OpenCloudOS-Kernel/fs/btrfs/file-item.c

1452 lines
40 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (C) 2007 Oracle. All rights reserved.
*/
#include <linux/bio.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/slab.h>
#include <linux/pagemap.h>
#include <linux/highmem.h>
#include <linux/sched/mm.h>
#include <crypto/hash.h>
#include "messages.h"
#include "misc.h"
#include "ctree.h"
#include "disk-io.h"
#include "transaction.h"
#include "bio.h"
#include "print-tree.h"
#include "compression.h"
#include "fs.h"
#include "accessors.h"
#include "file-item.h"
#include "super.h"
#define __MAX_CSUM_ITEMS(r, size) ((unsigned long)(((BTRFS_LEAF_DATA_SIZE(r) - \
sizeof(struct btrfs_item) * 2) / \
size) - 1))
#define MAX_CSUM_ITEMS(r, size) (min_t(u32, __MAX_CSUM_ITEMS(r, size), \
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
PAGE_SIZE))
/*
* Set inode's size according to filesystem options.
*
* @inode: inode we want to update the disk_i_size for
* @new_i_size: i_size we want to set to, 0 if we use i_size
*
* With NO_HOLES set this simply sets the disk_is_size to whatever i_size_read()
* returns as it is perfectly fine with a file that has holes without hole file
* extent items.
*
* However without NO_HOLES we need to only return the area that is contiguous
* from the 0 offset of the file. Otherwise we could end up adjust i_size up
* to an extent that has a gap in between.
*
* Finally new_i_size should only be set in the case of truncate where we're not
* ready to use i_size_read() as the limiter yet.
*/
void btrfs_inode_safe_disk_i_size_write(struct btrfs_inode *inode, u64 new_i_size)
{
struct btrfs_fs_info *fs_info = inode->root->fs_info;
u64 start, end, i_size;
int ret;
i_size = new_i_size ?: i_size_read(&inode->vfs_inode);
if (btrfs_fs_incompat(fs_info, NO_HOLES)) {
inode->disk_i_size = i_size;
return;
}
spin_lock(&inode->lock);
ret = find_contiguous_extent_bit(&inode->file_extent_tree, 0, &start,
&end, EXTENT_DIRTY);
if (!ret && start == 0)
i_size = min(i_size, end + 1);
else
i_size = 0;
inode->disk_i_size = i_size;
spin_unlock(&inode->lock);
}
/*
* Mark range within a file as having a new extent inserted.
*
* @inode: inode being modified
* @start: start file offset of the file extent we've inserted
* @len: logical length of the file extent item
*
* Call when we are inserting a new file extent where there was none before.
* Does not need to call this in the case where we're replacing an existing file
* extent, however if not sure it's fine to call this multiple times.
*
* The start and len must match the file extent item, so thus must be sectorsize
* aligned.
*/
int btrfs_inode_set_file_extent_range(struct btrfs_inode *inode, u64 start,
u64 len)
{
if (len == 0)
return 0;
ASSERT(IS_ALIGNED(start + len, inode->root->fs_info->sectorsize));
if (btrfs_fs_incompat(inode->root->fs_info, NO_HOLES))
return 0;
return set_extent_bits(&inode->file_extent_tree, start, start + len - 1,
EXTENT_DIRTY);
}
/*
* Mark an inode range as not having a backing extent.
*
* @inode: inode being modified
* @start: start file offset of the file extent we've inserted
* @len: logical length of the file extent item
*
* Called when we drop a file extent, for example when we truncate. Doesn't
* need to be called for cases where we're replacing a file extent, like when
* we've COWed a file extent.
*
* The start and len must match the file extent item, so thus must be sectorsize
* aligned.
*/
int btrfs_inode_clear_file_extent_range(struct btrfs_inode *inode, u64 start,
u64 len)
{
if (len == 0)
return 0;
ASSERT(IS_ALIGNED(start + len, inode->root->fs_info->sectorsize) ||
len == (u64)-1);
if (btrfs_fs_incompat(inode->root->fs_info, NO_HOLES))
return 0;
return clear_extent_bit(&inode->file_extent_tree, start,
start + len - 1, EXTENT_DIRTY, NULL);
}
static size_t bytes_to_csum_size(const struct btrfs_fs_info *fs_info, u32 bytes)
{
ASSERT(IS_ALIGNED(bytes, fs_info->sectorsize));
return (bytes >> fs_info->sectorsize_bits) * fs_info->csum_size;
}
static size_t csum_size_to_bytes(const struct btrfs_fs_info *fs_info, u32 csum_size)
{
ASSERT(IS_ALIGNED(csum_size, fs_info->csum_size));
return (csum_size / fs_info->csum_size) << fs_info->sectorsize_bits;
}
static inline u32 max_ordered_sum_bytes(const struct btrfs_fs_info *fs_info)
{
u32 max_csum_size = round_down(PAGE_SIZE - sizeof(struct btrfs_ordered_sum),
fs_info->csum_size);
return csum_size_to_bytes(fs_info, max_csum_size);
}
/*
* Calculate the total size needed to allocate for an ordered sum structure
* spanning @bytes in the file.
*/
static int btrfs_ordered_sum_size(struct btrfs_fs_info *fs_info, unsigned long bytes)
{
return sizeof(struct btrfs_ordered_sum) + bytes_to_csum_size(fs_info, bytes);
}
int btrfs_insert_hole_extent(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
u64 objectid, u64 pos, u64 num_bytes)
{
int ret = 0;
struct btrfs_file_extent_item *item;
struct btrfs_key file_key;
struct btrfs_path *path;
struct extent_buffer *leaf;
path = btrfs_alloc_path();
if (!path)
return -ENOMEM;
file_key.objectid = objectid;
file_key.offset = pos;
file_key.type = BTRFS_EXTENT_DATA_KEY;
ret = btrfs_insert_empty_item(trans, root, path, &file_key,
sizeof(*item));
if (ret < 0)
goto out;
BUG_ON(ret); /* Can't happen */
leaf = path->nodes[0];
item = btrfs_item_ptr(leaf, path->slots[0],
struct btrfs_file_extent_item);
btrfs_set_file_extent_disk_bytenr(leaf, item, 0);
btrfs_set_file_extent_disk_num_bytes(leaf, item, 0);
btrfs_set_file_extent_offset(leaf, item, 0);
btrfs_set_file_extent_num_bytes(leaf, item, num_bytes);
btrfs_set_file_extent_ram_bytes(leaf, item, num_bytes);
btrfs_set_file_extent_generation(leaf, item, trans->transid);
btrfs_set_file_extent_type(leaf, item, BTRFS_FILE_EXTENT_REG);
btrfs_set_file_extent_compression(leaf, item, 0);
btrfs_set_file_extent_encryption(leaf, item, 0);
btrfs_set_file_extent_other_encoding(leaf, item, 0);
Btrfs: Add zlib compression support This is a large change for adding compression on reading and writing, both for inline and regular extents. It does some fairly large surgery to the writeback paths. Compression is off by default and enabled by mount -o compress. Even when the -o compress mount option is not used, it is possible to read compressed extents off the disk. If compression for a given set of pages fails to make them smaller, the file is flagged to avoid future compression attempts later. * While finding delalloc extents, the pages are locked before being sent down to the delalloc handler. This allows the delalloc handler to do complex things such as cleaning the pages, marking them writeback and starting IO on their behalf. * Inline extents are inserted at delalloc time now. This allows us to compress the data before inserting the inline extent, and it allows us to insert an inline extent that spans multiple pages. * All of the in-memory extent representations (extent_map.c, ordered-data.c etc) are changed to record both an in-memory size and an on disk size, as well as a flag for compression. From a disk format point of view, the extent pointers in the file are changed to record the on disk size of a given extent and some encoding flags. Space in the disk format is allocated for compression encoding, as well as encryption and a generic 'other' field. Neither the encryption or the 'other' field are currently used. In order to limit the amount of data read for a single random read in the file, the size of a compressed extent is limited to 128k. This is a software only limit, the disk format supports u64 sized compressed extents. In order to limit the ram consumed while processing extents, the uncompressed size of a compressed extent is limited to 256k. This is a software only limit and will be subject to tuning later. Checksumming is still done on compressed extents, and it is done on the uncompressed version of the data. This way additional encodings can be layered on without having to figure out which encoding to checksum. Compression happens at delalloc time, which is basically singled threaded because it is usually done by a single pdflush thread. This makes it tricky to spread the compression load across all the cpus on the box. We'll have to look at parallel pdflush walks of dirty inodes at a later time. Decompression is hooked into readpages and it does spread across CPUs nicely. Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-10-30 02:49:59 +08:00
btrfs_mark_buffer_dirty(leaf);
out:
btrfs_free_path(path);
return ret;
}
static struct btrfs_csum_item *
btrfs_lookup_csum(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct btrfs_path *path,
u64 bytenr, int cow)
{
struct btrfs_fs_info *fs_info = root->fs_info;
int ret;
struct btrfs_key file_key;
struct btrfs_key found_key;
struct btrfs_csum_item *item;
struct extent_buffer *leaf;
u64 csum_offset = 0;
const u32 csum_size = fs_info->csum_size;
int csums_in_item;
Btrfs: move data checksumming into a dedicated tree Btrfs stores checksums for each data block. Until now, they have been stored in the subvolume trees, indexed by the inode that is referencing the data block. This means that when we read the inode, we've probably read in at least some checksums as well. But, this has a few problems: * The checksums are indexed by logical offset in the file. When compression is on, this means we have to do the expensive checksumming on the uncompressed data. It would be faster if we could checksum the compressed data instead. * If we implement encryption, we'll be checksumming the plain text and storing that on disk. This is significantly less secure. * For either compression or encryption, we have to get the plain text back before we can verify the checksum as correct. This makes the raid layer balancing and extent moving much more expensive. * It makes the front end caching code more complex, as we have touch the subvolume and inodes as we cache extents. * There is potentitally one copy of the checksum in each subvolume referencing an extent. The solution used here is to store the extent checksums in a dedicated tree. This allows us to index the checksums by phyiscal extent start and length. It means: * The checksum is against the data stored on disk, after any compression or encryption is done. * The checksum is stored in a central location, and can be verified without following back references, or reading inodes. This makes compression significantly faster by reducing the amount of data that needs to be checksummed. It will also allow much faster raid management code in general. The checksums are indexed by a key with a fixed objectid (a magic value in ctree.h) and offset set to the starting byte of the extent. This allows us to copy the checksum items into the fsync log tree directly (or any other tree), without having to invent a second format for them. Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-12-09 05:58:54 +08:00
file_key.objectid = BTRFS_EXTENT_CSUM_OBJECTID;
file_key.offset = bytenr;
file_key.type = BTRFS_EXTENT_CSUM_KEY;
ret = btrfs_search_slot(trans, root, &file_key, path, 0, cow);
if (ret < 0)
goto fail;
leaf = path->nodes[0];
if (ret > 0) {
ret = 1;
if (path->slots[0] == 0)
goto fail;
path->slots[0]--;
btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);
if (found_key.type != BTRFS_EXTENT_CSUM_KEY)
goto fail;
Btrfs: move data checksumming into a dedicated tree Btrfs stores checksums for each data block. Until now, they have been stored in the subvolume trees, indexed by the inode that is referencing the data block. This means that when we read the inode, we've probably read in at least some checksums as well. But, this has a few problems: * The checksums are indexed by logical offset in the file. When compression is on, this means we have to do the expensive checksumming on the uncompressed data. It would be faster if we could checksum the compressed data instead. * If we implement encryption, we'll be checksumming the plain text and storing that on disk. This is significantly less secure. * For either compression or encryption, we have to get the plain text back before we can verify the checksum as correct. This makes the raid layer balancing and extent moving much more expensive. * It makes the front end caching code more complex, as we have touch the subvolume and inodes as we cache extents. * There is potentitally one copy of the checksum in each subvolume referencing an extent. The solution used here is to store the extent checksums in a dedicated tree. This allows us to index the checksums by phyiscal extent start and length. It means: * The checksum is against the data stored on disk, after any compression or encryption is done. * The checksum is stored in a central location, and can be verified without following back references, or reading inodes. This makes compression significantly faster by reducing the amount of data that needs to be checksummed. It will also allow much faster raid management code in general. The checksums are indexed by a key with a fixed objectid (a magic value in ctree.h) and offset set to the starting byte of the extent. This allows us to copy the checksum items into the fsync log tree directly (or any other tree), without having to invent a second format for them. Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-12-09 05:58:54 +08:00
csum_offset = (bytenr - found_key.offset) >>
fs_info->sectorsize_bits;
csums_in_item = btrfs_item_size(leaf, path->slots[0]);
csums_in_item /= csum_size;
if (csum_offset == csums_in_item) {
ret = -EFBIG;
goto fail;
} else if (csum_offset > csums_in_item) {
goto fail;
}
}
item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_csum_item);
item = (struct btrfs_csum_item *)((unsigned char *)item +
csum_offset * csum_size);
return item;
fail:
if (ret > 0)
ret = -ENOENT;
return ERR_PTR(ret);
}
int btrfs_lookup_file_extent(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct btrfs_path *path, u64 objectid,
u64 offset, int mod)
{
struct btrfs_key file_key;
int ins_len = mod < 0 ? -1 : 0;
int cow = mod != 0;
file_key.objectid = objectid;
file_key.offset = offset;
file_key.type = BTRFS_EXTENT_DATA_KEY;
return btrfs_search_slot(trans, root, &file_key, path, ins_len, cow);
}
btrfs: refactor btrfs_lookup_bio_sums to handle out-of-order bvecs Refactor btrfs_lookup_bio_sums() by: - Remove the @file_offset parameter There are two factors making the @file_offset parameter useless: * For csum lookup in csum tree, file offset makes no sense We only need disk_bytenr, which is unrelated to file_offset * page_offset (file offset) of each bvec is not contiguous. Pages can be added to the same bio as long as their on-disk bytenr is contiguous, meaning we could have pages at different file offsets in the same bio. Thus passing file_offset makes no sense any more. The only user of file_offset is for data reloc inode, we will use a new function, search_file_offset_in_bio(), to handle it. - Extract the csum tree lookup into search_csum_tree() The new function will handle the csum search in csum tree. The return value is the same as btrfs_find_ordered_sum(), returning the number of found sectors which have checksum. - Change how we do the main loop The only needed info from bio is: * the on-disk bytenr * the length After extracting the above info, we can do the search without bio at all, which makes the main loop much simpler: for (cur_disk_bytenr = orig_disk_bytenr; cur_disk_bytenr < orig_disk_bytenr + orig_len; cur_disk_bytenr += count * sectorsize) { /* Lookup csum tree */ count = search_csum_tree(fs_info, path, cur_disk_bytenr, search_len, csum_dst); if (!count) { /* Csum hole handling */ } } - Use single variable as the source to calculate all other offsets Instead of all different type of variables, we use only one main variable, cur_disk_bytenr, which represents the current disk bytenr. All involved values can be calculated from that variable, and all those variable will only be visible in the inner loop. The above refactoring makes btrfs_lookup_bio_sums() way more robust than it used to be, especially related to the file offset lookup. Now file_offset lookup is only related to data reloc inode, otherwise we don't need to bother file_offset at all. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-12-02 14:48:06 +08:00
/*
* Find checksums for logical bytenr range [disk_bytenr, disk_bytenr + len) and
* store the result to @dst.
btrfs: refactor btrfs_lookup_bio_sums to handle out-of-order bvecs Refactor btrfs_lookup_bio_sums() by: - Remove the @file_offset parameter There are two factors making the @file_offset parameter useless: * For csum lookup in csum tree, file offset makes no sense We only need disk_bytenr, which is unrelated to file_offset * page_offset (file offset) of each bvec is not contiguous. Pages can be added to the same bio as long as their on-disk bytenr is contiguous, meaning we could have pages at different file offsets in the same bio. Thus passing file_offset makes no sense any more. The only user of file_offset is for data reloc inode, we will use a new function, search_file_offset_in_bio(), to handle it. - Extract the csum tree lookup into search_csum_tree() The new function will handle the csum search in csum tree. The return value is the same as btrfs_find_ordered_sum(), returning the number of found sectors which have checksum. - Change how we do the main loop The only needed info from bio is: * the on-disk bytenr * the length After extracting the above info, we can do the search without bio at all, which makes the main loop much simpler: for (cur_disk_bytenr = orig_disk_bytenr; cur_disk_bytenr < orig_disk_bytenr + orig_len; cur_disk_bytenr += count * sectorsize) { /* Lookup csum tree */ count = search_csum_tree(fs_info, path, cur_disk_bytenr, search_len, csum_dst); if (!count) { /* Csum hole handling */ } } - Use single variable as the source to calculate all other offsets Instead of all different type of variables, we use only one main variable, cur_disk_bytenr, which represents the current disk bytenr. All involved values can be calculated from that variable, and all those variable will only be visible in the inner loop. The above refactoring makes btrfs_lookup_bio_sums() way more robust than it used to be, especially related to the file offset lookup. Now file_offset lookup is only related to data reloc inode, otherwise we don't need to bother file_offset at all. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-12-02 14:48:06 +08:00
*
* Return >0 for the number of sectors we found.
* Return 0 for the range [disk_bytenr, disk_bytenr + sectorsize) has no csum
* for it. Caller may want to try next sector until one range is hit.
* Return <0 for fatal error.
