linux/fs/btrfs/lzo.c

453 lines
11 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (C) 2008 Oracle. All rights reserved.
*/
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/mm.h>
#include <linux/init.h>
#include <linux/err.h>
#include <linux/sched.h>
#include <linux/pagemap.h>
#include <linux/bio.h>
#include <linux/lzo.h>
#include <linux/refcount.h>
#include "compression.h"
btrfs: rework lzo_decompress_bio() to make it subpage compatible For the initial subpage support, although we won't support compressed write, we still need to support compressed read. But for lzo_decompress_bio() it has several problems: - The abuse of PAGE_SIZE for boundary detection For subpage case, we should follow sectorsize to detect the padding zeros. Using PAGE_SIZE will cause subpage compress read to skip certain bytes, and causing read error. - Too many helper variables There are half a dozen helper variables, which is only making things harder to read This patch will rework lzo_decompress_bio() to make it work for subpage: - Use sectorsize to do boundary check, while still use PAGE_SIZE for page switching This allows us to have the same on-disk format for 4K sectorsize fs, while take advantage of larger page size. - Use two main cursors Only @cur_in and @cur_out is utilized as the main cursor. The helper variables will only be declared inside the loop, and only 2 helper variables needed. - Introduce a helper function to copy compressed segment payload Introduce a new helper, copy_compressed_segment(), to copy a compressed segment to workspace buffer. This function will handle the page switching. Now the net result is, with all the excessive comments and new helper function, the refactored code is still smaller, and easier to read. For other decompression code, they have no special padding rule, thus no need to bother for initial subpage support, but will be refactored to the same style later. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-26 14:34:55 +08:00
#include "ctree.h"
#define LZO_LEN 4
/*
* Btrfs LZO compression format
*
* Regular and inlined LZO compressed data extents consist of:
*
* 1. Header
* Fixed size. LZO_LEN (4) bytes long, LE32.
* Records the total size (including the header) of compressed data.
*
* 2. Segment(s)
* Variable size. Each segment includes one segment header, followed by data
* payload.
* One regular LZO compressed extent can have one or more segments.
* For inlined LZO compressed extent, only one segment is allowed.
* One segment represents at most one page of uncompressed data.
*
* 2.1 Segment header
* Fixed size. LZO_LEN (4) bytes long, LE32.
* Records the total size of the segment (not including the header).
* Segment header never crosses page boundary, thus it's possible to
* have at most 3 padding zeros at the end of the page.
*
* 2.2 Data Payload
* Variable size. Size up limit should be lzo1x_worst_compress(PAGE_SIZE)
* which is 4419 for a 4KiB page.
*
* Example:
* Page 1:
* 0 0x2 0x4 0x6 0x8 0xa 0xc 0xe 0x10
* 0x0000 | Header | SegHdr 01 | Data payload 01 ... |
* ...
* 0x0ff0 | SegHdr N | Data payload N ... |00|
* ^^ padding zeros
* Page 2:
* 0x1000 | SegHdr N+1| Data payload N+1 ... |
*/
struct workspace {
void *mem;
void *buf; /* where decompressed data goes */
void *cbuf; /* where compressed data goes */
struct list_head list;
};
static struct workspace_manager wsm;
void lzo_free_workspace(struct list_head *ws)
{
struct workspace *workspace = list_entry(ws, struct workspace, list);
kvfree(workspace->buf);
kvfree(workspace->cbuf);
kvfree(workspace->mem);
kfree(workspace);
}
struct list_head *lzo_alloc_workspace(unsigned int level)
{
struct workspace *workspace;
workspace = kzalloc(sizeof(*workspace), GFP_KERNEL);
if (!workspace)
return ERR_PTR(-ENOMEM);
workspace->mem = kvmalloc(LZO1X_MEM_COMPRESS, GFP_KERNEL);
workspace->buf = kvmalloc(lzo1x_worst_compress(PAGE_SIZE), GFP_KERNEL);
workspace->cbuf = kvmalloc(lzo1x_worst_compress(PAGE_SIZE), GFP_KERNEL);
if (!workspace->mem || !workspace->buf || !workspace->cbuf)
goto fail;
INIT_LIST_HEAD(&workspace->list);
return &workspace->list;
fail:
lzo_free_workspace(&workspace->list);
return ERR_PTR(-ENOMEM);
}
static inline void write_compress_length(char *buf, size_t len)
{
__le32 dlen;
dlen = cpu_to_le32(len);
memcpy(buf, &dlen, LZO_LEN);
}
static inline size_t read_compress_length(const char *buf)
{
__le32 dlen;
memcpy(&dlen, buf, LZO_LEN);
return le32_to_cpu(dlen);
}
int lzo_compress_pages(struct list_head *ws, struct address_space *mapping,
u64 start, struct page **pages, unsigned long *out_pages,
unsigned long *total_in, unsigned long *total_out)
{
struct workspace *workspace = list_entry(ws, struct workspace, list);
int ret = 0;
char *data_in;
char *cpage_out, *sizes_ptr;
int nr_pages = 0;
struct page *in_page = NULL;
struct page *out_page = NULL;
unsigned long bytes_left;
unsigned long len = *total_out;
unsigned long nr_dest_pages = *out_pages;
const unsigned long max_out = nr_dest_pages * PAGE_SIZE;
size_t in_len;
size_t out_len;
char *buf;
unsigned long tot_in = 0;
unsigned long tot_out = 0;
unsigned long pg_bytes_left;
unsigned long out_offset;
unsigned long bytes;
*out_pages = 0;
*total_out = 0;
*total_in = 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
in_page = find_get_page(mapping, start >> PAGE_SHIFT);
data_in = page_address(in_page);
/*
* store the size of all chunks of compressed data in
* the first 4 bytes
*/
out_page = alloc_page(GFP_NOFS);
if (out_page == NULL) {
ret = -ENOMEM;
goto out;
}
cpage_out = page_address(out_page);
out_offset = LZO_LEN;
tot_out = LZO_LEN;
pages[0] = out_page;
nr_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 20:29:47 +08:00
pg_bytes_left = PAGE_SIZE - LZO_LEN;
/* compress at most one page of data each time */
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
in_len = min(len, PAGE_SIZE);
while (tot_in < len) {
ret = lzo1x_1_compress(data_in, in_len, workspace->cbuf,
&out_len, workspace->mem);
if (ret != LZO_E_OK) {
pr_debug("BTRFS: lzo in loop returned %d\n",
ret);
ret = -EIO;
goto out;
}
/* store the size of this chunk of compressed data */
write_compress_length(cpage_out + out_offset, out_len);
tot_out += LZO_LEN;
out_offset += LZO_LEN;
pg_bytes_left -= LZO_LEN;
tot_in += in_len;
tot_out += out_len;
/* copy bytes from the working buffer into the pages */
buf = workspace->cbuf;
while (out_len) {
bytes = min_t(unsigned long, pg_bytes_left, out_len);
memcpy(cpage_out + out_offset, buf, bytes);
out_len -= bytes;
pg_bytes_left -= bytes;
buf += bytes;
out_offset += bytes;
/*
* we need another page for writing out.
