linux/fs/squashfs/xz_wrapper.c

197 lines
4.0 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Squashfs - a compressed read only filesystem for Linux
*
* Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010
* Phillip Lougher <phillip@squashfs.org.uk>
*
* xz_wrapper.c
*/
#include <linux/mutex.h>
#include <linux/bio.h>
#include <linux/slab.h>
#include <linux/xz.h>
#include <linux/bitops.h>
#include "squashfs_fs.h"
#include "squashfs_fs_sb.h"
#include "squashfs.h"
#include "decompressor.h"
#include "page_actor.h"
struct squashfs_xz {
struct xz_dec *state;
struct xz_buf buf;
};
struct disk_comp_opts {
__le32 dictionary_size;
__le32 flags;
};
struct comp_opts {
int dict_size;
};
static void *squashfs_xz_comp_opts(struct squashfs_sb_info *msblk,
void *buff, int len)
{
struct disk_comp_opts *comp_opts = buff;
struct comp_opts *opts;
int err = 0, n;
opts = kmalloc(sizeof(*opts), GFP_KERNEL);
if (opts == NULL) {
err = -ENOMEM;
goto out2;
}
if (comp_opts) {
/* check compressor options are the expected length */
if (len < sizeof(*comp_opts)) {
err = -EIO;
goto out;
}
opts->dict_size = le32_to_cpu(comp_opts->dictionary_size);
/* the dictionary size should be 2^n or 2^n+2^(n+1) */
n = ffs(opts->dict_size) - 1;
if (opts->dict_size != (1 << n) && opts->dict_size != (1 << n) +
(1 << (n + 1))) {
err = -EIO;
goto out;
}
} else
/* use defaults */
opts->dict_size = max_t(int, msblk->block_size,
SQUASHFS_METADATA_SIZE);
return opts;
out:
kfree(opts);
out2:
return ERR_PTR(err);
}
static void *squashfs_xz_init(struct squashfs_sb_info *msblk, void *buff)
{
struct comp_opts *comp_opts = buff;
struct squashfs_xz *stream;
int err;
stream = kmalloc(sizeof(*stream), GFP_KERNEL);
if (stream == NULL) {
err = -ENOMEM;
goto failed;
}
stream->state = xz_dec_init(XZ_PREALLOC, comp_opts->dict_size);
if (stream->state == NULL) {
kfree(stream);
err = -ENOMEM;
goto failed;
}
return stream;
failed:
ERROR("Failed to initialise xz decompressor\n");
return ERR_PTR(err);
}
static void squashfs_xz_free(void *strm)
{
struct squashfs_xz *stream = strm;
if (stream) {
xz_dec_end(stream->state);
kfree(stream);
}
}
static int squashfs_xz_uncompress(struct squashfs_sb_info *msblk, void *strm,
struct bio *bio, int offset, int length,
struct squashfs_page_actor *output)
{
struct bvec_iter_all iter_all = {};
struct bio_vec *bvec = bvec_init_iter_all(&iter_all);
int total = 0, error = 0;
struct squashfs_xz *stream = strm;
xz_dec_reset(stream->state);
stream->buf.in_pos = 0;
stream->buf.in_size = 0;
stream->buf.out_pos = 0;
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 20:29:47 +08:00
stream->buf.out_size = PAGE_SIZE;
stream->buf.out = squashfs_first_page(output);
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 11:21:32 +08:00
if (IS_ERR(stream->buf.out)) {
error = PTR_ERR(stream->buf.out);
goto finish;
}
for (;;) {
enum xz_ret xz_err;
if (stream->buf.in_pos == stream->buf.in_size) {
const void *data;
int avail;
if (!bio_next_segment(bio, &iter_all)) {
/* XZ_STREAM_END must be reached. */
error = -EIO;
break;
}
avail = min(length, ((int)bvec->bv_len) - offset);
data = bvec_virt(bvec);
length -= avail;
stream->buf.in = data + offset;
stream->buf.in_size = avail;
stream->buf.in_pos = 0;
offset = 0;
}
if (stream->buf.out_pos == stream->buf.out_size) {
stream->buf.out = squashfs_next_page(output);
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 11:21:32 +08:00
if (IS_ERR(stream->buf.out)) {
error = PTR_ERR(stream->buf.out);
break;
} else if (stream->buf.out != NULL) {
stream->buf.out_pos = 0;
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 20:29:47 +08:00
total += PAGE_SIZE;
}
}
xz_err = xz_dec_run(stream->state, &stream->buf);
if (xz_err == XZ_STREAM_END)
break;
if (xz_err != XZ_OK) {
error = -EIO;
break;
}
}
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 11:21:32 +08:00
finish:
squashfs_finish_page(output);
return error ? error : total + stream->buf.out_pos;
}
const struct squashfs_decompressor squashfs_xz_comp_ops = {
.init = squashfs_xz_init,
.comp_opts = squashfs_xz_comp_opts,
.free = squashfs_xz_free,
.decompress = squashfs_xz_uncompress,
.id = XZ_COMPRESSION,
.name = "xz",
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 11:21:32 +08:00
.alloc_buffer = 1,
.supported = 1
};