*/
static int search_csum_tree(struct btrfs_fs_info *fs_info,
struct btrfs_path *path, u64 disk_bytenr,
u64 len, u8 *dst)
{
struct btrfs_root *csum_root;
btrfs: refactor btrfs_lookup_bio_sums to handle out-of-order bvecs Refactor btrfs_lookup_bio_sums() by: - Remove the @file_offset parameter There are two factors making the @file_offset parameter useless: * For csum lookup in csum tree, file offset makes no sense We only need disk_bytenr, which is unrelated to file_offset * page_offset (file offset) of each bvec is not contiguous. Pages can be added to the same bio as long as their on-disk bytenr is contiguous, meaning we could have pages at different file offsets in the same bio. Thus passing file_offset makes no sense any more. The only user of file_offset is for data reloc inode, we will use a new function, search_file_offset_in_bio(), to handle it. - Extract the csum tree lookup into search_csum_tree() The new function will handle the csum search in csum tree. The return value is the same as btrfs_find_ordered_sum(), returning the number of found sectors which have checksum. - Change how we do the main loop The only needed info from bio is: * the on-disk bytenr * the length After extracting the above info, we can do the search without bio at all, which makes the main loop much simpler: for (cur_disk_bytenr = orig_disk_bytenr; cur_disk_bytenr < orig_disk_bytenr + orig_len; cur_disk_bytenr += count * sectorsize) { /* Lookup csum tree */ count = search_csum_tree(fs_info, path, cur_disk_bytenr, search_len, csum_dst); if (!count) { /* Csum hole handling */ } } - Use single variable as the source to calculate all other offsets Instead of all different type of variables, we use only one main variable, cur_disk_bytenr, which represents the current disk bytenr. All involved values can be calculated from that variable, and all those variable will only be visible in the inner loop. The above refactoring makes btrfs_lookup_bio_sums() way more robust than it used to be, especially related to the file offset lookup. Now file_offset lookup is only related to data reloc inode, otherwise we don't need to bother file_offset at all. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-12-02 14:48:06 +08:00
struct btrfs_csum_item *item = NULL;
struct btrfs_key key;
const u32 sectorsize = fs_info->sectorsize;
const u32 csum_size = fs_info->csum_size;
u32 itemsize;
int ret;
u64 csum_start;
u64 csum_len;
ASSERT(IS_ALIGNED(disk_bytenr, sectorsize) &&
IS_ALIGNED(len, sectorsize));
/* Check if the current csum item covers disk_bytenr */
if (path->nodes[0]) {
item = btrfs_item_ptr(path->nodes[0], path->slots[0],
struct btrfs_csum_item);
btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
itemsize = btrfs_item_size(path->nodes[0], path->slots[0]);
btrfs: refactor btrfs_lookup_bio_sums to handle out-of-order bvecs Refactor btrfs_lookup_bio_sums() by: - Remove the @file_offset parameter There are two factors making the @file_offset parameter useless: * For csum lookup in csum tree, file offset makes no sense We only need disk_bytenr, which is unrelated to file_offset * page_offset (file offset) of each bvec is not contiguous. Pages can be added to the same bio as long as their on-disk bytenr is contiguous, meaning we could have pages at different file offsets in the same bio. Thus passing file_offset makes no sense any more. The only user of file_offset is for data reloc inode, we will use a new function, search_file_offset_in_bio(), to handle it. - Extract the csum tree lookup into search_csum_tree() The new function will handle the csum search in csum tree. The return value is the same as btrfs_find_ordered_sum(), returning the number of found sectors which have checksum. - Change how we do the main loop The only needed info from bio is: * the on-disk bytenr * the length After extracting the above info, we can do the search without bio at all, which makes the main loop much simpler: for (cur_disk_bytenr = orig_disk_bytenr; cur_disk_bytenr < orig_disk_bytenr + orig_len; cur_disk_bytenr += count * sectorsize) { /* Lookup csum tree */ count = search_csum_tree(fs_info, path, cur_disk_bytenr, search_len, csum_dst); if (!count) { /* Csum hole handling */ } } - Use single variable as the source to calculate all other offsets Instead of all different type of variables, we use only one main variable, cur_disk_bytenr, which represents the current disk bytenr. All involved values can be calculated from that variable, and all those variable will only be visible in the inner loop. The above refactoring makes btrfs_lookup_bio_sums() way more robust than it used to be, especially related to the file offset lookup. Now file_offset lookup is only related to data reloc inode, otherwise we don't need to bother file_offset at all. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-12-02 14:48:06 +08:00
csum_start = key.offset;
csum_len = (itemsize / csum_size) * sectorsize;
if (in_range(disk_bytenr, csum_start, csum_len))
goto found;
}
/* Current item doesn't contain the desired range, search again */
btrfs_release_path(path);
csum_root = btrfs_csum_root(fs_info, disk_bytenr);
item = btrfs_lookup_csum(NULL, csum_root, path, disk_bytenr, 0);
btrfs: refactor btrfs_lookup_bio_sums to handle out-of-order bvecs Refactor btrfs_lookup_bio_sums() by: - Remove the @file_offset parameter There are two factors making the @file_offset parameter useless: * For csum lookup in csum tree, file offset makes no sense We only need disk_bytenr, which is unrelated to file_offset * page_offset (file offset) of each bvec is not contiguous. Pages can be added to the same bio as long as their on-disk bytenr is contiguous, meaning we could have pages at different file offsets in the same bio. Thus passing file_offset makes no sense any more. The only user of file_offset is for data reloc inode, we will use a new function, search_file_offset_in_bio(), to handle it. - Extract the csum tree lookup into search_csum_tree() The new function will handle the csum search in csum tree. The return value is the same as btrfs_find_ordered_sum(), returning the number of found sectors which have checksum. - Change how we do the main loop The only needed info from bio is: * the on-disk bytenr * the length After extracting the above info, we can do the search without bio at all, which makes the main loop much simpler: for (cur_disk_bytenr = orig_disk_bytenr; cur_disk_bytenr < orig_disk_bytenr + orig_len; cur_disk_bytenr += count * sectorsize) { /* Lookup csum tree */ count = search_csum_tree(fs_info, path, cur_disk_bytenr, search_len, csum_dst); if (!count) { /* Csum hole handling */ } } - Use single variable as the source to calculate all other offsets Instead of all different type of variables, we use only one main variable, cur_disk_bytenr, which represents the current disk bytenr. All involved values can be calculated from that variable, and all those variable will only be visible in the inner loop. The above refactoring makes btrfs_lookup_bio_sums() way more robust than it used to be, especially related to the file offset lookup. Now file_offset lookup is only related to data reloc inode, otherwise we don't need to bother file_offset at all. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-12-02 14:48:06 +08:00
if (IS_ERR(item)) {
ret = PTR_ERR(item);
goto out;
}
btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
itemsize = btrfs_item_size(path->nodes[0], path->slots[0]);
btrfs: refactor btrfs_lookup_bio_sums to handle out-of-order bvecs Refactor btrfs_lookup_bio_sums() by: - Remove the @file_offset parameter There are two factors making the @file_offset parameter useless: * For csum lookup in csum tree, file offset makes no sense We only need disk_bytenr, which is unrelated to file_offset * page_offset (file offset) of each bvec is not contiguous. Pages can be added to the same bio as long as their on-disk bytenr is contiguous, meaning we could have pages at different file offsets in the same bio. Thus passing file_offset makes no sense any more. The only user of file_offset is for data reloc inode, we will use a new function, search_file_offset_in_bio(), to handle it. - Extract the csum tree lookup into search_csum_tree() The new function will handle the csum search in csum tree. The return value is the same as btrfs_find_ordered_sum(), returning the number of found sectors which have checksum. - Change how we do the main loop The only needed info from bio is: * the on-disk bytenr * the length After extracting the above info, we can do the search without bio at all, which makes the main loop much simpler: for (cur_disk_bytenr = orig_disk_bytenr; cur_disk_bytenr < orig_disk_bytenr + orig_len; cur_disk_bytenr += count * sectorsize) { /* Lookup csum tree */ count = search_csum_tree(fs_info, path, cur_disk_bytenr, search_len, csum_dst); if (!count) { /* Csum hole handling */ } } - Use single variable as the source to calculate all other offsets Instead of all different type of variables, we use only one main variable, cur_disk_bytenr, which represents the current disk bytenr. All involved values can be calculated from that variable, and all those variable will only be visible in the inner loop. The above refactoring makes btrfs_lookup_bio_sums() way more robust than it used to be, especially related to the file offset lookup. Now file_offset lookup is only related to data reloc inode, otherwise we don't need to bother file_offset at all. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-12-02 14:48:06 +08:00
csum_start = key.offset;
csum_len = (itemsize / csum_size) * sectorsize;
ASSERT(in_range(disk_bytenr, csum_start, csum_len));
found:
ret = (min(csum_start + csum_len, disk_bytenr + len) -
disk_bytenr) >> fs_info->sectorsize_bits;
read_extent_buffer(path->nodes[0], dst, (unsigned long)item,
ret * csum_size);
out:
if (ret == -ENOENT || ret == -EFBIG)
btrfs: refactor btrfs_lookup_bio_sums to handle out-of-order bvecs Refactor btrfs_lookup_bio_sums() by: - Remove the @file_offset parameter There are two factors making the @file_offset parameter useless: * For csum lookup in csum tree, file offset makes no sense We only need disk_bytenr, which is unrelated to file_offset * page_offset (file offset) of each bvec is not contiguous. Pages can be added to the same bio as long as their on-disk bytenr is contiguous, meaning we could have pages at different file offsets in the same bio. Thus passing file_offset makes no sense any more. The only user of file_offset is for data reloc inode, we will use a new function, search_file_offset_in_bio(), to handle it. - Extract the csum tree lookup into search_csum_tree() The new function will handle the csum search in csum tree. The return value is the same as btrfs_find_ordered_sum(), returning the number of found sectors which have checksum. - Change how we do the main loop The only needed info from bio is: * the on-disk bytenr * the length After extracting the above info, we can do the search without bio at all, which makes the main loop much simpler: for (cur_disk_bytenr = orig_disk_bytenr; cur_disk_bytenr < orig_disk_bytenr + orig_len; cur_disk_bytenr += count * sectorsize) { /* Lookup csum tree */ count = search_csum_tree(fs_info, path, cur_disk_bytenr, search_len, csum_dst); if (!count) { /* Csum hole handling */ } } - Use single variable as the source to calculate all other offsets Instead of all different type of variables, we use only one main variable, cur_disk_bytenr, which represents the current disk bytenr. All involved values can be calculated from that variable, and all those variable will only be visible in the inner loop. The above refactoring makes btrfs_lookup_bio_sums() way more robust than it used to be, especially related to the file offset lookup. Now file_offset lookup is only related to data reloc inode, otherwise we don't need to bother file_offset at all. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-12-02 14:48:06 +08:00
ret = 0;
return ret;
}
/*
* Locate the file_offset of @cur_disk_bytenr of a @bio.
*
* Bio of btrfs represents read range of
* [bi_sector << 9, bi_sector << 9 + bi_size).
* Knowing this, we can iterate through each bvec to locate the page belong to
* @cur_disk_bytenr and get the file offset.
*
* @inode is used to determine if the bvec page really belongs to @inode.
*
* Return 0 if we can't find the file offset
* Return >0 if we find the file offset and restore it to @file_offset_ret
*/
static int search_file_offset_in_bio(struct bio *bio, struct inode *inode,
u64 disk_bytenr, u64 *file_offset_ret)
{
struct bvec_iter iter;
struct bio_vec bvec;
u64 cur = bio->bi_iter.bi_sector << SECTOR_SHIFT;
int ret = 0;
bio_for_each_segment(bvec, bio, iter) {
struct page *page = bvec.bv_page;
if (cur > disk_bytenr)
break;
if (cur + bvec.bv_len <= disk_bytenr) {
cur += bvec.bv_len;
continue;
}
ASSERT(in_range(disk_bytenr, cur, bvec.bv_len));
if (page->mapping && page->mapping->host &&
page->mapping->host == inode) {
ret = 1;
*file_offset_ret = page_offset(page) + bvec.bv_offset +
disk_bytenr - cur;
break;
}
}
return ret;
}
/*
btrfs: refactor btrfs_lookup_bio_sums to handle out-of-order bvecs Refactor btrfs_lookup_bio_sums() by: - Remove the @file_offset parameter There are two factors making the @file_offset parameter useless: * For csum lookup in csum tree, file offset makes no sense We only need disk_bytenr, which is unrelated to file_offset * page_offset (file offset) of each bvec is not contiguous. Pages can be added to the same bio as long as their on-disk bytenr is contiguous, meaning we could have pages at different file offsets in the same bio. Thus passing file_offset makes no sense any more. The only user of file_offset is for data reloc inode, we will use a new function, search_file_offset_in_bio(), to handle it. - Extract the csum tree lookup into search_csum_tree() The new function will handle the csum search in csum tree. The return value is the same as btrfs_find_ordered_sum(), returning the number of found sectors which have checksum. - Change how we do the main loop The only needed info from bio is: * the on-disk bytenr * the length After extracting the above info, we can do the search without bio at all, which makes the main loop much simpler: for (cur_disk_bytenr = orig_disk_bytenr; cur_disk_bytenr < orig_disk_bytenr + orig_len; cur_disk_bytenr += count * sectorsize) { /* Lookup csum tree */ count = search_csum_tree(fs_info, path, cur_disk_bytenr, search_len, csum_dst); if (!count) { /* Csum hole handling */ } } - Use single variable as the source to calculate all other offsets Instead of all different type of variables, we use only one main variable, cur_disk_bytenr, which represents the current disk bytenr. All involved values can be calculated from that variable, and all those variable will only be visible in the inner loop. The above refactoring makes btrfs_lookup_bio_sums() way more robust than it used to be, especially related to the file offset lookup. Now file_offset lookup is only related to data reloc inode, otherwise we don't need to bother file_offset at all. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-12-02 14:48:06 +08:00
* Lookup the checksum for the read bio in csum tree.
*
* @inode: inode that the bio is for.
* @bio: bio to look up.
* @dst: Buffer of size nblocks * btrfs_super_csum_size() used to return
* checksum (nblocks = bio->bi_iter.bi_size / fs_info->sectorsize). If
* NULL, the checksum buffer is allocated and returned in
* btrfs_bio(bio)->csum instead.
*
* Return: BLK_STS_RESOURCE if allocating memory fails, BLK_STS_OK otherwise.
*/
btrfs: refactor btrfs_lookup_bio_sums to handle out-of-order bvecs Refactor btrfs_lookup_bio_sums() by: - Remove the @file_offset parameter There are two factors making the @file_offset parameter useless: * For csum lookup in csum tree, file offset makes no sense We only need disk_bytenr, which is unrelated to file_offset * page_offset (file offset) of each bvec is not contiguous. Pages can be added to the same bio as long as their on-disk bytenr is contiguous, meaning we could have pages at different file offsets in the same bio. Thus passing file_offset makes no sense any more. The only user of file_offset is for data reloc inode, we will use a new function, search_file_offset_in_bio(), to handle it. - Extract the csum tree lookup into search_csum_tree() The new function will handle the csum search in csum tree. The return value is the same as btrfs_find_ordered_sum(), returning the number of found sectors which have checksum. - Change how we do the main loop The only needed info from bio is: * the on-disk bytenr * the length After extracting the above info, we can do the search without bio at all, which makes the main loop much simpler: for (cur_disk_bytenr = orig_disk_bytenr; cur_disk_bytenr < orig_disk_bytenr + orig_len; cur_disk_bytenr += count * sectorsize) { /* Lookup csum tree */ count = search_csum_tree(fs_info, path, cur_disk_bytenr, search_len, csum_dst); if (!count) { /* Csum hole handling */ } } - Use single variable as the source to calculate all other offsets Instead of all different type of variables, we use only one main variable, cur_disk_bytenr, which represents the current disk bytenr. All involved values can be calculated from that variable, and all those variable will only be visible in the inner loop. The above refactoring makes btrfs_lookup_bio_sums() way more robust than it used to be, especially related to the file offset lookup. Now file_offset lookup is only related to data reloc inode, otherwise we don't need to bother file_offset at all. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-12-02 14:48:06 +08:00
blk_status_t btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio, u8 *dst)
{
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
struct btrfs_bio *bbio = NULL;
struct btrfs_path *path;
btrfs: refactor btrfs_lookup_bio_sums to handle out-of-order bvecs Refactor btrfs_lookup_bio_sums() by: - Remove the @file_offset parameter There are two factors making the @file_offset parameter useless: * For csum lookup in csum tree, file offset makes no sense We only need disk_bytenr, which is unrelated to file_offset * page_offset (file offset) of each bvec is not contiguous. Pages can be added to the same bio as long as their on-disk bytenr is contiguous, meaning we could have pages at different file offsets in the same bio. Thus passing file_offset makes no sense any more. The only user of file_offset is for data reloc inode, we will use a new function, search_file_offset_in_bio(), to handle it. - Extract the csum tree lookup into search_csum_tree() The new function will handle the csum search in csum tree. The return value is the same as btrfs_find_ordered_sum(), returning the number of found sectors which have checksum. - Change how we do the main loop The only needed info from bio is: * the on-disk bytenr * the length After extracting the above info, we can do the search without bio at all, which makes the main loop much simpler: for (cur_disk_bytenr = orig_disk_bytenr; cur_disk_bytenr < orig_disk_bytenr + orig_len; cur_disk_bytenr += count * sectorsize) { /* Lookup csum tree */ count = search_csum_tree(fs_info, path, cur_disk_bytenr, search_len, csum_dst); if (!count) { /* Csum hole handling */ } } - Use single variable as the source to calculate all other offsets Instead of all different type of variables, we use only one main variable, cur_disk_bytenr, which represents the current disk bytenr. All involved values can be calculated from that variable, and all those variable will only be visible in the inner loop. The above refactoring makes btrfs_lookup_bio_sums() way more robust than it used to be, especially related to the file offset lookup. Now file_offset lookup is only related to data reloc inode, otherwise we don't need to bother file_offset at all. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-12-02 14:48:06 +08:00
const u32 sectorsize = fs_info->sectorsize;
const u32 csum_size = fs_info->csum_size;
u32 orig_len = bio->bi_iter.bi_size;
u64 orig_disk_bytenr = bio->bi_iter.bi_sector << SECTOR_SHIFT;
u64 cur_disk_bytenr;
u8 *csum;
btrfs: refactor btrfs_lookup_bio_sums to handle out-of-order bvecs Refactor btrfs_lookup_bio_sums() by: - Remove the @file_offset parameter There are two factors making the @file_offset parameter useless: * For csum lookup in csum tree, file offset makes no sense We only need disk_bytenr, which is unrelated to file_offset * page_offset (file offset) of each bvec is not contiguous. Pages can be added to the same bio as long as their on-disk bytenr is contiguous, meaning we could have pages at different file offsets in the same bio. Thus passing file_offset makes no sense any more. The only user of file_offset is for data reloc inode, we will use a new function, search_file_offset_in_bio(), to handle it. - Extract the csum tree lookup into search_csum_tree() The new function will handle the csum search in csum tree. The return value is the same as btrfs_find_ordered_sum(), returning the number of found sectors which have checksum. - Change how we do the main loop The only needed info from bio is: * the on-disk bytenr * the length After extracting the above info, we can do the search without bio at all, which makes the main loop much simpler: for (cur_disk_bytenr = orig_disk_bytenr; cur_disk_bytenr < orig_disk_bytenr + orig_len; cur_disk_bytenr += count * sectorsize) { /* Lookup csum tree */ count = search_csum_tree(fs_info, path, cur_disk_bytenr, search_len, csum_dst); if (!count) { /* Csum hole handling */ } } - Use single variable as the source to calculate all other offsets Instead of all different type of variables, we use only one main variable, cur_disk_bytenr, which represents the current disk bytenr. All involved values can be calculated from that variable, and all those variable will only be visible in the inner loop. The above refactoring makes btrfs_lookup_bio_sums() way more robust than it used to be, especially related to the file offset lookup. Now file_offset lookup is only related to data reloc inode, otherwise we don't need to bother file_offset at all. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-12-02 14:48:06 +08:00
const unsigned int nblocks = orig_len >> fs_info->sectorsize_bits;
int count = 0;
blk_status_t ret = BLK_STS_OK;
if ((BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM) ||
test_bit(BTRFS_FS_STATE_NO_CSUMS, &fs_info->fs_state))
return BLK_STS_OK;
/*
* This function is only called for read bio.
*
* This means two things:
* - All our csums should only be in csum tree
* No ordered extents csums, as ordered extents are only for write
* path.
btrfs: refactor btrfs_lookup_bio_sums to handle out-of-order bvecs Refactor btrfs_lookup_bio_sums() by: - Remove the @file_offset parameter There are two factors making the @file_offset parameter useless: * For csum lookup in csum tree, file offset makes no sense We only need disk_bytenr, which is unrelated to file_offset * page_offset (file offset) of each bvec is not contiguous. Pages can be added to the same bio as long as their on-disk bytenr is contiguous, meaning we could have pages at different file offsets in the same bio. Thus passing file_offset makes no sense any more. The only user of file_offset is for data reloc inode, we will use a new function, search_file_offset_in_bio(), to handle it. - Extract the csum tree lookup into search_csum_tree() The new function will handle the csum search in csum tree. The return value is the same as btrfs_find_ordered_sum(), returning the number of found sectors which have checksum. - Change how we do the main loop The only needed info from bio is: * the on-disk bytenr * the length After extracting the above info, we can do the search without bio at all, which makes the main loop much simpler: for (cur_disk_bytenr = orig_disk_bytenr; cur_disk_bytenr < orig_disk_bytenr + orig_len; cur_disk_bytenr += count * sectorsize) { /* Lookup csum tree */ count = search_csum_tree(fs_info, path, cur_disk_bytenr, search_len, csum_dst); if (!count) { /* Csum hole handling */ } } - Use single variable as the source to calculate all other offsets Instead of all different type of variables, we use only one main variable, cur_disk_bytenr, which represents the current disk bytenr. All involved values can be calculated from that variable, and all those variable will only be visible in the inner loop. The above refactoring makes btrfs_lookup_bio_sums() way more robust than it used to be, especially related to the file offset lookup. Now file_offset lookup is only related to data reloc inode, otherwise we don't need to bother file_offset at all. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-12-02 14:48:06 +08:00
* - No need to bother any other info from bvec
* Since we're looking up csums, the only important info is the
* disk_bytenr and the length, which can be extracted from bi_iter
* directly.
*/
ASSERT(bio_op(bio) == REQ_OP_READ);
path = btrfs_alloc_path();
if (!path)
return BLK_STS_RESOURCE;
if (!dst) {
bbio = btrfs_bio(bio);
if (nblocks * csum_size > BTRFS_BIO_INLINE_CSUM_SIZE) {
bbio->csum = kmalloc_array(nblocks, csum_size, GFP_NOFS);
if (!bbio->csum) {
btrfs_free_path(path);
return BLK_STS_RESOURCE;
}
} else {
bbio->csum = bbio->csum_inline;
}
csum = bbio->csum;
} else {
csum = dst;
}
/*
* If requested number of sectors is larger than one leaf can contain,
* kick the readahead for csum tree.
*/
if (nblocks > fs_info->csums_per_leaf)
path->reada = READA_FORWARD;
/*
* the free space stuff is only read when it hasn't been
* updated in the current transaction. So, we can safely
* read from the commit root and sidestep a nasty deadlock
* between reading the free space cache and updating the csum tree.
