority to WB_SYNC threads */
if (atomic_read(&sbi->wb_sync_req[DATA]) &&
wbc->sync_mode == WB_SYNC_NONE) {
done = 1;
break;
}
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
#ifdef CONFIG_F2FS_FS_COMPRESSION
lock_folio:
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
#endif
done_index = folio->index;
retry_write:
folio_lock(folio);
if (unlikely(folio->mapping != mapping)) {
continue_unlock:
folio_unlock(folio);
continue;
}
if (!folio_test_dirty(folio)) {
/* someone wrote it for us */
goto continue_unlock;
}
if (folio_test_writeback(folio)) {
if (wbc->sync_mode == WB_SYNC_NONE)
goto continue_unlock;
f2fs_wait_on_page_writeback(&folio->page, DATA, true, true);
}
if (!folio_clear_dirty_for_io(folio))
goto continue_unlock;
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
#ifdef CONFIG_F2FS_FS_COMPRESSION
if (f2fs_compressed_file(inode)) {
folio_get(folio);
f2fs_compress_ctx_add_page(&cc, &folio->page);
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
continue;
}
#endif
ret = f2fs_write_single_data_page(&folio->page,
&submitted, &bio, &last_block,
wbc, io_type, 0, true);
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
if (ret == AOP_WRITEPAGE_ACTIVATE)
folio_unlock(folio);
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
#ifdef CONFIG_F2FS_FS_COMPRESSION
result:
#endif
nwritten += submitted;
wbc->nr_to_write -= submitted;
if (unlikely(ret)) {
/*
* keep nr_to_write, since vfs uses this to
* get # of written pages.
*/
if (ret == AOP_WRITEPAGE_ACTIVATE) {
ret = 0;
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
goto next;
} else if (ret == -EAGAIN) {
ret = 0;
if (wbc->sync_mode == WB_SYNC_ALL) {
f2fs_io_schedule_timeout(
DEFAULT_IO_TIMEOUT);
goto retry_write;
}
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
goto next;
}
done_index = folio_next_index(folio);
done = 1;
break;
}
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
if (wbc->nr_to_write <= 0 &&
wbc->sync_mode == WB_SYNC_NONE) {
done = 1;
break;
}
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
next:
if (need_readd)
goto readd;
}
release_pages(pages, nr_pages);
cond_resched();
}
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
#ifdef CONFIG_F2FS_FS_COMPRESSION
/* flush remained pages in compress cluster */
if (f2fs_compressed_file(inode) && !f2fs_cluster_is_empty(&cc)) {
ret = f2fs_write_multi_pages(&cc, &submitted, wbc, io_type);
nwritten += submitted;
wbc->nr_to_write -= submitted;
if (ret) {
done = 1;
retry = 0;
}
}
f2fs: fix slab leak of rpages pointer This fixes the below mem leak. [ 130.157600] ============================================================================= [ 130.159662] BUG f2fs_page_array_entry-252:16 (Tainted: G W O ): Objects remaining in f2fs_page_array_entry-252:16 on __kmem_cache_shutdown() [ 130.162742] ----------------------------------------------------------------------------- [ 130.162742] [ 130.164979] Disabling lock debugging due to kernel taint [ 130.166188] INFO: Slab 0x000000009f5a52d2 objects=22 used=4 fp=0x00000000ba72c3e9 flags=0xfffffc0010200 [ 130.168269] CPU: 7 PID: 3560 Comm: umount Tainted: G B W O 5.9.0-rc4+ #35 [ 130.170019] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1 04/01/2014 [ 130.171941] Call Trace: [ 130.172528] dump_stack+0x74/0x9a [ 130.173298] slab_err+0xb7/0xdc [ 130.174044] ? kernel_poison_pages+0xc0/0xc0 [ 130.175065] ? on_each_cpu_cond_mask+0x48/0x90 [ 130.176096] __kmem_cache_shutdown.cold+0x34/0x141 [ 130.177190] kmem_cache_destroy+0x59/0x100 [ 130.178223] f2fs_destroy_page_array_cache+0x15/0x20 [f2fs] [ 130.179527] f2fs_put_super+0x1bc/0x380 [f2fs] [ 130.180538] generic_shutdown_super+0x72/0x110 [ 130.181547] kill_block_super+0x27/0x50 [ 130.182438] kill_f2fs_super+0x76/0xe0 [f2fs] [ 130.183448] deactivate_locked_super+0x3b/0x80 [ 130.184456] deactivate_super+0x3e/0x50 [ 130.185363] cleanup_mnt+0x109/0x160 [ 130.186179] __cleanup_mnt+0x12/0x20 [ 130.187003] task_work_run+0x70/0xb0 [ 130.187841] exit_to_user_mode_prepare+0x18f/0x1b0 [ 130.188917] syscall_exit_to_user_mode+0x31/0x170 [ 130.189989] do_syscall_64+0x45/0x90 [ 130.190828] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 130.191986] RIP: 0033:0x7faf868ea2eb [ 130.192815] Code: 7b 0c 00 f7 d8 64 89 01 48 83 c8 ff c3 66 90 f3 0f 1e fa 31 f6 e9 05 00 00 00 0f 1f 44 00 00 f3 0f 1e fa b8 a6 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 75 7b 0c 00 f7 d8 64 89 01 [ 130.196872] RSP: 002b:00007fffb7edb478 EFLAGS: 00000246 ORIG_RAX: 00000000000000a6 [ 130.198494] RAX: 0000000000000000 RBX: 00007faf86a18204 RCX: 00007faf868ea2eb [ 130.201021] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 000055971df71c50 [ 130.203415] RBP: 000055971df71a40 R08: 0000000000000000 R09: 00007fffb7eda1f0 [ 130.205772] R10: 00007faf86a04339 R11: 0000000000000246 R12: 000055971df71c50 [ 130.208150] R13: 0000000000000000 R14: 000055971df71b38 R15: 0000000000000000 [ 130.210515] INFO: Object 0x00000000a980843a @offset=744 [ 130.212476] INFO: Allocated in page_array_alloc+0x3d/0xe0 [f2fs] age=1572 cpu=0 pid=3297 [ 130.215030] __slab_alloc+0x20/0x40 [ 130.216566] kmem_cache_alloc+0x2a0/0x2e0 [ 130.218217] page_array_alloc+0x3d/0xe0 [f2fs] [ 130.219940] f2fs_init_compress_ctx+0x1f/0x40 [f2fs] [ 130.221736] f2fs_write_cache_pages+0x3db/0x860 [f2fs] [ 130.223591] f2fs_write_data_pages+0x2c9/0x300 [f2fs] [ 130.225414] do_writepages+0x43/0xd0 [ 130.226907] __filemap_fdatawrite_range+0xd5/0x110 [ 130.228632] filemap_write_and_wait_range+0x48/0xb0 [ 130.230336] __generic_file_write_iter+0x18a/0x1d0 [ 130.232035] f2fs_file_write_iter+0x226/0x550 [f2fs] [ 130.233737] new_sync_write+0x113/0x1a0 [ 130.235204] vfs_write+0x1a6/0x200 [ 130.236579] ksys_write+0x67/0xe0 [ 130.237898] __x64_sys_write+0x1a/0x20 [ 130.239309] do_syscall_64+0x38/0x90 Reviewed-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2020-09-23 07:54:50 +00:00
if (f2fs_compressed_file(inode))
f2fs_destroy_compress_ctx(&cc, false);
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
#endif
if (retry) {
index = 0;
end = -1;
goto retry;
}
if (wbc->range_cyclic && !done)
done_index = 0;
if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
mapping->writeback_index = done_index;
if (nwritten)
f2fs_submit_merged_write_cond(F2FS_M_SB(mapping), mapping->host,
NULL, 0, DATA);
f2fs: add bio cache for IPU SQLite in Wal mode may trigger sequential IPU write in db-wal file, after commit d1b3e72d5490 ("f2fs: submit bio of in-place-update pages"), we lost the chance of merging page in inner managed bio cache, result in submitting more small-sized IO. So let's add temporary bio in writepages() to cache mergeable write IO as much as possible. Test case: 1. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" 2. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" Before: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65552, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65560, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65568, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65576, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65584, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65592, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65600, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65608, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65616, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65624, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65632, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65640, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65648, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65656, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65664, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57352, size = 4096 After: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 65536 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57368, size = 4096 Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-02-19 08:15:29 +00:00
/* submit cached bio of IPU write */
if (bio)
f2fs_submit_merged_ipu_write(sbi, &bio, NULL);
#ifdef CONFIG_F2FS_FS_COMPRESSION
if (pages != pages_local)
kfree(pages);
#endif
return ret;
}
static inline bool __should_serialize_io(struct inode *inode,
struct writeback_control *wbc)
{
/* to avoid deadlock in path of data flush */
if (F2FS_I(inode)->wb_task)
return false;
if (!S_ISREG(inode->i_mode))
return false;
if (IS_NOQUOTA(inode))
return false;
if (f2fs_need_compress_data(inode))
return true;
if (wbc->sync_mode != WB_SYNC_ALL)
return true;
if (get_dirty_pages(inode) >= SM_I(F2FS_I_SB(inode))->min_seq_blocks)
return true;
return false;
}
static int __f2fs_write_data_pages(struct address_space *mapping,
struct writeback_control *wbc,
enum iostat_type io_type)
{
struct inode *inode = mapping->host;
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct blk_plug plug;
int ret;
bool locked = false;
/* deal with chardevs and other special file */
if (!mapping->a_ops->writepage)
return 0;
/* skip writing if there is no dirty page in this inode */
if (!get_dirty_pages(inode) && wbc->sync_mode == WB_SYNC_NONE)
return 0;
/* during POR, we don't need to trigger writepage at all. */
if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
goto skip_write;
if ((S_ISDIR(inode->i_mode) || IS_NOQUOTA(inode)) &&
wbc->sync_mode == WB_SYNC_NONE &&
get_dirty_pages(inode) < nr_pages_to_skip(sbi, DATA) &&
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
f2fs_available_free_memory(sbi, DIRTY_DENTS))
goto skip_write;
/* skip writing in file defragment preparing stage */
if (is_inode_flag_set(inode, FI_SKIP_WRITES))
goto skip_write;
trace_f2fs_writepages(mapping->host, wbc, DATA);
/* to avoid spliting IOs due to mixed WB_SYNC_ALL and WB_SYNC_NONE */
if (wbc->sync_mode == WB_SYNC_ALL)
atomic_inc(&sbi->wb_sync_req[DATA]);
else if (atomic_read(&sbi->wb_sync_req[DATA])) {
/* to avoid potential deadlock */
if (current->plug)
blk_finish_plug(current->plug);
goto skip_write;
}
if (__should_serialize_io(inode, wbc)) {
mutex_lock(&sbi->writepages);
locked = true;
}
blk_start_plug(&plug);
ret = f2fs_write_cache_pages(mapping, wbc, io_type);
blk_finish_plug(&plug);
if (locked)
mutex_unlock(&sbi->writepages);
if (wbc->sync_mode == WB_SYNC_ALL)
atomic_dec(&sbi->wb_sync_req[DATA]);
/*
* if some pages were truncated, we cannot guarantee its mapping->host
* to detect pending bios.
*/
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
f2fs_remove_dirty_inode(inode);
return ret;
skip_write:
wbc->pages_skipped += get_dirty_pages(inode);
trace_f2fs_writepages(mapping->host, wbc, DATA);
return 0;
}
static int f2fs_write_data_pages(struct address_space *mapping,
struct writeback_control *wbc)
{
struct inode *inode = mapping->host;
return __f2fs_write_data_pages(mapping, wbc,
F2FS_I(inode)->cp_task == current ?