*
* Note if there's less than 4 bytes left, we just
* skip to a new page.
*/
if ((out_len == 0 && pg_bytes_left < LZO_LEN) ||
pg_bytes_left == 0) {
if (pg_bytes_left) {
memset(cpage_out + out_offset, 0,
pg_bytes_left);
tot_out += pg_bytes_left;
}
/* we're done, don't allocate new page */
if (out_len == 0 && tot_in >= len)
break;
if (nr_pages == nr_dest_pages) {
out_page = NULL;
ret = -E2BIG;
goto out;
}
out_page = alloc_page(GFP_NOFS);
if (out_page == NULL) {
ret = -ENOMEM;
goto out;
}
cpage_out = page_address(out_page);
pages[nr_pages++] = out_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 20:29:47 +08:00
pg_bytes_left = PAGE_SIZE;
out_offset = 0;
}
}
/* we're making it bigger, give up */
if (tot_in > 8192 && tot_in < tot_out) {
ret = -E2BIG;
goto out;
}
/* we're all done */
if (tot_in >= len)
break;
if (tot_out > max_out)
break;
bytes_left = len - tot_in;
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
put_page(in_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 20:29:47 +08:00
start += PAGE_SIZE;
in_page = find_get_page(mapping, start >> PAGE_SHIFT);
data_in = page_address(in_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 20:29:47 +08:00
in_len = min(bytes_left, PAGE_SIZE);
}
if (tot_out >= tot_in) {
ret = -E2BIG;
goto out;
}
/* store the size of all chunks of compressed data */
sizes_ptr = page_address(pages[0]);
write_compress_length(sizes_ptr, tot_out);
ret = 0;
*total_out = tot_out;
*total_in = tot_in;
out:
*out_pages = nr_pages;
if (in_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 20:29:47 +08:00
put_page(in_page);
return ret;
}
btrfs: rework lzo_decompress_bio() to make it subpage compatible For the initial subpage support, although we won't support compressed write, we still need to support compressed read. But for lzo_decompress_bio() it has several problems: - The abuse of PAGE_SIZE for boundary detection For subpage case, we should follow sectorsize to detect the padding zeros. Using PAGE_SIZE will cause subpage compress read to skip certain bytes, and causing read error. - Too many helper variables There are half a dozen helper variables, which is only making things harder to read This patch will rework lzo_decompress_bio() to make it work for subpage: - Use sectorsize to do boundary check, while still use PAGE_SIZE for page switching This allows us to have the same on-disk format for 4K sectorsize fs, while take advantage of larger page size. - Use two main cursors Only @cur_in and @cur_out is utilized as the main cursor. The helper variables will only be declared inside the loop, and only 2 helper variables needed. - Introduce a helper function to copy compressed segment payload Introduce a new helper, copy_compressed_segment(), to copy a compressed segment to workspace buffer. This function will handle the page switching. Now the net result is, with all the excessive comments and new helper function, the refactored code is still smaller, and easier to read. For other decompression code, they have no special padding rule, thus no need to bother for initial subpage support, but will be refactored to the same style later. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-26 14:34:55 +08:00
/*
* Copy the compressed segment payload into @dest.
*
* For the payload there will be no padding, just need to do page switching.
