OpenCloudOS-Kernel/fs/btrfs/compression.c

1890 lines
50 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
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
/*
* Copyright (C) 2008 Oracle. All rights reserved.
*/
#include <linux/kernel.h>
#include <linux/bio.h>
#include <linux/file.h>
#include <linux/fs.h>
#include <linux/pagemap.h>
#include <linux/highmem.h>
#include <linux/kthread.h>
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
#include <linux/time.h>
#include <linux/init.h>
#include <linux/string.h>
#include <linux/backing-dev.h>
#include <linux/writeback.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/sched/mm.h>
#include <linux/log2.h>
#include <crypto/hash.h>
#include "misc.h"
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
#include "ctree.h"
#include "disk-io.h"
#include "transaction.h"
#include "btrfs_inode.h"
#include "volumes.h"
#include "ordered-data.h"
#include "compression.h"
#include "extent_io.h"
#include "extent_map.h"
btrfs: subpage: make add_ra_bio_pages() compatible [BUG] If we remove the subpage limitation in add_ra_bio_pages(), then read a compressed extent which has part of its range in next page, like the following inode layout: 0 32K 64K 96K 128K |<--------------|-------------->| Btrfs will trigger ASSERT() in endio function: assertion failed: atomic_read(&subpage->readers) >= nbits ------------[ cut here ]------------ kernel BUG at fs/btrfs/ctree.h:3431! Internal error: Oops - BUG: 0 [#1] SMP Workqueue: btrfs-endio btrfs_work_helper [btrfs] Call trace: assertfail.constprop.0+0x28/0x2c [btrfs] btrfs_subpage_end_reader+0x148/0x14c [btrfs] end_page_read+0x8c/0x100 [btrfs] end_bio_extent_readpage+0x320/0x6b0 [btrfs] bio_endio+0x15c/0x1dc end_workqueue_fn+0x44/0x64 [btrfs] btrfs_work_helper+0x74/0x250 [btrfs] process_one_work+0x1d4/0x47c worker_thread+0x180/0x400 kthread+0x11c/0x120 ret_from_fork+0x10/0x30 ---[ end trace c8b7b552d3bb408c ]--- [CAUSE] When we read the page range [0, 64K), we find it's a compressed extent, and we will try to add extra pages in add_ra_bio_pages() to avoid reading the same compressed extent. But when we add such page into the read bio, it doesn't follow the behavior of btrfs_do_readpage() to properly set subpage::readers. This means, for page [64K, 128K), its subpage::readers is still 0. And when endio is executed on both pages, since page [64K, 128K) has 0 subpage::readers, it triggers above ASSERT() [FIX] Function add_ra_bio_pages() is far from subpage compatible, it always assume PAGE_SIZE == sectorsize, thus when it skip to next range it always just skip PAGE_SIZE. Make it subpage compatible by: - Skip to next page properly when needed If we find there is already a page cache, we need to skip to next page. For that case, we shouldn't just skip PAGE_SIZE bytes, but use @pg_index to calculate the next bytenr and continue. - Only add the page range covered by current extent map We need to calculate which range is covered by current extent map and only add that part into the read bio. - Update subpage::readers before submitting the bio - Use proper cursor other than confusing @last_offset - Calculate the missed threshold based on sector size It's no longer using missed pages, as for 64K page size, we have at most 3 pages to skip. (If aligned only 2 pages) - Add ASSERT() to make sure our bytenr is always aligned - Add comment for the function Add a special note for subpage case, as the function won't really work well for subpage cases. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-09-27 15:21:47 +08:00