*/
if (btrfs_is_free_space_inode(BTRFS_I(inode))) {
path->search_commit_root = 1;
path->skip_locking = 1;
}
btrfs: refactor btrfs_lookup_bio_sums to handle out-of-order bvecs Refactor btrfs_lookup_bio_sums() by: - Remove the @file_offset parameter There are two factors making the @file_offset parameter useless: * For csum lookup in csum tree, file offset makes no sense We only need disk_bytenr, which is unrelated to file_offset * page_offset (file offset) of each bvec is not contiguous. Pages can be added to the same bio as long as their on-disk bytenr is contiguous, meaning we could have pages at different file offsets in the same bio. Thus passing file_offset makes no sense any more. The only user of file_offset is for data reloc inode, we will use a new function, search_file_offset_in_bio(), to handle it. - Extract the csum tree lookup into search_csum_tree() The new function will handle the csum search in csum tree. The return value is the same as btrfs_find_ordered_sum(), returning the number of found sectors which have checksum. - Change how we do the main loop The only needed info from bio is: * the on-disk bytenr * the length After extracting the above info, we can do the search without bio at all, which makes the main loop much simpler: for (cur_disk_bytenr = orig_disk_bytenr; cur_disk_bytenr < orig_disk_bytenr + orig_len; cur_disk_bytenr += count * sectorsize) { /* Lookup csum tree */ count = search_csum_tree(fs_info, path, cur_disk_bytenr, search_len, csum_dst); if (!count) { /* Csum hole handling */ } } - Use single variable as the source to calculate all other offsets Instead of all different type of variables, we use only one main variable, cur_disk_bytenr, which represents the current disk bytenr. All involved values can be calculated from that variable, and all those variable will only be visible in the inner loop. The above refactoring makes btrfs_lookup_bio_sums() way more robust than it used to be, especially related to the file offset lookup. Now file_offset lookup is only related to data reloc inode, otherwise we don't need to bother file_offset at all. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-12-02 14:48:06 +08:00
for (cur_disk_bytenr = orig_disk_bytenr;
cur_disk_bytenr < orig_disk_bytenr + orig_len;
cur_disk_bytenr += (count * sectorsize)) {
u64 search_len = orig_disk_bytenr + orig_len - cur_disk_bytenr;
unsigned int sector_offset;
u8 *csum_dst;
/*
btrfs: refactor btrfs_lookup_bio_sums to handle out-of-order bvecs Refactor btrfs_lookup_bio_sums() by: - Remove the @file_offset parameter There are two factors making the @file_offset parameter useless: * For csum lookup in csum tree, file offset makes no sense We only need disk_bytenr, which is unrelated to file_offset * page_offset (file offset) of each bvec is not contiguous. Pages can be added to the same bio as long as their on-disk bytenr is contiguous, meaning we could have pages at different file offsets in the same bio. Thus passing file_offset makes no sense any more. The only user of file_offset is for data reloc inode, we will use a new function, search_file_offset_in_bio(), to handle it. - Extract the csum tree lookup into search_csum_tree() The new function will handle the csum search in csum tree. The return value is the same as btrfs_find_ordered_sum(), returning the number of found sectors which have checksum. - Change how we do the main loop The only needed info from bio is: * the on-disk bytenr * the length After extracting the above info, we can do the search without bio at all, which makes the main loop much simpler: for (cur_disk_bytenr = orig_disk_bytenr; cur_disk_bytenr < orig_disk_bytenr + orig_len; cur_disk_bytenr += count * sectorsize) { /* Lookup csum tree */ count = search_csum_tree(fs_info, path, cur_disk_bytenr, search_len, csum_dst); if (!count) { /* Csum hole handling */ } } - Use single variable as the source to calculate all other offsets Instead of all different type of variables, we use only one main variable, cur_disk_bytenr, which represents the current disk bytenr. All involved values can be calculated from that variable, and all those variable will only be visible in the inner loop. The above refactoring makes btrfs_lookup_bio_sums() way more robust than it used to be, especially related to the file offset lookup. Now file_offset lookup is only related to data reloc inode, otherwise we don't need to bother file_offset at all. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-12-02 14:48:06 +08:00
* Although both cur_disk_bytenr and orig_disk_bytenr is u64,
* we're calculating the offset to the bio start.
*
* Bio size is limited to UINT_MAX, thus unsigned int is large
* enough to contain the raw result, not to mention the right
* shifted result.
*/
btrfs: refactor btrfs_lookup_bio_sums to handle out-of-order bvecs Refactor btrfs_lookup_bio_sums() by: - Remove the @file_offset parameter There are two factors making the @file_offset parameter useless: * For csum lookup in csum tree, file offset makes no sense We only need disk_bytenr, which is unrelated to file_offset * page_offset (file offset) of each bvec is not contiguous. Pages can be added to the same bio as long as their on-disk bytenr is contiguous, meaning we could have pages at different file offsets in the same bio. Thus passing file_offset makes no sense any more. The only user of file_offset is for data reloc inode, we will use a new function, search_file_offset_in_bio(), to handle it. - Extract the csum tree lookup into search_csum_tree() The new function will handle the csum search in csum tree. The return value is the same as btrfs_find_ordered_sum(), returning the number of found sectors which have checksum. - Change how we do the main loop The only needed info from bio is: * the on-disk bytenr * the length After extracting the above info, we can do the search without bio at all, which makes the main loop much simpler: for (cur_disk_bytenr = orig_disk_bytenr; cur_disk_bytenr < orig_disk_bytenr + orig_len; cur_disk_bytenr += count * sectorsize) { /* Lookup csum tree */ count = search_csum_tree(fs_info, path, cur_disk_bytenr, search_len, csum_dst); if (!count) { /* Csum hole handling */ } } - Use single variable as the source to calculate all other offsets Instead of all different type of variables, we use only one main variable, cur_disk_bytenr, which represents the current disk bytenr. All involved values can be calculated from that variable, and all those variable will only be visible in the inner loop. The above refactoring makes btrfs_lookup_bio_sums() way more robust than it used to be, especially related to the file offset lookup. Now file_offset lookup is only related to data reloc inode, otherwise we don't need to bother file_offset at all. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-12-02 14:48:06 +08:00
ASSERT(cur_disk_bytenr - orig_disk_bytenr < UINT_MAX);
sector_offset = (cur_disk_bytenr - orig_disk_bytenr) >>
fs_info->sectorsize_bits;
csum_dst = csum + sector_offset * csum_size;
count = search_csum_tree(fs_info, path, cur_disk_bytenr,
search_len, csum_dst);
if (count < 0) {
ret = errno_to_blk_status(count);
if (bbio)
btrfs_bio_free_csum(bbio);
break;
}
/*
* We didn't find a csum for this range. We need to make sure
* we complain loudly about this, because we are not NODATASUM.
*
* However for the DATA_RELOC inode we could potentially be
* relocating data extents for a NODATASUM inode, so the inode
* itself won't be marked with NODATASUM, but the extent we're
* copying is in fact NODATASUM. If we don't find a csum we
* assume this is the case.
*/
if (count == 0) {
btrfs: refactor btrfs_lookup_bio_sums to handle out-of-order bvecs Refactor btrfs_lookup_bio_sums() by: - Remove the @file_offset parameter There are two factors making the @file_offset parameter useless: * For csum lookup in csum tree, file offset makes no sense We only need disk_bytenr, which is unrelated to file_offset * page_offset (file offset) of each bvec is not contiguous. Pages can be added to the same bio as long as their on-disk bytenr is contiguous, meaning we could have pages at different file offsets in the same bio. Thus passing file_offset makes no sense any more. The only user of file_offset is for data reloc inode, we will use a new function, search_file_offset_in_bio(), to handle it. - Extract the csum tree lookup into search_csum_tree() The new function will handle the csum search in csum tree. The return value is the same as btrfs_find_ordered_sum(), returning the number of found sectors which have checksum. - Change how we do the main loop The only needed info from bio is: * the on-disk bytenr * the length After extracting the above info, we can do the search without bio at all, which makes the main loop much simpler: for (cur_disk_bytenr = orig_disk_bytenr; cur_disk_bytenr < orig_disk_bytenr + orig_len; cur_disk_bytenr += count * sectorsize) { /* Lookup csum tree */ count = search_csum_tree(fs_info, path, cur_disk_bytenr, search_len, csum_dst); if (!count) { /* Csum hole handling */ } } - Use single variable as the source to calculate all other offsets Instead of all different type of variables, we use only one main variable, cur_disk_bytenr, which represents the current disk bytenr. All involved values can be calculated from that variable, and all those variable will only be visible in the inner loop. The above refactoring makes btrfs_lookup_bio_sums() way more robust than it used to be, especially related to the file offset lookup. Now file_offset lookup is only related to data reloc inode, otherwise we don't need to bother file_offset at all. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-12-02 14:48:06 +08:00
memset(csum_dst, 0, csum_size);
count = 1;
if (BTRFS_I(inode)->root->root_key.objectid ==
BTRFS_DATA_RELOC_TREE_OBJECTID) {
u64 file_offset;
int ret;
ret = search_file_offset_in_bio(bio, inode,
cur_disk_bytenr, &file_offset);
if (ret)
set_extent_bits(io_tree, file_offset,
file_offset + sectorsize - 1,
EXTENT_NODATASUM);
} else {
btrfs_warn_rl(fs_info,
"csum hole found for disk bytenr range [%llu, %llu)",
cur_disk_bytenr, cur_disk_bytenr + sectorsize);
}
}
}
btrfs_free_path(path);
return ret;
}
int btrfs_lookup_csums_list(struct btrfs_root *root, u64 start, u64 end,
struct list_head *list, int search_commit,
bool nowait)
{
struct btrfs_fs_info *fs_info = root->fs_info;
struct btrfs_key key;
struct btrfs_path *path;
struct extent_buffer *leaf;
struct btrfs_ordered_sum *sums;
struct btrfs_csum_item *item;
LIST_HEAD(tmplist);
int ret;
ASSERT(IS_ALIGNED(start, fs_info->sectorsize) &&
IS_ALIGNED(end + 1, fs_info->sectorsize));
path = btrfs_alloc_path();
if (!path)
return -ENOMEM;
path->nowait = nowait;
if (search_commit) {
path->skip_locking = 1;
path->reada = READA_FORWARD;
path->search_commit_root = 1;
}
key.objectid = BTRFS_EXTENT_CSUM_OBJECTID;
key.offset = start;
key.type = BTRFS_EXTENT_CSUM_KEY;
ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
if (ret < 0)
goto fail;
if (ret > 0 && path->slots[0] > 0) {
leaf = path->nodes[0];
btrfs_item_key_to_cpu(leaf, &key, path->slots[0] - 1);
/*
* There are two cases we can hit here for the previous csum
* item:
*
* |<- search range ->|
* |<- csum item ->|
*
* Or
* |<- search range ->|
* |<- csum item ->|
*
* Check if the previous csum item covers the leading part of
* the search range. If so we have to start from previous csum
* item.
*/
if (key.objectid == BTRFS_EXTENT_CSUM_OBJECTID &&
key.type == BTRFS_EXTENT_CSUM_KEY) {
if (bytes_to_csum_size(fs_info, start - key.offset) <
btrfs_item_size(leaf, path->slots[0] - 1))
path->slots[0]--;
}
}
while (start <= end) {
u64 csum_end;
leaf = path->nodes[0];
if (path->slots[0] >= btrfs_header_nritems(leaf)) {
ret = btrfs_next_leaf(root, path);
if (ret < 0)
goto fail;
if (ret > 0)
break;
leaf = path->nodes[0];
}
btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
if (key.objectid != BTRFS_EXTENT_CSUM_OBJECTID ||
key.type != BTRFS_EXTENT_CSUM_KEY ||
key.offset > end)
break;
if (key.offset > start)
start = key.offset;
csum_end = key.offset + csum_size_to_bytes(fs_info,
btrfs_item_size(leaf, path->slots[0]));
if (csum_end <= start) {
path->slots[0]++;
continue;
}
csum_end = min(csum_end, end + 1);
item = btrfs_item_ptr(path->nodes[0], path->slots[0],
struct btrfs_csum_item);
while (start < csum_end) {
unsigned long offset;
size_t size;
size = min_t(size_t, csum_end - start,
max_ordered_sum_bytes(fs_info));
sums = kzalloc(btrfs_ordered_sum_size(fs_info, size),
GFP_NOFS);
if (!sums) {
ret = -ENOMEM;
goto fail;
}
sums->bytenr = start;
sums->len = (int)size;
offset = bytes_to_csum_size(fs_info, start - key.offset);
read_extent_buffer(path->nodes[0],
sums->sums,
((unsigned long)item) + offset,
bytes_to_csum_size(fs_info, size));
start += size;
list_add_tail(&sums->list, &tmplist);
}
path->slots[0]++;
}
ret = 0;
fail:
while (ret < 0 && !list_empty(&tmplist)) {
sums = list_entry(tmplist.next, struct btrfs_ordered_sum, list);
list_del(&sums->list);
kfree(sums);
}
list_splice_tail(&tmplist, list);
btrfs_free_path(path);
return ret;
}
/*
* Do the same work as btrfs_lookup_csums_list(), the difference is in how
* we return the result.
*
* This version will set the corresponding bits in @csum_bitmap to represent
* that there is a csum found.
* Each bit represents a sector. Thus caller should ensure @csum_buf passed
* in is large enough to contain all csums.
*/
int btrfs_lookup_csums_bitmap(struct btrfs_root *root, u64 start, u64 end,
u8 *csum_buf, unsigned long *csum_bitmap)
{
struct btrfs_fs_info *fs_info = root->fs_info;
struct btrfs_key key;
struct btrfs_path *path;
struct extent_buffer *leaf;
struct btrfs_csum_item *item;
const u64 orig_start = start;
int ret;
ASSERT(IS_ALIGNED(start, fs_info->sectorsize) &&
IS_ALIGNED(end + 1, fs_info->sectorsize));
path = btrfs_alloc_path();
if (!path)
return -ENOMEM;
key.objectid = BTRFS_EXTENT_CSUM_OBJECTID;
key.type = BTRFS_EXTENT_CSUM_KEY;
key.offset = start;
ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
if (ret < 0)
goto fail;
if (ret > 0 && path->slots[0] > 0) {
leaf = path->nodes[0];
btrfs_item_key_to_cpu(leaf, &key, path->slots[0] - 1);
/*
* There are two cases we can hit here for the previous csum
* item:
*
* |<- search range ->|
* |<- csum item ->|
*
* Or
* |<- search range ->|
* |<- csum item ->|
*
* Check if the previous csum item covers the leading part of
* the search range. If so we have to start from previous csum
* item.
*/
if (key.objectid == BTRFS_EXTENT_CSUM_OBJECTID &&
key.type == BTRFS_EXTENT_CSUM_KEY) {
if (bytes_to_csum_size(fs_info, start - key.offset) <
btrfs_item_size(leaf, path->slots[0] - 1))
path->slots[0]--;
}
}
while (start <= end) {
u64 csum_end;
leaf = path->nodes[0];
if (path->slots[0] >= btrfs_header_nritems(leaf)) {
ret = btrfs_next_leaf(root, path);
if (ret < 0)
goto fail;
if (ret > 0)
break;
leaf = path->nodes[0];
}
btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
if (key.objectid != BTRFS_EXTENT_CSUM_OBJECTID ||
key.type != BTRFS_EXTENT_CSUM_KEY ||
key.offset > end)
break;
if (key.offset > start)
start = key.offset;
csum_end = key.offset + csum_size_to_bytes(fs_info,
btrfs_item_size(leaf, path->slots[0]));
if (csum_end <= start) {
path->slots[0]++;
continue;
}
csum_end = min(csum_end, end + 1);
item = btrfs_item_ptr(path->nodes[0], path->slots[0],
struct btrfs_csum_item);
while (start < csum_end) {
unsigned long offset;
size_t size;
u8 *csum_dest = csum_buf + bytes_to_csum_size(fs_info,
start - orig_start);
size = min_t(size_t, csum_end - start, end + 1 - start);
offset = bytes_to_csum_size(fs_info, start - key.offset);
read_extent_buffer(path->nodes[0], csum_dest,
((unsigned long)item) + offset,
bytes_to_csum_size(fs_info, size));
bitmap_set(csum_bitmap,
(start - orig_start) >> fs_info->sectorsize_bits,
size >> fs_info->sectorsize_bits);
start += size;
}
path->slots[0]++;
}
ret = 0;
fail:
btrfs_free_path(path);
return ret;
}
/*
* Calculate checksums of the data contained inside a bio.
*
* @inode: Owner of the data inside the bio
* @bio: Contains the data to be checksummed
* @offset: If (u64)-1, @bio may contain discontiguous bio vecs, so the
* file offsets are determined from the page offsets in the bio.
* Otherwise, this is the starting file offset of the bio vecs in
* @bio, which must be contiguous.
* @one_ordered: If true, @bio only refers to one ordered extent.
*/
blk_status_t btrfs_csum_one_bio(struct btrfs_inode *inode, struct bio *bio,
u64 offset, bool one_ordered)
{
struct btrfs_fs_info *fs_info = inode->root->fs_info;
SHASH_DESC_ON_STACK(shash, fs_info->csum_shash);
struct btrfs_ordered_sum *sums;
struct btrfs_ordered_extent *ordered = NULL;
const bool use_page_offsets = (offset == (u64)-1);
char *data;
struct bvec_iter iter;
struct bio_vec bvec;
int index;
unsigned int blockcount;
unsigned long total_bytes = 0;
unsigned long this_sum_bytes = 0;
int i;
unsigned nofs_flag;
nofs_flag = memalloc_nofs_save();
sums = kvzalloc(btrfs_ordered_sum_size(fs_info, bio->bi_iter.bi_size),
GFP_KERNEL);
memalloc_nofs_restore(nofs_flag);
if (!sums)
return BLK_STS_RESOURCE;
block: Abstract out bvec iterator Immutable biovecs are going to require an explicit iterator. To implement immutable bvecs, a later patch is going to add a bi_bvec_done member to this struct; for now, this patch effectively just renames things. Signed-off-by: Kent Overstreet <kmo@daterainc.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: "Ed L. Cashin" <ecashin@coraid.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Lars Ellenberg <drbd-dev@lists.linbit.com> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Matthew Wilcox <willy@linux.intel.com> Cc: Geoff Levand <geoff@infradead.org> Cc: Yehuda Sadeh <yehuda@inktank.com> Cc: Sage Weil <sage@inktank.com> Cc: Alex Elder <elder@inktank.com> Cc: ceph-devel@vger.kernel.org Cc: Joshua Morris <josh.h.morris@us.ibm.com> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Neil Brown <neilb@suse.de> Cc: Alasdair Kergon <agk@redhat.com> Cc: Mike Snitzer <snitzer@redhat.com> Cc: dm-devel@redhat.com Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: linux390@de.ibm.com Cc: Boaz Harrosh <bharrosh@panasas.com> Cc: Benny Halevy <bhalevy@tonian.com> Cc: "James E.J. Bottomley" <JBottomley@parallels.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: "Nicholas A. Bellinger" <nab@linux-iscsi.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Chris Mason <chris.mason@fusionio.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Jaegeuk Kim <jaegeuk.kim@samsung.com> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Dave Kleikamp <shaggy@kernel.org> Cc: Joern Engel <joern@logfs.org> Cc: Prasad Joshi <prasadjoshi.linux@gmail.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Cc: KONISHI Ryusuke <konishi.ryusuke@lab.ntt.co.jp> Cc: Mark Fasheh <mfasheh@suse.com> Cc: Joel Becker <jlbec@evilplan.org> Cc: Ben Myers <bpm@sgi.com> Cc: xfs@oss.sgi.com Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Len Brown <len.brown@intel.com> Cc: Pavel Machek <pavel@ucw.cz> Cc: "Rafael J. Wysocki" <rjw@sisk.pl> Cc: Herton Ronaldo Krzesinski <herton.krzesinski@canonical.com> Cc: Ben Hutchings <ben@decadent.org.uk> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Guo Chao <yan@linux.vnet.ibm.com> Cc: Tejun Heo <tj@kernel.org> Cc: Asai Thambi S P <asamymuthupa@micron.com> Cc: Selvan Mani <smani@micron.com> Cc: Sam Bradshaw <sbradshaw@micron.com> Cc: Wei Yongjun <yongjun_wei@trendmicro.com.cn> Cc: "Roger Pau Monné" <roger.pau@citrix.com> Cc: Jan Beulich <jbeulich@suse.com> Cc: Stefano Stabellini <stefano.stabellini@eu.citrix.com> Cc: Ian Campbell <Ian.Campbell@citrix.com> Cc: Sebastian Ott <sebott@linux.vnet.ibm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Jerome Marchand <jmarchand@redhat.com> Cc: Joe Perches <joe@perches.com> Cc: Peng Tao <tao.peng@emc.com> Cc: Andy Adamson <andros@netapp.com> Cc: fanchaoting <fanchaoting@cn.fujitsu.com> Cc: Jie Liu <jeff.liu@oracle.com> Cc: Sunil Mushran <sunil.mushran@gmail.com> Cc: "Martin K. Petersen" <martin.petersen@oracle.com> Cc: Namjae Jeon <namjae.jeon@samsung.com> Cc: Pankaj Kumar <pankaj.km@samsung.com> Cc: Dan Magenheimer <dan.magenheimer@oracle.com> Cc: Mel Gorman <mgorman@suse.de>6
2013-10-12 06:44:27 +08:00
sums->len = bio->bi_iter.bi_size;
INIT_LIST_HEAD(&sums->list);
Btrfs: move data checksumming into a dedicated tree Btrfs stores checksums for each data block. Until now, they have been stored in the subvolume trees, indexed by the inode that is referencing the data block. This means that when we read the inode, we've probably read in at least some checksums as well. But, this has a few problems: * The checksums are indexed by logical offset in the file. When compression is on, this means we have to do the expensive checksumming on the uncompressed data. It would be faster if we could checksum the compressed data instead. * If we implement encryption, we'll be checksumming the plain text and storing that on disk. This is significantly less secure. * For either compression or encryption, we have to get the plain text back before we can verify the checksum as correct. This makes the raid layer balancing and extent moving much more expensive. * It makes the front end caching code more complex, as we have touch the subvolume and inodes as we cache extents. * There is potentitally one copy of the checksum in each subvolume referencing an extent. The solution used here is to store the extent checksums in a dedicated tree. This allows us to index the checksums by phyiscal extent start and length. It means: * The checksum is against the data stored on disk, after any compression or encryption is done. * The checksum is stored in a central location, and can be verified without following back references, or reading inodes. This makes compression significantly faster by reducing the amount of data that needs to be checksummed. It will also allow much faster raid management code in general. The checksums are indexed by a key with a fixed objectid (a magic value in ctree.h) and offset set to the starting byte of the extent. This allows us to copy the checksum items into the fsync log tree directly (or any other tree), without having to invent a second format for them. Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-12-09 05:58:54 +08:00
sums->bytenr = bio->bi_iter.bi_sector << 9;
index = 0;
shash->tfm = fs_info->csum_shash;
bio_for_each_segment(bvec, bio, iter) {
if (use_page_offsets)
offset = page_offset(bvec.bv_page) + bvec.bv_offset;
Btrfs: move data checksumming into a dedicated tree Btrfs stores checksums for each data block. Until now, they have been stored in the subvolume trees, indexed by the inode that is referencing the data block. This means that when we read the inode, we've probably read in at least some checksums as well. But, this has a few problems: * The checksums are indexed by logical offset in the file. When compression is on, this means we have to do the expensive checksumming on the uncompressed data. It would be faster if we could checksum the compressed data instead. * If we implement encryption, we'll be checksumming the plain text and storing that on disk. This is significantly less secure. * For either compression or encryption, we have to get the plain text back before we can verify the checksum as correct. This makes the raid layer balancing and extent moving much more expensive. * It makes the front end caching code more complex, as we have touch the subvolume and inodes as we cache extents. * There is potentitally one copy of the checksum in each subvolume referencing an extent. The solution used here is to store the extent checksums in a dedicated tree. This allows us to index the checksums by phyiscal extent start and length. It means: * The checksum is against the data stored on disk, after any compression or encryption is done. * The checksum is stored in a central location, and can be verified without following back references, or reading inodes. This makes compression significantly faster by reducing the amount of data that needs to be checksummed. It will also allow much faster raid management code in general. The checksums are indexed by a key with a fixed objectid (a magic value in ctree.h) and offset set to the starting byte of the extent. This allows us to copy the checksum items into the fsync log tree directly (or any other tree), without having to invent a second format for them. Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-12-09 05:58:54 +08:00
if (!ordered) {
ordered = btrfs_lookup_ordered_extent(inode, offset);
/*
* The bio range is not covered by any ordered extent,
* must be a code logic error.