*/
static void copy_compressed_segment(struct compressed_bio *cb,
char *dest, u32 len, u32 *cur_in)
{
u32 orig_in = *cur_in;
while (*cur_in < orig_in + len) {
struct page *cur_page;
u32 copy_len = min_t(u32, PAGE_SIZE - offset_in_page(*cur_in),
orig_in + len - *cur_in);
ASSERT(copy_len);
cur_page = cb->compressed_pages[*cur_in / PAGE_SIZE];
memcpy(dest + *cur_in - orig_in,
page_address(cur_page) + offset_in_page(*cur_in),
copy_len);
*cur_in += copy_len;
}
}
int lzo_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
{
struct workspace *workspace = list_entry(ws, struct workspace, list);
btrfs: rework lzo_decompress_bio() to make it subpage compatible For the initial subpage support, although we won't support compressed write, we still need to support compressed read. But for lzo_decompress_bio() it has several problems: - The abuse of PAGE_SIZE for boundary detection For subpage case, we should follow sectorsize to detect the padding zeros. Using PAGE_SIZE will cause subpage compress read to skip certain bytes, and causing read error. - Too many helper variables There are half a dozen helper variables, which is only making things harder to read This patch will rework lzo_decompress_bio() to make it work for subpage: - Use sectorsize to do boundary check, while still use PAGE_SIZE for page switching This allows us to have the same on-disk format for 4K sectorsize fs, while take advantage of larger page size. - Use two main cursors Only @cur_in and @cur_out is utilized as the main cursor. The helper variables will only be declared inside the loop, and only 2 helper variables needed. - Introduce a helper function to copy compressed segment payload Introduce a new helper, copy_compressed_segment(), to copy a compressed segment to workspace buffer. This function will handle the page switching. Now the net result is, with all the excessive comments and new helper function, the refactored code is still smaller, and easier to read. For other decompression code, they have no special padding rule, thus no need to bother for initial subpage support, but will be refactored to the same style later. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-26 14:34:55 +08:00
const struct btrfs_fs_info *fs_info = btrfs_sb(cb->inode->i_sb);
const u32 sectorsize = fs_info->sectorsize;
int ret;
/* Compressed data length, can be unaligned */
u32 len_in;
/* Offset inside the compressed data */
u32 cur_in = 0;
/* Bytes decompressed so far */
u32 cur_out = 0;
len_in = read_compress_length(page_address(cb->compressed_pages[0]));
cur_in += LZO_LEN;
btrfs: lzo: Add header length check to avoid potential out-of-bounds access James Harvey reported that some corrupted compressed extent data can lead to various kernel memory corruption. Such corrupted extent data belongs to inode with NODATASUM flags, thus data csum won't help us detecting such bug. If lucky enough, KASAN could catch it like: BUG: KASAN: slab-out-of-bounds in lzo_decompress_bio+0x384/0x7a0 [btrfs] Write of size 4096 at addr ffff8800606cb0f8 by task kworker/u16:0/2338 CPU: 3 PID: 2338 Comm: kworker/u16:0 Tainted: G O 4.17.0-rc5-custom+ #50 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015 Workqueue: btrfs-endio btrfs_endio_helper [btrfs] Call Trace: dump_stack+0xc2/0x16b print_address_description+0x6a/0x270 kasan_report+0x260/0x380 memcpy+0x34/0x50 lzo_decompress_bio+0x384/0x7a0 [btrfs] end_compressed_bio_read+0x99f/0x10b0 [btrfs] bio_endio+0x32e/0x640 normal_work_helper+0x15a/0xea0 [btrfs] process_one_work+0x7e3/0x1470 worker_thread+0x1b0/0x1170 kthread+0x2db/0x390 ret_from_fork+0x22/0x40 ... The offending compressed data has the following info: Header: length 32768 (looks completely valid) Segment 0 Header: length 3472882419 (obviously out of bounds) Then when handling segment 0, since it's over the current page, we need the copy the compressed data to temporary buffer in workspace, then such large size would trigger out-of-bounds memory access, screwing up the whole kernel. Fix it by adding extra checks on header and segment headers to ensure we won't access out-of-bounds, and even checks the decompressed data won't be out-of-bounds. Reported-by: James Harvey <jamespharvey20@gmail.com> Signed-off-by: Qu Wenruo <wqu@suse.com> Reviewed-by: Misono Tomohiro <misono.tomohiro@jp.fujitsu.com> Reviewed-by: David Sterba <dsterba@suse.com> [ updated comments ] Signed-off-by: David Sterba <dsterba@suse.com>
2018-05-15 14:57:51 +08:00
/*
btrfs: rework lzo_decompress_bio() to make it subpage compatible For the initial subpage support, although we won't support compressed write, we still need to support compressed read. But for lzo_decompress_bio() it has several problems: - The abuse of PAGE_SIZE for boundary detection For subpage case, we should follow sectorsize to detect the padding zeros. Using PAGE_SIZE will cause subpage compress read to skip certain bytes, and causing read error. - Too many helper variables There are half a dozen helper variables, which is only making things harder to read This patch will rework lzo_decompress_bio() to make it work for subpage: - Use sectorsize to do boundary check, while still use PAGE_SIZE for page switching This allows us to have the same on-disk format for 4K sectorsize fs, while take advantage of larger page size. - Use two main cursors Only @cur_in and @cur_out is utilized as the main cursor. The helper variables will only be declared inside the loop, and only 2 helper variables needed. - Introduce a helper function to copy compressed segment payload Introduce a new helper, copy_compressed_segment(), to copy a compressed segment to workspace buffer. This function will handle the page switching. Now the net result is, with all the excessive comments and new helper function, the refactored code is still smaller, and easier to read. For other decompression code, they have no special padding rule, thus no need to bother for initial subpage support, but will be refactored to the same style later. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-26 14:34:55 +08:00
* LZO header length check