FS_CP_DATA_IO : FS_DATA_IO);
}
void f2fs_write_failed(struct inode *inode, loff_t to)
{
loff_t i_size = i_size_read(inode);
if (IS_NOQUOTA(inode))
return;
f2fs: add fs-verity support Add fs-verity support to f2fs. fs-verity is a filesystem feature that enables transparent integrity protection and authentication of read-only files. It uses a dm-verity like mechanism at the file level: a Merkle tree is used to verify any block in the file in log(filesize) time. It is implemented mainly by helper functions in fs/verity/. See Documentation/filesystems/fsverity.rst for the full documentation. The f2fs support for fs-verity consists of: - Adding a filesystem feature flag and an inode flag for fs-verity. - Implementing the fsverity_operations to support enabling verity on an inode and reading/writing the verity metadata. - Updating ->readpages() to verify data as it's read from verity files and to support reading verity metadata pages. - Updating ->write_begin(), ->write_end(), and ->writepages() to support writing verity metadata pages. - Calling the fs-verity hooks for ->open(), ->setattr(), and ->ioctl(). Like ext4, f2fs stores the verity metadata (Merkle tree and fsverity_descriptor) past the end of the file, starting at the first 64K boundary beyond i_size. This approach works because (a) verity files are readonly, and (b) pages fully beyond i_size aren't visible to userspace but can be read/written internally by f2fs with only some relatively small changes to f2fs. Extended attributes cannot be used because (a) f2fs limits the total size of an inode's xattr entries to 4096 bytes, which wouldn't be enough for even a single Merkle tree block, and (b) f2fs encryption doesn't encrypt xattrs, yet the verity metadata *must* be encrypted when the file is because it contains hashes of the plaintext data. Acked-by: Jaegeuk Kim <jaegeuk@kernel.org> Acked-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Eric Biggers <ebiggers@google.com>
2019-07-22 16:26:24 +00:00
/* In the fs-verity case, f2fs_end_enable_verity() does the truncate */
if (to > i_size && !f2fs_verity_in_progress(inode)) {
f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
f2fs-for-5.15-rc1 In this cycle, we've addressed some performance issues such as lock contention, misbehaving compress_cache, allowing extent_cache for compressed files, and new sysfs to adjust ra_size for fadvise. In order to diagnose the performance issues quickly, we also added an iostat which shows the IO latencies periodically. On the stability side, we've found two memory leakage cases in the error path in compression flow. And, we've also fixed various corner cases in fiemap, quota, checkpoint=disable, zstd, and so on. Enhancement: - avoid long checkpoint latency by releasing nat_tree_lock - collect and show iostats periodically - support extent_cache for compressed files - add a sysfs entry to manage ra_size given fadvise(POSIX_FADV_SEQUENTIAL) - report f2fs GC status via sysfs - add discard_unit=%s in mount option to handle zoned device Bug fix: - fix two memory leakages when an error happens in the compressed IO flow - fix commpress_cache to get the right LBA - fix fiemap to deal with compressed case correctly - fix wrong EIO returns due to SBI_NEED_FSCK - fix missing writes when enabling checkpoint back - fix quota deadlock - fix zstd level mount option In addition to the above major updates, we've cleaned up several code paths such as dio, unnecessary operations, debugfs/f2fs/status, sanity check, and typos. -----BEGIN PGP SIGNATURE----- iQIzBAABCgAdFiEE00UqedjCtOrGVvQiQBSofoJIUNIFAmEyw1sACgkQQBSofoJI UNLJmA/+NHUgwUjLMcHvmLyp6QYpQDZtKj93/sRDo+YHOYNdYFjWWUb329PYTKWS kEdzApCP+KHfVxeSkiL/x3qWP+RlTkIf96P0kR3/BKi0tjg25G2riFWztusDDFpt xi+AW5sUFDvIx1tFumvQHAQedSwBgcZ96ovT5EwxEuONkljhZC9phEC6vSXz9nOR e2EQIyezbC5O21np1KSeqSgqRMpVkJkVcEHy4VmpMBCLMOOYPepWwKw+yPaV/jR/ zUXdo2/53vma50M5LCDPCtjCtWQgLoeNeGLxyjfzQuTJU6TmtPY65JObLPt6pUSj fRW6qIziTZbVYXzOWBD0EYilv2N4c3BNJdhQCpx2Vyjw9/LLxzqKPOUyzBoa1kjY eZVvmaLXVCKsoJdHDSi7OH/4BqS6SuSZE8eO/nGkgswqiErHZ0Vwl3bFCWC7r/Bk r2U5spJx/83XO6c9H1bzeWEies1DRtwnCDIRRuw35RtJ4uHZaqCfkuJ7rOBwC90X 4SpaAKdUxP2RWc3GKELBIhaqPn7vyMy9ile6VU14PjM8UcY5hyE87T2azqR8gGut nVjRL4cbMGTPj6m1Qj8KqBRSaLuShe6AncUy7bNGiM+JlcLcdB6OJ1ZYLl9hjx2r TbIouXThgcZ4SIK0DEaBLKz2b9/0TfaO9gw1XzpRma+bWA1pApM= =W67o -----END PGP SIGNATURE----- Merge tag 'f2fs-for-5.15-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs Pull f2fs updates from Jaegeuk Kim: "In this cycle, we've addressed some performance issues such as lock contention, misbehaving compress_cache, allowing extent_cache for compressed files, and new sysfs to adjust ra_size for fadvise. In order to diagnose the performance issues quickly, we also added an iostat which shows the IO latencies periodically. On the stability side, we've found two memory leakage cases in the error path in compression flow. And, we've also fixed various corner cases in fiemap, quota, checkpoint=disable, zstd, and so on. Enhancements: - avoid long checkpoint latency by releasing nat_tree_lock - collect and show iostats periodically - support extent_cache for compressed files - add a sysfs entry to manage ra_size given fadvise(POSIX_FADV_SEQUENTIAL) - report f2fs GC status via sysfs - add discard_unit=%s in mount option to handle zoned device Bug fixes: - fix two memory leakages when an error happens in the compressed IO flow - fix commpress_cache to get the right LBA - fix fiemap to deal with compressed case correctly - fix wrong EIO returns due to SBI_NEED_FSCK - fix missing writes when enabling checkpoint back - fix quota deadlock - fix zstd level mount option In addition to the above major updates, we've cleaned up several code paths such as dio, unnecessary operations, debugfs/f2fs/status, sanity check, and typos" * tag 'f2fs-for-5.15-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (46 commits) f2fs: should put a page beyond EOF when preparing a write f2fs: deallocate compressed pages when error happens f2fs: enable realtime discard iff device supports discard f2fs: guarantee to write dirty data when enabling checkpoint back f2fs: fix to unmap pages from userspace process in punch_hole() f2fs: fix unexpected ENOENT comes from f2fs_map_blocks() f2fs: fix to account missing .skipped_gc_rwsem f2fs: adjust unlock order for cleanup f2fs: Don't create discard thread when device doesn't support realtime discard f2fs: rebuild nat_bits during umount f2fs: introduce periodic iostat io latency traces f2fs: separate out iostat feature f2fs: compress: do sanity check on cluster f2fs: fix description about main_blkaddr node f2fs: convert S_IRUGO to 0444 f2fs: fix to keep compatibility of fault injection interface f2fs: support fault injection for f2fs_kmem_cache_alloc() f2fs: compress: allow write compress released file after truncate to zero f2fs: correct comment in segment.h f2fs: improve sbi status info in debugfs/f2fs/status ...
2021-09-04 17:48:47 +00:00
filemap_invalidate_lock(inode->i_mapping);
truncate_pagecache(inode, i_size);
f2fs_truncate_blocks(inode, i_size, true);
f2fs-for-5.15-rc1 In this cycle, we've addressed some performance issues such as lock contention, misbehaving compress_cache, allowing extent_cache for compressed files, and new sysfs to adjust ra_size for fadvise. In order to diagnose the performance issues quickly, we also added an iostat which shows the IO latencies periodically. On the stability side, we've found two memory leakage cases in the error path in compression flow. And, we've also fixed various corner cases in fiemap, quota, checkpoint=disable, zstd, and so on. Enhancement: - avoid long checkpoint latency by releasing nat_tree_lock - collect and show iostats periodically - support extent_cache for compressed files - add a sysfs entry to manage ra_size given fadvise(POSIX_FADV_SEQUENTIAL) - report f2fs GC status via sysfs - add discard_unit=%s in mount option to handle zoned device Bug fix: - fix two memory leakages when an error happens in the compressed IO flow - fix commpress_cache to get the right LBA - fix fiemap to deal with compressed case correctly - fix wrong EIO returns due to SBI_NEED_FSCK - fix missing writes when enabling checkpoint back - fix quota deadlock - fix zstd level mount option In addition to the above major updates, we've cleaned up several code paths such as dio, unnecessary operations, debugfs/f2fs/status, sanity check, and typos. -----BEGIN PGP SIGNATURE----- iQIzBAABCgAdFiEE00UqedjCtOrGVvQiQBSofoJIUNIFAmEyw1sACgkQQBSofoJI UNLJmA/+NHUgwUjLMcHvmLyp6QYpQDZtKj93/sRDo+YHOYNdYFjWWUb329PYTKWS kEdzApCP+KHfVxeSkiL/x3qWP+RlTkIf96P0kR3/BKi0tjg25G2riFWztusDDFpt xi+AW5sUFDvIx1tFumvQHAQedSwBgcZ96ovT5EwxEuONkljhZC9phEC6vSXz9nOR e2EQIyezbC5O21np1KSeqSgqRMpVkJkVcEHy4VmpMBCLMOOYPepWwKw+yPaV/jR/ zUXdo2/53vma50M5LCDPCtjCtWQgLoeNeGLxyjfzQuTJU6TmtPY65JObLPt6pUSj fRW6qIziTZbVYXzOWBD0EYilv2N4c3BNJdhQCpx2Vyjw9/LLxzqKPOUyzBoa1kjY eZVvmaLXVCKsoJdHDSi7OH/4BqS6SuSZE8eO/nGkgswqiErHZ0Vwl3bFCWC7r/Bk r2U5spJx/83XO6c9H1bzeWEies1DRtwnCDIRRuw35RtJ4uHZaqCfkuJ7rOBwC90X 4SpaAKdUxP2RWc3GKELBIhaqPn7vyMy9ile6VU14PjM8UcY5hyE87T2azqR8gGut nVjRL4cbMGTPj6m1Qj8KqBRSaLuShe6AncUy7bNGiM+JlcLcdB6OJ1ZYLl9hjx2r TbIouXThgcZ4SIK0DEaBLKz2b9/0TfaO9gw1XzpRma+bWA1pApM= =W67o -----END PGP SIGNATURE----- Merge tag 'f2fs-for-5.15-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs Pull f2fs updates from Jaegeuk Kim: "In this cycle, we've addressed some performance issues such as lock contention, misbehaving compress_cache, allowing extent_cache for compressed files, and new sysfs to adjust ra_size for fadvise. In order to diagnose the performance issues quickly, we also added an iostat which shows the IO latencies periodically. On the stability side, we've found two memory leakage cases in the error path in compression flow. And, we've also fixed various corner cases in fiemap, quota, checkpoint=disable, zstd, and so on. Enhancements: - avoid long checkpoint latency by releasing nat_tree_lock - collect and show iostats periodically - support extent_cache for compressed files - add a sysfs entry to manage ra_size given fadvise(POSIX_FADV_SEQUENTIAL) - report f2fs GC status via sysfs - add discard_unit=%s in mount option to handle zoned device Bug fixes: - fix two memory leakages when an error happens in the compressed IO flow - fix commpress_cache to get the right LBA - fix fiemap to deal with compressed case correctly - fix wrong EIO returns due to SBI_NEED_FSCK - fix missing writes when enabling checkpoint back - fix quota deadlock - fix zstd level mount option In addition to the above major updates, we've cleaned up several code paths such as dio, unnecessary operations, debugfs/f2fs/status, sanity check, and typos" * tag 'f2fs-for-5.15-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (46 commits) f2fs: should put a page beyond EOF when preparing a write f2fs: deallocate compressed pages when error happens f2fs: enable realtime discard iff device supports discard f2fs: guarantee to write dirty data when enabling checkpoint back f2fs: fix to unmap pages from userspace process in punch_hole() f2fs: fix unexpected ENOENT comes from f2fs_map_blocks() f2fs: fix to account missing .skipped_gc_rwsem f2fs: adjust unlock order for cleanup f2fs: Don't create discard thread when device doesn't support realtime discard f2fs: rebuild nat_bits during umount f2fs: introduce periodic iostat io latency traces f2fs: separate out iostat feature f2fs: compress: do sanity check on cluster f2fs: fix description about main_blkaddr node f2fs: convert S_IRUGO to 0444 f2fs: fix to keep compatibility of fault injection interface f2fs: support fault injection for f2fs_kmem_cache_alloc() f2fs: compress: allow write compress released file after truncate to zero f2fs: correct comment in segment.h f2fs: improve sbi status info in debugfs/f2fs/status ...
2021-09-04 17:48:47 +00:00
filemap_invalidate_unlock(inode->i_mapping);
f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
}
}
static int prepare_write_begin(struct f2fs_sb_info *sbi,
struct page *page, loff_t pos, unsigned len,
block_t *blk_addr, bool *node_changed)
{
struct inode *inode = page->mapping->host;
pgoff_t index = page->index;
struct dnode_of_data dn;
struct page *ipage;
bool locked = false;
int flag = F2FS_GET_BLOCK_PRE_AIO;
int err = 0;
/*
* If a whole page is being written and we already preallocated all the
* blocks, then there is no need to get a block address now.
