leandrof/linux
1
0
Fork 0
forked from Minki/linux
Code Issues Pull Requests Packages Projects Releases Wiki Activity
master
linux/fs/squashfs/file_direct.c

125 lines
2.8 KiB
C
Raw Permalink Normal View History

treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 499 Based on 1 normalized pattern(s): this work is licensed under the terms of the gnu gpl version 2 see the copying file in the top level directory extracted by the scancode license scanner the SPDX license identifier GPL-2.0-only has been chosen to replace the boilerplate/reference in 35 file(s). Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Kate Stewart <kstewart@linuxfoundation.org> Reviewed-by: Enrico Weigelt <info@metux.net> Reviewed-by: Allison Randal <allison@lohutok.net> Cc: linux-spdx@vger.kernel.org Link: https://lkml.kernel.org/r/20190604081206.797835076@linutronix.de Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2019-06-04 08:11:32 +00:00
// SPDX-License-Identifier: GPL-2.0-only
Squashfs: Directly decompress into the page cache for file data This introduces an implementation of squashfs_readpage_block() that directly decompresses into the page cache. This uses the previously added page handler abstraction to push down the necessary kmap_atomic/kunmap_atomic operations on the page cache buffers into the decompressors. This enables direct copying into the page cache without using the slow kmap/kunmap calls. The code detects when multiple threads are racing in squashfs_readpage() to decompress the same block, and avoids this regression by falling back to using an intermediate buffer. This patch enhances the performance of Squashfs significantly when multiple processes are accessing the filesystem simultaneously because it not only reduces memcopying, but it more importantly eliminates the lock contention on the intermediate buffer. Using single-thread decompression. dd if=file1 of=/dev/null bs=4096 & dd if=file2 of=/dev/null bs=4096 & dd if=file3 of=/dev/null bs=4096 & dd if=file4 of=/dev/null bs=4096 Before: 629145600 bytes (629 MB) copied, 45.8046 s, 13.7 MB/s After: 629145600 bytes (629 MB) copied, 9.29414 s, 67.7 MB/s Signed-off-by: Phillip Lougher <phillip@squashfs.org.uk> Reviewed-by: Minchan Kim <minchan@kernel.org>
2013-11-13 02:04:19 +00:00
/*
* Copyright (c) 2013
* Phillip Lougher <phillip@squashfs.org.uk>
*/
#include <linux/fs.h>
#include <linux/vfs.h>
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/string.h>
#include <linux/pagemap.h>
#include <linux/mutex.h>
#include "squashfs_fs.h"
#include "squashfs_fs_sb.h"
#include "squashfs_fs_i.h"
#include "squashfs.h"
#include "page_actor.h"
/* Read separately compressed datablock directly into page cache */
Squashfs: Compute expected length from inode size rather than block length Previously in squashfs_readpage() when copying data into the page cache, it used the length of the datablock read from the filesystem (after decompression). However, if the filesystem has been corrupted this data block may be short, which will leave pages unfilled. The fix for this is to compute the expected number of bytes to copy from the inode size, and use this to detect if the block is short. Signed-off-by: Phillip Lougher <phillip@squashfs.org.uk> Tested-by: Willy Tarreau <w@1wt.eu> Cc: Анатолий Тросиненко <anatoly.trosinenko@gmail.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-08-02 15:45:15 +00:00
int squashfs_readpage_block(struct page *target_page, u64 block, int bsize,
int expected)
Squashfs: Directly decompress into the page cache for file data This introduces an implementation of squashfs_readpage_block() that directly decompresses into the page cache. This uses the previously added page handler abstraction to push down the necessary kmap_atomic/kunmap_atomic operations on the page cache buffers into the decompressors. This enables direct copying into the page cache without using the slow kmap/kunmap calls. The code detects when multiple threads are racing in squashfs_readpage() to decompress the same block, and avoids this regression by falling back to using an intermediate buffer. This patch enhances the performance of Squashfs significantly when multiple processes are accessing the filesystem simultaneously because it not only reduces memcopying, but it more importantly eliminates the lock contention on the intermediate buffer. Using single-thread decompression. dd if=file1 of=/dev/null bs=4096 & dd if=file2 of=/dev/null bs=4096 & dd if=file3 of=/dev/null bs=4096 & dd if=file4 of=/dev/null bs=4096 Before: 629145600 bytes (629 MB) copied, 45.8046 s, 13.7 MB/s After: 629145600 bytes (629 MB) copied, 9.29414 s, 67.7 MB/s Signed-off-by: Phillip Lougher <phillip@squashfs.org.uk> Reviewed-by: Minchan Kim <minchan@kernel.org>
2013-11-13 02:04:19 +00:00
{
struct inode *inode = target_page->mapping->host;
struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info;
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
int file_end = (i_size_read(inode) - 1) >> PAGE_SHIFT;
int mask = (1 << (msblk->block_log - PAGE_SHIFT)) - 1;