*/
if (unlikely(!ordered)) {
WARN(1, KERN_WARNING
"no ordered extent for root %llu ino %llu offset %llu\n",
inode->root->root_key.objectid,
btrfs_ino(inode), offset);
kvfree(sums);
return BLK_STS_IOERR;
}
}
blockcount = BTRFS_BYTES_TO_BLKS(fs_info,
bvec.bv_len + fs_info->sectorsize
- 1);
for (i = 0; i < blockcount; i++) {
if (!one_ordered &&
!in_range(offset, ordered->file_offset,
ordered->num_bytes)) {
unsigned long bytes_left;
sums->len = this_sum_bytes;
this_sum_bytes = 0;
btrfs_add_ordered_sum(ordered, sums);
btrfs_put_ordered_extent(ordered);
bytes_left = bio->bi_iter.bi_size - total_bytes;
nofs_flag = memalloc_nofs_save();
sums = kvzalloc(btrfs_ordered_sum_size(fs_info,
bytes_left), GFP_KERNEL);
memalloc_nofs_restore(nofs_flag);
BUG_ON(!sums); /* -ENOMEM */
sums->len = bytes_left;
ordered = btrfs_lookup_ordered_extent(inode,
offset);
ASSERT(ordered); /* Logic error */
sums->bytenr = (bio->bi_iter.bi_sector << 9)
+ total_bytes;
index = 0;
}
data = bvec_kmap_local(&bvec);
crypto_shash_digest(shash,
data + (i * fs_info->sectorsize),
fs_info->sectorsize,
sums->sums + index);
kunmap_local(data);
index += fs_info->csum_size;
offset += fs_info->sectorsize;
this_sum_bytes += fs_info->sectorsize;
total_bytes += fs_info->sectorsize;
}
}
this_sum_bytes = 0;
btrfs_add_ordered_sum(ordered, sums);
btrfs_put_ordered_extent(ordered);
return 0;
}
/*
* Remove one checksum overlapping a range.
*
* This expects the key to describe the csum pointed to by the path, and it
* expects the csum to overlap the range [bytenr, len]
*
* The csum should not be entirely contained in the range and the range should
* not be entirely contained in the csum.
*
* This calls btrfs_truncate_item with the correct args based on the overlap,
* and fixes up the key as required.
*/
static noinline void truncate_one_csum(struct btrfs_fs_info *fs_info,
struct btrfs_path *path,
struct btrfs_key *key,
u64 bytenr, u64 len)
{
struct extent_buffer *leaf;
const u32 csum_size = fs_info->csum_size;
u64 csum_end;
u64 end_byte = bytenr + len;
u32 blocksize_bits = fs_info->sectorsize_bits;
leaf = path->nodes[0];
csum_end = btrfs_item_size(leaf, path->slots[0]) / csum_size;
csum_end <<= blocksize_bits;
csum_end += key->offset;
if (key->offset < bytenr && csum_end <= end_byte) {
/*
* [ bytenr - len ]
* [ ]
* [csum ]
* A simple truncate off the end of the item
*/
u32 new_size = (bytenr - key->offset) >> blocksize_bits;
new_size *= csum_size;
btrfs_truncate_item(path, new_size, 1);
} else if (key->offset >= bytenr && csum_end > end_byte &&
end_byte > key->offset) {
/*
* [ bytenr - len ]
* [ ]
* [csum ]
* we need to truncate from the beginning of the csum
*/
u32 new_size = (csum_end - end_byte) >> blocksize_bits;
new_size *= csum_size;
btrfs_truncate_item(path, new_size, 0);
key->offset = end_byte;
btrfs_set_item_key_safe(fs_info, path, key);
} else {
BUG();
}
}
/*
* Delete the csum items from the csum tree for a given range of bytes.
*/
int btrfs_del_csums(struct btrfs_trans_handle *trans,
Btrfs: fix missing data checksums after replaying a log tree When logging a file that has shared extents (reflinked with other files or with itself), we can end up logging multiple checksum items that cover overlapping ranges. This confuses the search for checksums at log replay time causing some checksums to never be added to the fs/subvolume tree. Consider the following example of a file that shares the same extent at offsets 0 and 256Kb: [ bytenr 13893632, offset 64Kb, len 64Kb ] 0 64Kb [ bytenr 13631488, offset 64Kb, len 192Kb ] 64Kb 256Kb [ bytenr 13893632, offset 0, len 256Kb ] 256Kb 512Kb When logging the inode, at tree-log.c:copy_items(), when processing the file extent item at offset 0, we log a checksum item covering the range 13959168 to 14024704, which corresponds to 13893632 + 64Kb and 13893632 + 64Kb + 64Kb, respectively. Later when processing the extent item at offset 256K, we log the checksums for the range from 13893632 to 14155776 (which corresponds to 13893632 + 256Kb). These checksums get merged with the checksum item for the range from 13631488 to 13893632 (13631488 + 256Kb), logged by a previous fsync. So after this we get the two following checksum items in the log tree: (...) item 6 key (EXTENT_CSUM EXTENT_CSUM 13631488) itemoff 3095 itemsize 512 range start 13631488 end 14155776 length 524288 item 7 key (EXTENT_CSUM EXTENT_CSUM 13959168) itemoff 3031 itemsize 64 range start 13959168 end 14024704 length 65536 The first one covers the range from the second one, they overlap. So far this does not cause a problem after replaying the log, because when replaying the file extent item for offset 256K, we copy all the checksums for the extent 13893632 from the log tree to the fs/subvolume tree, since searching for an checksum item for bytenr 13893632 leaves us at the first checksum item, which covers the whole range of the extent. However if we write 64Kb to file offset 256Kb for example, we will not be able to find and copy the checksums for the last 128Kb of the extent at bytenr 13893632, referenced by the file range 384Kb to 512Kb. After writing 64Kb into file offset 256Kb we get the following extent layout for our file: [ bytenr 13893632, offset 64K, len 64Kb ] 0 64Kb [ bytenr 13631488, offset 64Kb, len 192Kb ] 64Kb 256Kb [ bytenr 14155776, offset 0, len 64Kb ] 256Kb 320Kb [ bytenr 13893632, offset 64Kb, len 192Kb ] 320Kb 512Kb After fsync'ing the file, if we have a power failure and then mount the filesystem to replay the log, the following happens: 1) When replaying the file extent item for file offset 320Kb, we lookup for the checksums for the extent range from 13959168 (13893632 + 64Kb) to 14155776 (13893632 + 256Kb), through a call to btrfs_lookup_csums_range(); 2) btrfs_lookup_csums_range() finds the checksum item that starts precisely at offset 13959168 (item 7 in the log tree, shown before); 3) However that checksum item only covers 64Kb of data, and not 192Kb of data; 4) As a result only the checksums for the first 64Kb of data referenced by the file extent item are found and copied to the fs/subvolume tree. The remaining 128Kb of data, file range 384Kb to 512Kb, doesn't get the corresponding data checksums found and copied to the fs/subvolume tree. 5) After replaying the log userspace will not be able to read the file range from 384Kb to 512Kb, because the checksums are missing and resulting in an -EIO error. The following steps reproduce this scenario: $ mkfs.btrfs -f /dev/sdc $ mount /dev/sdc /mnt/sdc $ xfs_io -f -c "pwrite -S 0xa3 0 256K" /mnt/sdc/foobar $ xfs_io -c "fsync" /mnt/sdc/foobar $ xfs_io -c "pwrite -S 0xc7 256K 256K" /mnt/sdc/foobar $ xfs_io -c "reflink /mnt/sdc/foobar 320K 0 64K" /mnt/sdc/foobar $ xfs_io -c "fsync" /mnt/sdc/foobar $ xfs_io -c "pwrite -S 0xe5 256K 64K" /mnt/sdc/foobar $ xfs_io -c "fsync" /mnt/sdc/foobar <power failure> $ mount /dev/sdc /mnt/sdc $ md5sum /mnt/sdc/foobar md5sum: /mnt/sdc/foobar: Input/output error $ dmesg | tail [165305.003464] BTRFS info (device sdc): no csum found for inode 257 start 401408 [165305.004014] BTRFS info (device sdc): no csum found for inode 257 start 405504 [165305.004559] BTRFS info (device sdc): no csum found for inode 257 start 409600 [165305.005101] BTRFS info (device sdc): no csum found for inode 257 start 413696 [165305.005627] BTRFS info (device sdc): no csum found for inode 257 start 417792 [165305.006134] BTRFS info (device sdc): no csum found for inode 257 start 421888 [165305.006625] BTRFS info (device sdc): no csum found for inode 257 start 425984 [165305.007278] BTRFS info (device sdc): no csum found for inode 257 start 430080 [165305.008248] BTRFS warning (device sdc): csum failed root 5 ino 257 off 393216 csum 0x1337385e expected csum 0x00000000 mirror 1 [165305.009550] BTRFS warning (device sdc): csum failed root 5 ino 257 off 393216 csum 0x1337385e expected csum 0x00000000 mirror 1 Fix this simply by deleting first any checksums, from the log tree, for the range of the extent we are logging at copy_items(). This ensures we do not get checksum items in the log tree that have overlapping ranges. This is a long time issue that has been present since we have the clone (and deduplication) ioctl, and can happen both when an extent is shared between different files and within the same file. A test case for fstests follows soon. CC: stable@vger.kernel.org # 4.4+ Signed-off-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2019-12-06 00:58:30 +08:00
struct btrfs_root *root, u64 bytenr, u64 len)
{
Btrfs: fix missing data checksums after replaying a log tree When logging a file that has shared extents (reflinked with other files or with itself), we can end up logging multiple checksum items that cover overlapping ranges. This confuses the search for checksums at log replay time causing some checksums to never be added to the fs/subvolume tree. Consider the following example of a file that shares the same extent at offsets 0 and 256Kb: [ bytenr 13893632, offset 64Kb, len 64Kb ] 0 64Kb [ bytenr 13631488, offset 64Kb, len 192Kb ] 64Kb 256Kb [ bytenr 13893632, offset 0, len 256Kb ] 256Kb 512Kb When logging the inode, at tree-log.c:copy_items(), when processing the file extent item at offset 0, we log a checksum item covering the range 13959168 to 14024704, which corresponds to 13893632 + 64Kb and 13893632 + 64Kb + 64Kb, respectively. Later when processing the extent item at offset 256K, we log the checksums for the range from 13893632 to 14155776 (which corresponds to 13893632 + 256Kb). These checksums get merged with the checksum item for the range from 13631488 to 13893632 (13631488 + 256Kb), logged by a previous fsync. So after this we get the two following checksum items in the log tree: (...) item 6 key (EXTENT_CSUM EXTENT_CSUM 13631488) itemoff 3095 itemsize 512 range start 13631488 end 14155776 length 524288 item 7 key (EXTENT_CSUM EXTENT_CSUM 13959168) itemoff 3031 itemsize 64 range start 13959168 end 14024704 length 65536 The first one covers the range from the second one, they overlap. So far this does not cause a problem after replaying the log, because when replaying the file extent item for offset 256K, we copy all the checksums for the extent 13893632 from the log tree to the fs/subvolume tree, since searching for an checksum item for bytenr 13893632 leaves us at the first checksum item, which covers the whole range of the extent. However if we write 64Kb to file offset 256Kb for example, we will not be able to find and copy the checksums for the last 128Kb of the extent at bytenr 13893632, referenced by the file range 384Kb to 512Kb. After writing 64Kb into file offset 256Kb we get the following extent layout for our file: [ bytenr 13893632, offset 64K, len 64Kb ] 0 64Kb [ bytenr 13631488, offset 64Kb, len 192Kb ] 64Kb 256Kb [ bytenr 14155776, offset 0, len 64Kb ] 256Kb 320Kb [ bytenr 13893632, offset 64Kb, len 192Kb ] 320Kb 512Kb After fsync'ing the file, if we have a power failure and then mount the filesystem to replay the log, the following happens: 1) When replaying the file extent item for file offset 320Kb, we lookup for the checksums for the extent range from 13959168 (13893632 + 64Kb) to 14155776 (13893632 + 256Kb), through a call to btrfs_lookup_csums_range(); 2) btrfs_lookup_csums_range() finds the checksum item that starts precisely at offset 13959168 (item 7 in the log tree, shown before); 3) However that checksum item only covers 64Kb of data, and not 192Kb of data; 4) As a result only the checksums for the first 64Kb of data referenced by the file extent item are found and copied to the fs/subvolume tree. The remaining 128Kb of data, file range 384Kb to 512Kb, doesn't get the corresponding data checksums found and copied to the fs/subvolume tree. 5) After replaying the log userspace will not be able to read the file range from 384Kb to 512Kb, because the checksums are missing and resulting in an -EIO error. The following steps reproduce this scenario: $ mkfs.btrfs -f /dev/sdc $ mount /dev/sdc /mnt/sdc $ xfs_io -f -c "pwrite -S 0xa3 0 256K" /mnt/sdc/foobar $ xfs_io -c "fsync" /mnt/sdc/foobar $ xfs_io -c "pwrite -S 0xc7 256K 256K" /mnt/sdc/foobar $ xfs_io -c "reflink /mnt/sdc/foobar 320K 0 64K" /mnt/sdc/foobar $ xfs_io -c "fsync" /mnt/sdc/foobar $ xfs_io -c "pwrite -S 0xe5 256K 64K" /mnt/sdc/foobar $ xfs_io -c "fsync" /mnt/sdc/foobar <power failure> $ mount /dev/sdc /mnt/sdc $ md5sum /mnt/sdc/foobar md5sum: /mnt/sdc/foobar: Input/output error $ dmesg | tail [165305.003464] BTRFS info (device sdc): no csum found for inode 257 start 401408 [165305.004014] BTRFS info (device sdc): no csum found for inode 257 start 405504 [165305.004559] BTRFS info (device sdc): no csum found for inode 257 start 409600 [165305.005101] BTRFS info (device sdc): no csum found for inode 257 start 413696 [165305.005627] BTRFS info (device sdc): no csum found for inode 257 start 417792 [165305.006134] BTRFS info (device sdc): no csum found for inode 257 start 421888 [165305.006625] BTRFS info (device sdc): no csum found for inode 257 start 425984 [165305.007278] BTRFS info (device sdc): no csum found for inode 257 start 430080 [165305.008248] BTRFS warning (device sdc): csum failed root 5 ino 257 off 393216 csum 0x1337385e expected csum 0x00000000 mirror 1 [165305.009550] BTRFS warning (device sdc): csum failed root 5 ino 257 off 393216 csum 0x1337385e expected csum 0x00000000 mirror 1 Fix this simply by deleting first any checksums, from the log tree, for the range of the extent we are logging at copy_items(). This ensures we do not get checksum items in the log tree that have overlapping ranges. This is a long time issue that has been present since we have the clone (and deduplication) ioctl, and can happen both when an extent is shared between different files and within the same file. A test case for fstests follows soon. CC: stable@vger.kernel.org # 4.4+ Signed-off-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2019-12-06 00:58:30 +08:00
struct btrfs_fs_info *fs_info = trans->fs_info;
struct btrfs_path *path;
struct btrfs_key key;
u64 end_byte = bytenr + len;
u64 csum_end;
struct extent_buffer *leaf;
int ret = 0;
const u32 csum_size = fs_info->csum_size;
u32 blocksize_bits = fs_info->sectorsize_bits;
ASSERT(root->root_key.objectid == BTRFS_CSUM_TREE_OBJECTID ||
Btrfs: fix missing data checksums after replaying a log tree When logging a file that has shared extents (reflinked with other files or with itself), we can end up logging multiple checksum items that cover overlapping ranges. This confuses the search for checksums at log replay time causing some checksums to never be added to the fs/subvolume tree. Consider the following example of a file that shares the same extent at offsets 0 and 256Kb: [ bytenr 13893632, offset 64Kb, len 64Kb ] 0 64Kb [ bytenr 13631488, offset 64Kb, len 192Kb ] 64Kb 256Kb [ bytenr 13893632, offset 0, len 256Kb ] 256Kb 512Kb When logging the inode, at tree-log.c:copy_items(), when processing the file extent item at offset 0, we log a checksum item covering the range 13959168 to 14024704, which corresponds to 13893632 + 64Kb and 13893632 + 64Kb + 64Kb, respectively. Later when processing the extent item at offset 256K, we log the checksums for the range from 13893632 to 14155776 (which corresponds to 13893632 + 256Kb). These checksums get merged with the checksum item for the range from 13631488 to 13893632 (13631488 + 256Kb), logged by a previous fsync. So after this we get the two following checksum items in the log tree: (...) item 6 key (EXTENT_CSUM EXTENT_CSUM 13631488) itemoff 3095 itemsize 512 range start 13631488 end 14155776 length 524288 item 7 key (EXTENT_CSUM EXTENT_CSUM 13959168) itemoff 3031 itemsize 64 range start 13959168 end 14024704 length 65536 The first one covers the range from the second one, they overlap. So far this does not cause a problem after replaying the log, because when replaying the file extent item for offset 256K, we copy all the checksums for the extent 13893632 from the log tree to the fs/subvolume tree, since searching for an checksum item for bytenr 13893632 leaves us at the first checksum item, which covers the whole range of the extent. However if we write 64Kb to file offset 256Kb for example, we will not be able to find and copy the checksums for the last 128Kb of the extent at bytenr 13893632, referenced by the file range 384Kb to 512Kb. After writing 64Kb into file offset 256Kb we get the following extent layout for our file: [ bytenr 13893632, offset 64K, len 64Kb ] 0 64Kb [ bytenr 13631488, offset 64Kb, len 192Kb ] 64Kb 256Kb [ bytenr 14155776, offset 0, len 64Kb ] 256Kb 320Kb [ bytenr 13893632, offset 64Kb, len 192Kb ] 320Kb 512Kb After fsync'ing the file, if we have a power failure and then mount the filesystem to replay the log, the following happens: 1) When replaying the file extent item for file offset 320Kb, we lookup for the checksums for the extent range from 13959168 (13893632 + 64Kb) to 14155776 (13893632 + 256Kb), through a call to btrfs_lookup_csums_range(); 2) btrfs_lookup_csums_range() finds the checksum item that starts precisely at offset 13959168 (item 7 in the log tree, shown before); 3) However that checksum item only covers 64Kb of data, and not 192Kb of data; 4) As a result only the checksums for the first 64Kb of data referenced by the file extent item are found and copied to the fs/subvolume tree. The remaining 128Kb of data, file range 384Kb to 512Kb, doesn't get the corresponding data checksums found and copied to the fs/subvolume tree. 5) After replaying the log userspace will not be able to read the file range from 384Kb to 512Kb, because the checksums are missing and resulting in an -EIO error. The following steps reproduce this scenario: $ mkfs.btrfs -f /dev/sdc $ mount /dev/sdc /mnt/sdc $ xfs_io -f -c "pwrite -S 0xa3 0 256K" /mnt/sdc/foobar $ xfs_io -c "fsync" /mnt/sdc/foobar $ xfs_io -c "pwrite -S 0xc7 256K 256K" /mnt/sdc/foobar $ xfs_io -c "reflink /mnt/sdc/foobar 320K 0 64K" /mnt/sdc/foobar $ xfs_io -c "fsync" /mnt/sdc/foobar $ xfs_io -c "pwrite -S 0xe5 256K 64K" /mnt/sdc/foobar $ xfs_io -c "fsync" /mnt/sdc/foobar <power failure> $ mount /dev/sdc /mnt/sdc $ md5sum /mnt/sdc/foobar md5sum: /mnt/sdc/foobar: Input/output error $ dmesg | tail [165305.003464] BTRFS info (device sdc): no csum found for inode 257 start 401408 [165305.004014] BTRFS info (device sdc): no csum found for inode 257 start 405504 [165305.004559] BTRFS info (device sdc): no csum found for inode 257 start 409600 [165305.005101] BTRFS info (device sdc): no csum found for inode 257 start 413696 [165305.005627] BTRFS info (device sdc): no csum found for inode 257 start 417792 [165305.006134] BTRFS info (device sdc): no csum found for inode 257 start 421888 [165305.006625] BTRFS info (device sdc): no csum found for inode 257 start 425984 [165305.007278] BTRFS info (device sdc): no csum found for inode 257 start 430080 [165305.008248] BTRFS warning (device sdc): csum failed root 5 ino 257 off 393216 csum 0x1337385e expected csum 0x00000000 mirror 1 [165305.009550] BTRFS warning (device sdc): csum failed root 5 ino 257 off 393216 csum 0x1337385e expected csum 0x00000000 mirror 1 Fix this simply by deleting first any checksums, from the log tree, for the range of the extent we are logging at copy_items(). This ensures we do not get checksum items in the log tree that have overlapping ranges. This is a long time issue that has been present since we have the clone (and deduplication) ioctl, and can happen both when an extent is shared between different files and within the same file. A test case for fstests follows soon. CC: stable@vger.kernel.org # 4.4+ Signed-off-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2019-12-06 00:58:30 +08:00
root->root_key.objectid == BTRFS_TREE_LOG_OBJECTID);
path = btrfs_alloc_path();
if (!path)
return -ENOMEM;
while (1) {
key.objectid = BTRFS_EXTENT_CSUM_OBJECTID;
key.offset = end_byte - 1;
key.type = BTRFS_EXTENT_CSUM_KEY;
ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
if (ret > 0) {
ret = 0;
if (path->slots[0] == 0)
break;
path->slots[0]--;
} else if (ret < 0) {
break;
}
leaf = path->nodes[0];
btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
if (key.objectid != BTRFS_EXTENT_CSUM_OBJECTID ||
key.type != BTRFS_EXTENT_CSUM_KEY) {
break;
}
if (key.offset >= end_byte)
break;
csum_end = btrfs_item_size(leaf, path->slots[0]) / csum_size;
csum_end <<= blocksize_bits;
csum_end += key.offset;
/* this csum ends before we start, we're done */
if (csum_end <= bytenr)
break;
/* delete the entire item, it is inside our range */
if (key.offset >= bytenr && csum_end <= end_byte) {
int del_nr = 1;
/*
* Check how many csum items preceding this one in this
* leaf correspond to our range and then delete them all
* at once.