btrfs: lzo: Add header length check to avoid potential out-of-bounds access James Harvey reported that some corrupted compressed extent data can lead to various kernel memory corruption. Such corrupted extent data belongs to inode with NODATASUM flags, thus data csum won't help us detecting such bug. If lucky enough, KASAN could catch it like: BUG: KASAN: slab-out-of-bounds in lzo_decompress_bio+0x384/0x7a0 [btrfs] Write of size 4096 at addr ffff8800606cb0f8 by task kworker/u16:0/2338 CPU: 3 PID: 2338 Comm: kworker/u16:0 Tainted: G O 4.17.0-rc5-custom+ #50 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015 Workqueue: btrfs-endio btrfs_endio_helper [btrfs] Call Trace: dump_stack+0xc2/0x16b print_address_description+0x6a/0x270 kasan_report+0x260/0x380 memcpy+0x34/0x50 lzo_decompress_bio+0x384/0x7a0 [btrfs] end_compressed_bio_read+0x99f/0x10b0 [btrfs] bio_endio+0x32e/0x640 normal_work_helper+0x15a/0xea0 [btrfs] process_one_work+0x7e3/0x1470 worker_thread+0x1b0/0x1170 kthread+0x2db/0x390 ret_from_fork+0x22/0x40 ... The offending compressed data has the following info: Header: length 32768 (looks completely valid) Segment 0 Header: length 3472882419 (obviously out of bounds) Then when handling segment 0, since it's over the current page, we need the copy the compressed data to temporary buffer in workspace, then such large size would trigger out-of-bounds memory access, screwing up the whole kernel. Fix it by adding extra checks on header and segment headers to ensure we won't access out-of-bounds, and even checks the decompressed data won't be out-of-bounds. Reported-by: James Harvey <jamespharvey20@gmail.com> Signed-off-by: Qu Wenruo <wqu@suse.com> Reviewed-by: Misono Tomohiro <misono.tomohiro@jp.fujitsu.com> Reviewed-by: David Sterba <dsterba@suse.com> [ updated comments ] Signed-off-by: David Sterba <dsterba@suse.com>
2018-05-15 14:57:51 +08:00
*
btrfs: rework lzo_decompress_bio() to make it subpage compatible For the initial subpage support, although we won't support compressed write, we still need to support compressed read. But for lzo_decompress_bio() it has several problems: - The abuse of PAGE_SIZE for boundary detection For subpage case, we should follow sectorsize to detect the padding zeros. Using PAGE_SIZE will cause subpage compress read to skip certain bytes, and causing read error. - Too many helper variables There are half a dozen helper variables, which is only making things harder to read This patch will rework lzo_decompress_bio() to make it work for subpage: - Use sectorsize to do boundary check, while still use PAGE_SIZE for page switching This allows us to have the same on-disk format for 4K sectorsize fs, while take advantage of larger page size. - Use two main cursors Only @cur_in and @cur_out is utilized as the main cursor. The helper variables will only be declared inside the loop, and only 2 helper variables needed. - Introduce a helper function to copy compressed segment payload Introduce a new helper, copy_compressed_segment(), to copy a compressed segment to workspace buffer. This function will handle the page switching. Now the net result is, with all the excessive comments and new helper function, the refactored code is still smaller, and easier to read. For other decompression code, they have no special padding rule, thus no need to bother for initial subpage support, but will be refactored to the same style later. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-26 14:34:55 +08:00
* The total length should not exceed the maximum extent length,
* and all sectors should be used.
* If this happens, it means the compressed extent is corrupted.
btrfs: lzo: Add header length check to avoid potential out-of-bounds access James Harvey reported that some corrupted compressed extent data can lead to various kernel memory corruption. Such corrupted extent data belongs to inode with NODATASUM flags, thus data csum won't help us detecting such bug. If lucky enough, KASAN could catch it like: BUG: KASAN: slab-out-of-bounds in lzo_decompress_bio+0x384/0x7a0 [btrfs] Write of size 4096 at addr ffff8800606cb0f8 by task kworker/u16:0/2338 CPU: 3 PID: 2338 Comm: kworker/u16:0 Tainted: G O 4.17.0-rc5-custom+ #50 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015 Workqueue: btrfs-endio btrfs_endio_helper [btrfs] Call Trace: dump_stack+0xc2/0x16b print_address_description+0x6a/0x270 kasan_report+0x260/0x380 memcpy+0x34/0x50 lzo_decompress_bio+0x384/0x7a0 [btrfs] end_compressed_bio_read+0x99f/0x10b0 [btrfs] bio_endio+0x32e/0x640 normal_work_helper+0x15a/0xea0 [btrfs] process_one_work+0x7e3/0x1470 worker_thread+0x1b0/0x1170 kthread+0x2db/0x390 ret_from_fork+0x22/0x40 ... The offending compressed data has the following info: Header: length 32768 (looks completely valid) Segment 0 Header: length 3472882419 (obviously out of bounds) Then when handling segment 0, since it's over the current page, we need the copy the compressed data to temporary buffer in workspace, then such large size would trigger out-of-bounds memory access, screwing up the whole kernel. Fix it by adding extra checks on header and segment headers to ensure we won't access out-of-bounds, and even checks the decompressed data won't be out-of-bounds. Reported-by: James Harvey <jamespharvey20@gmail.com> Signed-off-by: Qu Wenruo <wqu@suse.com> Reviewed-by: Misono Tomohiro <misono.tomohiro@jp.fujitsu.com> Reviewed-by: David Sterba <dsterba@suse.com> [ updated comments ] Signed-off-by: David Sterba <dsterba@suse.com>
2018-05-15 14:57:51 +08:00
*/