Squashfs: Directly decompress into the page cache for file data This introduces an implementation of squashfs_readpage_block() that directly decompresses into the page cache. This uses the previously added page handler abstraction to push down the necessary kmap_atomic/kunmap_atomic operations on the page cache buffers into the decompressors. This enables direct copying into the page cache without using the slow kmap/kunmap calls. The code detects when multiple threads are racing in squashfs_readpage() to decompress the same block, and avoids this regression by falling back to using an intermediate buffer. This patch enhances the performance of Squashfs significantly when multiple processes are accessing the filesystem simultaneously because it not only reduces memcopying, but it more importantly eliminates the lock contention on the intermediate buffer. Using single-thread decompression. dd if=file1 of=/dev/null bs=4096 & dd if=file2 of=/dev/null bs=4096 & dd if=file3 of=/dev/null bs=4096 & dd if=file4 of=/dev/null bs=4096 Before: 629145600 bytes (629 MB) copied, 45.8046 s, 13.7 MB/s After: 629145600 bytes (629 MB) copied, 9.29414 s, 67.7 MB/s Signed-off-by: Phillip Lougher <phillip@squashfs.org.uk> Reviewed-by: Minchan Kim <minchan@kernel.org>
2013-11-13 02:04:19 +00:00
int start_index = target_page->index & ~mask;
int end_index = start_index | mask;
squashfs: don't use intermediate buffer if pages missing Now that the "page actor" can handle missing pages, we don't have to fall back to using an intermediate buffer in Squashfs_readpage_block() if all the pages necessary can't be obtained. Link: https://lkml.kernel.org/r/20220611032133.5743-3-phillip@squashfs.org.uk Signed-off-by: Phillip Lougher <phillip@squashfs.org.uk> Cc: Hsin-Yi Wang <hsinyi@chromium.org> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Xiongwei Song <Xiongwei.Song@windriver.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-06-11 03:21:33 +00:00
int i, n, pages, bytes, res = -ENOMEM;
Squashfs: Directly decompress into the page cache for file data This introduces an implementation of squashfs_readpage_block() that directly decompresses into the page cache. This uses the previously added page handler abstraction to push down the necessary kmap_atomic/kunmap_atomic operations on the page cache buffers into the decompressors. This enables direct copying into the page cache without using the slow kmap/kunmap calls. The code detects when multiple threads are racing in squashfs_readpage() to decompress the same block, and avoids this regression by falling back to using an intermediate buffer. This patch enhances the performance of Squashfs significantly when multiple processes are accessing the filesystem simultaneously because it not only reduces memcopying, but it more importantly eliminates the lock contention on the intermediate buffer. Using single-thread decompression. dd if=file1 of=/dev/null bs=4096 & dd if=file2 of=/dev/null bs=4096 & dd if=file3 of=/dev/null bs=4096 & dd if=file4 of=/dev/null bs=4096 Before: 629145600 bytes (629 MB) copied, 45.8046 s, 13.7 MB/s After: 629145600 bytes (629 MB) copied, 9.29414 s, 67.7 MB/s Signed-off-by: Phillip Lougher <phillip@squashfs.org.uk> Reviewed-by: Minchan Kim <minchan@kernel.org>
2013-11-13 02:04:19 +00:00
struct page **page;
struct squashfs_page_actor *actor;
void *pageaddr;
if (end_index > file_end)
end_index = file_end;
pages = end_index - start_index + 1;
fs/squashfs/file_direct.c: replace count*size kmalloc by kmalloc_array kmalloc_array() manages count*sizeof overflow. Signed-off-by: Fabian Frederick <fabf@skynet.be> Cc: Phillip Lougher <phillip@squashfs.org.uk> Cc: Joe Perches <joe@perches.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-06 23:03:50 +00:00
page = kmalloc_array(pages, sizeof(void *), GFP_KERNEL);
Squashfs: Directly decompress into the page cache for file data This introduces an implementation of squashfs_readpage_block() that directly decompresses into the page cache. This uses the previously added page handler abstraction to push down the necessary kmap_atomic/kunmap_atomic operations on the page cache buffers into the decompressors. This enables direct copying into the page cache without using the slow kmap/kunmap calls. The code detects when multiple threads are racing in squashfs_readpage() to decompress the same block, and avoids this regression by falling back to using an intermediate buffer. This patch enhances the performance of Squashfs significantly when multiple processes are accessing the filesystem simultaneously because it not only reduces memcopying, but it more importantly eliminates the lock contention on the intermediate buffer. Using single-thread decompression. dd if=file1 of=/dev/null bs=4096 & dd if=file2 of=/dev/null bs=4096 & dd if=file3 of=/dev/null bs=4096 & dd if=file4 of=/dev/null bs=4096 Before: 629145600 bytes (629 MB) copied, 45.8046 s, 13.7 MB/s After: 629145600 bytes (629 MB) copied, 9.29414 s, 67.7 MB/s Signed-off-by: Phillip Lougher <phillip@squashfs.org.uk> Reviewed-by: Minchan Kim <minchan@kernel.org>
2013-11-13 02:04:19 +00:00
if (page == NULL)
return res;
/* Try to grab all the pages covered by the Squashfs block */