*/
if (key.offset > bytenr && path->slots[0] > 0) {
int slot = path->slots[0] - 1;
while (slot >= 0) {
struct btrfs_key pk;
btrfs_item_key_to_cpu(leaf, &pk, slot);
if (pk.offset < bytenr ||
pk.type != BTRFS_EXTENT_CSUM_KEY ||
pk.objectid !=
BTRFS_EXTENT_CSUM_OBJECTID)
break;
path->slots[0] = slot;
del_nr++;
key.offset = pk.offset;
slot--;
}
}
ret = btrfs_del_items(trans, root, path,
path->slots[0], del_nr);
if (ret)
break;
if (key.offset == bytenr)
break;
} else if (key.offset < bytenr && csum_end > end_byte) {
unsigned long offset;
unsigned long shift_len;
unsigned long item_offset;
/*
* [ bytenr - len ]
* [csum ]
*
* Our bytes are in the middle of the csum,
* we need to split this item and insert a new one.
*
* But we can't drop the path because the
* csum could change, get removed, extended etc.
*
* The trick here is the max size of a csum item leaves
* enough room in the tree block for a single
* item header. So, we split the item in place,
* adding a new header pointing to the existing
* bytes. Then we loop around again and we have
* a nicely formed csum item that we can neatly
* truncate.
*/
offset = (bytenr - key.offset) >> blocksize_bits;
offset *= csum_size;
shift_len = (len >> blocksize_bits) * csum_size;
item_offset = btrfs_item_ptr_offset(leaf,
path->slots[0]);
memzero_extent_buffer(leaf, item_offset + offset,
shift_len);
key.offset = bytenr;
/*
* btrfs_split_item returns -EAGAIN when the
* item changed size or key
*/
ret = btrfs_split_item(trans, root, path, &key, offset);
if (ret && ret != -EAGAIN) {
btrfs_abort_transaction(trans, ret);
break;
}
ret = 0;
key.offset = end_byte - 1;
} else {
truncate_one_csum(fs_info, path, &key, bytenr, len);
if (key.offset < bytenr)
break;
}
btrfs_release_path(path);
}
btrfs_free_path(path);
return ret;
}
btrfs: fix fsync failure and transaction abort after writes to prealloc extents When doing a series of partial writes to different ranges of preallocated extents with transaction commits and fsyncs in between, we can end up with a checksum items in a log tree. This causes an fsync to fail with -EIO and abort the transaction, turning the filesystem to RO mode, when syncing the log. For this to happen, we need to have a full fsync of a file following one or more fast fsyncs. The following example reproduces the problem and explains how it happens: $ mkfs.btrfs -f /dev/sdc $ mount /dev/sdc /mnt # Create our test file with 2 preallocated extents. Leave a 1M hole # between them to ensure that we get two file extent items that will # never be merged into a single one. The extents are contiguous on disk, # which will later result in the checksums for their data to be merged # into a single checksum item in the csums btree. # $ xfs_io -f \ -c "falloc 0 1M" \ -c "falloc 3M 3M" \ /mnt/foobar # Now write to the second extent and leave only 1M of it as unwritten, # which corresponds to the file range [4M, 5M[. # # Then fsync the file to flush delalloc and to clear full sync flag from # the inode, so that a future fsync will use the fast code path. # # After the writeback triggered by the fsync we have 3 file extent items # that point to the second extent we previously allocated: # # 1) One file extent item of type BTRFS_FILE_EXTENT_REG that covers the # file range [3M, 4M[ # # 2) One file extent item of type BTRFS_FILE_EXTENT_PREALLOC that covers # the file range [4M, 5M[ # # 3) One file extent item of type BTRFS_FILE_EXTENT_REG that covers the # file range [5M, 6M[ # # All these file extent items have a generation of 6, which is the ID of # the transaction where they were created. The split of the original file # extent item is done at btrfs_mark_extent_written() when ordered extents # complete for the file ranges [3M, 4M[ and [5M, 6M[. # $ xfs_io -c "pwrite -S 0xab 3M 1M" \ -c "pwrite -S 0xef 5M 1M" \ -c "fsync" \ /mnt/foobar # Commit the current transaction. This wipes out the log tree created by # the previous fsync. sync # Now write to the unwritten range of the second extent we allocated, # corresponding to the file range [4M, 5M[, and fsync the file, which # triggers the fast fsync code path. # # The fast fsync code path sees that there is a new extent map covering # the file range [4M, 5M[ and therefore it will log a checksum item # covering the range [1M, 2M[ of the second extent we allocated. # # Also, after the fsync finishes we no longer have the 3 file extent # items that pointed to 3 sections of the second extent we allocated. # Instead we end up with a single file extent item pointing to the whole # extent, with a type of BTRFS_FILE_EXTENT_REG and a generation of 7 (the # current transaction ID). This is due to the file extent item merging we # do when completing ordered extents into ranges that point to unwritten # (preallocated) extents. This merging is done at # btrfs_mark_extent_written(). # $ xfs_io -c "pwrite -S 0xcd 4M 1M" \ -c "fsync" \ /mnt/foobar # Now do some write to our file outside the range of the second extent # that we allocated with fallocate() and truncate the file size from 6M # down to 5M. # # The truncate operation sets the full sync runtime flag on the inode, # forcing the next fsync to use the slow code path. It also changes the # length of the second file extent item so that it represents the file # range [3M, 5M[ and not the range [3M, 6M[ anymore. # # Finally fsync the file. Since this is a fsync that triggers the slow # code path, it will remove all items associated to the inode from the # log tree and then it will scan for file extent items in the # fs/subvolume tree that have a generation matching the current # transaction ID, which is 7. This means it will log 2 file extent # items: # # 1) One for the first extent we allocated, covering the file range # [0, 1M[ # # 2) Another for the first 2M of the second extent we allocated, # covering the file range [3M, 5M[ # # When logging the first file extent item we log a single checksum item # that has all the checksums for the entire extent. # # When logging the second file extent item, we also lookup for the # checksums that are associated with the range [0, 2M[ of the second # extent we allocated (file range [3M, 5M[), and then we log them with # btrfs_csum_file_blocks(). However that results in ending up with a log # that has two checksum items with ranges that overlap: # # 1) One for the range [1M, 2M[ of the second extent we allocated, # corresponding to the file range [4M, 5M[, which we logged in the # previous fsync that used the fast code path; # # 2) One for the ranges [0, 1M[ and [0, 2M[ of the first and second # extents, respectively, corresponding to the files ranges [0, 1M[ # and [3M, 5M[. This one was added during this last fsync that uses # the slow code path and overlaps with the previous one logged by # the previous fast fsync. # # This happens because when logging the checksums for the second # extent, we notice they start at an offset that matches the end of the # checksums item that we logged for the first extent, and because both # extents are contiguous on disk, btrfs_csum_file_blocks() decides to # extend that existing checksums item and append the checksums for the # second extent to this item. The end result is we end up with two # checksum items in the log tree that have overlapping ranges, as # listed before, resulting in the fsync to fail with -EIO and aborting # the transaction, turning the filesystem into RO mode. # $ xfs_io -c "pwrite -S 0xff 0 1M" \ -c "truncate 5M" \ -c "fsync" \ /mnt/foobar fsync: Input/output error After running the example, dmesg/syslog shows the tree checker complained about the checksum items with overlapping ranges and we aborted the transaction: $ dmesg (...) [756289.557487] BTRFS critical (device sdc): corrupt leaf: root=18446744073709551610 block=30720000 slot=5, csum end range (16777216) goes beyond the start range (15728640) of the next csum item [756289.560583] BTRFS info (device sdc): leaf 30720000 gen 7 total ptrs 7 free space 11677 owner 18446744073709551610 [756289.562435] BTRFS info (device sdc): refs 2 lock_owner 0 current 2303929 [756289.563654] item 0 key (257 1 0) itemoff 16123 itemsize 160 [756289.564649] inode generation 6 size 5242880 mode 100600 [756289.565636] item 1 key (257 12 256) itemoff 16107 itemsize 16 [756289.566694] item 2 key (257 108 0) itemoff 16054 itemsize 53 [756289.567725] extent data disk bytenr 13631488 nr 1048576 [756289.568697] extent data offset 0 nr 1048576 ram 1048576 [756289.569689] item 3 key (257 108 1048576) itemoff 16001 itemsize 53 [756289.570682] extent data disk bytenr 0 nr 0 [756289.571363] extent data offset 0 nr 2097152 ram 2097152 [756289.572213] item 4 key (257 108 3145728) itemoff 15948 itemsize 53 [756289.573246] extent data disk bytenr 14680064 nr 3145728 [756289.574121] extent data offset 0 nr 2097152 ram 3145728 [756289.574993] item 5 key (18446744073709551606 128 13631488) itemoff 12876 itemsize 3072 [756289.576113] item 6 key (18446744073709551606 128 15728640) itemoff 11852 itemsize 1024 [756289.577286] BTRFS error (device sdc): block=30720000 write time tree block corruption detected [756289.578644] ------------[ cut here ]------------ [756289.579376] WARNING: CPU: 0 PID: 2303929 at fs/btrfs/disk-io.c:465 csum_one_extent_buffer+0xed/0x100 [btrfs] [756289.580857] Modules linked in: btrfs dm_zero dm_dust loop dm_snapshot (...) [756289.591534] CPU: 0 PID: 2303929 Comm: xfs_io Tainted: G W 5.12.0-rc8-btrfs-next-87 #1 [756289.592580] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qemu.org 04/01/2014 [756289.594161] RIP: 0010:csum_one_extent_buffer+0xed/0x100 [btrfs] [756289.595122] Code: 5d c3 e8 76 60 (...) [756289.597509] RSP: 0018:ffffb51b416cb898 EFLAGS: 00010282 [756289.598142] RAX: 0000000000000000 RBX: fffff02b8a365bc0 RCX: 0000000000000000 [756289.598970] RDX: 0000000000000000 RSI: ffffffffa9112421 RDI: 00000000ffffffff [756289.599798] RBP: ffffa06500880000 R08: 0000000000000000 R09: 0000000000000000 [756289.600619] R10: 0000000000000000 R11: 0000000000000001 R12: 0000000000000000 [756289.601456] R13: ffffa0652b1d8980 R14: ffffa06500880000 R15: 0000000000000000 [756289.602278] FS: 00007f08b23c9800(0000) GS:ffffa0682be00000(0000) knlGS:0000000000000000 [756289.603217] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [756289.603892] CR2: 00005652f32d0138 CR3: 000000025d616003 CR4: 0000000000370ef0 [756289.604725] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [756289.605563] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [756289.606400] Call Trace: [756289.606704] btree_csum_one_bio+0x244/0x2b0 [btrfs] [756289.607313] btrfs_submit_metadata_bio+0xb7/0x100 [btrfs] [756289.608040] submit_one_bio+0x61/0x70 [btrfs] [756289.608587] btree_write_cache_pages+0x587/0x610 [btrfs] [756289.609258] ? free_debug_processing+0x1d5/0x240 [756289.609812] ? __module_address+0x28/0xf0 [756289.610298] ? lock_acquire+0x1a0/0x3e0 [756289.610754] ? lock_acquired+0x19f/0x430 [756289.611220] ? lock_acquire+0x1a0/0x3e0 [756289.611675] do_writepages+0x43/0xf0 [756289.612101] ? __filemap_fdatawrite_range+0xa4/0x100 [756289.612800] __filemap_fdatawrite_range+0xc5/0x100 [756289.613393] btrfs_write_marked_extents+0x68/0x160 [btrfs] [756289.614085] btrfs_sync_log+0x21c/0xf20 [btrfs] [756289.614661] ? finish_wait+0x90/0x90 [756289.615096] ? __mutex_unlock_slowpath+0x45/0x2a0 [756289.615661] ? btrfs_log_inode_parent+0x3c9/0xdc0 [btrfs] [756289.616338] ? lock_acquire+0x1a0/0x3e0 [756289.616801] ? lock_acquired+0x19f/0x430 [756289.617284] ? lock_acquire+0x1a0/0x3e0 [756289.617750] ? lock_release+0x214/0x470 [756289.618221] ? lock_acquired+0x19f/0x430 [756289.618704] ? dput+0x20/0x4a0 [756289.619079] ? dput+0x20/0x4a0 [756289.619452] ? lockref_put_or_lock+0x9/0x30 [756289.619969] ? lock_release+0x214/0x470 [756289.620445] ? lock_release+0x214/0x470 [756289.620924] ? lock_release+0x214/0x470 [756289.621415] btrfs_sync_file+0x46a/0x5b0 [btrfs] [756289.621982] do_fsync+0x38/0x70 [756289.622395] __x64_sys_fsync+0x10/0x20 [756289.622907] do_syscall_64+0x33/0x80 [756289.623438] entry_SYSCALL_64_after_hwframe+0x44/0xae [756289.624063] RIP: 0033:0x7f08b27fbb7b [756289.624588] Code: 0f 05 48 3d 00 (...) [756289.626760] RSP: 002b:00007ffe2583f940 EFLAGS: 00000293 ORIG_RAX: 000000000000004a [756289.627639] RAX: ffffffffffffffda RBX: 00005652f32cd0f0 RCX: 00007f08b27fbb7b [756289.628464] RDX: 00005652f32cbca0 RSI: 00005652f32cd110 RDI: 0000000000000003 [756289.629323] RBP: 00005652f32cd110 R08: 0000000000000000 R09: 00007f08b28c4be0 [756289.630172] R10: fffffffffffff39a R11: 0000000000000293 R12: 0000000000000001 [756289.631007] R13: 00005652f32cd0f0 R14: 0000000000000001 R15: 00005652f32cc480 [756289.631819] irq event stamp: 0 [756289.632188] hardirqs last enabled at (0): [<0000000000000000>] 0x0 [756289.632911] hardirqs last disabled at (0): [<ffffffffa7e97c29>] copy_process+0x879/0x1cc0 [756289.633893] softirqs last enabled at (0): [<ffffffffa7e97c29>] copy_process+0x879/0x1cc0 [756289.634871] softirqs last disabled at (0): [<0000000000000000>] 0x0 [756289.635606] ---[ end trace 0a039fdc16ff3fef ]--- [756289.636179] BTRFS: error (device sdc) in btrfs_sync_log:3136: errno=-5 IO failure [756289.637082] BTRFS info (device sdc): forced readonly Having checksum items covering ranges that overlap is dangerous as in some cases it can lead to having extent ranges for which we miss checksums after log replay or getting the wrong checksum item. There were some fixes in the past for bugs that resulted in this problem, and were explained and fixed by the following commits: 27b9a8122ff71a ("Btrfs: fix csum tree corruption, duplicate and outdated checksums") b84b8390d6009c ("Btrfs: fix file read corruption after extent cloning and fsync") 40e046acbd2f36 ("Btrfs: fix missing data checksums after replaying a log tree") e289f03ea79bbc ("btrfs: fix corrupt log due to concurrent fsync of inodes with shared extents") Fix the issue by making btrfs_csum_file_blocks() taking into account the start offset of the next checksum item when it decides to extend an existing checksum item, so that it never extends the checksum to end at a range that goes beyond the start range of the next checksum item. When we can not access the next checksum item without releasing the path, simply drop the optimization of extending the previous checksum item and fallback to inserting a new checksum item - this happens rarely and the optimization is not significant enough for a log tree in order to justify the extra complexity, as it would only save a few bytes (the size of a struct btrfs_item) of leaf space. This behaviour is only needed when inserting into a log tree because for the regular checksums tree we never have a case where we try to insert a range of checksums that overlap with a range that was previously inserted. A test case for fstests will follow soon. Reported-by: Philipp Fent <fent@in.tum.de> Link: https://lore.kernel.org/linux-btrfs/93c4600e-5263-5cba-adf0-6f47526e7561@in.tum.de/ CC: stable@vger.kernel.org # 5.4+ Tested-by: Anand Jain <anand.jain@oracle.com> Signed-off-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-05-24 18:35:53 +08:00
static int find_next_csum_offset(struct btrfs_root *root,
struct btrfs_path *path,
u64 *next_offset)
{
const u32 nritems = btrfs_header_nritems(path->nodes[0]);
struct btrfs_key found_key;
int slot = path->slots[0] + 1;
int ret;
if (nritems == 0 || slot >= nritems) {
ret = btrfs_next_leaf(root, path);
if (ret < 0) {
return ret;
} else if (ret > 0) {
*next_offset = (u64)-1;
return 0;
}
slot = path->slots[0];
}
btrfs_item_key_to_cpu(path->nodes[0], &found_key, slot);
if (found_key.objectid != BTRFS_EXTENT_CSUM_OBJECTID ||
found_key.type != BTRFS_EXTENT_CSUM_KEY)
*next_offset = (u64)-1;
else
*next_offset = found_key.offset;
return 0;
}
int btrfs_csum_file_blocks(struct btrfs_trans_handle *trans,
Btrfs: move data checksumming into a dedicated tree Btrfs stores checksums for each data block. Until now, they have been stored in the subvolume trees, indexed by the inode that is referencing the data block. This means that when we read the inode, we've probably read in at least some checksums as well. But, this has a few problems: * The checksums are indexed by logical offset in the file. When compression is on, this means we have to do the expensive checksumming on the uncompressed data. It would be faster if we could checksum the compressed data instead. * If we implement encryption, we'll be checksumming the plain text and storing that on disk. This is significantly less secure. * For either compression or encryption, we have to get the plain text back before we can verify the checksum as correct. This makes the raid layer balancing and extent moving much more expensive. * It makes the front end caching code more complex, as we have touch the subvolume and inodes as we cache extents. * There is potentitally one copy of the checksum in each subvolume referencing an extent. The solution used here is to store the extent checksums in a dedicated tree. This allows us to index the checksums by phyiscal extent start and length. It means: * The checksum is against the data stored on disk, after any compression or encryption is done. * The checksum is stored in a central location, and can be verified without following back references, or reading inodes. This makes compression significantly faster by reducing the amount of data that needs to be checksummed. It will also allow much faster raid management code in general. The checksums are indexed by a key with a fixed objectid (a magic value in ctree.h) and offset set to the starting byte of the extent. This allows us to copy the checksum items into the fsync log tree directly (or any other tree), without having to invent a second format for them. Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-12-09 05:58:54 +08:00
struct btrfs_root *root,
struct btrfs_ordered_sum *sums)
{
struct btrfs_fs_info *fs_info = root->fs_info;
struct btrfs_key file_key;
struct btrfs_key found_key;
struct btrfs_path *path;
struct btrfs_csum_item *item;
struct btrfs_csum_item *item_end;
struct extent_buffer *leaf = NULL;
u64 next_offset;
u64 total_bytes = 0;
u64 csum_offset;
u64 bytenr;
u32 ins_size;
int index = 0;
int found_next;
int ret;
const u32 csum_size = fs_info->csum_size;
path = btrfs_alloc_path();
if (!path)
return -ENOMEM;
again:
next_offset = (u64)-1;
found_next = 0;
bytenr = sums->bytenr + total_bytes;