btrfs: rework lzo_decompress_bio() to make it subpage compatible For the initial subpage support, although we won't support compressed write, we still need to support compressed read. But for lzo_decompress_bio() it has several problems: - The abuse of PAGE_SIZE for boundary detection For subpage case, we should follow sectorsize to detect the padding zeros. Using PAGE_SIZE will cause subpage compress read to skip certain bytes, and causing read error. - Too many helper variables There are half a dozen helper variables, which is only making things harder to read This patch will rework lzo_decompress_bio() to make it work for subpage: - Use sectorsize to do boundary check, while still use PAGE_SIZE for page switching This allows us to have the same on-disk format for 4K sectorsize fs, while take advantage of larger page size. - Use two main cursors Only @cur_in and @cur_out is utilized as the main cursor. The helper variables will only be declared inside the loop, and only 2 helper variables needed. - Introduce a helper function to copy compressed segment payload Introduce a new helper, copy_compressed_segment(), to copy a compressed segment to workspace buffer. This function will handle the page switching. Now the net result is, with all the excessive comments and new helper function, the refactored code is still smaller, and easier to read. For other decompression code, they have no special padding rule, thus no need to bother for initial subpage support, but will be refactored to the same style later. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-26 14:34:55 +08:00
if (len_in > min_t(size_t, BTRFS_MAX_COMPRESSED, cb->compressed_len) ||
round_up(len_in, sectorsize) < cb->compressed_len) {
btrfs_err(fs_info,
"invalid lzo header, lzo len %u compressed len %u",
len_in, cb->compressed_len);
return -EUCLEAN;
btrfs: lzo: Add header length check to avoid potential out-of-bounds access James Harvey reported that some corrupted compressed extent data can lead to various kernel memory corruption. Such corrupted extent data belongs to inode with NODATASUM flags, thus data csum won't help us detecting such bug. If lucky enough, KASAN could catch it like: BUG: KASAN: slab-out-of-bounds in lzo_decompress_bio+0x384/0x7a0 [btrfs] Write of size 4096 at addr ffff8800606cb0f8 by task kworker/u16:0/2338 CPU: 3 PID: 2338 Comm: kworker/u16:0 Tainted: G O 4.17.0-rc5-custom+ #50 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015 Workqueue: btrfs-endio btrfs_endio_helper [btrfs] Call Trace: dump_stack+0xc2/0x16b print_address_description+0x6a/0x270 kasan_report+0x260/0x380 memcpy+0x34/0x50 lzo_decompress_bio+0x384/0x7a0 [btrfs] end_compressed_bio_read+0x99f/0x10b0 [btrfs] bio_endio+0x32e/0x640 normal_work_helper+0x15a/0xea0 [btrfs] process_one_work+0x7e3/0x1470 worker_thread+0x1b0/0x1170 kthread+0x2db/0x390 ret_from_fork+0x22/0x40 ... The offending compressed data has the following info: Header: length 32768 (looks completely valid) Segment 0 Header: length 3472882419 (obviously out of bounds) Then when handling segment 0, since it's over the current page, we need the copy the compressed data to temporary buffer in workspace, then such large size would trigger out-of-bounds memory access, screwing up the whole kernel. Fix it by adding extra checks on header and segment headers to ensure we won't access out-of-bounds, and even checks the decompressed data won't be out-of-bounds. Reported-by: James Harvey <jamespharvey20@gmail.com> Signed-off-by: Qu Wenruo <wqu@suse.com> Reviewed-by: Misono Tomohiro <misono.tomohiro@jp.fujitsu.com> Reviewed-by: David Sterba <dsterba@suse.com> [ updated comments ] Signed-off-by: David Sterba <dsterba@suse.com>
2018-05-15 14:57:51 +08:00
}
btrfs: rework lzo_decompress_bio() to make it subpage compatible For the initial subpage support, although we won't support compressed write, we still need to support compressed read. But for lzo_decompress_bio() it has several problems: - The abuse of PAGE_SIZE for boundary detection For subpage case, we should follow sectorsize to detect the padding zeros. Using PAGE_SIZE will cause subpage compress read to skip certain bytes, and causing read error. - Too many helper variables There are half a dozen helper variables, which is only making things harder to read This patch will rework lzo_decompress_bio() to make it work for subpage: - Use sectorsize to do boundary check, while still use PAGE_SIZE for page switching This allows us to have the same on-disk format for 4K sectorsize fs, while take advantage of larger page size. - Use two main cursors Only @cur_in and @cur_out is utilized as the main cursor. The helper variables will only be declared inside the loop, and only 2 helper variables needed. - Introduce a helper function to copy compressed segment payload Introduce a new helper, copy_compressed_segment(), to copy a compressed segment to workspace buffer. This function will handle the page switching. Now the net result is, with all the excessive comments and new helper function, the refactored code is still smaller, and easier to read. For other decompression code, they have no special padding rule, thus no need to bother for initial subpage support, but will be refactored to the same style later. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-26 14:34:55 +08:00
/* Go through each lzo segment */
while (cur_in < len_in) {
struct page *cur_page;
/* Length of the compressed segment */
u32 seg_len;
u32 sector_bytes_left;
size_t out_len = lzo1x_worst_compress(sectorsize);
btrfs: lzo: Add header length check to avoid potential out-of-bounds access James Harvey reported that some corrupted compressed extent data can lead to various kernel memory corruption. Such corrupted extent data belongs to inode with NODATASUM flags, thus data csum won't help us detecting such bug. If lucky enough, KASAN could catch it like: BUG: KASAN: slab-out-of-bounds in lzo_decompress_bio+0x384/0x7a0 [btrfs] Write of size 4096 at addr ffff8800606cb0f8 by task kworker/u16:0/2338 CPU: 3 PID: 2338 Comm: kworker/u16:0 Tainted: G O 4.17.0-rc5-custom+ #50 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015 Workqueue: btrfs-endio btrfs_endio_helper [btrfs] Call Trace: dump_stack+0xc2/0x16b print_address_description+0x6a/0x270 kasan_report+0x260/0x380 memcpy+0x34/0x50 lzo_decompress_bio+0x384/0x7a0 [btrfs] end_compressed_bio_read+0x99f/0x10b0 [btrfs] bio_endio+0x32e/0x640 normal_work_helper+0x15a/0xea0 [btrfs] process_one_work+0x7e3/0x1470 worker_thread+0x1b0/0x1170 kthread+0x2db/0x390 ret_from_fork+0x22/0x40 ... The offending compressed data has the following info: Header: length 32768 (looks completely valid) Segment 0 Header: length 3472882419 (obviously out of bounds) Then when handling segment 0, since it's over the current page, we need the copy the compressed data to temporary buffer in workspace, then such large size would trigger out-of-bounds memory access, screwing up the whole kernel. Fix it by adding extra checks on header and segment headers to ensure we won't access out-of-bounds, and even checks the decompressed data won't be out-of-bounds. Reported-by: James Harvey <jamespharvey20@gmail.com> Signed-off-by: Qu Wenruo <wqu@suse.com> Reviewed-by: Misono Tomohiro <misono.tomohiro@jp.fujitsu.com> Reviewed-by: David Sterba <dsterba@suse.com> [ updated comments ] Signed-off-by: David Sterba <dsterba@suse.com>