squashfs: don't use intermediate buffer if pages missing Now that the "page actor" can handle missing pages, we don't have to fall back to using an intermediate buffer in Squashfs_readpage_block() if all the pages necessary can't be obtained. Link: https://lkml.kernel.org/r/20220611032133.5743-3-phillip@squashfs.org.uk Signed-off-by: Phillip Lougher <phillip@squashfs.org.uk> Cc: Hsin-Yi Wang <hsinyi@chromium.org> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Xiongwei Song <Xiongwei.Song@windriver.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-06-11 03:21:33 +00:00
for (i = 0, n = start_index; n <= end_index; n++) {
Squashfs: Directly decompress into the page cache for file data This introduces an implementation of squashfs_readpage_block() that directly decompresses into the page cache. This uses the previously added page handler abstraction to push down the necessary kmap_atomic/kunmap_atomic operations on the page cache buffers into the decompressors. This enables direct copying into the page cache without using the slow kmap/kunmap calls. The code detects when multiple threads are racing in squashfs_readpage() to decompress the same block, and avoids this regression by falling back to using an intermediate buffer. This patch enhances the performance of Squashfs significantly when multiple processes are accessing the filesystem simultaneously because it not only reduces memcopying, but it more importantly eliminates the lock contention on the intermediate buffer. Using single-thread decompression. dd if=file1 of=/dev/null bs=4096 & dd if=file2 of=/dev/null bs=4096 & dd if=file3 of=/dev/null bs=4096 & dd if=file4 of=/dev/null bs=4096 Before: 629145600 bytes (629 MB) copied, 45.8046 s, 13.7 MB/s After: 629145600 bytes (629 MB) copied, 9.29414 s, 67.7 MB/s Signed-off-by: Phillip Lougher <phillip@squashfs.org.uk> Reviewed-by: Minchan Kim <minchan@kernel.org>
2013-11-13 02:04:19 +00:00
page[i] = (n == target_page->index) ? target_page :
grab_cache_page_nowait(target_page->mapping, n);
squashfs: don't use intermediate buffer if pages missing Now that the "page actor" can handle missing pages, we don't have to fall back to using an intermediate buffer in Squashfs_readpage_block() if all the pages necessary can't be obtained. Link: https://lkml.kernel.org/r/20220611032133.5743-3-phillip@squashfs.org.uk Signed-off-by: Phillip Lougher <phillip@squashfs.org.uk> Cc: Hsin-Yi Wang <hsinyi@chromium.org> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Xiongwei Song <Xiongwei.Song@windriver.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-06-11 03:21:33 +00:00
if (page[i] == NULL)
Squashfs: Directly decompress into the page cache for file data This introduces an implementation of squashfs_readpage_block() that directly decompresses into the page cache. This uses the previously added page handler abstraction to push down the necessary kmap_atomic/kunmap_atomic operations on the page cache buffers into the decompressors. This enables direct copying into the page cache without using the slow kmap/kunmap calls. The code detects when multiple threads are racing in squashfs_readpage() to decompress the same block, and avoids this regression by falling back to using an intermediate buffer. This patch enhances the performance of Squashfs significantly when multiple processes are accessing the filesystem simultaneously because it not only reduces memcopying, but it more importantly eliminates the lock contention on the intermediate buffer. Using single-thread decompression. dd if=file1 of=/dev/null bs=4096 & dd if=file2 of=/dev/null bs=4096 & dd if=file3 of=/dev/null bs=4096 & dd if=file4 of=/dev/null bs=4096 Before: 629145600 bytes (629 MB) copied, 45.8046 s, 13.7 MB/s After: 629145600 bytes (629 MB) copied, 9.29414 s, 67.7 MB/s Signed-off-by: Phillip Lougher <phillip@squashfs.org.uk> Reviewed-by: Minchan Kim <minchan@kernel.org>
2013-11-13 02:04:19 +00:00
continue;
if (PageUptodate(page[i])) {
unlock_page(page[i]);
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
put_page(page[i]);
squashfs: don't use intermediate buffer if pages missing Now that the "page actor" can handle missing pages, we don't have to fall back to using an intermediate buffer in Squashfs_readpage_block() if all the pages necessary can't be obtained. Link: https://lkml.kernel.org/r/20220611032133.5743-3-phillip@squashfs.org.uk Signed-off-by: Phillip Lougher <phillip@squashfs.org.uk> Cc: Hsin-Yi Wang <hsinyi@chromium.org> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Xiongwei Song <Xiongwei.Song@windriver.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-06-11 03:21:33 +00:00
continue;
Squashfs: Directly decompress into the page cache for file data This introduces an implementation of squashfs_readpage_block() that directly decompresses into the page cache. This uses the previously added page handler abstraction to push down the necessary kmap_atomic/kunmap_atomic operations on the page cache buffers into the decompressors. This enables direct copying into the page cache without using the slow kmap/kunmap calls. The code detects when multiple threads are racing in squashfs_readpage() to decompress the same block, and avoids this regression by falling back to using an intermediate buffer. This patch enhances the performance of Squashfs significantly when multiple processes are accessing the filesystem simultaneously because it not only reduces memcopying, but it more importantly eliminates the lock contention on the intermediate buffer. Using single-thread decompression. dd if=file1 of=/dev/null bs=4096 & dd if=file2 of=/dev/null bs=4096 & dd if=file3 of=/dev/null bs=4096 & dd if=file4 of=/dev/null bs=4096 Before: 629145600 bytes (629 MB) copied, 45.8046 s, 13.7 MB/s After: 629145600 bytes (629 MB) copied, 9.29414 s, 67.7 MB/s Signed-off-by: Phillip Lougher <phillip@squashfs.org.uk> Reviewed-by: Minchan Kim <minchan@kernel.org>