Btrfs: move data checksumming into a dedicated tree Btrfs stores checksums for each data block. Until now, they have been stored in the subvolume trees, indexed by the inode that is referencing the data block. This means that when we read the inode, we've probably read in at least some checksums as well. But, this has a few problems: * The checksums are indexed by logical offset in the file. When compression is on, this means we have to do the expensive checksumming on the uncompressed data. It would be faster if we could checksum the compressed data instead. * If we implement encryption, we'll be checksumming the plain text and storing that on disk. This is significantly less secure. * For either compression or encryption, we have to get the plain text back before we can verify the checksum as correct. This makes the raid layer balancing and extent moving much more expensive. * It makes the front end caching code more complex, as we have touch the subvolume and inodes as we cache extents. * There is potentitally one copy of the checksum in each subvolume referencing an extent. The solution used here is to store the extent checksums in a dedicated tree. This allows us to index the checksums by phyiscal extent start and length. It means: * The checksum is against the data stored on disk, after any compression or encryption is done. * The checksum is stored in a central location, and can be verified without following back references, or reading inodes. This makes compression significantly faster by reducing the amount of data that needs to be checksummed. It will also allow much faster raid management code in general. The checksums are indexed by a key with a fixed objectid (a magic value in ctree.h) and offset set to the starting byte of the extent. This allows us to copy the checksum items into the fsync log tree directly (or any other tree), without having to invent a second format for them. Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-12-09 05:58:54 +08:00
file_key.objectid = BTRFS_EXTENT_CSUM_OBJECTID;
file_key.offset = bytenr;
file_key.type = BTRFS_EXTENT_CSUM_KEY;
item = btrfs_lookup_csum(trans, root, path, bytenr, 1);
if (!IS_ERR(item)) {
ret = 0;
leaf = path->nodes[0];
item_end = btrfs_item_ptr(leaf, path->slots[0],
struct btrfs_csum_item);
item_end = (struct btrfs_csum_item *)((char *)item_end +
btrfs_item_size(leaf, path->slots[0]));
goto found;
}
ret = PTR_ERR(item);
if (ret != -EFBIG && ret != -ENOENT)
goto out;
if (ret == -EFBIG) {
u32 item_size;
/* we found one, but it isn't big enough yet */
leaf = path->nodes[0];
item_size = btrfs_item_size(leaf, path->slots[0]);
if ((item_size / csum_size) >=
MAX_CSUM_ITEMS(fs_info, csum_size)) {
/* already at max size, make a new one */
goto insert;
}
} else {
btrfs: fix fsync failure and transaction abort after writes to prealloc extents When doing a series of partial writes to different ranges of preallocated extents with transaction commits and fsyncs in between, we can end up with a checksum items in a log tree. This causes an fsync to fail with -EIO and abort the transaction, turning the filesystem to RO mode, when syncing the log. For this to happen, we need to have a full fsync of a file following one or more fast fsyncs. The following example reproduces the problem and explains how it happens: $ mkfs.btrfs -f /dev/sdc $ mount /dev/sdc /mnt # Create our test file with 2 preallocated extents. Leave a 1M hole # between them to ensure that we get two file extent items that will # never be merged into a single one. The extents are contiguous on disk, # which will later result in the checksums for their data to be merged # into a single checksum item in the csums btree. # $ xfs_io -f \ -c "falloc 0 1M" \ -c "falloc 3M 3M" \ /mnt/foobar # Now write to the second extent and leave only 1M of it as unwritten, # which corresponds to the file range [4M, 5M[. # # Then fsync the file to flush delalloc and to clear full sync flag from # the inode, so that a future fsync will use the fast code path. # # After the writeback triggered by the fsync we have 3 file extent items # that point to the second extent we previously allocated: # # 1) One file extent item of type BTRFS_FILE_EXTENT_REG that covers the # file range [3M, 4M[ # # 2) One file extent item of type BTRFS_FILE_EXTENT_PREALLOC that covers # the file range [4M, 5M[ # # 3) One file extent item of type BTRFS_FILE_EXTENT_REG that covers the # file range [5M, 6M[ # # All these file extent items have a generation of 6, which is the ID of # the transaction where they were created. The split of the original file # extent item is done at btrfs_mark_extent_written() when ordered extents # complete for the file ranges [3M, 4M[ and [5M, 6M[. # $ xfs_io -c "pwrite -S 0xab 3M 1M" \ -c "pwrite -S 0xef 5M 1M" \ -c "fsync" \ /mnt/foobar # Commit the current transaction. This wipes out the log tree created by # the previous fsync. sync # Now write to the unwritten range of the second extent we allocated, # corresponding to the file range [4M, 5M[, and fsync the file, which # triggers the fast fsync code path. # # The fast fsync code path sees that there is a new extent map covering # the file range [4M, 5M[ and therefore it will log a checksum item # covering the range [1M, 2M[ of the second extent we allocated. # # Also, after the fsync finishes we no longer have the 3 file extent # items that pointed to 3 sections of the second extent we allocated. # Instead we end up with a single file extent item pointing to the whole # extent, with a type of BTRFS_FILE_EXTENT_REG and a generation of 7 (the # current transaction ID). This is due to the file extent item merging we # do when completing ordered extents into ranges that point to unwritten # (preallocated) extents. This merging is done at # btrfs_mark_extent_written(). # $ xfs_io -c "pwrite -S 0xcd 4M 1M" \ -c "fsync" \ /mnt/foobar # Now do some write to our file outside the range of the second extent # that we allocated with fallocate() and truncate the file size from 6M # down to 5M. # # The truncate operation sets the full sync runtime flag on the inode, # forcing the next fsync to use the slow code path. It also changes the # length of the second file extent item so that it represents the file # range [3M, 5M[ and not the range [3M, 6M[ anymore. # # Finally fsync the file. Since this is a fsync that triggers the slow # code path, it will remove all items associated to the inode from the # log tree and then it will scan for file extent items in the # fs/subvolume tree that have a generation matching the current # transaction ID, which is 7. This means it will log 2 file extent # items: # # 1) One for the first extent we allocated, covering the file range # [0, 1M[ # # 2) Another for the first 2M of the second extent we allocated, # covering the file range [3M, 5M[ # # When logging the first file extent item we log a single checksum item # that has all the checksums for the entire extent. # # When logging the second file extent item, we also lookup for the # checksums that are associated with the range [0, 2M[ of the second # extent we allocated (file range [3M, 5M[), and then we log them with # btrfs_csum_file_blocks(). However that results in ending up with a log # that has two checksum items with ranges that overlap: # # 1) One for the range [1M, 2M[ of the second extent we allocated, # corresponding to the file range [4M, 5M[, which we logged in the # previous fsync that used the fast code path; # # 2) One for the ranges [0, 1M[ and [0, 2M[ of the first and second # extents, respectively, corresponding to the files ranges [0, 1M[ # and [3M, 5M[. This one was added during this last fsync that uses # the slow code path and overlaps with the previous one logged by # the previous fast fsync. # # This happens because when logging the checksums for the second # extent, we notice they start at an offset that matches the end of the # checksums item that we logged for the first extent, and because both # extents are contiguous on disk, btrfs_csum_file_blocks() decides to # extend that existing checksums item and append the checksums for the # second extent to this item. The end result is we end up with two # checksum items in the log tree that have overlapping ranges, as # listed before, resulting in the fsync to fail with -EIO and aborting # the transaction, turning the filesystem into RO mode. # $ xfs_io -c "pwrite -S 0xff 0 1M" \ -c "truncate 5M" \ -c "fsync" \ /mnt/foobar fsync: Input/output error After running the example, dmesg/syslog shows the tree checker complained about the checksum items with overlapping ranges and we aborted the transaction: $ dmesg (...) [756289.557487] BTRFS critical (device sdc): corrupt leaf: root=18446744073709551610 block=30720000 slot=5, csum end range (16777216) goes beyond the start range (15728640) of the next csum item [756289.560583] BTRFS info (device sdc): leaf 30720000 gen 7 total ptrs 7 free space 11677 owner 18446744073709551610 [756289.562435] BTRFS info (device sdc): refs 2 lock_owner 0 current 2303929 [756289.563654] item 0 key (257 1 0) itemoff 16123 itemsize 160 [756289.564649] inode generation 6 size 5242880 mode 100600 [756289.565636] item 1 key (257 12 256) itemoff 16107 itemsize 16 [756289.566694] item 2 key (257 108 0) itemoff 16054 itemsize 53 [756289.567725] extent data disk bytenr 13631488 nr 1048576 [756289.568697] extent data offset 0 nr 1048576 ram 1048576 [756289.569689] item 3 key (257 108 1048576) itemoff 16001 itemsize 53 [756289.570682] extent data disk bytenr 0 nr 0 [756289.571363] extent data offset 0 nr 2097152 ram 2097152 [756289.572213] item 4 key (257 108 3145728) itemoff 15948 itemsize 53 [756289.573246] extent data disk bytenr 14680064 nr 3145728 [756289.574121] extent data offset 0 nr 2097152 ram 3145728 [756289.574993] item 5 key (18446744073709551606 128 13631488) itemoff 12876 itemsize 3072 [756289.576113] item 6 key (18446744073709551606 128 15728640) itemoff 11852 itemsize 1024 [756289.577286] BTRFS error (device sdc): block=30720000 write time tree block corruption detected [756289.578644] ------------[ cut here ]------------ [756289.579376] WARNING: CPU: 0 PID: 2303929 at fs/btrfs/disk-io.c:465 csum_one_extent_buffer+0xed/0x100 [btrfs] [756289.580857] Modules linked in: btrfs dm_zero dm_dust loop dm_snapshot (...) [756289.591534] CPU: 0 PID: 2303929 Comm: xfs_io Tainted: G W 5.12.0-rc8-btrfs-next-87 #1 [756289.592580] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qemu.org 04/01/2014 [756289.594161] RIP: 0010:csum_one_extent_buffer+0xed/0x100 [btrfs] [756289.595122] Code: 5d c3 e8 76 60 (...) [756289.597509] RSP: 0018:ffffb51b416cb898 EFLAGS: 00010282 [756289.598142] RAX: 0000000000000000 RBX: fffff02b8a365bc0 RCX: 0000000000000000 [756289.598970] RDX: 0000000000000000 RSI: ffffffffa9112421 RDI: 00000000ffffffff [756289.599798] RBP: ffffa06500880000 R08: 0000000000000000 R09: 0000000000000000 [756289.600619] R10: 0000000000000000 R11: 0000000000000001 R12: 0000000000000000 [756289.601456] R13: ffffa0652b1d8980 R14: ffffa06500880000 R15: 0000000000000000 [756289.602278] FS: 00007f08b23c9800(0000) GS:ffffa0682be00000(0000) knlGS:0000000000000000 [756289.603217] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [756289.603892] CR2: 00005652f32d0138 CR3: 000000025d616003 CR4: 0000000000370ef0 [756289.604725] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [756289.605563] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [756289.606400] Call Trace: [756289.606704] btree_csum_one_bio+0x244/0x2b0 [btrfs] [756289.607313] btrfs_submit_metadata_bio+0xb7/0x100 [btrfs] [756289.608040] submit_one_bio+0x61/0x70 [btrfs] [756289.608587] btree_write_cache_pages+0x587/0x610 [btrfs] [756289.609258] ? free_debug_processing+0x1d5/0x240 [756289.609812] ? __module_address+0x28/0xf0 [756289.610298] ? lock_acquire+0x1a0/0x3e0 [756289.610754] ? lock_acquired+0x19f/0x430 [756289.611220] ? lock_acquire+0x1a0/0x3e0 [756289.611675] do_writepages+0x43/0xf0 [756289.612101] ? __filemap_fdatawrite_range+0xa4/0x100 [756289.612800] __filemap_fdatawrite_range+0xc5/0x100 [756289.613393] btrfs_write_marked_extents+0x68/0x160 [btrfs] [756289.614085] btrfs_sync_log+0x21c/0xf20 [btrfs] [756289.614661] ? finish_wait+0x90/0x90 [756289.615096] ? __mutex_unlock_slowpath+0x45/0x2a0 [756289.615661] ? btrfs_log_inode_parent+0x3c9/0xdc0 [btrfs] [756289.616338] ? lock_acquire+0x1a0/0x3e0 [756289.616801] ? lock_acquired+0x19f/0x430 [756289.617284] ? lock_acquire+0x1a0/0x3e0 [756289.617750] ? lock_release+0x214/0x470 [756289.618221] ? lock_acquired+0x19f/0x430 [756289.618704] ? dput+0x20/0x4a0 [756289.619079] ? dput+0x20/0x4a0 [756289.619452] ? lockref_put_or_lock+0x9/0x30 [756289.619969] ? lock_release+0x214/0x470 [756289.620445] ? lock_release+0x214/0x470 [756289.620924] ? lock_release+0x214/0x470 [756289.621415] btrfs_sync_file+0x46a/0x5b0 [btrfs] [756289.621982] do_fsync+0x38/0x70 [756289.622395] __x64_sys_fsync+0x10/0x20 [756289.622907] do_syscall_64+0x33/0x80 [756289.623438] entry_SYSCALL_64_after_hwframe+0x44/0xae [756289.624063] RIP: 0033:0x7f08b27fbb7b [756289.624588] Code: 0f 05 48 3d 00 (...) [756289.626760] RSP: 002b:00007ffe2583f940 EFLAGS: 00000293 ORIG_RAX: 000000000000004a [756289.627639] RAX: ffffffffffffffda RBX: 00005652f32cd0f0 RCX: 00007f08b27fbb7b [756289.628464] RDX: 00005652f32cbca0 RSI: 00005652f32cd110 RDI: 0000000000000003 [756289.629323] RBP: 00005652f32cd110 R08: 0000000000000000 R09: 00007f08b28c4be0 [756289.630172] R10: fffffffffffff39a R11: 0000000000000293 R12: 0000000000000001 [756289.631007] R13: 00005652f32cd0f0 R14: 0000000000000001 R15: 00005652f32cc480 [756289.631819] irq event stamp: 0 [756289.632188] hardirqs last enabled at (0): [<0000000000000000>] 0x0 [756289.632911] hardirqs last disabled at (0): [<ffffffffa7e97c29>] copy_process+0x879/0x1cc0 [756289.633893] softirqs last enabled at (0): [<ffffffffa7e97c29>] copy_process+0x879/0x1cc0 [756289.634871] softirqs last disabled at (0): [<0000000000000000>] 0x0 [756289.635606] ---[ end trace 0a039fdc16ff3fef ]--- [756289.636179] BTRFS: error (device sdc) in btrfs_sync_log:3136: errno=-5 IO failure [756289.637082] BTRFS info (device sdc): forced readonly Having checksum items covering ranges that overlap is dangerous as in some cases it can lead to having extent ranges for which we miss checksums after log replay or getting the wrong checksum item. There were some fixes in the past for bugs that resulted in this problem, and were explained and fixed by the following commits: 27b9a8122ff71a ("Btrfs: fix csum tree corruption, duplicate and outdated checksums") b84b8390d6009c ("Btrfs: fix file read corruption after extent cloning and fsync") 40e046acbd2f36 ("Btrfs: fix missing data checksums after replaying a log tree") e289f03ea79bbc ("btrfs: fix corrupt log due to concurrent fsync of inodes with shared extents") Fix the issue by making btrfs_csum_file_blocks() taking into account the start offset of the next checksum item when it decides to extend an existing checksum item, so that it never extends the checksum to end at a range that goes beyond the start range of the next checksum item. When we can not access the next checksum item without releasing the path, simply drop the optimization of extending the previous checksum item and fallback to inserting a new checksum item - this happens rarely and the optimization is not significant enough for a log tree in order to justify the extra complexity, as it would only save a few bytes (the size of a struct btrfs_item) of leaf space. This behaviour is only needed when inserting into a log tree because for the regular checksums tree we never have a case where we try to insert a range of checksums that overlap with a range that was previously inserted. A test case for fstests will follow soon. Reported-by: Philipp Fent <fent@in.tum.de> Link: https://lore.kernel.org/linux-btrfs/93c4600e-5263-5cba-adf0-6f47526e7561@in.tum.de/ CC: stable@vger.kernel.org # 5.4+ Tested-by: Anand Jain <anand.jain@oracle.com> Signed-off-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-05-24 18:35:53 +08:00
/* We didn't find a csum item, insert one. */
ret = find_next_csum_offset(root, path, &next_offset);
if (ret < 0)
goto out;
found_next = 1;
goto insert;
}
/*
btrfs: make checksum item extension more efficient When we want to add checksums into the checksums tree, or a log tree, we try whenever possible to extend existing checksum items, as this helps reduce amount of metadata space used, since adding a new item uses extra metadata space for a btrfs_item structure (25 bytes). However we have two inefficiencies in the current approach: 1) After finding a checksum item that covers a range with an end offset that matches the start offset of the checksum range we want to insert, we release the search path populated by btrfs_lookup_csum() and then do another COW search on tree with the goal of getting additional space for at least one checksum. Doing this path release and then searching again is a waste of time because very often the leaf already has enough free space for at least one more checksum; 2) After the COW search that guarantees we get free space in the leaf for at least one more checksum, we end up not doing the extension of the previous checksum item, and fallback to insertion of a new checksum item, if the leaf doesn't have an amount of free space larger then the space required for 2 checksums plus one btrfs_item structure - this is pointless for two reasons: a) We want to extend an existing item, so we don't need to account for a btrfs_item structure (25 bytes); b) We made the COW search with an insertion size for 1 single checksum, so if the leaf ends up with a free space amount smaller then 2 checksums plus the size of a btrfs_item structure, we give up on the extension of the existing item and jump to the 'insert' label, where we end up releasing the path and then doing yet another search to insert a new checksum item for a single checksum. Fix these inefficiencies by doing the following: - For case 1), before releasing the path just check if the leaf already has enough space for at least 1 more checksum, and if it does, jump directly to the item extension code, with releasing our current path, which was already COWed by btrfs_lookup_csum(); - For case 2), fix the logic so that for item extension we require only that the leaf has enough free space for 1 checksum, and not a minimum of 2 checksums plus space for a btrfs_item structure. Signed-off-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-05-18 19:15:00 +08:00
* At this point, we know the tree has a checksum item that ends at an
* offset matching the start of the checksum range we want to insert.
* We try to extend that item as much as possible and then add as many
* checksums to it as they fit.
*
* First check if the leaf has enough free space for at least one
* checksum. If it has go directly to the item extension code, otherwise
* release the path and do a search for insertion before the extension.