#include "subpage.h"
#include "zoned.h"
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
static const char* const btrfs_compress_types[] = { "", "zlib", "lzo", "zstd" };
const char* btrfs_compress_type2str(enum btrfs_compression_type type)
{
switch (type) {
case BTRFS_COMPRESS_ZLIB:
case BTRFS_COMPRESS_LZO:
case BTRFS_COMPRESS_ZSTD:
case BTRFS_COMPRESS_NONE:
return btrfs_compress_types[type];
default:
break;
}
return NULL;
}
btrfs: correctly validate compression type Nikolay reported the following KASAN splat when running btrfs/048: [ 1843.470920] ================================================================== [ 1843.471971] BUG: KASAN: slab-out-of-bounds in strncmp+0x66/0xb0 [ 1843.472775] Read of size 1 at addr ffff888111e369e2 by task btrfs/3979 [ 1843.473904] CPU: 3 PID: 3979 Comm: btrfs Not tainted 5.2.0-rc3-default #536 [ 1843.475009] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1ubuntu1 04/01/2014 [ 1843.476322] Call Trace: [ 1843.476674] dump_stack+0x7c/0xbb [ 1843.477132] ? strncmp+0x66/0xb0 [ 1843.477587] print_address_description+0x114/0x320 [ 1843.478256] ? strncmp+0x66/0xb0 [ 1843.478740] ? strncmp+0x66/0xb0 [ 1843.479185] __kasan_report+0x14e/0x192 [ 1843.479759] ? strncmp+0x66/0xb0 [ 1843.480209] kasan_report+0xe/0x20 [ 1843.480679] strncmp+0x66/0xb0 [ 1843.481105] prop_compression_validate+0x24/0x70 [ 1843.481798] btrfs_xattr_handler_set_prop+0x65/0x160 [ 1843.482509] __vfs_setxattr+0x71/0x90 [ 1843.483012] __vfs_setxattr_noperm+0x84/0x130 [ 1843.483606] vfs_setxattr+0xac/0xb0 [ 1843.484085] setxattr+0x18c/0x230 [ 1843.484546] ? vfs_setxattr+0xb0/0xb0 [ 1843.485048] ? __mod_node_page_state+0x1f/0xa0 [ 1843.485672] ? _raw_spin_unlock+0x24/0x40 [ 1843.486233] ? __handle_mm_fault+0x988/0x1290 [ 1843.486823] ? lock_acquire+0xb4/0x1e0 [ 1843.487330] ? lock_acquire+0xb4/0x1e0 [ 1843.487842] ? mnt_want_write_file+0x3c/0x80 [ 1843.488442] ? debug_lockdep_rcu_enabled+0x22/0x40 [ 1843.489089] ? rcu_sync_lockdep_assert+0xe/0x70 [ 1843.489707] ? __sb_start_write+0x158/0x200 [ 1843.490278] ? mnt_want_write_file+0x3c/0x80 [ 1843.490855] ? __mnt_want_write+0x98/0xe0 [ 1843.491397] __x64_sys_fsetxattr+0xba/0xe0 [ 1843.492201] ? trace_hardirqs_off_thunk+0x1a/0x1c [ 1843.493201] do_syscall_64+0x6c/0x230 [ 1843.493988] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 1843.495041] RIP: 0033:0x7fa7a8a7707a [ 1843.495819] Code: 48 8b 0d 21 de 2b 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 49 89 ca b8 be 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d ee dd 2b 00 f7 d8 64 89 01 48 [ 1843.499203] RSP: 002b:00007ffcb73bca38 EFLAGS: 00000202 ORIG_RAX: 00000000000000be [ 1843.500210] RAX: ffffffffffffffda RBX: 00007ffcb73bda9d RCX: 00007fa7a8a7707a [ 1843.501170] RDX: 00007ffcb73bda9d RSI: 00000000006dc050 RDI: 0000000000000003 [ 1843.502152] RBP: 00000000006dc050 R08: 0000000000000000 R09: 0000000000000000 [ 1843.503109] R10: 0000000000000002 R11: 0000000000000202 R12: 00007ffcb73bda91 [ 1843.504055] R13: 0000000000000003 R14: 00007ffcb73bda82 R15: ffffffffffffffff [ 1843.505268] Allocated by task 3979: [ 1843.505771] save_stack+0x19/0x80 [ 1843.506211] __kasan_kmalloc.constprop.5+0xa0/0xd0 [ 1843.506836] setxattr+0xeb/0x230 [ 1843.507264] __x64_sys_fsetxattr+0xba/0xe0 [ 1843.507886] do_syscall_64+0x6c/0x230 [ 1843.508429] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 1843.509558] Freed by task 0: [ 1843.510188] (stack is not available) [ 1843.511309] The buggy address belongs to the object at ffff888111e369e0 which belongs to the