2013-11-13 02:04:19 +00:00
}
Squashfs: fix failure to unlock pages on decompress error Direct decompression into the page cache. If we fall back to using an intermediate buffer (because we cannot grab all the page cache pages) and we get a decompress fail, we forgot to release the pages. Reported-by: Roman Peniaev <r.peniaev@gmail.com> Signed-off-by: Phillip Lougher <phillip@squashfs.org.uk>
2013-11-24 00:40:49 +00:00
squashfs: don't use intermediate buffer if pages missing Now that the "page actor" can handle missing pages, we don't have to fall back to using an intermediate buffer in Squashfs_readpage_block() if all the pages necessary can't be obtained. Link: https://lkml.kernel.org/r/20220611032133.5743-3-phillip@squashfs.org.uk Signed-off-by: Phillip Lougher <phillip@squashfs.org.uk> Cc: Hsin-Yi Wang <hsinyi@chromium.org> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Xiongwei Song <Xiongwei.Song@windriver.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-06-11 03:21:33 +00:00
i++;
Squashfs: Directly decompress into the page cache for file data This introduces an implementation of squashfs_readpage_block() that directly decompresses into the page cache. This uses the previously added page handler abstraction to push down the necessary kmap_atomic/kunmap_atomic operations on the page cache buffers into the decompressors. This enables direct copying into the page cache without using the slow kmap/kunmap calls. The code detects when multiple threads are racing in squashfs_readpage() to decompress the same block, and avoids this regression by falling back to using an intermediate buffer. This patch enhances the performance of Squashfs significantly when multiple processes are accessing the filesystem simultaneously because it not only reduces memcopying, but it more importantly eliminates the lock contention on the intermediate buffer. Using single-thread decompression. dd if=file1 of=/dev/null bs=4096 & dd if=file2 of=/dev/null bs=4096 & dd if=file3 of=/dev/null bs=4096 & dd if=file4 of=/dev/null bs=4096 Before: 629145600 bytes (629 MB) copied, 45.8046 s, 13.7 MB/s After: 629145600 bytes (629 MB) copied, 9.29414 s, 67.7 MB/s Signed-off-by: Phillip Lougher <phillip@squashfs.org.uk> Reviewed-by: Minchan Kim <minchan@kernel.org>
2013-11-13 02:04:19 +00:00
}
squashfs: don't use intermediate buffer if pages missing Now that the "page actor" can handle missing pages, we don't have to fall back to using an intermediate buffer in Squashfs_readpage_block() if all the pages necessary can't be obtained. Link: https://lkml.kernel.org/r/20220611032133.5743-3-phillip@squashfs.org.uk Signed-off-by: Phillip Lougher <phillip@squashfs.org.uk> Cc: Hsin-Yi Wang <hsinyi@chromium.org> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Xiongwei Song <Xiongwei.Song@windriver.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-06-11 03:21:33 +00:00
pages = i;
squashfs: extend "page actor" to handle missing pages Patch series "Squashfs: handle missing pages decompressing into page cache". This patchset enables Squashfs to handle missing pages when directly decompressing datablocks into the page cache. Previously if the full set of pages needed was not available, Squashfs would have to fall back to using an intermediate buffer (the older method), which is slower, involving a memcopy, and it introduces contention on a shared buffer. The first patch extends the "page actor" code to handle missing pages. The second patch updates Squashfs_readpage_block() to use the new functionality, and removes the code that falls back to using an intermediate buffer. This patchset is independent of the readahead work, and it is standalone. It can be merged on its own. But the readahead patch for efficiency also needs this patch-set. This patch (of 2): This patch extends the "page actor" code to handle missing pages. Previously if the full set of pages needed to decompress a Squashfs datablock was unavailable, this would cause decompression to fail on the missing pages. In this case direct decompression into the page cache could not be achieved and the code would fall back to using the older intermediate buffer method. With this patch, direct decompression into the page cache can be achieved with missing pages. For "multi-shot" decompressors (zlib, xz, zstd), the page actor will allocate a temporary buffer which is passed to the decompressor, and then freed by the page actor. For "single shot" decompressors (lz4, lzo) which decompress into a contiguous "bounce buffer", and which is then copied into the page cache, it would be pointless to allocate a temporary buffer, memcpy into it, and then free it. For these decompressors -ENOMEM is returned, which signifies that the memcpy for that page should be skipped. This also happens if the data block is uncompressed. Link: https://lkml.kernel.org/r/20220611032133.5743-1-phillip@squashfs.org.uk Link: https://lkml.kernel.org/r/20220611032133.5743-2-phillip@squashfs.org.uk Signed-off-by: Phillip Lougher <phillip@squashfs.org.uk> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Hsin-Yi Wang <hsinyi@chromium.org> Cc: Xiongwei Song <Xiongwei.Song@windriver.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-06-11 03:21:32 +00:00