*/
if (len == PAGE_SIZE && is_inode_flag_set(inode, FI_PREALLOCATED_ALL))
return 0;
/* f2fs_lock_op avoids race between write CP and convert_inline_page */
if (f2fs_has_inline_data(inode)) {
if (pos + len > MAX_INLINE_DATA(inode))
flag = F2FS_GET_BLOCK_DEFAULT;
f2fs_map_lock(sbi, flag);
locked = true;
} else if ((pos & PAGE_MASK) >= i_size_read(inode)) {
f2fs_map_lock(sbi, flag);
locked = true;
}
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
restart:
/* check inline_data */
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
ipage = f2fs_get_node_page(sbi, inode->i_ino);
if (IS_ERR(ipage)) {
err = PTR_ERR(ipage);
goto unlock_out;
}
set_new_dnode(&dn, inode, ipage, ipage, 0);
if (f2fs_has_inline_data(inode)) {
if (pos + len <= MAX_INLINE_DATA(inode)) {
f2fs_do_read_inline_data(page_folio(page), ipage);
set_inode_flag(inode, FI_DATA_EXIST);
f2fs: fix deadlock when flush inline data Below backtrace info was reported by Yunlei He: Call Trace: [<ffffffff817a9395>] schedule+0x35/0x80 [<ffffffff817abb7d>] rwsem_down_read_failed+0xed/0x130 [<ffffffff813c12a8>] call_rwsem_down_read_failed+0x18/0x [<ffffffff817ab1d0>] down_read+0x20/0x30 [<ffffffffa02a1a12>] f2fs_evict_inode+0x242/0x3a0 [f2fs] [<ffffffff81217057>] evict+0xc7/0x1a0 [<ffffffff81217cd6>] iput+0x196/0x200 [<ffffffff812134f9>] __dentry_kill+0x179/0x1e0 [<ffffffff812136f9>] dput+0x199/0x1f0 [<ffffffff811fe77b>] __fput+0x18b/0x220 [<ffffffff811fe84e>] ____fput+0xe/0x10 [<ffffffff81097427>] task_work_run+0x77/0x90 [<ffffffff81074d62>] exit_to_usermode_loop+0x73/0xa2 [<ffffffff81003b7a>] do_syscall_64+0xfa/0x110 [<ffffffff817acf65>] entry_SYSCALL64_slow_path+0x25/0x25 Call Trace: [<ffffffff817a9395>] schedule+0x35/0x80 [<ffffffff81216dc3>] __wait_on_freeing_inode+0xa3/0xd0 [<ffffffff810bc300>] ? autoremove_wake_function+0x40/0x4 [<ffffffff8121771d>] find_inode_fast+0x7d/0xb0 [<ffffffff8121794a>] ilookup+0x6a/0xd0 [<ffffffffa02bc740>] sync_node_pages+0x210/0x650 [f2fs] [<ffffffff8122e690>] ? do_fsync+0x70/0x70 [<ffffffffa02b085e>] block_operations+0x9e/0xf0 [f2fs] [<ffffffff8137b795>] ? bio_endio+0x55/0x60 [<ffffffffa02b0942>] write_checkpoint+0x92/0xba0 [f2fs] [<ffffffff8117da57>] ? mempool_free_slab+0x17/0x20 [<ffffffff8117de8b>] ? mempool_free+0x2b/0x80 [<ffffffff8122e690>] ? do_fsync+0x70/0x70 [<ffffffffa02a53e3>] f2fs_sync_fs+0x63/0xd0 [f2fs] [<ffffffff8129630f>] ? ext4_sync_fs+0xbf/0x190 [<ffffffff8122e6b0>] sync_fs_one_sb+0x20/0x30 [<ffffffff812002e9>] iterate_supers+0xb9/0x110 [<ffffffff8122e7b5>] sys_sync+0x55/0x90 [<ffffffff81003ae9>] do_syscall_64+0x69/0x110 [<ffffffff817acf65>] entry_SYSCALL64_slow_path+0x25/0x25 With following excuting serials, we will set inline_node in inode page after inode was unlinked, result in a deadloop described as below: 1. open file 2. write file 3. unlink file 4. write file 5. close file Thread A Thread B - dput - iput_final - inode->i_state |= I_FREEING - evict - f2fs_evict_inode - f2fs_sync_fs - write_checkpoint - block_operations - f2fs_lock_all (down_write(cp_rwsem)) - f2fs_lock_op (down_read(cp_rwsem)) - sync_node_pages - ilookup - find_inode_fast - __wait_on_freeing_inode (wait on I_FREEING clear) Here, we change to set inline_node flag only for linked inode for fixing. Reported-by: Yunlei He <heyunlei@huawei.com> Signed-off-by: Chao Yu <yuchao0@huawei.com> Tested-by: Jaegeuk Kim <jaegeuk@kernel.org> Cc: stable@vger.kernel.org # v4.6 Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2016-05-11 11:48:44 +00:00
if (inode->i_nlink)
f2fs: restructure f2fs page.private layout Restruct f2fs page private layout for below reasons: There are some cases that f2fs wants to set a flag in a page to indicate a specified status of page: a) page is in transaction list for atomic write b) page contains dummy data for aligned write c) page is migrating for GC d) page contains inline data for inline inode flush e) page belongs to merkle tree, and is verified for fsverity f) page is dirty and has filesystem/inode reference count for writeback g) page is temporary and has decompress io context reference for compression There are existed places in page structure we can use to store f2fs private status/data: - page.flags: PG_checked, PG_private - page.private However it was a mess when we using them, which may cause potential confliction: page.private PG_private PG_checked page._refcount (+1 at most) a) -1 set +1 b) -2 set c), d), e) set f) 0 set +1 g) pointer set The other problem is page.flags has no free slot, if we can avoid set zero to page.private and set PG_private flag, then we use non-zero value to indicate PG_private status, so that we may have chance to reclaim PG_private slot for other usage. [1] The other concern is f2fs has bad scalability in aspect of indicating more page status. So in this patch, let's restructure f2fs' page.private as below to solve above issues: Layout A: lowest bit should be 1 | bit0 = 1 | bit1 | bit2 | ... | bit MAX | private data .... | bit 0 PAGE_PRIVATE_NOT_POINTER bit 1 PAGE_PRIVATE_ATOMIC_WRITE bit 2 PAGE_PRIVATE_DUMMY_WRITE bit 3 PAGE_PRIVATE_ONGOING_MIGRATION bit 4 PAGE_PRIVATE_INLINE_INODE bit 5 PAGE_PRIVATE_REF_RESOURCE bit 6- f2fs private data Layout B: lowest bit should be 0 page.private is a wrapped pointer. After the change: page.private PG_private PG_checked page._refcount (+1 at most) a) 11 set +1 b) 101 set +1 c) 1001 set +1 d) 10001 set +1 e) set f) 100001 set +1 g) pointer set +1 [1] https://lore.kernel.org/linux-f2fs-devel/20210422154705.GO3596236@casper.infradead.org/T/#u Cc: Matthew Wilcox <willy@infradead.org> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2021-04-28 09:20:31 +00:00
set_page_private_inline(ipage);
goto out;
}
err = f2fs_convert_inline_page(&dn, page);
if (err || dn.data_blkaddr != NULL_ADDR)
goto out;
}
if (!f2fs_lookup_read_extent_cache_block(inode, index,
&dn.data_blkaddr)) {
if (locked) {
err = f2fs_reserve_block(&dn, index);
goto out;
}
/* hole case */
err = f2fs_get_dnode_of_data(&dn, index, LOOKUP_NODE);
if (!err && dn.data_blkaddr != NULL_ADDR)
goto out;
f2fs_put_dnode(&dn);
f2fs_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO);
WARN_ON(flag != F2FS_GET_BLOCK_PRE_AIO);
locked = true;
goto restart;
}
out:
if (!err) {
/* convert_inline_page can make node_changed */
*blk_addr = dn.data_blkaddr;
*node_changed = dn.node_changed;
}
f2fs_put_dnode(&dn);
unlock_out:
if (locked)
f2fs_map_unlock(sbi, flag);
return err;
}
static int __find_data_block(struct inode *inode, pgoff_t index,
block_t *blk_addr)
{
struct dnode_of_data dn;
struct page *ipage;
int err = 0;
ipage = f2fs_get_node_page(F2FS_I_SB(inode), inode->i_ino);
if (IS_ERR(ipage))
return PTR_ERR(ipage);
set_new_dnode(&dn, inode, ipage, ipage, 0);
if (!f2fs_lookup_read_extent_cache_block(inode, index,
&dn.data_blkaddr)) {
/* hole case */
err = f2fs_get_dnode_of_data(&dn, index, LOOKUP_NODE);
if (err) {
dn.data_blkaddr = NULL_ADDR;
err = 0;
}
}
*blk_addr = dn.data_blkaddr;
f2fs_put_dnode(&dn);
return err;
}
static int __reserve_data_block(struct inode *inode, pgoff_t index,
block_t *blk_addr, bool *node_changed)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct dnode_of_data dn;
struct page *ipage;
int err = 0;
f2fs_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO);
ipage = f2fs_get_node_page(sbi, inode->i_ino);
if (IS_ERR(ipage)) {
err = PTR_ERR(ipage);
goto unlock_out;
}
set_new_dnode(&dn, inode, ipage, ipage, 0);
if (!f2fs_lookup_read_extent_cache_block(dn.inode, index,
&dn.data_blkaddr))
err = f2fs_reserve_block(&dn, index);
*blk_addr = dn.data_blkaddr;
*node_changed = dn.node_changed;
f2fs_put_dnode(&dn);
unlock_out:
f2fs_map_unlock(sbi, F2FS_GET_BLOCK_PRE_AIO);
return err;
}
static int prepare_atomic_write_begin(struct f2fs_sb_info *sbi,
struct page *page, loff_t pos, unsigned int len,
block_t *blk_addr, bool *node_changed, bool *use_cow)
{
struct inode *inode = page->mapping->host;
struct inode *cow_inode = F2FS_I(inode)->cow_inode;
pgoff_t index = page->index;
int err = 0;
block_t ori_blk_addr = NULL_ADDR;
/* If pos is beyond the end of file, reserve a new block in COW inode */
if ((pos & PAGE_MASK) >= i_size_read(inode))
goto reserve_block;
/* Look for the block in COW inode first */
err = __find_data_block(cow_inode, index, blk_addr);
if (err) {
return err;
} else if (*blk_addr != NULL_ADDR) {
*use_cow = true;
return 0;
}
if (is_inode_flag_set(inode, FI_ATOMIC_REPLACE))
goto reserve_block;
/* Look for the block in the original inode */
err = __find_data_block(inode, index, &ori_blk_addr);
if (err)
return err;
reserve_block:
/* Finally, we should reserve a new block in COW inode for the update */
err = __reserve_data_block(cow_inode, index, blk_addr, node_changed);
if (err)
return err;
inc_atomic_write_cnt(inode);
if (ori_blk_addr != NULL_ADDR)
*blk_addr = ori_blk_addr;
return 0;
}
static int f2fs_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, struct page **pagep, void **fsdata)
{
struct inode *inode = mapping->host;
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct page *page = NULL;
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 12:29:47 +00:00
pgoff_t index = ((unsigned long long) pos) >> PAGE_SHIFT;
bool need_balance = false;
bool use_cow = false;
block_t blkaddr = NULL_ADDR;
int err = 0;
trace_f2fs_write_begin(inode, pos, len);
if (!f2fs_is_checkpoint_ready(sbi)) {
err = -ENOSPC;
goto fail;
}
/*
* We should check this at this moment to avoid deadlock on inode page
* and #0 page. The locking rule for inline_data conversion should be:
* lock_page(page #0) -> lock_page(inode_page)
*/
if (index != 0) {
err = f2fs_convert_inline_inode(inode);
if (err)
goto fail;
}
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
#ifdef CONFIG_F2FS_FS_COMPRESSION
if (f2fs_compressed_file(inode)) {
int ret;
*fsdata = NULL;
if (len == PAGE_SIZE && !(f2fs_is_atomic_file(inode)))
goto repeat;
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
ret = f2fs_prepare_compress_overwrite(inode, pagep,
index, fsdata);
if (ret < 0) {
err = ret;
goto fail;
} else if (ret) {
return 0;
}
}
#endif
repeat:
/*
* Do not use grab_cache_page_write_begin() to avoid deadlock due to
* wait_for_stable_page. Will wait that below with our IO control.
*/
page = f2fs_pagecache_get_page(mapping, index,
FGP_LOCK | FGP_WRITE | FGP_CREAT, GFP_NOFS);
if (!page) {
err = -ENOMEM;
goto fail;
}
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
/* TODO: cluster can be compressed due to race with .writepage */
*pagep = page;
if (f2fs_is_atomic_file(inode))
err = prepare_atomic_write_begin(sbi, page, pos, len,
&blkaddr, &need_balance, &use_cow);
else
err = prepare_write_begin(sbi, page, pos, len,
&blkaddr, &need_balance);
if (err)
goto fail;
if (need_balance && !IS_NOQUOTA(inode) &&
has_not_enough_free_secs(sbi, 0, 0)) {
unlock_page(page);
f2fs_balance_fs(sbi, true);
lock_page(page);
if (page->mapping != mapping) {
/* The page got truncated from under us */
f2fs_put_page(page, 1);
goto repeat;
}
}
f2fs_wait_on_page_writeback(page, DATA, false, true);
if (len == PAGE_SIZE || PageUptodate(page))
return 0;
f2fs: add fs-verity support Add fs-verity support to f2fs. fs-verity is a filesystem feature that enables transparent integrity protection and authentication of read-only files. It uses a dm-verity like mechanism at the file level: a Merkle tree is used to verify any block in the file in log(filesize) time. It is implemented mainly by helper functions in fs/verity/. See Documentation/filesystems/fsverity.rst for the full documentation. The f2fs support for fs-verity consists of: - Adding a filesystem feature flag and an inode flag for fs-verity. - Implementing the fsverity_operations to support enabling verity on an inode and reading/writing the verity metadata. - Updating ->readpages() to verify data as it's read from verity files and to support reading verity metadata pages. - Updating ->write_begin(), ->write_end(), and ->writepages() to support writing verity metadata pages. - Calling the fs-verity hooks for ->open(), ->setattr(), and ->ioctl(). Like ext4, f2fs stores the verity metadata (Merkle tree and fsverity_descriptor) past the end of the file, starting at the first 64K boundary beyond i_size. This approach works because (a) verity files are readonly, and (b) pages fully beyond i_size aren't visible to userspace but can be read/written internally by f2fs with only some relatively small changes to f2fs. Extended attributes cannot be used because (a) f2fs limits the total size of an inode's xattr entries to 4096 bytes, which wouldn't be enough for even a single Merkle tree block, and (b) f2fs encryption doesn't encrypt xattrs, yet the verity metadata *must* be encrypted when the file is because it contains hashes of the plaintext data. Acked-by: Jaegeuk Kim <jaegeuk@kernel.org> Acked-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Eric Biggers <ebiggers@google.com>
2019-07-22 16:26:24 +00:00
if (!(pos & (PAGE_SIZE - 1)) && (pos + len) >= i_size_read(inode) &&
!f2fs_verity_in_progress(inode)) {
zero_user_segment(page, len, PAGE_SIZE);
return 0;
}
if (blkaddr == NEW_ADDR) {
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 12:29:47 +00:00
zero_user_segment(page, 0, PAGE_SIZE);
SetPageUptodate(page);
} else {
f2fs: introduce DATA_GENERIC_ENHANCE Previously, f2fs_is_valid_blkaddr(, blkaddr, DATA_GENERIC) will check whether @blkaddr locates in main area or not. That check is weak, since the block address in range of main area can point to the address which is not valid in segment info table, and we can not detect such condition, we may suffer worse corruption as system continues running. So this patch introduce DATA_GENERIC_ENHANCE to enhance the sanity check which trigger SIT bitmap check rather than only range check. This patch did below changes as wel: - set SBI_NEED_FSCK in f2fs_is_valid_blkaddr(). - get rid of is_valid_data_blkaddr() to avoid panic if blkaddr is invalid. - introduce verify_fio_blkaddr() to wrap fio {new,old}_blkaddr validation check. - spread blkaddr check in: * f2fs_get_node_info() * __read_out_blkaddrs() * f2fs_submit_page_read() * ra_data_block() * do_recover_data() This patch can fix bug reported from bugzilla below: https://bugzilla.kernel.org/show_bug.cgi?id=203215 https://bugzilla.kernel.org/show_bug.cgi?id=203223 https://bugzilla.kernel.org/show_bug.cgi?id=203231 https://bugzilla.kernel.org/show_bug.cgi?id=203235 https://bugzilla.kernel.org/show_bug.cgi?id=203241 = Update by Jaegeuk Kim = DATA_GENERIC_ENHANCE enhanced to validate block addresses on read/write paths. But, xfstest/generic/446 compalins some generated kernel messages saying invalid bitmap was detected when reading a block. The reaons is, when we get the block addresses from extent_cache, there is no lock to synchronize it from truncating the blocks in parallel. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-04-15 07:26:32 +00:00
if (!f2fs_is_valid_blkaddr(sbi, blkaddr,
DATA_GENERIC_ENHANCE_READ)) {
err = -EFSCORRUPTED;
f2fs: introduce DATA_GENERIC_ENHANCE Previously, f2fs_is_valid_blkaddr(, blkaddr, DATA_GENERIC) will check whether @blkaddr locates in main area or not. That check is weak, since the block address in range of main area can point to the address which is not valid in segment info table, and we can not detect such condition, we may suffer worse corruption as system continues running. So this patch introduce DATA_GENERIC_ENHANCE to enhance the sanity check which trigger SIT bitmap check rather than only range check. This patch did below changes as wel: - set SBI_NEED_FSCK in f2fs_is_valid_blkaddr(). - get rid of is_valid_data_blkaddr() to avoid panic if blkaddr is invalid. - introduce verify_fio_blkaddr() to wrap fio {new,old}_blkaddr validation check. - spread blkaddr check in: * f2fs_get_node_info() * __read_out_blkaddrs() * f2fs_submit_page_read() * ra_data_block() * do_recover_data() This patch can fix bug reported from bugzilla below: https://bugzilla.kernel.org/show_bug.cgi?id=203215 https://bugzilla.kernel.org/show_bug.cgi?id=203223 https://bugzilla.kernel.org/show_bug.cgi?id=203231 https://bugzilla.kernel.org/show_bug.cgi?id=203235 https://bugzilla.kernel.org/show_bug.cgi?id=203241 = Update by Jaegeuk Kim = DATA_GENERIC_ENHANCE enhanced to validate block addresses on read/write paths. But, xfstest/generic/446 compalins some generated kernel messages saying invalid bitmap was detected when reading a block. The reaons is, when we get the block addresses from extent_cache, there is no lock to synchronize it from truncating the blocks in parallel. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-04-15 07:26:32 +00:00
goto fail;
}
err = f2fs_submit_page_read(use_cow ?