2018-05-15 14:57:51 +08:00
/*
btrfs: rework lzo_decompress_bio() to make it subpage compatible For the initial subpage support, although we won't support compressed write, we still need to support compressed read. But for lzo_decompress_bio() it has several problems: - The abuse of PAGE_SIZE for boundary detection For subpage case, we should follow sectorsize to detect the padding zeros. Using PAGE_SIZE will cause subpage compress read to skip certain bytes, and causing read error. - Too many helper variables There are half a dozen helper variables, which is only making things harder to read This patch will rework lzo_decompress_bio() to make it work for subpage: - Use sectorsize to do boundary check, while still use PAGE_SIZE for page switching This allows us to have the same on-disk format for 4K sectorsize fs, while take advantage of larger page size. - Use two main cursors Only @cur_in and @cur_out is utilized as the main cursor. The helper variables will only be declared inside the loop, and only 2 helper variables needed. - Introduce a helper function to copy compressed segment payload Introduce a new helper, copy_compressed_segment(), to copy a compressed segment to workspace buffer. This function will handle the page switching. Now the net result is, with all the excessive comments and new helper function, the refactored code is still smaller, and easier to read. For other decompression code, they have no special padding rule, thus no need to bother for initial subpage support, but will be refactored to the same style later. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-26 14:34:55 +08:00
* We should always have enough space for one segment header
* inside current sector.
btrfs: lzo: Add header length check to avoid potential out-of-bounds access James Harvey reported that some corrupted compressed extent data can lead to various kernel memory corruption. Such corrupted extent data belongs to inode with NODATASUM flags, thus data csum won't help us detecting such bug. If lucky enough, KASAN could catch it like: BUG: KASAN: slab-out-of-bounds in lzo_decompress_bio+0x384/0x7a0 [btrfs] Write of size 4096 at addr ffff8800606cb0f8 by task kworker/u16:0/2338 CPU: 3 PID: 2338 Comm: kworker/u16:0 Tainted: G O 4.17.0-rc5-custom+ #50 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015 Workqueue: btrfs-endio btrfs_endio_helper [btrfs] Call Trace: dump_stack+0xc2/0x16b print_address_description+0x6a/0x270 kasan_report+0x260/0x380 memcpy+0x34/0x50 lzo_decompress_bio+0x384/0x7a0 [btrfs] end_compressed_bio_read+0x99f/0x10b0 [btrfs] bio_endio+0x32e/0x640 normal_work_helper+0x15a/0xea0 [btrfs] process_one_work+0x7e3/0x1470 worker_thread+0x1b0/0x1170 kthread+0x2db/0x390 ret_from_fork+0x22/0x40 ... The offending compressed data has the following info: Header: length 32768 (looks completely valid) Segment 0 Header: length 3472882419 (obviously out of bounds) Then when handling segment 0, since it's over the current page, we need the copy the compressed data to temporary buffer in workspace, then such large size would trigger out-of-bounds memory access, screwing up the whole kernel. Fix it by adding extra checks on header and segment headers to ensure we won't access out-of-bounds, and even checks the decompressed data won't be out-of-bounds. Reported-by: James Harvey <jamespharvey20@gmail.com> Signed-off-by: Qu Wenruo <wqu@suse.com> Reviewed-by: Misono Tomohiro <misono.tomohiro@jp.fujitsu.com> Reviewed-by: David Sterba <dsterba@suse.com> [ updated comments ] Signed-off-by: David Sterba <dsterba@suse.com>
2018-05-15 14:57:51 +08:00
*/
btrfs: rework lzo_decompress_bio() to make it subpage compatible For the initial subpage support, although we won't support compressed write, we still need to support compressed read. But for lzo_decompress_bio() it has several problems: - The abuse of PAGE_SIZE for boundary detection For subpage case, we should follow sectorsize to detect the padding zeros. Using PAGE_SIZE will cause subpage compress read to skip certain bytes, and causing read error. - Too many helper variables There are half a dozen helper variables, which is only making things harder to read This patch will rework lzo_decompress_bio() to make it work for subpage: - Use sectorsize to do boundary check, while still use PAGE_SIZE for page switching This allows us to have the same on-disk format for 4K sectorsize fs, while take advantage of larger page size. - Use two main cursors Only @cur_in and @cur_out is utilized as the main cursor. The helper variables will only be declared inside the loop, and only 2 helper variables needed. - Introduce a helper function to copy compressed segment payload Introduce a new helper, copy_compressed_segment(), to copy a compressed segment to workspace buffer. This function will handle the page switching. Now the net result is, with all the excessive comments and new helper function, the refactored code is still smaller, and easier to read. For other decompression code, they have no special padding rule, thus no need to bother for initial subpage support, but will be refactored to the same style later. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-26 14:34:55 +08:00
ASSERT(cur_in / sectorsize ==
(cur_in + LZO_LEN - 1) / sectorsize);
cur_page = cb->compressed_pages[cur_in / PAGE_SIZE];
ASSERT(cur_page);
seg_len = read_compress_length(page_address(cur_page) +
offset_in_page(cur_in));
cur_in += LZO_LEN;