cache kmalloc-8 of size 8 [ 1843.514095] The buggy address is located 2 bytes inside of 8-byte region [ffff888111e369e0, ffff888111e369e8) [ 1843.516524] The buggy address belongs to the page: [ 1843.517561] page:ffff88813f478d80 refcount:1 mapcount:0 mapping:ffff88811940c300 index:0xffff888111e373b8 compound_mapcount: 0 [ 1843.519993] flags: 0x4404000010200(slab|head) [ 1843.520951] raw: 0004404000010200 ffff88813f48b008 ffff888119403d50 ffff88811940c300 [ 1843.522616] raw: ffff888111e373b8 000000000016000f 00000001ffffffff 0000000000000000 [ 1843.524281] page dumped because: kasan: bad access detected [ 1843.525936] Memory state around the buggy address: [ 1843.526975] ffff888111e36880: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 1843.528479] ffff888111e36900: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 1843.530138] >ffff888111e36980: fc fc fc fc fc fc fc fc fc fc fc fc 02 fc fc fc [ 1843.531877] ^ [ 1843.533287] ffff888111e36a00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 1843.534874] ffff888111e36a80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 1843.536468] ================================================================== This is caused by supplying a too short compression value ('lz') in the test-case and comparing it to 'lzo' with strncmp() and a length of 3. strncmp() read past the 'lz' when looking for the 'o' and thus caused an out-of-bounds read. Introduce a new check 'btrfs_compress_is_valid_type()' which not only checks the user-supplied value against known compression types, but also employs checks for too short values. Reported-by: Nikolay Borisov <nborisov@suse.com> Fixes: 272e5326c783 ("btrfs: prop: fix vanished compression property after failed set") CC: stable@vger.kernel.org # 5.1+ Reviewed-by: Nikolay Borisov <nborisov@suse.com> Signed-off-by: Johannes Thumshirn <jthumshirn@suse.de> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2019-06-06 18:07:15 +08:00
bool btrfs_compress_is_valid_type(const char *str, size_t len)
{
int i;
for (i = 1; i < ARRAY_SIZE(btrfs_compress_types); i++) {
size_t comp_len = strlen(btrfs_compress_types[i]);
if (len < comp_len)
continue;
if (!strncmp(btrfs_compress_types[i], str, comp_len))
return true;
}
return false;
}
static int compression_compress_pages(int type, struct list_head *ws,
struct address_space *mapping, u64 start, struct page **pages,
unsigned long *out_pages, unsigned long *total_in,
unsigned long *total_out)
{
switch (type) {
case BTRFS_COMPRESS_ZLIB:
return zlib_compress_pages(ws, mapping, start, pages,
out_pages, total_in, total_out);
case BTRFS_COMPRESS_LZO:
return lzo_compress_pages(ws, mapping, start, pages,
out_pages, total_in, total_out);
case BTRFS_COMPRESS_ZSTD:
return zstd_compress_pages(ws, mapping, start, pages,
out_pages, total_in, total_out);
case BTRFS_COMPRESS_NONE:
default:
/*
btrfs: handle remount to no compress during compression [BUG] When running btrfs/071 with inode_need_compress() removed from compress_file_range(), we got the following crash: BUG: kernel NULL pointer dereference, address: 0000000000000018 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page Workqueue: btrfs-delalloc btrfs_work_helper [btrfs] RIP: 0010:compress_file_range+0x476/0x7b0 [btrfs] Call Trace: ? submit_compressed_extents+0x450/0x450 [btrfs] async_cow_start+0x16/0x40 [btrfs] btrfs_work_helper+0xf2/0x3e0 [btrfs] process_one_work+0x278/0x5e0 worker_thread+0x55/0x400 ? process_one_work+0x5e0/0x5e0 kthread+0x168/0x190 ? kthread_create_worker_on_cpu+0x70/0x70 ret_from_fork+0x22/0x30 ---[ end trace 65faf4eae941fa7d ]--- This is already after the patch "btrfs: inode: fix NULL pointer dereference if inode doesn't need compression." [CAUSE] @pages is firstly created by kcalloc() in compress_file_extent(): pages = kcalloc(nr_pages, sizeof(struct page *), GFP_NOFS); Then passed to btrfs_compress_pages() to be utilized there: ret = btrfs_compress_pages(... pages, &nr_pages, ...); btrfs_compress_pages() will initialize each page as output, in zlib_compress_pages() we have: pages[nr_pages] = out_page; nr_pages++; Normally this is completely fine, but there is a special case which is in btrfs_compress_pages() itself: switch (type) { default: return -E2BIG; } In this case, we didn't modify @pages nor @out_pages, leaving them untouched, then when we cleanup pages, the we can hit NULL pointer dereference again: if (pages) { for (i = 0; i < nr_pages; i++) { WARN_ON(pages[i]->mapping); put_page(pages[i]); } ... } Since pages[i] are all initialized to zero, and btrfs_compress_pages() doesn't change them at all, accessing pages[i]->mapping would lead to NULL pointer dereference. This is not possible for current kernel, as we check inode_need_compress() before doing pages allocation. But if we're going to remove that inode_need_compress() in compress_file_extent(), then it's going to be a problem. [FIX] When btrfs_compress_pages() hits its default case, modify @out_pages to 0 to prevent such problem from happening. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=212331 CC: stable@vger.kernel.org # 5.10+ Reviewed-by: Josef Bacik <josef@toxicpanda.com> Signed-off-by: Qu Wenruo <wqu@suse.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-08-04 15:25:47 +08:00
* This can happen when compression races with remount setting
* it to 'no compress', while caller doesn't call
* inode_need_compress() to check if we really need to
* compress.
*
* Not a big deal, just need to inform caller that we
* haven't allocated any pages yet.
*/
btrfs: handle remount to no compress during compression [BUG] When running btrfs/071 with inode_need_compress() removed from compress_file_range(), we got the following crash: BUG: kernel NULL pointer dereference, address: 0000000000000018 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page Workqueue: btrfs-delalloc btrfs_work_helper [btrfs] RIP: 0010:compress_file_range+0x476/0x7b0 [btrfs] Call Trace: ? submit_compressed_extents+0x450/0x450 [btrfs] async_cow_start+0x16/0x40 [btrfs] btrfs_work_helper+0xf2/0x3e0 [btrfs] process_one_work+0x278/0x5e0 worker_thread+0x55/0x400 ? process_one_work+0x5e0/0x5e0 kthread+0x168/0x190 ? kthread_create_worker_on_cpu+0x70/0x70 ret_from_fork+0x22/0x30 ---[ end trace 65faf4eae941fa7d ]--- This is already after the patch "btrfs: inode: fix NULL pointer dereference if inode doesn't need compression." [CAUSE] @pages is firstly created by kcalloc() in compress_file_extent(): pages = kcalloc(nr_pages, sizeof(struct page *), GFP_NOFS); Then passed to btrfs_compress_pages() to be utilized there: ret = btrfs_compress_pages(... pages, &nr_pages, ...); btrfs_compress_pages() will initialize each page as output, in zlib_compress_pages() we have: pages[nr_pages] = out_page; nr_pages++; Normally this is completely fine, but there is a special case which is in btrfs_compress_pages() itself: switch (type) { default: return -E2BIG; } In this case, we didn't modify @pages nor @out_pages, leaving them untouched, then when we cleanup pages, the we can hit NULL pointer dereference again: if (pages) { for (i = 0; i < nr_pages; i++) { WARN_ON(pages[i]->mapping); put_page(pages[i]); } ... } Since pages[i] are all initialized to zero, and btrfs_compress_pages() doesn't change them at all, accessing pages[i]->mapping would lead to NULL pointer dereference. This is not possible for current kernel, as we check inode_need_compress() before doing pages allocation. But if we're going to remove that inode_need_compress() in compress_file_extent(), then it's going to be a problem. [FIX] When btrfs_compress_pages() hits its default case, modify @out_pages to 0 to prevent such problem from happening. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=212331 CC: stable@vger.kernel.org # 5.10+ Reviewed-by: Josef Bacik <josef@toxicpanda.com> Signed-off-by: Qu Wenruo <wqu@suse.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-08-04 15:25:47 +08:00
*out_pages = 0;
return -E2BIG;
}
}
static int compression_decompress_bio(int type, struct list_head *ws,
struct compressed_bio *cb)
{
switch (type) {
case BTRFS_COMPRESS_ZLIB: return zlib_decompress_bio(ws, cb);
case BTRFS_COMPRESS_LZO: return lzo_decompress_bio(ws, cb);
case BTRFS_COMPRESS_ZSTD: return zstd_decompress_bio(ws, cb);
case BTRFS_COMPRESS_NONE:
default:
/*
* This can't happen, the type is validated several times
* before we get here.
*/
BUG();
}
}
static int compression_decompress(int type, struct list_head *ws,
unsigned char *data_in, struct page *dest_page,
unsigned long start_byte, size_t srclen, size_t destlen)
{
switch (type) {
case BTRFS_COMPRESS_ZLIB: return zlib_decompress(ws, data_in, dest_page,
start_byte, srclen, destlen);
case BTRFS_COMPRESS_LZO: return lzo_decompress(ws, data_in, dest_page,
start_byte, srclen, destlen);
case BTRFS_COMPRESS_ZSTD: return zstd_decompress(ws, data_in, dest_page,
start_byte, srclen, destlen);
case BTRFS_COMPRESS_NONE:
default:
/*
* This can't happen, the type is validated several times
* before we get here.
*/
BUG();
}
}
static int btrfs_decompress_bio(struct compressed_bio *cb);
static inline int compressed_bio_size(struct btrfs_fs_info *fs_info,
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
unsigned long disk_size)
{
return sizeof(struct compressed_bio) +
(DIV_ROUND_UP(disk_size, fs_info->sectorsize)) * fs_info->csum_size;
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
}
static int check_compressed_csum(struct btrfs_inode *inode, struct bio *bio,
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
u64 disk_start)
{
struct btrfs_fs_info *fs_info = inode->root->fs_info;
SHASH_DESC_ON_STACK(shash, fs_info->csum_shash);
const u32 csum_size = fs_info->csum_size;
const u32 sectorsize = fs_info->sectorsize;
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 page *page;
unsigned int i;
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
char *kaddr;
u8 csum[BTRFS_CSUM_SIZE];
struct compressed_bio *cb = bio->bi_private;
u8 *cb_sum = cb->sums;
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 (!fs_info->csum_root || (inode->flags & BTRFS_INODE_NODATASUM))
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
return 0;
shash->tfm = fs_info->csum_shash;
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
for (i = 0; i < cb->nr_pages; i++) {
u32 pg_offset;
u32 bytes_left = PAGE_SIZE;
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
page = cb->compressed_pages[i];
/* Determine the remaining bytes inside the page first */
if (i == cb->nr_pages - 1)
bytes_left = cb->compressed_len - i * PAGE_SIZE;
/* Hash through the page sector by sector */
for (pg_offset = 0; pg_offset < bytes_left;