F2FS_I(inode)->cow_inode : inode, page,
blkaddr, 0, true);
if (err)
goto fail;
lock_page(page);
if (unlikely(page->mapping != mapping)) {
f2fs_put_page(page, 1);
goto repeat;
}
if (unlikely(!PageUptodate(page))) {
err = -EIO;
goto fail;
}
}
return 0;
fail:
f2fs_put_page(page, 1);
f2fs_write_failed(inode, pos + len);
return err;
}
static int f2fs_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;
trace_f2fs_write_end(inode, pos, len, copied);
/*
* This should be come from len == PAGE_SIZE, and we expect copied
* should be PAGE_SIZE. Otherwise, we treat it with zero copied and
* let generic_perform_write() try to copy data again through copied=0.
*/
if (!PageUptodate(page)) {
if (unlikely(copied != len))
copied = 0;
else
SetPageUptodate(page);
}
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
#ifdef CONFIG_F2FS_FS_COMPRESSION
/* overwrite compressed file */
if (f2fs_compressed_file(inode) && fsdata) {
f2fs_compress_write_end(inode, fsdata, page->index, copied);
f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
if (pos + copied > i_size_read(inode) &&
!f2fs_verity_in_progress(inode))
f2fs_i_size_write(inode, pos + copied);
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
return copied;
}
#endif
if (!copied)
goto unlock_out;
set_page_dirty(page);
f2fs: add fs-verity support Add fs-verity support to f2fs. fs-verity is a filesystem feature that enables transparent integrity protection and authentication of read-only files. It uses a dm-verity like mechanism at the file level: a Merkle tree is used to verify any block in the file in log(filesize) time. It is implemented mainly by helper functions in fs/verity/. See Documentation/filesystems/fsverity.rst for the full documentation. The f2fs support for fs-verity consists of: - Adding a filesystem feature flag and an inode flag for fs-verity. - Implementing the fsverity_operations to support enabling verity on an inode and reading/writing the verity metadata. - Updating ->readpages() to verify data as it's read from verity files and to support reading verity metadata pages. - Updating ->write_begin(), ->write_end(), and ->writepages() to support writing verity metadata pages. - Calling the fs-verity hooks for ->open(), ->setattr(), and ->ioctl(). Like ext4, f2fs stores the verity metadata (Merkle tree and fsverity_descriptor) past the end of the file, starting at the first 64K boundary beyond i_size. This approach works because (a) verity files are readonly, and (b) pages fully beyond i_size aren't visible to userspace but can be read/written internally by f2fs with only some relatively small changes to f2fs. Extended attributes cannot be used because (a) f2fs limits the total size of an inode's xattr entries to 4096 bytes, which wouldn't be enough for even a single Merkle tree block, and (b) f2fs encryption doesn't encrypt xattrs, yet the verity metadata *must* be encrypted when the file is because it contains hashes of the plaintext data. Acked-by: Jaegeuk Kim <jaegeuk@kernel.org> Acked-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Eric Biggers <ebiggers@google.com>
2019-07-22 16:26:24 +00:00
if (pos + copied > i_size_read(inode) &&
!f2fs_verity_in_progress(inode)) {
f2fs_i_size_write(inode, pos + copied);
if (f2fs_is_atomic_file(inode))
f2fs_i_size_write(F2FS_I(inode)->cow_inode,
pos + copied);
}
unlock_out:
f2fs_put_page(page, 1);
f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
return copied;
}
void f2fs_invalidate_folio(struct folio *folio, size_t offset, size_t length)
{
struct inode *inode = folio->mapping->host;
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
if (inode->i_ino >= F2FS_ROOT_INO(sbi) &&
(offset || length != folio_size(folio)))
return;
if (folio_test_dirty(folio)) {
if (inode->i_ino == F2FS_META_INO(sbi)) {
dec_page_count(sbi, F2FS_DIRTY_META);
} else if (inode->i_ino == F2FS_NODE_INO(sbi)) {
dec_page_count(sbi, F2FS_DIRTY_NODES);
} else {
inode_dec_dirty_pages(inode);
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
f2fs_remove_dirty_inode(inode);
}
}
clear_page_private_all(&folio->page);
}
bool f2fs_release_folio(struct folio *folio, gfp_t wait)
{
/* If this is dirty folio, keep private data */
if (folio_test_dirty(folio))
return false;
clear_page_private_all(&folio->page);
return true;
}
static bool f2fs_dirty_data_folio(struct address_space *mapping,
struct folio *folio)
{
struct inode *inode = mapping->host;
trace_f2fs_set_page_dirty(folio, DATA);
if (!folio_test_uptodate(folio))
folio_mark_uptodate(folio);
BUG_ON(folio_test_swapcache(folio));
f2fs: fix wrong dirty page count when race between mmap and fallocate. This is a BUG_ON issue as follows when running xfstest-generic-503: WARNING: CPU: 21 PID: 1385 at fs/f2fs/inode.c:762 f2fs_evict_inode+0x847/0xaa0 Modules linked in: CPU: 21 PID: 1385 Comm: umount Not tainted 5.19.0-rc5+ #73 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.14.0-4.fc34 04/01/2014 Call Trace: evict+0x129/0x2d0 dispose_list+0x4f/0xb0 evict_inodes+0x204/0x230 generic_shutdown_super+0x5b/0x1e0 kill_block_super+0x29/0x80 kill_f2fs_super+0xe6/0x140 deactivate_locked_super+0x44/0xc0 deactivate_super+0x79/0x90 cleanup_mnt+0x114/0x1a0 __cleanup_mnt+0x16/0x20 task_work_run+0x98/0x100 exit_to_user_mode_prepare+0x3d0/0x3e0 syscall_exit_to_user_mode+0x12/0x30 do_syscall_64+0x42/0x80 entry_SYSCALL_64_after_hwframe+0x46/0xb0 Function flow analysis when BUG occurs: f2fs_fallocate mmap do_page_fault pte_spinlock // ---lock_pte do_wp_page wp_page_shared pte_unmap_unlock // unlock_pte do_page_mkwrite f2fs_vm_page_mkwrite down_read(invalidate_lock) lock_page if (PageMappedToDisk(page)) goto out; // set_page_dirty --NOT RUN out: up_read(invalidate_lock); finish_mkwrite_fault // unlock_pte f2fs_collapse_range down_write(i_mmap_sem) truncate_pagecache unmap_mapping_pages i_mmap_lock_write // down_write(i_mmap_rwsem) ...... zap_pte_range pte_offset_map_lock // ---lock_pte set_page_dirty f2fs_dirty_data_folio if (!folio_test_dirty(folio)) { fault_dirty_shared_page set_page_dirty f2fs_dirty_data_folio if (!folio_test_dirty(folio)) { filemap_dirty_folio f2fs_update_dirty_folio // ++ } unlock_page filemap_dirty_folio f2fs_update_dirty_folio // page count++ } pte_unmap_unlock // --unlock_pte i_mmap_unlock_write // up_write(i_mmap_rwsem) truncate_inode_pages up_write(i_mmap_sem) When race happens between mmap-do_page_fault-wp_page_shared and fallocate-truncate_pagecache-zap_pte_range, the zap_pte_range calls function set_page_dirty without page lock. Besides, though truncate_pagecache has immap and pte lock, wp_page_shared calls fault_dirty_shared_page without any. In this case, two threads race in f2fs_dirty_data_folio function. Page is set to dirty only ONCE, but the count is added TWICE by calling filemap_dirty_folio. Thus the count of dirty page cannot accord with the real dirty pages. Following is the solution to in case of race happens without any lock. Since folio_test_set_dirty in filemap_dirty_folio is atomic, judge return value will not be at risk of race. Signed-off-by: Shuqi Zhang <zhangshuqi3@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2022-08-31 02:24:40 +00:00
if (filemap_dirty_folio(mapping, folio)) {
f2fs_update_dirty_folio(inode, folio);
return true;
}
return false;
}
static sector_t f2fs_bmap_compress(struct inode *inode, sector_t block)
{
#ifdef CONFIG_F2FS_FS_COMPRESSION
struct dnode_of_data dn;
sector_t start_idx, blknr = 0;
int ret;
start_idx = round_down(block, F2FS_I(inode)->i_cluster_size);
set_new_dnode(&dn, inode, NULL, NULL, 0);
ret = f2fs_get_dnode_of_data(&dn, start_idx, LOOKUP_NODE);
if (ret)
return 0;
if (dn.data_blkaddr != COMPRESS_ADDR) {
dn.ofs_in_node += block - start_idx;
blknr = f2fs_data_blkaddr(&dn);
if (!__is_valid_data_blkaddr(blknr))
blknr = 0;
}
f2fs_put_dnode(&dn);
return blknr;
#else
return 0;
#endif
}
static sector_t f2fs_bmap(struct address_space *mapping, sector_t block)
{
struct inode *inode = mapping->host;
sector_t blknr = 0;
if (f2fs_has_inline_data(inode))
goto out;
/* make sure allocating whole blocks */
if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
filemap_write_and_wait(mapping);
/* Block number less than F2FS MAX BLOCKS */
if (unlikely(block >= max_file_blocks(inode)))
goto out;
if (f2fs_compressed_file(inode)) {
blknr = f2fs_bmap_compress(inode, block);
} else {
struct f2fs_map_blocks map;
memset(&map, 0, sizeof(map));
map.m_lblk = block;
map.m_len = 1;
map.m_next_pgofs = NULL;
map.m_seg_type = NO_CHECK_TYPE;
if (!f2fs_map_blocks(inode, &map, F2FS_GET_BLOCK_BMAP))
blknr = map.m_pblk;
}
out:
trace_f2fs_bmap(inode, block, blknr);
return blknr;
}
#ifdef CONFIG_SWAP
f2fs: swap: support migrating swapfile in aligned write mode This patch supports to migrate swapfile in aligned write mode during swapon in order to keep swapfile being aligned to section as much as possible, then pinned swapfile will locates fully filled section which may not affected by GC. However, for the case that swapfile's size is not aligned to section size, it will still leave last extent in file's tail as unaligned due to its size is smaller than section size, like case #2. case #1 xfs_io -f /mnt/f2fs/file -c "pwrite 0 4M" -c "fsync" Before swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..3047]: 1123352..1126399 3048 0x1000 1: [3048..7143]: 237568..241663 4096 0x1000 2: [7144..8191]: 245760..246807 1048 0x1001 After swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..8191]: 249856..258047 8192 0x1001 Kmsg: F2FS-fs (zram0): Swapfile (2) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(2097152 * n) case #2 xfs_io -f /mnt/f2fs/file -c "pwrite 0 3M" -c "fsync" Before swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..3047]: 246808..249855 3048 0x1000 1: [3048..6143]: 237568..240663 3096 0x1001 After swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..4095]: 258048..262143 4096 0x1000 1: [4096..6143]: 238616..240663 2048 0x1001 Kmsg: F2FS-fs (zram0): Swapfile: last extent is not aligned to section F2FS-fs (zram0): Swapfile (2) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(2097152 * n) Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2021-05-26 06:29:27 +00:00
static int f2fs_migrate_blocks(struct inode *inode, block_t start_blk,
unsigned int blkcnt)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
unsigned int blkofs;
unsigned int blk_per_sec = BLKS_PER_SEC(sbi);
unsigned int end_blk = start_blk + blkcnt - 1;
f2fs: swap: support migrating swapfile in aligned write mode This patch supports to migrate swapfile in aligned write mode during swapon in order to keep swapfile being aligned to section as much as possible, then pinned swapfile will locates fully filled section which may not affected by GC. However, for the case that swapfile's size is not aligned to section size, it will still leave last extent in file's tail as unaligned due to its size is smaller than section size, like case #2. case #1 xfs_io -f /mnt/f2fs/file -c "pwrite 0 4M" -c "fsync" Before swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..3047]: 1123352..1126399 3048 0x1000 1: [3048..7143]: 237568..241663 4096 0x1000 2: [7144..8191]: 245760..246807 1048 0x1001 After swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..8191]: 249856..258047 8192 0x1001 Kmsg: F2FS-fs (zram0): Swapfile (2) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(2097152 * n) case #2 xfs_io -f /mnt/f2fs/file -c "pwrite 0 3M" -c "fsync" Before swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..3047]: 246808..249855 3048 0x1000 1: [3048..6143]: 237568..240663 3096 0x1001 After swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..4095]: 258048..262143 4096 0x1000 1: [4096..6143]: 238616..240663 2048 0x1001 Kmsg: F2FS-fs (zram0): Swapfile: last extent is not aligned to section F2FS-fs (zram0): Swapfile (2) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(2097152 * n) Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2021-05-26 06:29:27 +00:00
unsigned int secidx = start_blk / blk_per_sec;
unsigned int end_sec;
f2fs: swap: support migrating swapfile in aligned write mode This patch supports to migrate swapfile in aligned write mode during swapon in order to keep swapfile being aligned to section as much as possible, then pinned swapfile will locates fully filled section which may not affected by GC. However, for the case that swapfile's size is not aligned to section size, it will still leave last extent in file's tail as unaligned due to its size is smaller than section size, like case #2. case #1 xfs_io -f /mnt/f2fs/file -c "pwrite 0 4M" -c "fsync" Before swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..3047]: 1123352..1126399 3048 0x1000 1: [3048..7143]: 237568..241663 4096 0x1000 2: [7144..8191]: 245760..246807 1048 0x1001 After swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..8191]: 249856..258047 8192 0x1001 Kmsg: F2FS-fs (zram0): Swapfile (2) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(2097152 * n) case #2 xfs_io -f /mnt/f2fs/file -c "pwrite 0 3M" -c "fsync" Before swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..3047]: 246808..249855 3048 0x1000 1: [3048..6143]: 237568..240663 3096 0x1001 After swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..4095]: 258048..262143 4096 0x1000 1: [4096..6143]: 238616..240663 2048 0x1001 Kmsg: F2FS-fs (zram0): Swapfile: last extent is not aligned to section F2FS-fs (zram0): Swapfile (2) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(2097152 * n) Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2021-05-26 06:29:27 +00:00
int ret = 0;
if (!blkcnt)
return 0;
end_sec = end_blk / blk_per_sec;
f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
filemap_invalidate_lock(inode->i_mapping);