/* Copy the compressed segment payload into workspace */
copy_compressed_segment(cb, workspace->cbuf, seg_len, &cur_in);
/* Decompress the data */
ret = lzo1x_decompress_safe(workspace->cbuf, seg_len,
workspace->buf, &out_len);
if (ret != LZO_E_OK) {
btrfs: rework lzo_decompress_bio() to make it subpage compatible For the initial subpage support, although we won't support compressed write, we still need to support compressed read. But for lzo_decompress_bio() it has several problems: - The abuse of PAGE_SIZE for boundary detection For subpage case, we should follow sectorsize to detect the padding zeros. Using PAGE_SIZE will cause subpage compress read to skip certain bytes, and causing read error. - Too many helper variables There are half a dozen helper variables, which is only making things harder to read This patch will rework lzo_decompress_bio() to make it work for subpage: - Use sectorsize to do boundary check, while still use PAGE_SIZE for page switching This allows us to have the same on-disk format for 4K sectorsize fs, while take advantage of larger page size. - Use two main cursors Only @cur_in and @cur_out is utilized as the main cursor. The helper variables will only be declared inside the loop, and only 2 helper variables needed. - Introduce a helper function to copy compressed segment payload Introduce a new helper, copy_compressed_segment(), to copy a compressed segment to workspace buffer. This function will handle the page switching. Now the net result is, with all the excessive comments and new helper function, the refactored code is still smaller, and easier to read. For other decompression code, they have no special padding rule, thus no need to bother for initial subpage support, but will be refactored to the same style later. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-26 14:34:55 +08:00
btrfs_err(fs_info, "failed to decompress");
ret = -EIO;
btrfs: rework lzo_decompress_bio() to make it subpage compatible For the initial subpage support, although we won't support compressed write, we still need to support compressed read. But for lzo_decompress_bio() it has several problems: - The abuse of PAGE_SIZE for boundary detection For subpage case, we should follow sectorsize to detect the padding zeros. Using PAGE_SIZE will cause subpage compress read to skip certain bytes, and causing read error. - Too many helper variables There are half a dozen helper variables, which is only making things harder to read This patch will rework lzo_decompress_bio() to make it work for subpage: - Use sectorsize to do boundary check, while still use PAGE_SIZE for page switching This allows us to have the same on-disk format for 4K sectorsize fs, while take advantage of larger page size. - Use two main cursors Only @cur_in and @cur_out is utilized as the main cursor. The helper variables will only be declared inside the loop, and only 2 helper variables needed. - Introduce a helper function to copy compressed segment payload Introduce a new helper, copy_compressed_segment(), to copy a compressed segment to workspace buffer. This function will handle the page switching. Now the net result is, with all the excessive comments and new helper function, the refactored code is still smaller, and easier to read. For other decompression code, they have no special padding rule, thus no need to bother for initial subpage support, but will be refactored to the same style later. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-26 14:34:55 +08:00
goto out;
}
btrfs: rework lzo_decompress_bio() to make it subpage compatible For the initial subpage support, although we won't support compressed write, we still need to support compressed read. But for lzo_decompress_bio() it has several problems: - The abuse of PAGE_SIZE for boundary detection For subpage case, we should follow sectorsize to detect the padding zeros. Using PAGE_SIZE will cause subpage compress read to skip certain bytes, and causing read error. - Too many helper variables There are half a dozen helper variables, which is only making things harder to read This patch will rework lzo_decompress_bio() to make it work for subpage: - Use sectorsize to do boundary check, while still use PAGE_SIZE for page switching This allows us to have the same on-disk format for 4K sectorsize fs, while take advantage of larger page size. - Use two main cursors Only @cur_in and @cur_out is utilized as the main cursor. The helper variables will only be declared inside the loop, and only 2 helper variables needed. - Introduce a helper function to copy compressed segment payload Introduce a new helper, copy_compressed_segment(), to copy a compressed segment to workspace buffer. This function will handle the page switching. Now the net result is, with all the excessive comments and new helper function, the refactored code is still smaller, and easier to read. For other decompression code, they have no special padding rule, thus no need to bother for initial subpage support, but will be refactored to the same style later. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-26 14:34:55 +08:00
/* Copy the data into inode pages */
ret = btrfs_decompress_buf2page(workspace->buf, out_len, cb, cur_out);
cur_out += out_len;
btrfs: rework lzo_decompress_bio() to make it subpage compatible For the initial subpage support, although we won't support compressed write, we still need to support compressed read. But for lzo_decompress_bio() it has several problems: - The abuse of PAGE_SIZE for boundary detection For subpage case, we should follow sectorsize to detect the padding zeros. Using PAGE_SIZE will cause subpage compress read to skip certain bytes, and causing read error. - Too many helper variables There are half a dozen helper variables, which is only making things harder to read This patch will rework lzo_decompress_bio() to make it work for subpage: - Use sectorsize to do boundary check, while still use PAGE_SIZE for page switching This allows us to have the same on-disk format for 4K sectorsize fs, while take advantage of larger page size. - Use two main cursors Only @cur_in and @cur_out is utilized as the main cursor. The helper variables will only be declared inside the loop, and only 2 helper variables needed. - Introduce a helper function to copy compressed segment payload Introduce a new helper, copy_compressed_segment(), to copy a compressed segment to workspace buffer. This function will handle the page switching. Now the net result is, with all the excessive comments and new helper function, the refactored code is still smaller, and easier to read. For other decompression code, they have no special padding rule, thus no need to bother for initial subpage support, but will be refactored to the same style later. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-26 14:34:55 +08:00