/*
* Create a "page actor" which will kmap and kunmap the
* page cache pages appropriately within the decompressor
*/
squashfs: don't use intermediate buffer if pages missing Now that the "page actor" can handle missing pages, we don't have to fall back to using an intermediate buffer in Squashfs_readpage_block() if all the pages necessary can't be obtained. Link: https://lkml.kernel.org/r/20220611032133.5743-3-phillip@squashfs.org.uk Signed-off-by: Phillip Lougher <phillip@squashfs.org.uk> Cc: Hsin-Yi Wang <hsinyi@chromium.org> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Xiongwei Song <Xiongwei.Song@windriver.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-06-11 03:21:33 +00:00
actor = squashfs_page_actor_init_special(msblk, page, pages, expected);
squashfs: extend "page actor" to handle missing pages Patch series "Squashfs: handle missing pages decompressing into page cache". This patchset enables Squashfs to handle missing pages when directly decompressing datablocks into the page cache. Previously if the full set of pages needed was not available, Squashfs would have to fall back to using an intermediate buffer (the older method), which is slower, involving a memcopy, and it introduces contention on a shared buffer. The first patch extends the "page actor" code to handle missing pages. The second patch updates Squashfs_readpage_block() to use the new functionality, and removes the code that falls back to using an intermediate buffer. This patchset is independent of the readahead work, and it is standalone. It can be merged on its own. But the readahead patch for efficiency also needs this patch-set. This patch (of 2): This patch extends the "page actor" code to handle missing pages. Previously if the full set of pages needed to decompress a Squashfs datablock was unavailable, this would cause decompression to fail on the missing pages. In this case direct decompression into the page cache could not be achieved and the code would fall back to using the older intermediate buffer method. With this patch, direct decompression into the page cache can be achieved with missing pages. For "multi-shot" decompressors (zlib, xz, zstd), the page actor will allocate a temporary buffer which is passed to the decompressor, and then freed by the page actor. For "single shot" decompressors (lz4, lzo) which decompress into a contiguous "bounce buffer", and which is then copied into the page cache, it would be pointless to allocate a temporary buffer, memcpy into it, and then free it. For these decompressors -ENOMEM is returned, which signifies that the memcpy for that page should be skipped. This also happens if the data block is uncompressed. Link: https://lkml.kernel.org/r/20220611032133.5743-1-phillip@squashfs.org.uk Link: https://lkml.kernel.org/r/20220611032133.5743-2-phillip@squashfs.org.uk Signed-off-by: Phillip Lougher <phillip@squashfs.org.uk> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Hsin-Yi Wang <hsinyi@chromium.org> Cc: Xiongwei Song <Xiongwei.Song@windriver.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-06-11 03:21:32 +00:00
if (actor == NULL)
goto out;
Squashfs: Directly decompress into the page cache for file data This introduces an implementation of squashfs_readpage_block() that directly decompresses into the page cache. This uses the previously added page handler abstraction to push down the necessary kmap_atomic/kunmap_atomic operations on the page cache buffers into the decompressors. This enables direct copying into the page cache without using the slow kmap/kunmap calls. The code detects when multiple threads are racing in squashfs_readpage() to decompress the same block, and avoids this regression by falling back to using an intermediate buffer. This patch enhances the performance of Squashfs significantly when multiple processes are accessing the filesystem simultaneously because it not only reduces memcopying, but it more importantly eliminates the lock contention on the intermediate buffer. Using single-thread decompression. dd if=file1 of=/dev/null bs=4096 & dd if=file2 of=/dev/null bs=4096 & dd if=file3 of=/dev/null bs=4096 & dd if=file4 of=/dev/null bs=4096 Before: 629145600 bytes (629 MB) copied, 45.8046 s, 13.7 MB/s After: 629145600 bytes (629 MB) copied, 9.29414 s, 67.7 MB/s Signed-off-by: Phillip Lougher <phillip@squashfs.org.uk> Reviewed-by: Minchan Kim <minchan@kernel.org>
2013-11-13 02:04:19 +00:00
/* Decompress directly into the page cache buffers */
res = squashfs_read_data(inode->i_sb, block, bsize, NULL, actor);