*/
btrfs: make checksum item extension more efficient When we want to add checksums into the checksums tree, or a log tree, we try whenever possible to extend existing checksum items, as this helps reduce amount of metadata space used, since adding a new item uses extra metadata space for a btrfs_item structure (25 bytes). However we have two inefficiencies in the current approach: 1) After finding a checksum item that covers a range with an end offset that matches the start offset of the checksum range we want to insert, we release the search path populated by btrfs_lookup_csum() and then do another COW search on tree with the goal of getting additional space for at least one checksum. Doing this path release and then searching again is a waste of time because very often the leaf already has enough free space for at least one more checksum; 2) After the COW search that guarantees we get free space in the leaf for at least one more checksum, we end up not doing the extension of the previous checksum item, and fallback to insertion of a new checksum item, if the leaf doesn't have an amount of free space larger then the space required for 2 checksums plus one btrfs_item structure - this is pointless for two reasons: a) We want to extend an existing item, so we don't need to account for a btrfs_item structure (25 bytes); b) We made the COW search with an insertion size for 1 single checksum, so if the leaf ends up with a free space amount smaller then 2 checksums plus the size of a btrfs_item structure, we give up on the extension of the existing item and jump to the 'insert' label, where we end up releasing the path and then doing yet another search to insert a new checksum item for a single checksum. Fix these inefficiencies by doing the following: - For case 1), before releasing the path just check if the leaf already has enough space for at least 1 more checksum, and if it does, jump directly to the item extension code, with releasing our current path, which was already COWed by btrfs_lookup_csum(); - For case 2), fix the logic so that for item extension we require only that the leaf has enough free space for 1 checksum, and not a minimum of 2 checksums plus space for a btrfs_item structure. Signed-off-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-05-18 19:15:00 +08:00
if (btrfs_leaf_free_space(leaf) >= csum_size) {
btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);
csum_offset = (bytenr - found_key.offset) >>
fs_info->sectorsize_bits;
btrfs: make checksum item extension more efficient When we want to add checksums into the checksums tree, or a log tree, we try whenever possible to extend existing checksum items, as this helps reduce amount of metadata space used, since adding a new item uses extra metadata space for a btrfs_item structure (25 bytes). However we have two inefficiencies in the current approach: 1) After finding a checksum item that covers a range with an end offset that matches the start offset of the checksum range we want to insert, we release the search path populated by btrfs_lookup_csum() and then do another COW search on tree with the goal of getting additional space for at least one checksum. Doing this path release and then searching again is a waste of time because very often the leaf already has enough free space for at least one more checksum; 2) After the COW search that guarantees we get free space in the leaf for at least one more checksum, we end up not doing the extension of the previous checksum item, and fallback to insertion of a new checksum item, if the leaf doesn't have an amount of free space larger then the space required for 2 checksums plus one btrfs_item structure - this is pointless for two reasons: a) We want to extend an existing item, so we don't need to account for a btrfs_item structure (25 bytes); b) We made the COW search with an insertion size for 1 single checksum, so if the leaf ends up with a free space amount smaller then 2 checksums plus the size of a btrfs_item structure, we give up on the extension of the existing item and jump to the 'insert' label, where we end up releasing the path and then doing yet another search to insert a new checksum item for a single checksum. Fix these inefficiencies by doing the following: - For case 1), before releasing the path just check if the leaf already has enough space for at least 1 more checksum, and if it does, jump directly to the item extension code, with releasing our current path, which was already COWed by btrfs_lookup_csum(); - For case 2), fix the logic so that for item extension we require only that the leaf has enough free space for 1 checksum, and not a minimum of 2 checksums plus space for a btrfs_item structure. Signed-off-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-05-18 19:15:00 +08:00
goto extend_csum;
}
btrfs_release_path(path);
btrfs: correctly calculate item size used when item key collision happens Item key collision is allowed for some item types, like dir item and inode refs, but the overall item size is limited by the nodesize. item size(ins_len) passed from btrfs_insert_empty_items to btrfs_search_slot already contains size of btrfs_item. When btrfs_search_slot reaches leaf, we'll see if we need to split leaf. The check incorrectly reports that split leaf is required, because it treats the space required by the newly inserted item as btrfs_item + item data. But in item key collision case, only item data is actually needed, the newly inserted item could merge into the existing one. No new btrfs_item will be inserted. And split_leaf return EOVERFLOW from following code: if (extend && data_size + btrfs_item_size_nr(l, slot) + sizeof(struct btrfs_item) > BTRFS_LEAF_DATA_SIZE(fs_info)) return -EOVERFLOW; In most cases, when callers receive EOVERFLOW, they either return this error or handle in different ways. For example, in normal dir item creation the userspace will get errno EOVERFLOW; in inode ref case INODE_EXTREF is used instead. However, this is not the case for rename. To avoid the unrecoverable situation in rename, btrfs_check_dir_item_collision is called in early phase of rename. In this function, when item key collision is detected leaf space is checked: data_size = sizeof(*di) + name_len; if (data_size + btrfs_item_size_nr(leaf, slot) + sizeof(struct btrfs_item) > BTRFS_LEAF_DATA_SIZE(root->fs_info)) the sizeof(struct btrfs_item) + btrfs_item_size_nr(leaf, slot) here refers to existing item size, the condition here correctly calculates the needed size for collision case rather than the wrong case above. The consequence of inconsistent condition check between btrfs_check_dir_item_collision and btrfs_search_slot when item key collision happens is that we might pass check here but fail later at btrfs_search_slot. Rename fails and volume is forced readonly [436149.586170] ------------[ cut here ]------------ [436149.586173] BTRFS: Transaction aborted (error -75) [436149.586196] WARNING: CPU: 0 PID: 16733 at fs/btrfs/inode.c:9870 btrfs_rename2+0x1938/0x1b70 [btrfs] [436149.586227] CPU: 0 PID: 16733 Comm: python Tainted: G D 4.18.0-rc5+ #1 [436149.586228] Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 04/05/2016 [436149.586238] RIP: 0010:btrfs_rename2+0x1938/0x1b70 [btrfs] [436149.586254] RSP: 0018:ffffa327043a7ce0 EFLAGS: 00010286 [436149.586255] RAX: 0000000000000000 RBX: ffff8d8a17d13340 RCX: 0000000000000006 [436149.586256] RDX: 0000000000000007 RSI: 0000000000000096 RDI: ffff8d8a7fc164b0 [436149.586257] RBP: ffffa327043a7da0 R08: 0000000000000560 R09: 7265282064657472 [436149.586258] R10: 0000000000000000 R11: 6361736e61725420 R12: ffff8d8a0d4c8b08 [436149.586258] R13: ffff8d8a17d13340 R14: ffff8d8a33e0a540 R15: 00000000000001fe [436149.586260] FS: 00007fa313933740(0000) GS:ffff8d8a7fc00000(0000) knlGS:0000000000000000 [436149.586261] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [436149.586262] CR2: 000055d8d9c9a720 CR3: 000000007aae0003 CR4: 00000000003606f0 [436149.586295] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [436149.586296] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [436149.586296] Call Trace: [436149.586311] vfs_rename+0x383/0x920 [436149.586313] ? vfs_rename+0x383/0x920 [436149.586315] do_renameat2+0x4ca/0x590 [436149.586317] __x64_sys_rename+0x20/0x30 [436149.586324] do_syscall_64+0x5a/0x120 [436149.586330] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [436149.586332] RIP: 0033:0x7fa3133b1d37 [436149.586348] RSP: 002b:00007fffd3e43908 EFLAGS: 00000246 ORIG_RAX: 0000000000000052 [436149.586349] RAX: ffffffffffffffda RBX: 00007fa3133b1d30 RCX: 00007fa3133b1d37 [436149.586350] RDX: 000055d8da06b5e0 RSI: 000055d8da225d60 RDI: 000055d8da2c4da0 [436149.586351] RBP: 000055d8da2252f0 R08: 00007fa313782000 R09: 00000000000177e0 [436149.586351] R10: 000055d8da010680 R11: 0000000000000246 R12: 00007fa313840b00 Thanks to Hans van Kranenburg for information about crc32 hash collision tools, I was able to reproduce the dir item collision with following python script. https://github.com/wutzuchieh/misc_tools/blob/master/crc32_forge.py Run it under a btrfs volume will trigger the abort transaction. It simply creates files and rename them to forged names that leads to hash collision. There are two ways to fix this. One is to simply revert the patch 878f2d2cb355 ("Btrfs: fix max dir item size calculation") to make the condition consistent although that patch is correct about the size. The other way is to handle the leaf space check correctly when collision happens. I prefer the second one since it correct leaf space check in collision case. This fix will not account sizeof(struct btrfs_item) when the item already exists. There are two places where ins_len doesn't contain sizeof(struct btrfs_item), however. 1. extent-tree.c: lookup_inline_extent_backref 2. file-item.c: btrfs_csum_file_blocks to make the logic of btrfs_search_slot more clear, we add a flag search_for_extension in btrfs_path. This flag indicates that ins_len passed to btrfs_search_slot doesn't contain sizeof(struct btrfs_item). When key exists, btrfs_search_slot will use the actual size needed to calculate the required leaf space. CC: stable@vger.kernel.org # 4.4+ Reviewed-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: ethanwu <ethanwu@synology.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-12-01 17:25:12 +08:00
path->search_for_extension = 1;
ret = btrfs_search_slot(trans, root, &file_key, path,
csum_size, 1);
btrfs: correctly calculate item size used when item key collision happens Item key collision is allowed for some item types, like dir item and inode refs, but the overall item size is limited by the nodesize. item size(ins_len) passed from btrfs_insert_empty_items to btrfs_search_slot already contains size of btrfs_item. When btrfs_search_slot reaches leaf, we'll see if we need to split leaf. The check incorrectly reports that split leaf is required, because it treats the space required by the newly inserted item as btrfs_item + item data. But in item key collision case, only item data is actually needed, the newly inserted item could merge into the existing one. No new btrfs_item will be inserted. And split_leaf return EOVERFLOW from following code: if (extend && data_size + btrfs_item_size_nr(l, slot) + sizeof(struct btrfs_item) > BTRFS_LEAF_DATA_SIZE(fs_info)) return -EOVERFLOW; In most cases, when callers receive EOVERFLOW, they either return this error or handle in different ways. For example, in normal dir item creation the userspace will get errno EOVERFLOW; in inode ref case INODE_EXTREF is used instead. However, this is not the case for rename. To avoid the unrecoverable situation in rename, btrfs_check_dir_item_collision is called in early phase of rename. In this function, when item key collision is detected leaf space is checked: data_size = sizeof(*di) + name_len; if (data_size + btrfs_item_size_nr(leaf, slot) + sizeof(struct btrfs_item) > BTRFS_LEAF_DATA_SIZE(root->fs_info)) the sizeof(struct btrfs_item) + btrfs_item_size_nr(leaf, slot) here refers to existing item size, the condition here correctly calculates the needed size for collision case rather than the wrong case above. The consequence of inconsistent condition check between btrfs_check_dir_item_collision and btrfs_search_slot when item key collision happens is that we might pass check here but fail later at btrfs_search_slot. Rename fails and volume is forced readonly [436149.586170] ------------[ cut here ]------------ [436149.586173] BTRFS: Transaction aborted (error -75) [436149.586196] WARNING: CPU: 0 PID: 16733 at fs/btrfs/inode.c:9870 btrfs_rename2+0x1938/0x1b70 [btrfs] [436149.586227] CPU: 0 PID: 16733 Comm: python Tainted: G D 4.18.0-rc5+ #1 [436149.586228] Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 04/05/2016 [436149.586238] RIP: 0010:btrfs_rename2+0x1938/0x1b70 [btrfs] [436149.586254] RSP: 0018:ffffa327043a7ce0 EFLAGS: 00010286 [436149.586255] RAX: 0000000000000000 RBX: ffff8d8a17d13340 RCX: 0000000000000006 [436149.586256] RDX: 0000000000000007 RSI: 0000000000000096 RDI: ffff8d8a7fc164b0 [436149.586257] RBP: ffffa327043a7da0 R08: 0000000000000560 R09: 7265282064657472 [436149.586258] R10: 0000000000000000 R11: 6361736e61725420 R12: ffff8d8a0d4c8b08 [436149.586258] R13: ffff8d8a17d13340 R14: ffff8d8a33e0a540 R15: 00000000000001fe [436149.586260] FS: 00007fa313933740(0000) GS:ffff8d8a7fc00000(0000) knlGS:0000000000000000 [436149.586261] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [436149.586262] CR2: 000055d8d9c9a720 CR3: 000000007aae0003 CR4: 00000000003606f0 [436149.586295] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [436149.586296] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [436149.586296] Call Trace: [436149.586311] vfs_rename+0x383/0x920 [436149.586313] ? vfs_rename+0x383/0x920 [436149.586315] do_renameat2+0x4ca/0x590 [436149.586317] __x64_sys_rename+0x20/0x30 [436149.586324] do_syscall_64+0x5a/0x120 [436149.586330] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [436149.586332] RIP: 0033:0x7fa3133b1d37 [436149.586348] RSP: 002b:00007fffd3e43908 EFLAGS: 00000246 ORIG_RAX: 0000000000000052 [436149.586349] RAX: ffffffffffffffda RBX: 00007fa3133b1d30 RCX: 00007fa3133b1d37 [436149.586350] RDX: 000055d8da06b5e0 RSI: 000055d8da225d60 RDI: 000055d8da2c4da0 [436149.586351] RBP: 000055d8da2252f0 R08: 00007fa313782000 R09: 00000000000177e0 [436149.586351] R10: 000055d8da010680 R11: 0000000000000246 R12: 00007fa313840b00 Thanks to Hans van Kranenburg for information about crc32 hash collision tools, I was able to reproduce the dir item collision with following python script. https://github.com/wutzuchieh/misc_tools/blob/master/crc32_forge.py Run it under a btrfs volume will trigger the abort transaction. It simply creates files and rename them to forged names that leads to hash collision. There are two ways to fix this. One is to simply revert the patch 878f2d2cb355 ("Btrfs: fix max dir item size calculation") to make the condition consistent although that patch is correct about the size. The other way is to handle the leaf space check correctly when collision happens. I prefer the second one since it correct leaf space check in collision case. This fix will not account sizeof(struct btrfs_item) when the item already exists. There are two places where ins_len doesn't contain sizeof(struct btrfs_item), however. 1. extent-tree.c: lookup_inline_extent_backref 2. file-item.c: btrfs_csum_file_blocks to make the logic of btrfs_search_slot more clear, we add a flag search_for_extension in btrfs_path. This flag indicates that ins_len passed to btrfs_search_slot doesn't contain sizeof(struct btrfs_item). When key exists, btrfs_search_slot will use the actual size needed to calculate the required leaf space. CC: stable@vger.kernel.org # 4.4+ Reviewed-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: ethanwu <ethanwu@synology.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-12-01 17:25:12 +08:00
path->search_for_extension = 0;
if (ret < 0)
goto out;
if (ret > 0) {
if (path->slots[0] == 0)
goto insert;
path->slots[0]--;
}
leaf = path->nodes[0];
btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);
csum_offset = (bytenr - found_key.offset) >> fs_info->sectorsize_bits;
if (found_key.type != BTRFS_EXTENT_CSUM_KEY ||
Btrfs: move data checksumming into a dedicated tree Btrfs stores checksums for each data block. Until now, they have been stored in the subvolume trees, indexed by the inode that is referencing the data block. This means that when we read the inode, we've probably read in at least some checksums as well. But, this has a few problems: * The checksums are indexed by logical offset in the file. When compression is on, this means we have to do the expensive checksumming on the uncompressed data. It would be faster if we could checksum the compressed data instead. * If we implement encryption, we'll be checksumming the plain text and storing that on disk. This is significantly less secure. * For either compression or encryption, we have to get the plain text back before we can verify the checksum as correct. This makes the raid layer balancing and extent moving much more expensive. * It makes the front end caching code more complex, as we have touch the subvolume and inodes as we cache extents. * There is potentitally one copy of the checksum in each subvolume referencing an extent. The solution used here is to store the extent checksums in a dedicated tree. This allows us to index the checksums by phyiscal extent start and length. It means: * The checksum is against the data stored on disk, after any compression or encryption is done. * The checksum is stored in a central location, and can be verified without following back references, or reading inodes. This makes compression significantly faster by reducing the amount of data that needs to be checksummed. It will also allow much faster raid management code in general. The checksums are indexed by a key with a fixed objectid (a magic value in ctree.h) and offset set to the starting byte of the extent. This allows us to copy the checksum items into the fsync log tree directly (or any other tree), without having to invent a second format for them. Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-12-09 05:58:54 +08:00
found_key.objectid != BTRFS_EXTENT_CSUM_OBJECTID ||
csum_offset >= MAX_CSUM_ITEMS(fs_info, csum_size)) {
goto insert;
}
btrfs: make checksum item extension more efficient When we want to add checksums into the checksums tree, or a log tree, we try whenever possible to extend existing checksum items, as this helps reduce amount of metadata space used, since adding a new item uses extra metadata space for a btrfs_item structure (25 bytes). However we have two inefficiencies in the current approach: 1) After finding a checksum item that covers a range with an end offset that matches the start offset of the checksum range we want to insert, we release the search path populated by btrfs_lookup_csum() and then do another COW search on tree with the goal of getting additional space for at least one checksum. Doing this path release and then searching again is a waste of time because very often the leaf already has enough free space for at least one more checksum; 2) After the COW search that guarantees we get free space in the leaf for at least one more checksum, we end up not doing the extension of the previous checksum item, and fallback to insertion of a new checksum item, if the leaf doesn't have an amount of free space larger then the space required for 2 checksums plus one btrfs_item structure - this is pointless for two reasons: a) We want to extend an existing item, so we don't need to account for a btrfs_item structure (25 bytes); b) We made the COW search with an insertion size for 1 single checksum, so if the leaf ends up with a free space amount smaller then 2 checksums plus the size of a btrfs_item structure, we give up on the extension of the existing item and jump to the 'insert' label, where we end up releasing the path and then doing yet another search to insert a new checksum item for a single checksum. Fix these inefficiencies by doing the following: - For case 1), before releasing the path just check if the leaf already has enough space for at least 1 more checksum, and if it does, jump directly to the item extension code, with releasing our current path, which was already COWed by btrfs_lookup_csum(); - For case 2), fix the logic so that for item extension we require only that the leaf has enough free space for 1 checksum, and not a minimum of 2 checksums plus space for a btrfs_item structure. Signed-off-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-05-18 19:15:00 +08:00
extend_csum:
if (csum_offset == btrfs_item_size(leaf, path->slots[0]) /
csum_size) {
int extend_nr;
u64 tmp;
u32 diff;
tmp = sums->len - total_bytes;
tmp >>= fs_info->sectorsize_bits;
WARN_ON(tmp < 1);