f2fs: swap: support migrating swapfile in aligned write mode This patch supports to migrate swapfile in aligned write mode during swapon in order to keep swapfile being aligned to section as much as possible, then pinned swapfile will locates fully filled section which may not affected by GC. However, for the case that swapfile's size is not aligned to section size, it will still leave last extent in file's tail as unaligned due to its size is smaller than section size, like case #2. case #1 xfs_io -f /mnt/f2fs/file -c "pwrite 0 4M" -c "fsync" Before swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..3047]: 1123352..1126399 3048 0x1000 1: [3048..7143]: 237568..241663 4096 0x1000 2: [7144..8191]: 245760..246807 1048 0x1001 After swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..8191]: 249856..258047 8192 0x1001 Kmsg: F2FS-fs (zram0): Swapfile (2) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(2097152 * n) case #2 xfs_io -f /mnt/f2fs/file -c "pwrite 0 3M" -c "fsync" Before swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..3047]: 246808..249855 3048 0x1000 1: [3048..6143]: 237568..240663 3096 0x1001 After swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..4095]: 258048..262143 4096 0x1000 1: [4096..6143]: 238616..240663 2048 0x1001 Kmsg: F2FS-fs (zram0): Swapfile: last extent is not aligned to section F2FS-fs (zram0): Swapfile (2) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(2097152 * n) Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2021-05-26 06:29:27 +00:00
set_inode_flag(inode, FI_ALIGNED_WRITE);
set_inode_flag(inode, FI_OPU_WRITE);
f2fs: swap: support migrating swapfile in aligned write mode This patch supports to migrate swapfile in aligned write mode during swapon in order to keep swapfile being aligned to section as much as possible, then pinned swapfile will locates fully filled section which may not affected by GC. However, for the case that swapfile's size is not aligned to section size, it will still leave last extent in file's tail as unaligned due to its size is smaller than section size, like case #2. case #1 xfs_io -f /mnt/f2fs/file -c "pwrite 0 4M" -c "fsync" Before swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..3047]: 1123352..1126399 3048 0x1000 1: [3048..7143]: 237568..241663 4096 0x1000 2: [7144..8191]: 245760..246807 1048 0x1001 After swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..8191]: 249856..258047 8192 0x1001 Kmsg: F2FS-fs (zram0): Swapfile (2) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(2097152 * n) case #2 xfs_io -f /mnt/f2fs/file -c "pwrite 0 3M" -c "fsync" Before swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..3047]: 246808..249855 3048 0x1000 1: [3048..6143]: 237568..240663 3096 0x1001 After swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..4095]: 258048..262143 4096 0x1000 1: [4096..6143]: 238616..240663 2048 0x1001 Kmsg: F2FS-fs (zram0): Swapfile: last extent is not aligned to section F2FS-fs (zram0): Swapfile (2) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(2097152 * n) Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2021-05-26 06:29:27 +00:00
for (; secidx <= end_sec; secidx++) {
unsigned int blkofs_end = secidx == end_sec ?
end_blk % blk_per_sec : blk_per_sec - 1;
f2fs_down_write(&sbi->pin_sem);
f2fs: swap: support migrating swapfile in aligned write mode This patch supports to migrate swapfile in aligned write mode during swapon in order to keep swapfile being aligned to section as much as possible, then pinned swapfile will locates fully filled section which may not affected by GC. However, for the case that swapfile's size is not aligned to section size, it will still leave last extent in file's tail as unaligned due to its size is smaller than section size, like case #2. case #1 xfs_io -f /mnt/f2fs/file -c "pwrite 0 4M" -c "fsync" Before swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..3047]: 1123352..1126399 3048 0x1000 1: [3048..7143]: 237568..241663 4096 0x1000 2: [7144..8191]: 245760..246807 1048 0x1001 After swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..8191]: 249856..258047 8192 0x1001 Kmsg: F2FS-fs (zram0): Swapfile (2) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(2097152 * n) case #2 xfs_io -f /mnt/f2fs/file -c "pwrite 0 3M" -c "fsync" Before swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..3047]: 246808..249855 3048 0x1000 1: [3048..6143]: 237568..240663 3096 0x1001 After swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..4095]: 258048..262143 4096 0x1000 1: [4096..6143]: 238616..240663 2048 0x1001 Kmsg: F2FS-fs (zram0): Swapfile: last extent is not aligned to section F2FS-fs (zram0): Swapfile (2) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(2097152 * n) Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2021-05-26 06:29:27 +00:00
ret = f2fs_allocate_pinning_section(sbi);
if (ret) {
f2fs_up_write(&sbi->pin_sem);
break;
}
f2fs: swap: support migrating swapfile in aligned write mode This patch supports to migrate swapfile in aligned write mode during swapon in order to keep swapfile being aligned to section as much as possible, then pinned swapfile will locates fully filled section which may not affected by GC. However, for the case that swapfile's size is not aligned to section size, it will still leave last extent in file's tail as unaligned due to its size is smaller than section size, like case #2. case #1 xfs_io -f /mnt/f2fs/file -c "pwrite 0 4M" -c "fsync" Before swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..3047]: 1123352..1126399 3048 0x1000 1: [3048..7143]: 237568..241663 4096 0x1000 2: [7144..8191]: 245760..246807 1048 0x1001 After swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..8191]: 249856..258047 8192 0x1001 Kmsg: F2FS-fs (zram0): Swapfile (2) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(2097152 * n) case #2 xfs_io -f /mnt/f2fs/file -c "pwrite 0 3M" -c "fsync" Before swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..3047]: 246808..249855 3048 0x1000 1: [3048..6143]: 237568..240663 3096 0x1001 After swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..4095]: 258048..262143 4096 0x1000 1: [4096..6143]: 238616..240663 2048 0x1001 Kmsg: F2FS-fs (zram0): Swapfile: last extent is not aligned to section F2FS-fs (zram0): Swapfile (2) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(2097152 * n) Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2021-05-26 06:29:27 +00:00
set_inode_flag(inode, FI_SKIP_WRITES);
f2fs: swap: support migrating swapfile in aligned write mode This patch supports to migrate swapfile in aligned write mode during swapon in order to keep swapfile being aligned to section as much as possible, then pinned swapfile will locates fully filled section which may not affected by GC. However, for the case that swapfile's size is not aligned to section size, it will still leave last extent in file's tail as unaligned due to its size is smaller than section size, like case #2. case #1 xfs_io -f /mnt/f2fs/file -c "pwrite 0 4M" -c "fsync" Before swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..3047]: 1123352..1126399 3048 0x1000 1: [3048..7143]: 237568..241663 4096 0x1000 2: [7144..8191]: 245760..246807 1048 0x1001 After swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..8191]: 249856..258047 8192 0x1001 Kmsg: F2FS-fs (zram0): Swapfile (2) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(2097152 * n) case #2 xfs_io -f /mnt/f2fs/file -c "pwrite 0 3M" -c "fsync" Before swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..3047]: 246808..249855 3048 0x1000 1: [3048..6143]: 237568..240663 3096 0x1001 After swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..4095]: 258048..262143 4096 0x1000 1: [4096..6143]: 238616..240663 2048 0x1001 Kmsg: F2FS-fs (zram0): Swapfile: last extent is not aligned to section F2FS-fs (zram0): Swapfile (2) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(2097152 * n) Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2021-05-26 06:29:27 +00:00
for (blkofs = 0; blkofs <= blkofs_end; blkofs++) {
f2fs: swap: support migrating swapfile in aligned write mode This patch supports to migrate swapfile in aligned write mode during swapon in order to keep swapfile being aligned to section as much as possible, then pinned swapfile will locates fully filled section which may not affected by GC. However, for the case that swapfile's size is not aligned to section size, it will still leave last extent in file's tail as unaligned due to its size is smaller than section size, like case #2. case #1 xfs_io -f /mnt/f2fs/file -c "pwrite 0 4M" -c "fsync" Before swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..3047]: 1123352..1126399 3048 0x1000 1: [3048..7143]: 237568..241663 4096 0x1000 2: [7144..8191]: 245760..246807 1048 0x1001 After swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..8191]: 249856..258047 8192 0x1001 Kmsg: F2FS-fs (zram0): Swapfile (2) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(2097152 * n) case #2 xfs_io -f /mnt/f2fs/file -c "pwrite 0 3M" -c "fsync" Before swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..3047]: 246808..249855 3048 0x1000 1: [3048..6143]: 237568..240663 3096 0x1001 After swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..4095]: 258048..262143 4096 0x1000 1: [4096..6143]: 238616..240663 2048 0x1001 Kmsg: F2FS-fs (zram0): Swapfile: last extent is not aligned to section F2FS-fs (zram0): Swapfile (2) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(2097152 * n) Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2021-05-26 06:29:27 +00:00
struct page *page;
unsigned int blkidx = secidx * blk_per_sec + blkofs;
page = f2fs_get_lock_data_page(inode, blkidx, true);
if (IS_ERR(page)) {
f2fs_up_write(&sbi->pin_sem);
f2fs: swap: support migrating swapfile in aligned write mode This patch supports to migrate swapfile in aligned write mode during swapon in order to keep swapfile being aligned to section as much as possible, then pinned swapfile will locates fully filled section which may not affected by GC. However, for the case that swapfile's size is not aligned to section size, it will still leave last extent in file's tail as unaligned due to its size is smaller than section size, like case #2. case #1 xfs_io -f /mnt/f2fs/file -c "pwrite 0 4M" -c "fsync" Before swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..3047]: 1123352..1126399 3048 0x1000 1: [3048..7143]: 237568..241663 4096 0x1000 2: [7144..8191]: 245760..246807 1048 0x1001 After swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..8191]: 249856..258047 8192 0x1001 Kmsg: F2FS-fs (zram0): Swapfile (2) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(2097152 * n) case #2 xfs_io -f /mnt/f2fs/file -c "pwrite 0 3M" -c "fsync" Before swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..3047]: 246808..249855 3048 0x1000 1: [3048..6143]: 237568..240663 3096 0x1001 After swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..4095]: 258048..262143 4096 0x1000 1: [4096..6143]: 238616..240663 2048 0x1001 Kmsg: F2FS-fs (zram0): Swapfile: last extent is not aligned to section F2FS-fs (zram0): Swapfile (2) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(2097152 * n) Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2021-05-26 06:29:27 +00:00
ret = PTR_ERR(page);
goto done;
}
set_page_dirty(page);
f2fs_put_page(page, 1);
}
clear_inode_flag(inode, FI_SKIP_WRITES);
f2fs: swap: support migrating swapfile in aligned write mode This patch supports to migrate swapfile in aligned write mode during swapon in order to keep swapfile being aligned to section as much as possible, then pinned swapfile will locates fully filled section which may not affected by GC. However, for the case that swapfile's size is not aligned to section size, it will still leave last extent in file's tail as unaligned due to its size is smaller than section size, like case #2. case #1 xfs_io -f /mnt/f2fs/file -c "pwrite 0 4M" -c "fsync" Before swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..3047]: 1123352..1126399 3048 0x1000 1: [3048..7143]: 237568..241663 4096 0x1000 2: [7144..8191]: 245760..246807 1048 0x1001 After swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..8191]: 249856..258047 8192 0x1001 Kmsg: F2FS-fs (zram0): Swapfile (2) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(2097152 * n) case #2 xfs_io -f /mnt/f2fs/file -c "pwrite 0 3M" -c "fsync" Before swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..3047]: 246808..249855 3048 0x1000 1: [3048..6143]: 237568..240663 3096 0x1001 After swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..4095]: 258048..262143 4096 0x1000 1: [4096..6143]: 238616..240663 2048 0x1001 Kmsg: F2FS-fs (zram0): Swapfile: last extent is not aligned to section F2FS-fs (zram0): Swapfile (2) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(2097152 * n) Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2021-05-26 06:29:27 +00:00
ret = filemap_fdatawrite(inode->i_mapping);
f2fs_up_write(&sbi->pin_sem);
f2fs: swap: support migrating swapfile in aligned write mode This patch supports to migrate swapfile in aligned write mode during swapon in order to keep swapfile being aligned to section as much as possible, then pinned swapfile will locates fully filled section which may not affected by GC. However, for the case that swapfile's size is not aligned to section size, it will still leave last extent in file's tail as unaligned due to its size is smaller than section size, like case #2. case #1 xfs_io -f /mnt/f2fs/file -c "pwrite 0 4M" -c "fsync" Before swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..3047]: 1123352..1126399 3048 0x1000 1: [3048..7143]: 237568..241663 4096 0x1000 2: [7144..8191]: 245760..246807 1048 0x1001 After swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..8191]: 249856..258047 8192 0x1001 Kmsg: F2FS-fs (zram0): Swapfile (2) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(2097152 * n) case #2 xfs_io -f /mnt/f2fs/file -c "pwrite 0 3M" -c "fsync" Before swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..3047]: 246808..249855 3048 0x1000 1: [3048..6143]: 237568..240663 3096 0x1001 After swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..4095]: 258048..262143 4096 0x1000 1: [4096..6143]: 238616..240663 2048 0x1001 Kmsg: F2FS-fs (zram0): Swapfile: last extent is not aligned to section F2FS-fs (zram0): Swapfile (2) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(2097152 * n) Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2021-05-26 06:29:27 +00:00
if (ret)
break;
}
done:
clear_inode_flag(inode, FI_SKIP_WRITES);
clear_inode_flag(inode, FI_OPU_WRITE);