squashfs: extend "page actor" to handle missing pages Patch series "Squashfs: handle missing pages decompressing into page cache". This patchset enables Squashfs to handle missing pages when directly decompressing datablocks into the page cache. Previously if the full set of pages needed was not available, Squashfs would have to fall back to using an intermediate buffer (the older method), which is slower, involving a memcopy, and it introduces contention on a shared buffer. The first patch extends the "page actor" code to handle missing pages. The second patch updates Squashfs_readpage_block() to use the new functionality, and removes the code that falls back to using an intermediate buffer. This patchset is independent of the readahead work, and it is standalone. It can be merged on its own. But the readahead patch for efficiency also needs this patch-set. This patch (of 2): This patch extends the "page actor" code to handle missing pages. Previously if the full set of pages needed to decompress a Squashfs datablock was unavailable, this would cause decompression to fail on the missing pages. In this case direct decompression into the page cache could not be achieved and the code would fall back to using the older intermediate buffer method. With this patch, direct decompression into the page cache can be achieved with missing pages. For "multi-shot" decompressors (zlib, xz, zstd), the page actor will allocate a temporary buffer which is passed to the decompressor, and then freed by the page actor. For "single shot" decompressors (lz4, lzo) which decompress into a contiguous "bounce buffer", and which is then copied into the page cache, it would be pointless to allocate a temporary buffer, memcpy into it, and then free it. For these decompressors -ENOMEM is returned, which signifies that the memcpy for that page should be skipped. This also happens if the data block is uncompressed. Link: https://lkml.kernel.org/r/20220611032133.5743-1-phillip@squashfs.org.uk Link: https://lkml.kernel.org/r/20220611032133.5743-2-phillip@squashfs.org.uk Signed-off-by: Phillip Lougher <phillip@squashfs.org.uk> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Hsin-Yi Wang <hsinyi@chromium.org> Cc: Xiongwei Song <Xiongwei.Song@windriver.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-06-11 03:21:32 +00:00
squashfs: don't call kmalloc in decompressors The decompressors may be called while in an atomic section. So move the kmalloc() out of this path, and into the "page actor" init function. This fixes a regression introduced by commit f268eedddf35 ("squashfs: extend "page actor" to handle missing pages") Link: https://lkml.kernel.org/r/20220822215430.15933-1-phillip@squashfs.org.uk Fixes: f268eedddf35 ("squashfs: extend "page actor" to handle missing pages") Reported-by: Chris Murphy <lists@colorremedies.com> Signed-off-by: Phillip Lougher <phillip@squashfs.org.uk> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-08-22 21:54:30 +00:00
squashfs_page_actor_free(actor);
squashfs: extend "page actor" to handle missing pages Patch series "Squashfs: handle missing pages decompressing into page cache". This patchset enables Squashfs to handle missing pages when directly decompressing datablocks into the page cache. Previously if the full set of pages needed was not available, Squashfs would have to fall back to using an intermediate buffer (the older method), which is slower, involving a memcopy, and it introduces contention on a shared buffer. The first patch extends the "page actor" code to handle missing pages. The second patch updates Squashfs_readpage_block() to use the new functionality, and removes the code that falls back to using an intermediate buffer. This patchset is independent of the readahead work, and it is standalone. It can be merged on its own. But the readahead patch for efficiency also needs this patch-set. This patch (of 2): This patch extends the "page actor" code to handle missing pages. Previously if the full set of pages needed to decompress a Squashfs datablock was unavailable, this would cause decompression to fail on the missing pages. In this case direct decompression into the page cache could not be achieved and the code would fall back to using the older intermediate buffer method. With this patch, direct decompression into the page cache can be achieved with missing pages. For "multi-shot" decompressors (zlib, xz, zstd), the page actor will allocate a temporary buffer which is passed to the decompressor, and then freed by the page actor. For "single shot" decompressors (lz4, lzo) which decompress into a contiguous "bounce buffer", and which is then copied into the page cache, it would be pointless to allocate a temporary buffer, memcpy into it, and then free it. For these decompressors -ENOMEM is returned, which signifies that the memcpy for that page should be skipped. This also happens if the data block is uncompressed. Link: https://lkml.kernel.org/r/20220611032133.5743-1-phillip@squashfs.org.uk Link: https://lkml.kernel.org/r/20220611032133.5743-2-phillip@squashfs.org.uk Signed-off-by: Phillip Lougher <phillip@squashfs.org.uk> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Hsin-Yi Wang <hsinyi@chromium.org> Cc: Xiongwei Song <Xiongwei.Song@windriver.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-06-11 03:21:32 +00:00