pg_offset += sectorsize) {
kaddr = kmap_atomic(page);
crypto_shash_digest(shash, kaddr + pg_offset,
sectorsize, csum);
kunmap_atomic(kaddr);
if (memcmp(&csum, cb_sum, csum_size) != 0) {
btrfs_print_data_csum_error(inode, disk_start,
csum, cb_sum, cb->mirror_num);
if (btrfs_bio(bio)->device)
btrfs_dev_stat_inc_and_print(
btrfs_bio(bio)->device,
BTRFS_DEV_STAT_CORRUPTION_ERRS);
return -EIO;
}
cb_sum += csum_size;
disk_start += sectorsize;
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
}
}
return 0;
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
}
btrfs: introduce compressed_bio::pending_sectors to trace compressed bio For btrfs_submit_compressed_read() and btrfs_submit_compressed_write(), we have a pretty weird dance around compressed_bio::pending_bios: btrfs_submit_compressed_read/write() { cb = kmalloc() refcount_set(&cb->pending_bios, 0); bio = btrfs_alloc_bio(); /* NOTE here, we haven't yet submitted any bio */ refcount_set(&cb->pending_bios, 1); for (pg_index = 0; pg_index < cb->nr_pages; pg_index++) { if (submit) { /* Here we submit bio, but we always have one * extra pending_bios */ refcount_inc(&cb->pending_bios); ret = btrfs_map_bio(); } } /* Submit the last bio */ ret = btrfs_map_bio(); } There are two reasons why we do this: - compressed_bio::pending_bios is a refcount Thus if it's reduced to 0, it can not be increased again. - To ensure the compressed_bio is not freed by some submitted bios If the submitted bio is finished before the next bio submitted, we can free the compressed_bio completely. But the above code is sometimes confusing, and we can do it better by introducing a new member, compressed_bio::pending_sectors. Now we use compressed_bio::pending_sectors to indicate whether we have any pending sectors under IO or not yet submitted. If pending_sectors == 0, we're definitely the last bio of compressed_bio, and is OK to release the compressed bio. Now the workflow looks like this: btrfs_submit_compressed_read/write() { cb = kmalloc() atomic_set(&cb->pending_bios, 0); refcount_set(&cb->pending_sectors, compressed_len >> sectorsize_bits); bio = btrfs_alloc_bio(); for (pg_index = 0; pg_index < cb->nr_pages; pg_index++) { if (submit) { refcount_inc(&cb->pending_bios); ret = btrfs_map_bio(); } } /* Submit the last bio */ refcount_inc(&cb->pending_bios); ret = btrfs_map_bio(); } For now we still need pending_bios for later error handling, but will remove pending_bios eventually after properly handling the errors. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-09-27 15:21:48 +08:00
/*
* Reduce bio and io accounting for a compressed_bio with its corresponding bio.
*
* Return true if there is no pending bio nor io.
* Return false otherwise.
*/
static bool dec_and_test_compressed_bio(struct compressed_bio *cb, struct bio *bio)
{
struct btrfs_fs_info *fs_info = btrfs_sb(cb->inode->i_sb);
unsigned int bi_size = 0;
bool last_io = false;
struct bio_vec *bvec;
struct bvec_iter_all iter_all;
/*
* At endio time, bi_iter.bi_size doesn't represent the real bio size.
* Thus here we have to iterate through all segments to grab correct
* bio size.
*/
bio_for_each_segment_all(bvec, bio, iter_all)
bi_size += bvec->bv_len;
if (bio->bi_status)
cb->errors = 1;
ASSERT(bi_size && bi_size <= cb->compressed_len);
last_io = refcount_sub_and_test(bi_size >> fs_info->sectorsize_bits,
&cb->pending_sectors);
/*
* Here we must wake up the possible error handler after all other
* operations on @cb finished, or we can race with
* finish_compressed_bio_*() which may free @cb.