f2fs: swap: support migrating swapfile in aligned write mode This patch supports to migrate swapfile in aligned write mode during swapon in order to keep swapfile being aligned to section as much as possible, then pinned swapfile will locates fully filled section which may not affected by GC. However, for the case that swapfile's size is not aligned to section size, it will still leave last extent in file's tail as unaligned due to its size is smaller than section size, like case #2. case #1 xfs_io -f /mnt/f2fs/file -c "pwrite 0 4M" -c "fsync" Before swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..3047]: 1123352..1126399 3048 0x1000 1: [3048..7143]: 237568..241663 4096 0x1000 2: [7144..8191]: 245760..246807 1048 0x1001 After swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..8191]: 249856..258047 8192 0x1001 Kmsg: F2FS-fs (zram0): Swapfile (2) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(2097152 * n) case #2 xfs_io -f /mnt/f2fs/file -c "pwrite 0 3M" -c "fsync" Before swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..3047]: 246808..249855 3048 0x1000 1: [3048..6143]: 237568..240663 3096 0x1001 After swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..4095]: 258048..262143 4096 0x1000 1: [4096..6143]: 238616..240663 2048 0x1001 Kmsg: F2FS-fs (zram0): Swapfile: last extent is not aligned to section F2FS-fs (zram0): Swapfile (2) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(2097152 * n) Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2021-05-26 06:29:27 +00:00
clear_inode_flag(inode, FI_ALIGNED_WRITE);
filemap_invalidate_unlock(inode->i_mapping);
f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
f2fs: swap: support migrating swapfile in aligned write mode This patch supports to migrate swapfile in aligned write mode during swapon in order to keep swapfile being aligned to section as much as possible, then pinned swapfile will locates fully filled section which may not affected by GC. However, for the case that swapfile's size is not aligned to section size, it will still leave last extent in file's tail as unaligned due to its size is smaller than section size, like case #2. case #1 xfs_io -f /mnt/f2fs/file -c "pwrite 0 4M" -c "fsync" Before swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..3047]: 1123352..1126399 3048 0x1000 1: [3048..7143]: 237568..241663 4096 0x1000 2: [7144..8191]: 245760..246807 1048 0x1001 After swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..8191]: 249856..258047 8192 0x1001 Kmsg: F2FS-fs (zram0): Swapfile (2) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(2097152 * n) case #2 xfs_io -f /mnt/f2fs/file -c "pwrite 0 3M" -c "fsync" Before swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..3047]: 246808..249855 3048 0x1000 1: [3048..6143]: 237568..240663 3096 0x1001 After swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..4095]: 258048..262143 4096 0x1000 1: [4096..6143]: 238616..240663 2048 0x1001 Kmsg: F2FS-fs (zram0): Swapfile: last extent is not aligned to section F2FS-fs (zram0): Swapfile (2) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(2097152 * n) Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2021-05-26 06:29:27 +00:00
return ret;
}
static int check_swap_activate(struct swap_info_struct *sis,
struct file *swap_file, sector_t *span)
{
struct address_space *mapping = swap_file->f_mapping;
struct inode *inode = mapping->host;
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
block_t cur_lblock;
block_t last_lblock;
block_t pblock;
block_t lowest_pblock = -1;
block_t highest_pblock = 0;
int nr_extents = 0;
unsigned int nr_pblocks;
f2fs: swap: support migrating swapfile in aligned write mode This patch supports to migrate swapfile in aligned write mode during swapon in order to keep swapfile being aligned to section as much as possible, then pinned swapfile will locates fully filled section which may not affected by GC. However, for the case that swapfile's size is not aligned to section size, it will still leave last extent in file's tail as unaligned due to its size is smaller than section size, like case #2. case #1 xfs_io -f /mnt/f2fs/file -c "pwrite 0 4M" -c "fsync" Before swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..3047]: 1123352..1126399 3048 0x1000 1: [3048..7143]: 237568..241663 4096 0x1000 2: [7144..8191]: 245760..246807 1048 0x1001 After swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..8191]: 249856..258047 8192 0x1001 Kmsg: F2FS-fs (zram0): Swapfile (2) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(2097152 * n) case #2 xfs_io -f /mnt/f2fs/file -c "pwrite 0 3M" -c "fsync" Before swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..3047]: 246808..249855 3048 0x1000 1: [3048..6143]: 237568..240663 3096 0x1001 After swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..4095]: 258048..262143 4096 0x1000 1: [4096..6143]: 238616..240663 2048 0x1001 Kmsg: F2FS-fs (zram0): Swapfile: last extent is not aligned to section F2FS-fs (zram0): Swapfile (2) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(2097152 * n) Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2021-05-26 06:29:27 +00:00
unsigned int blks_per_sec = BLKS_PER_SEC(sbi);
unsigned int not_aligned = 0;
int ret = 0;
/*
* Map all the blocks into the extent list. This code doesn't try
* to be very smart.
*/
cur_lblock = 0;
last_lblock = bytes_to_blks(inode, i_size_read(inode));
while (cur_lblock < last_lblock && cur_lblock < sis->max) {
struct f2fs_map_blocks map;
f2fs: swap: support migrating swapfile in aligned write mode This patch supports to migrate swapfile in aligned write mode during swapon in order to keep swapfile being aligned to section as much as possible, then pinned swapfile will locates fully filled section which may not affected by GC. However, for the case that swapfile's size is not aligned to section size, it will still leave last extent in file's tail as unaligned due to its size is smaller than section size, like case #2. case #1 xfs_io -f /mnt/f2fs/file -c "pwrite 0 4M" -c "fsync" Before swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..3047]: 1123352..1126399 3048 0x1000 1: [3048..7143]: 237568..241663 4096 0x1000 2: [7144..8191]: 245760..246807 1048 0x1001 After swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..8191]: 249856..258047 8192 0x1001 Kmsg: F2FS-fs (zram0): Swapfile (2) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(2097152 * n) case #2 xfs_io -f /mnt/f2fs/file -c "pwrite 0 3M" -c "fsync" Before swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..3047]: 246808..249855 3048 0x1000 1: [3048..6143]: 237568..240663 3096 0x1001 After swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..4095]: 258048..262143 4096 0x1000 1: [4096..6143]: 238616..240663 2048 0x1001 Kmsg: F2FS-fs (zram0): Swapfile: last extent is not aligned to section F2FS-fs (zram0): Swapfile (2) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(2097152 * n) Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2021-05-26 06:29:27 +00:00
retry:
cond_resched();
memset(&map, 0, sizeof(map));
map.m_lblk = cur_lblock;
map.m_len = last_lblock - cur_lblock;
map.m_next_pgofs = NULL;
map.m_next_extent = NULL;
map.m_seg_type = NO_CHECK_TYPE;
map.m_may_create = false;
ret = f2fs_map_blocks(inode, &map, F2FS_GET_BLOCK_FIEMAP);
if (ret)
goto out;
/* hole */
if (!(map.m_flags & F2FS_MAP_FLAGS)) {
f2fs_err(sbi, "Swapfile has holes");
ret = -EINVAL;
goto out;
}
pblock = map.m_pblk;
nr_pblocks = map.m_len;
if ((pblock - SM_I(sbi)->main_blkaddr) % blks_per_sec ||
nr_pblocks % blks_per_sec ||
!f2fs_valid_pinned_area(sbi, pblock)) {
bool last_extent = false;
not_aligned++;
f2fs: swap: support migrating swapfile in aligned write mode This patch supports to migrate swapfile in aligned write mode during swapon in order to keep swapfile being aligned to section as much as possible, then pinned swapfile will locates fully filled section which may not affected by GC. However, for the case that swapfile's size is not aligned to section size, it will still leave last extent in file's tail as unaligned due to its size is smaller than section size, like case #2. case #1 xfs_io -f /mnt/f2fs/file -c "pwrite 0 4M" -c "fsync" Before swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..3047]: 1123352..1126399 3048 0x1000 1: [3048..7143]: 237568..241663 4096 0x1000 2: [7144..8191]: 245760..246807 1048 0x1001 After swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..8191]: 249856..258047 8192 0x1001 Kmsg: F2FS-fs (zram0): Swapfile (2) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(2097152 * n) case #2 xfs_io -f /mnt/f2fs/file -c "pwrite 0 3M" -c "fsync" Before swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..3047]: 246808..249855 3048 0x1000 1: [3048..6143]: 237568..240663 3096 0x1001 After swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..4095]: 258048..262143 4096 0x1000 1: [4096..6143]: 238616..240663 2048 0x1001 Kmsg: F2FS-fs (zram0): Swapfile: last extent is not aligned to section F2FS-fs (zram0): Swapfile (2) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(2097152 * n) Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2021-05-26 06:29:27 +00:00
nr_pblocks = roundup(nr_pblocks, blks_per_sec);
if (cur_lblock + nr_pblocks > sis->max)
nr_pblocks -= blks_per_sec;
/* this extent is last one */
f2fs: swap: support migrating swapfile in aligned write mode This patch supports to migrate swapfile in aligned write mode during swapon in order to keep swapfile being aligned to section as much as possible, then pinned swapfile will locates fully filled section which may not affected by GC. However, for the case that swapfile's size is not aligned to section size, it will still leave last extent in file's tail as unaligned due to its size is smaller than section size, like case #2. case #1 xfs_io -f /mnt/f2fs/file -c "pwrite 0 4M" -c "fsync" Before swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..3047]: 1123352..1126399 3048 0x1000 1: [3048..7143]: 237568..241663 4096 0x1000 2: [7144..8191]: 245760..246807 1048 0x1001 After swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..8191]: 249856..258047 8192 0x1001 Kmsg: F2FS-fs (zram0): Swapfile (2) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(2097152 * n) case #2 xfs_io -f /mnt/f2fs/file -c "pwrite 0 3M" -c "fsync" Before swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..3047]: 246808..249855 3048 0x1000 1: [3048..6143]: 237568..240663 3096 0x1001 After swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..4095]: 258048..262143 4096 0x1000 1: [4096..6143]: 238616..240663 2048 0x1001 Kmsg: F2FS-fs (zram0): Swapfile: last extent is not aligned to section F2FS-fs (zram0): Swapfile (2) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(2097152 * n) Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2021-05-26 06:29:27 +00:00
if (!nr_pblocks) {
nr_pblocks = last_lblock - cur_lblock;
last_extent = true;
f2fs: swap: support migrating swapfile in aligned write mode This patch supports to migrate swapfile in aligned write mode during swapon in order to keep swapfile being aligned to section as much as possible, then pinned swapfile will locates fully filled section which may not affected by GC. However, for the case that swapfile's size is not aligned to section size, it will still leave last extent in file's tail as unaligned due to its size is smaller than section size, like case #2. case #1 xfs_io -f /mnt/f2fs/file -c "pwrite 0 4M" -c "fsync" Before swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..3047]: 1123352..1126399 3048 0x1000 1: [3048..7143]: 237568..241663 4096 0x1000 2: [7144..8191]: 245760..246807 1048 0x1001 After swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..8191]: 249856..258047 8192 0x1001 Kmsg: F2FS-fs (zram0): Swapfile (2) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(2097152 * n) case #2 xfs_io -f /mnt/f2fs/file -c "pwrite 0 3M" -c "fsync" Before swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..3047]: 246808..249855 3048 0x1000 1: [3048..6143]: 237568..240663 3096 0x1001 After swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..4095]: 258048..262143 4096 0x1000 1: [4096..6143]: 238616..240663 2048 0x1001 Kmsg: F2FS-fs (zram0): Swapfile: last extent is not aligned to section F2FS-fs (zram0): Swapfile (2) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(2097152 * n) Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2021-05-26 06:29:27 +00:00
}
ret = f2fs_migrate_blocks(inode, cur_lblock,
nr_pblocks);
if (ret) {
if (ret == -ENOENT)
ret = -EINVAL;
f2fs: swap: support migrating swapfile in aligned write mode This patch supports to migrate swapfile in aligned write mode during swapon in order to keep swapfile being aligned to section as much as possible, then pinned swapfile will locates fully filled section which may not affected by GC. However, for the case that swapfile's size is not aligned to section size, it will still leave last extent in file's tail as unaligned due to its size is smaller than section size, like case #2. case #1 xfs_io -f /mnt/f2fs/file -c "pwrite 0 4M" -c "fsync" Before swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..3047]: 1123352..1126399 3048 0x1000 1: [3048..7143]: 237568..241663 4096 0x1000 2: [7144..8191]: 245760..246807 1048 0x1001 After swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..8191]: 249856..258047 8192 0x1001 Kmsg: F2FS-fs (zram0): Swapfile (2) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(2097152 * n) case #2 xfs_io -f /mnt/f2fs/file -c "pwrite 0 3M" -c "fsync" Before swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..3047]: 246808..249855 3048 0x1000 1: [3048..6143]: 237568..240663 3096 0x1001 After swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..4095]: 258048..262143 4096 0x1000 1: [4096..6143]: 238616..240663 2048 0x1001 Kmsg: F2FS-fs (zram0): Swapfile: last extent is not aligned to section F2FS-fs (zram0): Swapfile (2) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(2097152 * n) Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2021-05-26 06:29:27 +00:00
goto out;
}
if (!last_extent)
goto retry;