Squashfs: Directly decompress into the page cache for file data This introduces an implementation of squashfs_readpage_block() that directly decompresses into the page cache. This uses the previously added page handler abstraction to push down the necessary kmap_atomic/kunmap_atomic operations on the page cache buffers into the decompressors. This enables direct copying into the page cache without using the slow kmap/kunmap calls. The code detects when multiple threads are racing in squashfs_readpage() to decompress the same block, and avoids this regression by falling back to using an intermediate buffer. This patch enhances the performance of Squashfs significantly when multiple processes are accessing the filesystem simultaneously because it not only reduces memcopying, but it more importantly eliminates the lock contention on the intermediate buffer. Using single-thread decompression. dd if=file1 of=/dev/null bs=4096 & dd if=file2 of=/dev/null bs=4096 & dd if=file3 of=/dev/null bs=4096 & dd if=file4 of=/dev/null bs=4096 Before: 629145600 bytes (629 MB) copied, 45.8046 s, 13.7 MB/s After: 629145600 bytes (629 MB) copied, 9.29414 s, 67.7 MB/s Signed-off-by: Phillip Lougher <phillip@squashfs.org.uk> Reviewed-by: Minchan Kim <minchan@kernel.org>
2013-11-13 02:04:19 +00:00
if (res < 0)
goto mark_errored;
Squashfs: Compute expected length from inode size rather than block length Previously in squashfs_readpage() when copying data into the page cache, it used the length of the datablock read from the filesystem (after decompression). However, if the filesystem has been corrupted this data block may be short, which will leave pages unfilled. The fix for this is to compute the expected number of bytes to copy from the inode size, and use this to detect if the block is short. Signed-off-by: Phillip Lougher <phillip@squashfs.org.uk> Tested-by: Willy Tarreau <w@1wt.eu> Cc: Анатолий Тросиненко <anatoly.trosinenko@gmail.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-08-02 15:45:15 +00:00
if (res != expected) {
res = -EIO;
goto mark_errored;
}
squashfs: don't use intermediate buffer if pages missing Now that the "page actor" can handle missing pages, we don't have to fall back to using an intermediate buffer in Squashfs_readpage_block() if all the pages necessary can't be obtained. Link: https://lkml.kernel.org/r/20220611032133.5743-3-phillip@squashfs.org.uk Signed-off-by: Phillip Lougher <phillip@squashfs.org.uk> Cc: Hsin-Yi Wang <hsinyi@chromium.org> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Xiongwei Song <Xiongwei.Song@windriver.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-06-11 03:21:33 +00:00
/* Last page (if present) may have trailing bytes not filled */
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
bytes = res % PAGE_SIZE;
squashfs: don't use intermediate buffer if pages missing Now that the "page actor" can handle missing pages, we don't have to fall back to using an intermediate buffer in Squashfs_readpage_block() if all the pages necessary can't be obtained. Link: https://lkml.kernel.org/r/20220611032133.5743-3-phillip@squashfs.org.uk Signed-off-by: Phillip Lougher <phillip@squashfs.org.uk> Cc: Hsin-Yi Wang <hsinyi@chromium.org> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Xiongwei Song <Xiongwei.Song@windriver.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-06-11 03:21:33 +00:00
if (page[pages - 1]->index == end_index && bytes) {
pageaddr = kmap_local_page(page[pages - 1]);
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
memset(pageaddr + bytes, 0, PAGE_SIZE - bytes);
squashfs: don't use intermediate buffer if pages missing Now that the "page actor" can handle missing pages, we don't have to fall back to using an intermediate buffer in Squashfs_readpage_block() if all the pages necessary can't be obtained. Link: https://lkml.kernel.org/r/20220611032133.5743-3-phillip@squashfs.org.uk Signed-off-by: Phillip Lougher <phillip@squashfs.org.uk> Cc: Hsin-Yi Wang <hsinyi@chromium.org> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Xiongwei Song <Xiongwei.Song@windriver.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-06-11 03:21:33 +00:00
kunmap_local(pageaddr);
Squashfs: Directly decompress into the page cache for file data This introduces an implementation of squashfs_readpage_block() that directly decompresses into the page cache. This uses the previously added page handler abstraction to push down the necessary kmap_atomic/kunmap_atomic operations on the page cache buffers into the decompressors. This enables direct copying into the page cache without using the slow kmap/kunmap calls. The code detects when multiple threads are racing in squashfs_readpage() to decompress the same block, and avoids this regression by falling back to using an intermediate buffer. This patch enhances the performance of Squashfs significantly when multiple processes are accessing the filesystem simultaneously because it not only reduces memcopying, but it more importantly eliminates the lock contention on the intermediate buffer. Using single-thread decompression. dd if=file1 of=/dev/null bs=4096 & dd if=file2 of=/dev/null bs=4096 & dd if=file3 of=/dev/null bs=4096 & dd if=file4 of=/dev/null bs=4096 Before: 629145600 bytes (629 MB) copied, 45.8046 s, 13.7 MB/s After: 629145600 bytes (629 MB) copied, 9.29414 s, 67.7 MB/s Signed-off-by: Phillip Lougher <phillip@squashfs.org.uk> Reviewed-by: Minchan Kim <minchan@kernel.org>