btrfs: fix fsync failure and transaction abort after writes to prealloc extents When doing a series of partial writes to different ranges of preallocated extents with transaction commits and fsyncs in between, we can end up with a checksum items in a log tree. This causes an fsync to fail with -EIO and abort the transaction, turning the filesystem to RO mode, when syncing the log. For this to happen, we need to have a full fsync of a file following one or more fast fsyncs. The following example reproduces the problem and explains how it happens: $ mkfs.btrfs -f /dev/sdc $ mount /dev/sdc /mnt # Create our test file with 2 preallocated extents. Leave a 1M hole # between them to ensure that we get two file extent items that will # never be merged into a single one. The extents are contiguous on disk, # which will later result in the checksums for their data to be merged # into a single checksum item in the csums btree. # $ xfs_io -f \ -c "falloc 0 1M" \ -c "falloc 3M 3M" \ /mnt/foobar # Now write to the second extent and leave only 1M of it as unwritten, # which corresponds to the file range [4M, 5M[. # # Then fsync the file to flush delalloc and to clear full sync flag from # the inode, so that a future fsync will use the fast code path. # # After the writeback triggered by the fsync we have 3 file extent items # that point to the second extent we previously allocated: # # 1) One file extent item of type BTRFS_FILE_EXTENT_REG that covers the # file range [3M, 4M[ # # 2) One file extent item of type BTRFS_FILE_EXTENT_PREALLOC that covers # the file range [4M, 5M[ # # 3) One file extent item of type BTRFS_FILE_EXTENT_REG that covers the # file range [5M, 6M[ # # All these file extent items have a generation of 6, which is the ID of # the transaction where they were created. The split of the original file # extent item is done at btrfs_mark_extent_written() when ordered extents # complete for the file ranges [3M, 4M[ and [5M, 6M[. # $ xfs_io -c "pwrite -S 0xab 3M 1M" \ -c "pwrite -S 0xef 5M 1M" \ -c "fsync" \ /mnt/foobar # Commit the current transaction. This wipes out the log tree created by # the previous fsync. sync # Now write to the unwritten range of the second extent we allocated, # corresponding to the file range [4M, 5M[, and fsync the file, which # triggers the fast fsync code path. # # The fast fsync code path sees that there is a new extent map covering # the file range [4M, 5M[ and therefore it will log a checksum item # covering the range [1M, 2M[ of the second extent we allocated. # # Also, after the fsync finishes we no longer have the 3 file extent # items that pointed to 3 sections of the second extent we allocated. # Instead we end up with a single file extent item pointing to the whole # extent, with a type of BTRFS_FILE_EXTENT_REG and a generation of 7 (the # current transaction ID). This is due to the file extent item merging we # do when completing ordered extents into ranges that point to unwritten # (preallocated) extents. This merging is done at # btrfs_mark_extent_written(). # $ xfs_io -c "pwrite -S 0xcd 4M 1M" \ -c "fsync" \ /mnt/foobar # Now do some write to our file outside the range of the second extent # that we allocated with fallocate() and truncate the file size from 6M # down to 5M. # # The truncate operation sets the full sync runtime flag on the inode, # forcing the next fsync to use the slow code path. It also changes the # length of the second file extent item so that it represents the file # range [3M, 5M[ and not the range [3M, 6M[ anymore. # # Finally fsync the file. Since this is a fsync that triggers the slow # code path, it will remove all items associated to the inode from the # log tree and then it will scan for file extent items in the # fs/subvolume tree that have a generation matching the current # transaction ID, which is 7. This means it will log 2 file extent # items: # # 1) One for the first extent we allocated, covering the file range # [0, 1M[ # # 2) Another for the first 2M of the second extent we allocated, # covering the file range [3M, 5M[ # # When logging the first file extent item we log a single checksum item # that has all the checksums for the entire extent. # # When logging the second file extent item, we also lookup for the # checksums that are associated with the range [0, 2M[ of the second # extent we allocated (file range [3M, 5M[), and then we log them with # btrfs_csum_file_blocks(). However that results in ending up with a log # that has two checksum items with ranges that overlap: # # 1) One for the range [1M, 2M[ of the second extent we allocated, # corresponding to the file range [4M, 5M[, which we logged in the # previous fsync that used the fast code path; # # 2) One for the ranges [0, 1M[ and [0, 2M[ of the first and second # extents, respectively, corresponding to the files ranges [0, 1M[ # and [3M, 5M[. This one was added during this last fsync that uses # the slow code path and overlaps with the previous one logged by # the previous fast fsync. # # This happens because when logging the checksums for the second # extent, we notice they start at an offset that matches the end of the # checksums item that we logged for the first extent, and because both # extents are contiguous on disk, btrfs_csum_file_blocks() decides to # extend that existing checksums item and append the checksums for the # second extent to this item. The end result is we end up with two # checksum items in the log tree that have overlapping ranges, as # listed before, resulting in the fsync to fail with -EIO and aborting # the transaction, turning the filesystem into RO mode. # $ xfs_io -c "pwrite -S 0xff 0 1M" \ -c "truncate 5M" \ -c "fsync" \ /mnt/foobar fsync: Input/output error After running the example, dmesg/syslog shows the tree checker complained about the checksum items with overlapping ranges and we aborted the transaction: $ dmesg (...) [756289.557487] BTRFS critical (device sdc): corrupt leaf: root=18446744073709551610 block=30720000 slot=5, csum end range (16777216) goes beyond the start range (15728640) of the next csum item [756289.560583] BTRFS info (device sdc): leaf 30720000 gen 7 total ptrs 7 free space 11677 owner 18446744073709551610 [756289.562435] BTRFS info (device sdc): refs 2 lock_owner 0 current 2303929 [756289.563654] item 0 key (257 1 0) itemoff 16123 itemsize 160 [756289.564649] inode generation 6 size 5242880 mode 100600 [756289.565636] item 1 key (257 12 256) itemoff 16107 itemsize 16 [756289.566694] item 2 key (257 108 0) itemoff 16054 itemsize 53 [756289.567725] extent data disk bytenr 13631488 nr 1048576 [756289.568697] extent data offset 0 nr 1048576 ram 1048576 [756289.569689] item 3 key (257 108 1048576) itemoff 16001 itemsize 53 [756289.570682] extent data disk bytenr 0 nr 0 [756289.571363] extent data offset 0 nr 2097152 ram 2097152 [756289.572213] item 4 key (257 108 3145728) itemoff 15948 itemsize 53 [756289.573246] extent data disk bytenr 14680064 nr 3145728 [756289.574121] extent data offset 0 nr 2097152 ram 3145728 [756289.574993] item 5 key (18446744073709551606 128 13631488) itemoff 12876 itemsize 3072 [756289.576113] item 6 key (18446744073709551606 128 15728640) itemoff 11852 itemsize 1024 [756289.577286] BTRFS error (device sdc): block=30720000 write time tree block corruption detected [756289.578644] ------------[ cut here ]------------ [756289.579376] WARNING: CPU: 0 PID: 2303929 at fs/btrfs/disk-io.c:465 csum_one_extent_buffer+0xed/0x100 [btrfs] [756289.580857] Modules linked in: btrfs dm_zero dm_dust loop dm_snapshot (...) [756289.591534] CPU: 0 PID: 2303929 Comm: xfs_io Tainted: G W 5.12.0-rc8-btrfs-next-87 #1 [756289.592580] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qemu.org 04/01/2014 [756289.594161] RIP: 0010:csum_one_extent_buffer+0xed/0x100 [btrfs] [756289.595122] Code: 5d c3 e8 76 60 (...) [756289.597509] RSP: 0018:ffffb51b416cb898 EFLAGS: 00010282 [756289.598142] RAX: 0000000000000000 RBX: fffff02b8a365bc0 RCX: 0000000000000000 [756289.598970] RDX: 0000000000000000 RSI: ffffffffa9112421 RDI: 00000000ffffffff [756289.599798] RBP: ffffa06500880000 R08: 0000000000000000 R09: 0000000000000000 [756289.600619] R10: 0000000000000000 R11: 0000000000000001 R12: 0000000000000000 [756289.601456] R13: ffffa0652b1d8980 R14: ffffa06500880000 R15: 0000000000000000 [756289.602278] FS: 00007f08b23c9800(0000) GS:ffffa0682be00000(0000) knlGS:0000000000000000 [756289.603217] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [756289.603892] CR2: 00005652f32d0138 CR3: 000000025d616003 CR4: 0000000000370ef0 [756289.604725] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [756289.605563] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [756289.606400] Call Trace: [756289.606704] btree_csum_one_bio+0x244/0x2b0 [btrfs] [756289.607313] btrfs_submit_metadata_bio+0xb7/0x100 [btrfs] [756289.608040] submit_one_bio+0x61/0x70 [btrfs] [756289.608587] btree_write_cache_pages+0x587/0x610 [btrfs] [756289.609258] ? free_debug_processing+0x1d5/0x240 [756289.609812] ? __module_address+0x28/0xf0 [756289.610298] ? lock_acquire+0x1a0/0x3e0 [756289.610754] ? lock_acquired+0x19f/0x430 [756289.611220] ? lock_acquire+0x1a0/0x3e0 [756289.611675] do_writepages+0x43/0xf0 [756289.612101] ? __filemap_fdatawrite_range+0xa4/0x100 [756289.612800] __filemap_fdatawrite_range+0xc5/0x100 [756289.613393] btrfs_write_marked_extents+0x68/0x160 [btrfs] [756289.614085] btrfs_sync_log+0x21c/0xf20 [btrfs] [756289.614661] ? finish_wait+0x90/0x90 [756289.615096] ? __mutex_unlock_slowpath+0x45/0x2a0 [756289.615661] ? btrfs_log_inode_parent+0x3c9/0xdc0 [btrfs] [756289.616338] ? lock_acquire+0x1a0/0x3e0 [756289.616801] ? lock_acquired+0x19f/0x430 [756289.617284] ? lock_acquire+0x1a0/0x3e0 [756289.617750] ? lock_release+0x214/0x470 [756289.618221] ? lock_acquired+0x19f/0x430 [756289.618704] ? dput+0x20/0x4a0 [756289.619079] ? dput+0x20/0x4a0 [756289.619452] ? lockref_put_or_lock+0x9/0x30 [756289.619969] ? lock_release+0x214/0x470 [756289.620445] ? lock_release+0x214/0x470 [756289.620924] ? lock_release+0x214/0x470 [756289.621415] btrfs_sync_file+0x46a/0x5b0 [btrfs] [756289.621982] do_fsync+0x38/0x70 [756289.622395] __x64_sys_fsync+0x10/0x20 [756289.622907] do_syscall_64+0x33/0x80 [756289.623438] entry_SYSCALL_64_after_hwframe+0x44/0xae [756289.624063] RIP: 0033:0x7f08b27fbb7b [756289.624588] Code: 0f 05 48 3d 00 (...) [756289.626760] RSP: 002b:00007ffe2583f940 EFLAGS: 00000293 ORIG_RAX: 000000000000004a [756289.627639] RAX: ffffffffffffffda RBX: 00005652f32cd0f0 RCX: 00007f08b27fbb7b [756289.628464] RDX: 00005652f32cbca0 RSI: 00005652f32cd110 RDI: 0000000000000003 [756289.629323] RBP: 00005652f32cd110 R08: 0000000000000000 R09: 00007f08b28c4be0 [756289.630172] R10: fffffffffffff39a R11: 0000000000000293 R12: 0000000000000001 [756289.631007] R13: 00005652f32cd0f0 R14: 0000000000000001 R15: 00005652f32cc480 [756289.631819] irq event stamp: 0 [756289.632188] hardirqs last enabled at (0): [<0000000000000000>] 0x0 [756289.632911] hardirqs last disabled at (0): [<ffffffffa7e97c29>] copy_process+0x879/0x1cc0 [756289.633893] softirqs last enabled at (0): [<ffffffffa7e97c29>] copy_process+0x879/0x1cc0 [756289.634871] softirqs last disabled at (0): [<0000000000000000>] 0x0 [756289.635606] ---[ end trace 0a039fdc16ff3fef ]--- [756289.636179] BTRFS: error (device sdc) in btrfs_sync_log:3136: errno=-5 IO failure [756289.637082] BTRFS info (device sdc): forced readonly Having checksum items covering ranges that overlap is dangerous as in some cases it can lead to having extent ranges for which we miss checksums after log replay or getting the wrong checksum item. There were some fixes in the past for bugs that resulted in this problem, and were explained and fixed by the following commits: 27b9a8122ff71a ("Btrfs: fix csum tree corruption, duplicate and outdated checksums") b84b8390d6009c ("Btrfs: fix file read corruption after extent cloning and fsync") 40e046acbd2f36 ("Btrfs: fix missing data checksums after replaying a log tree") e289f03ea79bbc ("btrfs: fix corrupt log due to concurrent fsync of inodes with shared extents") Fix the issue by making btrfs_csum_file_blocks() taking into account the start offset of the next checksum item when it decides to extend an existing checksum item, so that it never extends the checksum to end at a range that goes beyond the start range of the next checksum item. When we can not access the next checksum item without releasing the path, simply drop the optimization of extending the previous checksum item and fallback to inserting a new checksum item - this happens rarely and the optimization is not significant enough for a log tree in order to justify the extra complexity, as it would only save a few bytes (the size of a struct btrfs_item) of leaf space. This behaviour is only needed when inserting into a log tree because for the regular checksums tree we never have a case where we try to insert a range of checksums that overlap with a range that was previously inserted. A test case for fstests will follow soon. Reported-by: Philipp Fent <fent@in.tum.de> Link: https://lore.kernel.org/linux-btrfs/93c4600e-5263-5cba-adf0-6f47526e7561@in.tum.de/ CC: stable@vger.kernel.org # 5.4+ Tested-by: Anand Jain <anand.jain@oracle.com> Signed-off-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-05-24 18:35:53 +08:00
extend_nr = max_t(int, 1, tmp);
/*
* A log tree can already have checksum items with a subset of
* the checksums we are trying to log. This can happen after
* doing a sequence of partial writes into prealloc extents and
* fsyncs in between, with a full fsync logging a larger subrange
* of an extent for which a previous fast fsync logged a smaller
* subrange. And this happens in particular due to merging file
* extent items when we complete an ordered extent for a range
* covered by a prealloc extent - this is done at
* btrfs_mark_extent_written().
*
* So if we try to extend the previous checksum item, which has
* a range that ends at the start of the range we want to insert,
* make sure we don't extend beyond the start offset of the next
* checksum item. If we are at the last item in the leaf, then
* forget the optimization of extending and add a new checksum
* item - it is not worth the complexity of releasing the path,
* getting the first key for the next leaf, repeat the btree
* search, etc, because log trees are temporary anyway and it
* would only save a few bytes of leaf space.
*/
if (root->root_key.objectid == BTRFS_TREE_LOG_OBJECTID) {
if (path->slots[0] + 1 >=
btrfs_header_nritems(path->nodes[0])) {
ret = find_next_csum_offset(root, path, &next_offset);
if (ret < 0)
goto out;
found_next = 1;
goto insert;
}
ret = find_next_csum_offset(root, path, &next_offset);
if (ret < 0)
goto out;
tmp = (next_offset - bytenr) >> fs_info->sectorsize_bits;
if (tmp <= INT_MAX)
extend_nr = min_t(int, extend_nr, tmp);
}
diff = (csum_offset + extend_nr) * csum_size;
diff = min(diff,
MAX_CSUM_ITEMS(fs_info, csum_size) * csum_size);
diff = diff - btrfs_item_size(leaf, path->slots[0]);
btrfs: make checksum item extension more efficient When we want to add checksums into the checksums tree, or a log tree, we try whenever possible to extend existing checksum items, as this helps reduce amount of metadata space used, since adding a new item uses extra metadata space for a btrfs_item structure (25 bytes). However we have two inefficiencies in the current approach: 1) After finding a checksum item that covers a range with an end offset that matches the start offset of the checksum range we want to insert, we release the search path populated by btrfs_lookup_csum() and then do another COW search on tree with the goal of getting additional space for at least one checksum. Doing this path release and then searching again is a waste of time because very often the leaf already has enough free space for at least one more checksum; 2) After the COW search that guarantees we get free space in the leaf for at least one more checksum, we end up not doing the extension of the previous checksum item, and fallback to insertion of a new checksum item, if the leaf doesn't have an amount of free space larger then the space required for 2 checksums plus one btrfs_item structure - this is pointless for two reasons: a) We want to extend an existing item, so we don't need to account for a btrfs_item structure (25 bytes); b) We made the COW search with an insertion size for 1 single checksum, so if the leaf ends up with a free space amount smaller then 2 checksums plus the size of a btrfs_item structure, we give up on the extension of the existing item and jump to the 'insert' label, where we end up releasing the path and then doing yet another search to insert a new checksum item for a single checksum. Fix these inefficiencies by doing the following: - For case 1), before releasing the path just check if the leaf already has enough space for at least 1 more checksum, and if it does, jump directly to the item extension code, with releasing our current path, which was already COWed by btrfs_lookup_csum(); - For case 2), fix the logic so that for item extension we require only that the leaf has enough free space for 1 checksum, and not a minimum of 2 checksums plus space for a btrfs_item structure. Signed-off-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-05-18 19:15:00 +08:00
diff = min_t(u32, btrfs_leaf_free_space(leaf), diff);
diff /= csum_size;
diff *= csum_size;
btrfs_extend_item(path, diff);
ret = 0;
goto csum;
}
insert:
btrfs_release_path(path);
csum_offset = 0;
if (found_next) {
u64 tmp;
Btrfs: move data checksumming into a dedicated tree Btrfs stores checksums for each data block. Until now, they have been stored in the subvolume trees, indexed by the inode that is referencing the data block. This means that when we read the inode, we've probably read in at least some checksums as well. But, this has a few problems: * The checksums are indexed by logical offset in the file. When compression is on, this means we have to do the expensive checksumming on the uncompressed data. It would be faster if we could checksum the compressed data instead. * If we implement encryption, we'll be checksumming the plain text and storing that on disk. This is significantly less secure. * For either compression or encryption, we have to get the plain text back before we can verify the checksum as correct. This makes the raid layer balancing and extent moving much more expensive. * It makes the front end caching code more complex, as we have touch the subvolume and inodes as we cache extents. * There is potentitally one copy of the checksum in each subvolume referencing an extent. The solution used here is to store the extent checksums in a dedicated tree. This allows us to index the checksums by phyiscal extent start and length. It means: * The checksum is against the data stored on disk, after any compression or encryption is done. * The checksum is stored in a central location, and can be verified without following back references, or reading inodes. This makes compression significantly faster by reducing the amount of data that needs to be checksummed. It will also allow much faster raid management code in general. The checksums are indexed by a key with a fixed objectid (a magic value in ctree.h) and offset set to the starting byte of the extent. This allows us to copy the checksum items into the fsync log tree directly (or any other tree), without having to invent a second format for them. Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-12-09 05:58:54 +08:00
tmp = sums->len - total_bytes;
tmp >>= fs_info->sectorsize_bits;
tmp = min(tmp, (next_offset - file_key.offset) >>
fs_info->sectorsize_bits);
tmp = max_t(u64, 1, tmp);
tmp = min_t(u64, tmp, MAX_CSUM_ITEMS(fs_info, csum_size));
ins_size = csum_size * tmp;
} else {
ins_size = csum_size;
}
ret = btrfs_insert_empty_item(trans, root, path, &file_key,
ins_size);
if (ret < 0)
goto out;
if (WARN_ON(ret != 0))
goto out;
leaf = path->nodes[0];
csum:
item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_csum_item);
item_end = (struct btrfs_csum_item *)((unsigned char *)item +
btrfs_item_size(leaf, path->slots[0]));
item = (struct btrfs_csum_item *)((unsigned char *)item +
csum_offset * csum_size);
found:
ins_size = (u32)(sums->len - total_bytes) >> fs_info->sectorsize_bits;
ins_size *= csum_size;
ins_size = min_t(u32, (unsigned long)item_end - (unsigned long)item,
ins_size);
write_extent_buffer(leaf, sums->sums + index, (unsigned long)item,
ins_size);
index += ins_size;
ins_size /= csum_size;
total_bytes += ins_size * fs_info->sectorsize;
btrfs_mark_buffer_dirty(path->nodes[0]);
if (total_bytes < sums->len) {
btrfs_release_path(path);
cond_resched();
goto again;
}
out:
btrfs_free_path(path);
return ret;
}
void btrfs_extent_item_to_extent_map(struct btrfs_inode *inode,
const struct btrfs_path *path,
struct btrfs_file_extent_item *fi,
struct extent_map *em)
{
struct btrfs_fs_info *fs_info = inode->root->fs_info;
struct btrfs_root *root = inode->root;
struct extent_buffer *leaf = path->nodes[0];
const int slot = path->slots[0];
struct btrfs_key key;
u64 extent_start, extent_end;
u64 bytenr;
u8 type = btrfs_file_extent_type(leaf, fi);
int compress_type = btrfs_file_extent_compression(leaf, fi);
btrfs_item_key_to_cpu(leaf, &key, slot);
extent_start = key.offset;
extent_end = btrfs_file_extent_end(path);
em->ram_bytes = btrfs_file_extent_ram_bytes(leaf, fi);
btrfs: populate extent_map::generation when reading from disk When btrfs_get_extent() tries to get some file extent from disk, it never populates extent_map::generation, leaving the value to be 0. On the other hand, for extent map generated by IO, it will get its generation properly set at finish_ordered_io() finish_ordered_io() |- unpin_extent_cache(gen = trans->transid) |- em->generation = gen; [CAUSE] Since extent_map::generation is mostly used by fsync code, and for fsync they only care about modified extents, which all have their em::generation > 0. Thus it's fine to not populate em read from disk for fsync. [CORNER CASE] However autodefrag also relies on em::generation to determine if one extent needs to be defragged. This unpopulated extent_map::generation can prevent the following autodefrag case from working: mkfs.btrfs -f $dev mount $dev $mnt -o autodefrag # initial write to queue the inode for autodefrag xfs_io -f -c "pwrite 0 4k" $mnt/file sync # Real fragmented write xfs_io -f -s -c "pwrite -b 4096 0 32k" $mnt/file sync echo "=== before autodefrag ===" xfs_io -c "fiemap -v" $mnt/file # Drop cache to force em to be read from disk echo 3 > /proc/sys/vm/drop_caches mount -o remount,commit=1 $mnt sleep 3 sync echo "=== After autodefrag ===" xfs_io -c "fiemap -v" $mnt/file umount $mnt The result looks like this: === before autodefrag === /mnt/btrfs/file: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..15]: 26672..26687 16 0x0 1: [16..31]: 26656..26671 16 0x0 2: [32..47]: 26640..26655 16 0x0 3: [48..63]: 26624..26639 16 0x1 === After autodefrag === /mnt/btrfs/file: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..15]: 26672..26687 16 0x0 1: [16..31]: 26656..26671 16 0x0 2: [32..47]: 26640..26655 16 0x0 3: [48..63]: 26624..26639 16 0x1 This fragmented 32K will not be defragged by autodefrag. [FIX] To make things less weird, just populate extent_map::generation when reading file extents from disk. This would make above fragmented extents to be properly defragged: == before autodefrag === /mnt/btrfs/file: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..15]: 26672..26687 16 0x0 1: [16..31]: 26656..26671 16 0x0 2: [32..47]: 26640..26655 16 0x0 3: [48..63]: 26624..26639 16 0x1 === After autodefrag === /mnt/btrfs/file: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..63]: 26688..26751 64 0x1 Reviewed-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2022-02-08 13:31:19 +08:00
em->generation = btrfs_file_extent_generation(leaf, fi);
if (type == BTRFS_FILE_EXTENT_REG ||
type == BTRFS_FILE_EXTENT_PREALLOC) {
em->start = extent_start;
em->len = extent_end - extent_start;
em->orig_start = extent_start -
btrfs_file_extent_offset(leaf, fi);
em->orig_block_len = btrfs_file_extent_disk_num_bytes(leaf, fi);
bytenr = btrfs_file_extent_disk_bytenr(leaf, fi);
if (bytenr == 0) {
em->block_start = EXTENT_MAP_HOLE;
return;
}
if (compress_type != BTRFS_COMPRESS_NONE) {
set_bit(EXTENT_FLAG_COMPRESSED, &em->flags);
em->compress_type = compress_type;
em->block_start = bytenr;
em->block_len = em->orig_block_len;
} else {
bytenr += btrfs_file_extent_offset(leaf, fi);
em->block_start = bytenr;
em->block_len = em->len;
if (type == BTRFS_FILE_EXTENT_PREALLOC)
set_bit(EXTENT_FLAG_PREALLOC, &em->flags);
}
} else if (type == BTRFS_FILE_EXTENT_INLINE) {
em->block_start = EXTENT_MAP_INLINE;
em->start = extent_start;
em->len = extent_end - extent_start;
/*
* Initialize orig_start and block_len with the same values
* as in inode.c:btrfs_get_extent().
*/
em->orig_start = EXTENT_MAP_HOLE;
em->block_len = (u64)-1;
em->compress_type = compress_type;
if (compress_type != BTRFS_COMPRESS_NONE)
set_bit(EXTENT_FLAG_COMPRESSED, &em->flags);
} else {
btrfs_err(fs_info,
"unknown file extent item type %d, inode %llu, offset %llu, "
"root %llu", type, btrfs_ino(inode), extent_start,
root->root_key.objectid);
}
}
/*
* Returns the end offset (non inclusive) of the file extent item the given path
* points to. If it points to an inline extent, the returned offset is rounded
* up to the sector size.
*/
u64 btrfs_file_extent_end(const struct btrfs_path *path)
{
const struct extent_buffer *leaf = path->nodes[0];
const int slot = path->slots[0];
struct btrfs_file_extent_item *fi;
struct btrfs_key key;
u64 end;
btrfs_item_key_to_cpu(leaf, &key, slot);
ASSERT(key.type == BTRFS_EXTENT_DATA_KEY);
fi = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item);
if (btrfs_file_extent_type(leaf, fi) == BTRFS_FILE_EXTENT_INLINE) {
end = btrfs_file_extent_ram_bytes(leaf, fi);
end = ALIGN(key.offset + end, leaf->fs_info->sectorsize);
} else {
end = key.offset + btrfs_file_extent_num_bytes(leaf, fi);
}
return end;
}