f2fs: swap: support migrating swapfile in aligned write mode This patch supports to migrate swapfile in aligned write mode during swapon in order to keep swapfile being aligned to section as much as possible, then pinned swapfile will locates fully filled section which may not affected by GC. However, for the case that swapfile's size is not aligned to section size, it will still leave last extent in file's tail as unaligned due to its size is smaller than section size, like case #2. case #1 xfs_io -f /mnt/f2fs/file -c "pwrite 0 4M" -c "fsync" Before swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..3047]: 1123352..1126399 3048 0x1000 1: [3048..7143]: 237568..241663 4096 0x1000 2: [7144..8191]: 245760..246807 1048 0x1001 After swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..8191]: 249856..258047 8192 0x1001 Kmsg: F2FS-fs (zram0): Swapfile (2) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(2097152 * n) case #2 xfs_io -f /mnt/f2fs/file -c "pwrite 0 3M" -c "fsync" Before swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..3047]: 246808..249855 3048 0x1000 1: [3048..6143]: 237568..240663 3096 0x1001 After swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..4095]: 258048..262143 4096 0x1000 1: [4096..6143]: 238616..240663 2048 0x1001 Kmsg: F2FS-fs (zram0): Swapfile: last extent is not aligned to section F2FS-fs (zram0): Swapfile (2) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(2097152 * n) Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2021-05-26 06:29:27 +00:00
}
if (cur_lblock + nr_pblocks >= sis->max)
nr_pblocks = sis->max - cur_lblock;
if (cur_lblock) { /* exclude the header page */
if (pblock < lowest_pblock)
lowest_pblock = pblock;
if (pblock + nr_pblocks - 1 > highest_pblock)
highest_pblock = pblock + nr_pblocks - 1;
}
/*
* We found a PAGE_SIZE-length, PAGE_SIZE-aligned run of blocks
*/
ret = add_swap_extent(sis, cur_lblock, nr_pblocks, pblock);
if (ret < 0)
goto out;
nr_extents += ret;
cur_lblock += nr_pblocks;
}
ret = nr_extents;
*span = 1 + highest_pblock - lowest_pblock;
if (cur_lblock == 0)
cur_lblock = 1; /* force Empty message */
sis->max = cur_lblock;
sis->pages = cur_lblock - 1;
sis->highest_bit = cur_lblock - 1;
out:
f2fs: swap: support migrating swapfile in aligned write mode This patch supports to migrate swapfile in aligned write mode during swapon in order to keep swapfile being aligned to section as much as possible, then pinned swapfile will locates fully filled section which may not affected by GC. However, for the case that swapfile's size is not aligned to section size, it will still leave last extent in file's tail as unaligned due to its size is smaller than section size, like case #2. case #1 xfs_io -f /mnt/f2fs/file -c "pwrite 0 4M" -c "fsync" Before swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..3047]: 1123352..1126399 3048 0x1000 1: [3048..7143]: 237568..241663 4096 0x1000 2: [7144..8191]: 245760..246807 1048 0x1001 After swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..8191]: 249856..258047 8192 0x1001 Kmsg: F2FS-fs (zram0): Swapfile (2) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(2097152 * n) case #2 xfs_io -f /mnt/f2fs/file -c "pwrite 0 3M" -c "fsync" Before swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..3047]: 246808..249855 3048 0x1000 1: [3048..6143]: 237568..240663 3096 0x1001 After swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..4095]: 258048..262143 4096 0x1000 1: [4096..6143]: 238616..240663 2048 0x1001 Kmsg: F2FS-fs (zram0): Swapfile: last extent is not aligned to section F2FS-fs (zram0): Swapfile (2) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(2097152 * n) Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2021-05-26 06:29:27 +00:00
if (not_aligned)
f2fs_warn(sbi, "Swapfile (%u) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(%lu * N)",
f2fs: swap: support migrating swapfile in aligned write mode This patch supports to migrate swapfile in aligned write mode during swapon in order to keep swapfile being aligned to section as much as possible, then pinned swapfile will locates fully filled section which may not affected by GC. However, for the case that swapfile's size is not aligned to section size, it will still leave last extent in file's tail as unaligned due to its size is smaller than section size, like case #2. case #1 xfs_io -f /mnt/f2fs/file -c "pwrite 0 4M" -c "fsync" Before swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..3047]: 1123352..1126399 3048 0x1000 1: [3048..7143]: 237568..241663 4096 0x1000 2: [7144..8191]: 245760..246807 1048 0x1001 After swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..8191]: 249856..258047 8192 0x1001 Kmsg: F2FS-fs (zram0): Swapfile (2) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(2097152 * n) case #2 xfs_io -f /mnt/f2fs/file -c "pwrite 0 3M" -c "fsync" Before swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..3047]: 246808..249855 3048 0x1000 1: [3048..6143]: 237568..240663 3096 0x1001 After swapon: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..4095]: 258048..262143 4096 0x1000 1: [4096..6143]: 238616..240663 2048 0x1001 Kmsg: F2FS-fs (zram0): Swapfile: last extent is not aligned to section F2FS-fs (zram0): Swapfile (2) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(2097152 * n) Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2021-05-26 06:29:27 +00:00
not_aligned, blks_per_sec * F2FS_BLKSIZE);
return ret;
}
static int f2fs_swap_activate(struct swap_info_struct *sis, struct file *file,
sector_t *span)
{
struct inode *inode = file_inode(file);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
int ret;
if (!S_ISREG(inode->i_mode))
return -EINVAL;
if (f2fs_readonly(sbi->sb))
return -EROFS;
if (f2fs_lfs_mode(sbi) && !f2fs_sb_has_blkzoned(sbi)) {
f2fs_err(sbi, "Swapfile not supported in LFS mode");
return -EINVAL;
}
ret = f2fs_convert_inline_inode(inode);
if (ret)
return ret;
if (!f2fs_disable_compressed_file(inode))
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
return -EINVAL;
ret = filemap_fdatawrite(inode->i_mapping);
if (ret < 0)
return ret;
f2fs_precache_extents(inode);
ret = check_swap_activate(sis, file, span);
if (ret < 0)
return ret;
stat_inc_swapfile_inode(inode);
set_inode_flag(inode, FI_PIN_FILE);
f2fs_update_time(sbi, REQ_TIME);
return ret;
}
static void f2fs_swap_deactivate(struct file *file)
{
struct inode *inode = file_inode(file);
stat_dec_swapfile_inode(inode);
clear_inode_flag(inode, FI_PIN_FILE);
}
#else
static int f2fs_swap_activate(struct swap_info_struct *sis, struct file *file,
sector_t *span)
{
return -EOPNOTSUPP;
}
static void f2fs_swap_deactivate(struct file *file)
{
}
#endif
const struct address_space_operations f2fs_dblock_aops = {
.read_folio = f2fs_read_data_folio,
.readahead = f2fs_readahead,
.writepage = f2fs_write_data_page,
.writepages = f2fs_write_data_pages,
.write_begin = f2fs_write_begin,
.write_end = f2fs_write_end,
.dirty_folio = f2fs_dirty_data_folio,
.migrate_folio = filemap_migrate_folio,
.invalidate_folio = f2fs_invalidate_folio,
.release_folio = f2fs_release_folio,
.bmap = f2fs_bmap,
.swap_activate = f2fs_swap_activate,
.swap_deactivate = f2fs_swap_deactivate,
};
void f2fs_clear_page_cache_dirty_tag(struct page *page)
{
struct folio *folio = page_folio(page);
struct address_space *mapping = folio->mapping;
unsigned long flags;
xa_lock_irqsave(&mapping->i_pages, flags);
__xa_clear_mark(&mapping->i_pages, folio->index,
PAGECACHE_TAG_DIRTY);
xa_unlock_irqrestore(&mapping->i_pages, flags);
}
int __init f2fs_init_post_read_processing(void)
{
f2fs: add fs-verity support Add fs-verity support to f2fs. fs-verity is a filesystem feature that enables transparent integrity protection and authentication of read-only files. It uses a dm-verity like mechanism at the file level: a Merkle tree is used to verify any block in the file in log(filesize) time. It is implemented mainly by helper functions in fs/verity/. See Documentation/filesystems/fsverity.rst for the full documentation. The f2fs support for fs-verity consists of: - Adding a filesystem feature flag and an inode flag for fs-verity. - Implementing the fsverity_operations to support enabling verity on an inode and reading/writing the verity metadata. - Updating ->readpages() to verify data as it's read from verity files and to support reading verity metadata pages. - Updating ->write_begin(), ->write_end(), and ->writepages() to support writing verity metadata pages. - Calling the fs-verity hooks for ->open(), ->setattr(), and ->ioctl(). Like ext4, f2fs stores the verity metadata (Merkle tree and fsverity_descriptor) past the end of the file, starting at the first 64K boundary beyond i_size. This approach works because (a) verity files are readonly, and (b) pages fully beyond i_size aren't visible to userspace but can be read/written internally by f2fs with only some relatively small changes to f2fs. Extended attributes cannot be used because (a) f2fs limits the total size of an inode's xattr entries to 4096 bytes, which wouldn't be enough for even a single Merkle tree block, and (b) f2fs encryption doesn't encrypt xattrs, yet the verity metadata *must* be encrypted when the file is because it contains hashes of the plaintext data. Acked-by: Jaegeuk Kim <jaegeuk@kernel.org> Acked-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Eric Biggers <ebiggers@google.com>
2019-07-22 16:26:24 +00:00
bio_post_read_ctx_cache =
kmem_cache_create("f2fs_bio_post_read_ctx",
sizeof(struct bio_post_read_ctx), 0, 0, NULL);
if (!bio_post_read_ctx_cache)
goto fail;
bio_post_read_ctx_pool =
mempool_create_slab_pool(NUM_PREALLOC_POST_READ_CTXS,
bio_post_read_ctx_cache);
if (!bio_post_read_ctx_pool)
goto fail_free_cache;
return 0;
fail_free_cache:
kmem_cache_destroy(bio_post_read_ctx_cache);
fail:
return -ENOMEM;
}
void f2fs_destroy_post_read_processing(void)
{
mempool_destroy(bio_post_read_ctx_pool);
kmem_cache_destroy(bio_post_read_ctx_cache);
}
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
int f2fs_init_post_read_wq(struct f2fs_sb_info *sbi)
{
if (!f2fs_sb_has_encrypt(sbi) &&
!f2fs_sb_has_verity(sbi) &&
!f2fs_sb_has_compression(sbi))
return 0;
sbi->post_read_wq = alloc_workqueue("f2fs_post_read_wq",
WQ_UNBOUND | WQ_HIGHPRI,
num_online_cpus());
return sbi->post_read_wq ? 0 : -ENOMEM;
f2fs: support data compression This patch tries to support compression in f2fs. - New term named cluster is defined as basic unit of compression, file can be divided into multiple clusters logically. One cluster includes 4 << n (n >= 0) logical pages, compression size is also cluster size, each of cluster can be compressed or not. - In cluster metadata layout, one special flag is used to indicate cluster is compressed one or normal one, for compressed cluster, following metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only support compression on write-once file, data can be compressed only when all logical blocks in file are valid and cluster compress ratio is lower than specified threshold. - To enable compression on regular inode, there are three ways: * chattr +c file * chattr +c dir; touch dir/file * mount w/ -o compress_extension=ext; touch file.ext Compress metadata layout: [Dnode Structure] +-----------------------------------------------+ | cluster 1 | cluster 2 | ......... | cluster N | +-----------------------------------------------+ . . . . . . . . . Compressed Cluster . . Normal Cluster . +----------+---------+---------+---------+ +---------+---------+---------+---------+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | +----------+---------+---------+---------+ +---------+---------+---------+---------+ . . . . . . +-------------+-------------+----------+----------------------------+ | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ Changelog: 20190326: - fix error handling of read_end_io(). - remove unneeded comments in f2fs_encrypt_one_page(). 20190327: - fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages(). - don't jump into loop directly to avoid uninitialized variables. - add TODO tag in error path of f2fs_write_cache_pages(). 20190328: - fix wrong merge condition in f2fs_read_multi_pages(). - check compressed file in f2fs_post_read_required(). 20190401 - allow overwrite on non-compressed cluster. - check cluster meta before writing compressed data. 20190402 - don't preallocate blocks for compressed file. - add lz4 compress algorithm - process multiple post read works in one workqueue Now f2fs supports processing post read work in multiple workqueue, it shows low performance due to schedule overhead of multiple workqueue executing orderly. 20190921 - compress: support buffered overwrite C: compress cluster flag V: valid block address N: NEW_ADDR One cluster contain 4 blocks before overwrite after overwrite - VVVV -> CVNN - CVNN -> VVVV - CVNN -> CVNN - CVNN -> CVVV - CVVV -> CVNN - CVVV -> CVVV 20191029 - add kconfig F2FS_FS_COMPRESSION to isolate compression related codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm. note that: will remove lzo backend if Jaegeuk agreed that too. - update codes according to Eric's comments. 20191101 - apply fixes from Jaegeuk 20191113 - apply fixes from Jaegeuk - split workqueue for fsverity 20191216 - apply fixes from Jaegeuk 20200117 - fix to avoid NULL pointer dereference [Jaegeuk Kim] - add tracepoint for f2fs_{,de}compress_pages() - fix many bugs and add some compression stats - fix overwrite/mmap bugs - address 32bit build error, reported by Geert. - bug fixes when handling errors and i_compressed_blocks Reported-by: <noreply@ellerman.id.au> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-11-01 10:07:14 +00:00
}
void f2fs_destroy_post_read_wq(struct f2fs_sb_info *sbi)
{
if (sbi->post_read_wq)
destroy_workqueue(sbi->post_read_wq);
}
int __init f2fs_init_bio_entry_cache(void)
{
bio_entry_slab = f2fs_kmem_cache_create("f2fs_bio_entry_slab",
sizeof(struct bio_entry));
return bio_entry_slab ? 0 : -ENOMEM;
}
void f2fs_destroy_bio_entry_cache(void)
{
kmem_cache_destroy(bio_entry_slab);
}
static int f2fs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
unsigned int flags, struct iomap *iomap,
struct iomap *srcmap)
{
struct f2fs_map_blocks map = {};
pgoff_t next_pgofs = 0;
int err;
map.m_lblk = bytes_to_blks(inode, offset);
map.m_len = bytes_to_blks(inode, offset + length - 1) - map.m_lblk + 1;
map.m_next_pgofs = &next_pgofs;
map.m_seg_type = f2fs_rw_hint_to_seg_type(F2FS_I_SB(inode),
inode->i_write_hint);
if (flags & IOMAP_WRITE)
map.m_may_create = true;
err = f2fs_map_blocks(inode, &map, F2FS_GET_BLOCK_DIO);
if (err)
return err;
iomap->offset = blks_to_bytes(inode, map.m_lblk);
/*
* When inline encryption is enabled, sometimes I/O to an encrypted file
* has to be broken up to guarantee DUN contiguity. Handle this by
* limiting the length of the mapping returned.