2013-11-13 02:04:19 +00:00
}
/* Mark pages as uptodate, unlock and release */
for (i = 0; i < pages; i++) {
flush_dcache_page(page[i]);
SetPageUptodate(page[i]);
unlock_page(page[i]);
if (page[i] != target_page)
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 12:29:47 +00:00
put_page(page[i]);
Squashfs: Directly decompress into the page cache for file data This introduces an implementation of squashfs_readpage_block() that directly decompresses into the page cache. This uses the previously added page handler abstraction to push down the necessary kmap_atomic/kunmap_atomic operations on the page cache buffers into the decompressors. This enables direct copying into the page cache without using the slow kmap/kunmap calls. The code detects when multiple threads are racing in squashfs_readpage() to decompress the same block, and avoids this regression by falling back to using an intermediate buffer. This patch enhances the performance of Squashfs significantly when multiple processes are accessing the filesystem simultaneously because it not only reduces memcopying, but it more importantly eliminates the lock contention on the intermediate buffer. Using single-thread decompression. dd if=file1 of=/dev/null bs=4096 & dd if=file2 of=/dev/null bs=4096 & dd if=file3 of=/dev/null bs=4096 & dd if=file4 of=/dev/null bs=4096 Before: 629145600 bytes (629 MB) copied, 45.8046 s, 13.7 MB/s After: 629145600 bytes (629 MB) copied, 9.29414 s, 67.7 MB/s Signed-off-by: Phillip Lougher <phillip@squashfs.org.uk> Reviewed-by: Minchan Kim <minchan@kernel.org>
2013-11-13 02:04:19 +00:00
}
kfree(page);
return 0;
mark_errored:
/* Decompression failed, mark pages as errored. Target_page is
* dealt with by the caller
*/
for (i = 0; i < pages; i++) {
Squashfs: fix failure to unlock pages on decompress error Direct decompression into the page cache. If we fall back to using an intermediate buffer (because we cannot grab all the page cache pages) and we get a decompress fail, we forgot to release the pages. Reported-by: Roman Peniaev <r.peniaev@gmail.com> Signed-off-by: Phillip Lougher <phillip@squashfs.org.uk>
2013-11-24 00:40:49 +00:00
if (page[i] == NULL || page[i] == target_page)
Squashfs: Directly decompress into the page cache for file data This introduces an implementation of squashfs_readpage_block() that directly decompresses into the page cache. This uses the previously added page handler abstraction to push down the necessary kmap_atomic/kunmap_atomic operations on the page cache buffers into the decompressors. This enables direct copying into the page cache without using the slow kmap/kunmap calls. The code detects when multiple threads are racing in squashfs_readpage() to decompress the same block, and avoids this regression by falling back to using an intermediate buffer. This patch enhances the performance of Squashfs significantly when multiple processes are accessing the filesystem simultaneously because it not only reduces memcopying, but it more importantly eliminates the lock contention on the intermediate buffer. Using single-thread decompression. dd if=file1 of=/dev/null bs=4096 & dd if=file2 of=/dev/null bs=4096 & dd if=file3 of=/dev/null bs=4096 & dd if=file4 of=/dev/null bs=4096 Before: 629145600 bytes (629 MB) copied, 45.8046 s, 13.7 MB/s After: 629145600 bytes (629 MB) copied, 9.29414 s, 67.7 MB/s Signed-off-by: Phillip Lougher <phillip@squashfs.org.uk> Reviewed-by: Minchan Kim <minchan@kernel.org>
2013-11-13 02:04:19 +00:00
continue;
flush_dcache_page(page[i]);
SetPageError(page[i]);
unlock_page(page[i]);
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
put_page(page[i]);
Squashfs: Directly decompress into the page cache for file data This introduces an implementation of squashfs_readpage_block() that directly decompresses into the page cache. This uses the previously added page handler abstraction to push down the necessary kmap_atomic/kunmap_atomic operations on the page cache buffers into the decompressors. This enables direct copying into the page cache without using the slow kmap/kunmap calls. The code detects when multiple threads are racing in squashfs_readpage() to decompress the same block, and avoids this regression by falling back to using an intermediate buffer. This patch enhances the performance of Squashfs significantly when multiple processes are accessing the filesystem simultaneously because it not only reduces memcopying, but it more importantly eliminates the lock contention on the intermediate buffer. Using single-thread decompression. dd if=file1 of=/dev/null bs=4096 & dd if=file2 of=/dev/null bs=4096 & dd if=file3 of=/dev/null bs=4096 & dd if=file4 of=/dev/null bs=4096 Before: 629145600 bytes (629 MB) copied, 45.8046 s, 13.7 MB/s After: 629145600 bytes (629 MB) copied, 9.29414 s, 67.7 MB/s Signed-off-by: Phillip Lougher <phillip@squashfs.org.uk> Reviewed-by: Minchan Kim <minchan@kernel.org>
2013-11-13 02:04:19 +00:00
}
out:
kfree(page);
return res;
}
Reference in New Issue Copy Permalink