/* All data read, exit */
if (ret == 0)
goto out;
ret = 0;
/* Check if the sector has enough space for a segment header */
sector_bytes_left = sectorsize - (cur_in % sectorsize);
if (sector_bytes_left >= LZO_LEN)
continue;
/* Skip the padding zeros */
cur_in += sector_bytes_left;
}
btrfs: rework lzo_decompress_bio() to make it subpage compatible For the initial subpage support, although we won't support compressed write, we still need to support compressed read. But for lzo_decompress_bio() it has several problems: - The abuse of PAGE_SIZE for boundary detection For subpage case, we should follow sectorsize to detect the padding zeros. Using PAGE_SIZE will cause subpage compress read to skip certain bytes, and causing read error. - Too many helper variables There are half a dozen helper variables, which is only making things harder to read This patch will rework lzo_decompress_bio() to make it work for subpage: - Use sectorsize to do boundary check, while still use PAGE_SIZE for page switching This allows us to have the same on-disk format for 4K sectorsize fs, while take advantage of larger page size. - Use two main cursors Only @cur_in and @cur_out is utilized as the main cursor. The helper variables will only be declared inside the loop, and only 2 helper variables needed. - Introduce a helper function to copy compressed segment payload Introduce a new helper, copy_compressed_segment(), to copy a compressed segment to workspace buffer. This function will handle the page switching. Now the net result is, with all the excessive comments and new helper function, the refactored code is still smaller, and easier to read. For other decompression code, they have no special padding rule, thus no need to bother for initial subpage support, but will be refactored to the same style later. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-26 14:34:55 +08:00
out:
if (!ret)
btrfs: rework btrfs_decompress_buf2page() There are several bugs inside the function btrfs_decompress_buf2page() - @start_byte doesn't take bvec.bv_offset into consideration Thus it can't handle case where the target range is not page aligned. - Too many helper variables There are tons of helper variables, @buf_offset, @current_buf_start, @start_byte, @prev_start_byte, @working_bytes, @bytes. This hurts anyone who wants to read the function. - No obvious main cursor for the iteartion A new problem caused by previous problem. - Comments for parameter list makes no sense Like @buf_start is the offset to @buf, or offset inside the full decompressed extent? (Spoiler alert, the later case) And @total_out acts more like @buf_start + @size_of_buf. The worst is @disk_start. The real meaning of it is the file offset of the full decompressed extent. This patch will rework the whole function by: - Add a proper comment with ASCII art to explain the parameter list - Rework parameter list The old @buf_start is renamed to @decompressed, to show how many bytes are already decompressed inside the full decompressed extent. The old @total_out is replaced by @buf_len, which is the decompressed data size. For old @disk_start and @bio, just pass @compressed_bio in. - Use single main cursor The main cursor will be @cur_file_offset, to show what's the current file offset. Other helper variables will be declared inside the main loop, and only minimal amount of helper variables: * offset_inside_decompressed_buf: The only real helper * copy_start_file_offset: File offset we start memcpy * bvec_file_offset: File offset of current bvec Even with all these extensive comments, the final function is still smaller than the original function, which is definitely a win. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-05 10:00:58 +08:00
zero_fill_bio(cb->orig_bio);
return ret;
}
int lzo_decompress(struct list_head *ws, unsigned char *data_in,
struct page *dest_page, unsigned long start_byte, size_t srclen,
size_t destlen)
{
struct workspace *workspace = list_entry(ws, struct workspace, list);
size_t in_len;
size_t out_len;
size_t max_segment_len = lzo1x_worst_compress(PAGE_SIZE);
int ret = 0;
char *kaddr;
unsigned long bytes;
if (srclen < LZO_LEN || srclen > max_segment_len + LZO_LEN * 2)
return -EUCLEAN;
in_len = read_compress_length(data_in);
if (in_len != srclen)
return -EUCLEAN;
data_in += LZO_LEN;
in_len = read_compress_length(data_in);
if (in_len != srclen - LZO_LEN * 2) {
ret = -EUCLEAN;
goto out;
}
data_in += LZO_LEN;
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
out_len = PAGE_SIZE;
ret = lzo1x_decompress_safe(data_in, in_len, workspace->buf, &out_len);
if (ret != LZO_E_OK) {
pr_warn("BTRFS: decompress failed!\n");
ret = -EIO;
goto out;
}
if (out_len < start_byte) {
ret = -EIO;
goto out;
}
/*
* the caller is already checking against PAGE_SIZE, but lets
* move this check closer to the memcpy/memset
*/
destlen = min_t(unsigned long, destlen, PAGE_SIZE);
bytes = min_t(unsigned long, destlen, out_len - start_byte);
kaddr = page_address(dest_page);
memcpy(kaddr, workspace->buf + start_byte, bytes);
/*
* btrfs_getblock is doing a zero on the tail of the page too,
* but this will cover anything missing from the decompressed
* data.
*/
if (bytes < destlen)
memset(kaddr+bytes, 0, destlen-bytes);
out:
return ret;
}
const struct btrfs_compress_op btrfs_lzo_compress = {
.workspace_manager = &wsm,
.max_level = 1,
.default_level = 1,
};