*/
map.m_len = fscrypt_limit_io_blocks(inode, map.m_lblk, map.m_len);
/*
* We should never see delalloc or compressed extents here based on
* prior flushing and checks.
*/
if (WARN_ON_ONCE(map.m_pblk == COMPRESS_ADDR))
return -EINVAL;
f2fs: multidev: fix to recognize valid zero block address As reported by Yi Zhang in mailing list [1], kernel warning was catched during zbd/010 test as below: ./check zbd/010 zbd/010 (test gap zone support with F2FS) [failed] runtime ... 3.752s something found in dmesg: [ 4378.146781] run blktests zbd/010 at 2024-02-18 11:31:13 [ 4378.192349] null_blk: module loaded [ 4378.209860] null_blk: disk nullb0 created [ 4378.413285] scsi_debug:sdebug_driver_probe: scsi_debug: trim poll_queues to 0. poll_q/nr_hw = (0/1) [ 4378.422334] scsi host15: scsi_debug: version 0191 [20210520] dev_size_mb=1024, opts=0x0, submit_queues=1, statistics=0 [ 4378.434922] scsi 15:0:0:0: Direct-Access-ZBC Linux scsi_debug 0191 PQ: 0 ANSI: 7 [ 4378.443343] scsi 15:0:0:0: Power-on or device reset occurred [ 4378.449371] sd 15:0:0:0: Attached scsi generic sg5 type 20 [ 4378.449418] sd 15:0:0:0: [sdf] Host-managed zoned block device ... (See '/mnt/tests/gitlab.com/api/v4/projects/19168116/repository/archive.zip/storage/blktests/blk/blktests/results/nodev/zbd/010.dmesg' WARNING: CPU: 22 PID: 44011 at fs/iomap/iter.c:51 CPU: 22 PID: 44011 Comm: fio Not tainted 6.8.0-rc3+ #1 RIP: 0010:iomap_iter+0x32b/0x350 Call Trace: <TASK> __iomap_dio_rw+0x1df/0x830 f2fs_file_read_iter+0x156/0x3d0 [f2fs] aio_read+0x138/0x210 io_submit_one+0x188/0x8c0 __x64_sys_io_submit+0x8c/0x1a0 do_syscall_64+0x86/0x170 entry_SYSCALL_64_after_hwframe+0x6e/0x76 Shinichiro Kawasaki helps to analyse this issue and proposes a potential fixing patch in [2]. Quoted from reply of Shinichiro Kawasaki: "I confirmed that the trigger commit is dbf8e63f48af as Yi reported. I took a look in the commit, but it looks fine to me. So I thought the cause is not in the commit diff. I found the WARN is printed when the f2fs is set up with multiple devices, and read requests are mapped to the very first block of the second device in the direct read path. In this case, f2fs_map_blocks() and f2fs_map_blocks_cached() modify map->m_pblk as the physical block address from each block device. It becomes zero when it is mapped to the first block of the device. However, f2fs_iomap_begin() assumes that map->m_pblk is the physical block address of the whole f2fs, across the all block devices. It compares map->m_pblk against NULL_ADDR == 0, then go into the unexpected branch and sets the invalid iomap->length. The WARN catches the invalid iomap->length. This WARN is printed even for non-zoned block devices, by following steps. - Create two (non-zoned) null_blk devices memory backed with 128MB size each: nullb0 and nullb1. # mkfs.f2fs /dev/nullb0 -c /dev/nullb1 # mount -t f2fs /dev/nullb0 "${mount_dir}" # dd if=/dev/zero of="${mount_dir}/test.dat" bs=1M count=192 # dd if="${mount_dir}/test.dat" of=/dev/null bs=1M count=192 iflag=direct ..." So, the root cause of this issue is: when multi-devices feature is on, f2fs_map_blocks() may return zero blkaddr in non-primary device, which is a verified valid block address, however, f2fs_iomap_begin() treats it as an invalid block address, and then it triggers the warning in iomap framework code. Finally, as discussed, we decide to use a more simple and direct way that checking (map.m_flags & F2FS_MAP_MAPPED) condition instead of (map.m_pblk != NULL_ADDR) to fix this issue. Thanks a lot for the effort of Yi Zhang and Shinichiro Kawasaki on this issue. [1] https://lore.kernel.org/linux-f2fs-devel/CAHj4cs-kfojYC9i0G73PRkYzcxCTex=-vugRFeP40g_URGvnfQ@mail.gmail.com/ [2] https://lore.kernel.org/linux-f2fs-devel/gngdj77k4picagsfdtiaa7gpgnup6fsgwzsltx6milmhegmjff@iax2n4wvrqye/ Reported-by: Yi Zhang <yi.zhang@redhat.com> Closes: https://lore.kernel.org/linux-f2fs-devel/CAHj4cs-kfojYC9i0G73PRkYzcxCTex=-vugRFeP40g_URGvnfQ@mail.gmail.com/ Tested-by: Shin'ichiro Kawasaki <shinichiro.kawasaki@wdc.com> Tested-by: Yi Zhang <yi.zhang@redhat.com> Fixes: 1517c1a7a445 ("f2fs: implement iomap operations") Fixes: 8d3c1fa3fa5e ("f2fs: don't rely on F2FS_MAP_* in f2fs_iomap_begin") Signed-off-by: Chao Yu <chao@kernel.org> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2024-03-27 07:42:23 +00:00
if (map.m_flags & F2FS_MAP_MAPPED) {
f2fs: support to map continuous holes or preallocated address This patch supports to map continuous holes or preallocated addresses to improve performace of lookuping mapping info during read DIO. [testcase 1] xfs_io -f /mnt/f2fs/hole -c "truncate 1m" -c "fsync" xfs_io -d /mnt/f2fs/hole -c "pread -b 1m 0 1m" [before] f2fs_direct_IO_enter: dev = (253,16), ino = 6 pos = 0 len = 1048576 ki_flags = 20000 ki_ioprio = 0 rw = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 0, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 1, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 2, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 3, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 4, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 5, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 6, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 7, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 8, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 9, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 10, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 11, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 12, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 13, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 14, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 15, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 16, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 ...... f2fs_direct_IO_exit: dev = (253,16), ino = 6 pos = 0 len = 1048576 rw = 0 ret = 1048576 [after] f2fs_direct_IO_enter: dev = (253,16), ino = 6 pos = 0 len = 1048576 ki_flags = 20000 ki_ioprio = 0 rw = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 0, start blkaddr = 0x0, len = 0x100, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_direct_IO_exit: dev = (253,16), ino = 6 pos = 0 len = 1048576 rw = 0 ret = 1048576 [testcase 2] xfs_io -f /mnt/f2fs/preallocated -c "falloc 0 1m" -c "fsync" xfs_io -d /mnt/f2fs/preallocated -c "pread -b 1m 0 1m" [before] f2fs_direct_IO_enter: dev = (253,16), ino = 11 pos = 0 len = 1048576 ki_flags = 20000 ki_ioprio = 0 rw = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 0, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 1, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 2, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 3, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 4, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 5, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 6, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 7, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 8, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 9, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 10, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 11, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 12, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 13, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 14, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 15, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 16, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 ...... f2fs_direct_IO_exit: dev = (253,16), ino = 11 pos = 0 len = 1048576 rw = 0 ret = 1048576 [after] f2fs_direct_IO_enter: dev = (253,16), ino = 11 pos = 0 len = 1048576 ki_flags = 20000 ki_ioprio = 0 rw = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 0, start blkaddr = 0xffffffff, len = 0x100, flags = 4, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_direct_IO_exit: dev = (253,16), ino = 11 pos = 0 len = 1048576 rw = 0 ret = 1048576 Signed-off-by: Chao Yu <chao@kernel.org> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2024-03-25 15:27:26 +00:00
if (WARN_ON_ONCE(map.m_pblk == NEW_ADDR))
return -EINVAL;
iomap->length = blks_to_bytes(inode, map.m_len);
iomap->type = IOMAP_MAPPED;
iomap->flags |= IOMAP_F_MERGED;
iomap->bdev = map.m_bdev;
iomap->addr = blks_to_bytes(inode, map.m_pblk);
} else {
if (flags & IOMAP_WRITE)
return -ENOTBLK;
f2fs: support to map continuous holes or preallocated address This patch supports to map continuous holes or preallocated addresses to improve performace of lookuping mapping info during read DIO. [testcase 1] xfs_io -f /mnt/f2fs/hole -c "truncate 1m" -c "fsync" xfs_io -d /mnt/f2fs/hole -c "pread -b 1m 0 1m" [before] f2fs_direct_IO_enter: dev = (253,16), ino = 6 pos = 0 len = 1048576 ki_flags = 20000 ki_ioprio = 0 rw = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 0, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 1, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 2, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 3, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 4, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 5, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 6, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 7, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 8, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 9, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 10, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 11, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 12, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 13, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 14, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 15, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 16, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 ...... f2fs_direct_IO_exit: dev = (253,16), ino = 6 pos = 0 len = 1048576 rw = 0 ret = 1048576 [after] f2fs_direct_IO_enter: dev = (253,16), ino = 6 pos = 0 len = 1048576 ki_flags = 20000 ki_ioprio = 0 rw = 0 f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 0, start blkaddr = 0x0, len = 0x100, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_direct_IO_exit: dev = (253,16), ino = 6 pos = 0 len = 1048576 rw = 0 ret = 1048576 [testcase 2] xfs_io -f /mnt/f2fs/preallocated -c "falloc 0 1m" -c "fsync" xfs_io -d /mnt/f2fs/preallocated -c "pread -b 1m 0 1m" [before] f2fs_direct_IO_enter: dev = (253,16), ino = 11 pos = 0 len = 1048576 ki_flags = 20000 ki_ioprio = 0 rw = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 0, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 1, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 2, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 3, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 4, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 5, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 6, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 7, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 8, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 9, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 10, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 11, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 12, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 13, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 14, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 15, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 16, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 ...... f2fs_direct_IO_exit: dev = (253,16), ino = 11 pos = 0 len = 1048576 rw = 0 ret = 1048576 [after] f2fs_direct_IO_enter: dev = (253,16), ino = 11 pos = 0 len = 1048576 ki_flags = 20000 ki_ioprio = 0 rw = 0 f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 0, start blkaddr = 0xffffffff, len = 0x100, flags = 4, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0 f2fs_direct_IO_exit: dev = (253,16), ino = 11 pos = 0 len = 1048576 rw = 0 ret = 1048576 Signed-off-by: Chao Yu <chao@kernel.org> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2024-03-25 15:27:26 +00:00
if (map.m_pblk == NULL_ADDR) {
iomap->length = blks_to_bytes(inode, next_pgofs) -
iomap->offset;
iomap->type = IOMAP_HOLE;
} else if (map.m_pblk == NEW_ADDR) {
iomap->length = blks_to_bytes(inode, map.m_len);
iomap->type = IOMAP_UNWRITTEN;
} else {
f2fs_bug_on(F2FS_I_SB(inode), 1);
}
iomap->addr = IOMAP_NULL_ADDR;
}
if (map.m_flags & F2FS_MAP_NEW)
iomap->flags |= IOMAP_F_NEW;
if ((inode->i_state & I_DIRTY_DATASYNC) ||
offset + length > i_size_read(inode))
iomap->flags |= IOMAP_F_DIRTY;
return 0;
}
const struct iomap_ops f2fs_iomap_ops = {
.iomap_begin = f2fs_iomap_begin,
};