*/
wake_up_var(cb);
btrfs: introduce compressed_bio::pending_sectors to trace compressed bio For btrfs_submit_compressed_read() and btrfs_submit_compressed_write(), we have a pretty weird dance around compressed_bio::pending_bios: btrfs_submit_compressed_read/write() { cb = kmalloc() refcount_set(&cb->pending_bios, 0); bio = btrfs_alloc_bio(); /* NOTE here, we haven't yet submitted any bio */ refcount_set(&cb->pending_bios, 1); for (pg_index = 0; pg_index < cb->nr_pages; pg_index++) { if (submit) { /* Here we submit bio, but we always have one * extra pending_bios */ refcount_inc(&cb->pending_bios); ret = btrfs_map_bio(); } } /* Submit the last bio */ ret = btrfs_map_bio(); } There are two reasons why we do this: - compressed_bio::pending_bios is a refcount Thus if it's reduced to 0, it can not be increased again. - To ensure the compressed_bio is not freed by some submitted bios If the submitted bio is finished before the next bio submitted, we can free the compressed_bio completely. But the above code is sometimes confusing, and we can do it better by introducing a new member, compressed_bio::pending_sectors. Now we use compressed_bio::pending_sectors to indicate whether we have any pending sectors under IO or not yet submitted. If pending_sectors == 0, we're definitely the last bio of compressed_bio, and is OK to release the compressed bio. Now the workflow looks like this: btrfs_submit_compressed_read/write() { cb = kmalloc() atomic_set(&cb->pending_bios, 0); refcount_set(&cb->pending_sectors, compressed_len >> sectorsize_bits); bio = btrfs_alloc_bio(); for (pg_index = 0; pg_index < cb->nr_pages; pg_index++) { if (submit) { refcount_inc(&cb->pending_bios); ret = btrfs_map_bio(); } } /* Submit the last bio */ refcount_inc(&cb->pending_bios); ret = btrfs_map_bio(); } For now we still need pending_bios for later error handling, but will remove pending_bios eventually after properly handling the errors. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-09-27 15:21:48 +08:00
return last_io;
}
static void finish_compressed_bio_read(struct compressed_bio *cb, struct bio *bio)
{
unsigned int index;
struct page *page;
/* Release the compressed pages */
for (index = 0; index < cb->nr_pages; index++) {
page = cb->compressed_pages[index];
page->mapping = NULL;
put_page(page);
}
/* Do io completion on the original bio */
if (cb->errors) {
bio_io_error(cb->orig_bio);
} else {
struct bio_vec *bvec;
struct bvec_iter_all iter_all;
ASSERT(bio);
ASSERT(!bio->bi_status);
/*
* We have verified the checksum already, set page checked so
* the end_io handlers know about it
*/
ASSERT(!bio_flagged(bio, BIO_CLONED));
bio_for_each_segment_all(bvec, cb->orig_bio, iter_all) {
u64 bvec_start = page_offset(bvec->bv_page) +
bvec->bv_offset;
btrfs_page_set_checked(btrfs_sb(cb->inode->i_sb),
bvec->bv_page, bvec_start,
bvec->bv_len);
}
bio_endio(cb->orig_bio);
}
/* Finally free the cb struct */
kfree(cb->compressed_pages);
kfree(cb);
}
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
/* when we finish reading compressed pages from the disk, we
* decompress them and then run the bio end_io routines on the
* decompressed pages (in the inode address space).
*
* This allows the checksumming and other IO error handling routines
* to work normally
*
* The compressed pages are freed here, and it must be run
* in process context
*/
static void end_compressed_bio_read(struct bio *bio)
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
{
struct compressed_bio *cb = bio->bi_private;
struct inode *inode;
unsigned int mirror = btrfs_bio(bio)->mirror_num;
int ret = 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: introduce compressed_bio::pending_sectors to trace compressed bio For btrfs_submit_compressed_read() and btrfs_submit_compressed_write(), we have a pretty weird dance around compressed_bio::pending_bios: btrfs_submit_compressed_read/write() { cb = kmalloc() refcount_set(&cb->pending_bios, 0); bio = btrfs_alloc_bio(); /* NOTE here, we haven't yet submitted any bio */ refcount_set(&cb->pending_bios, 1); for (pg_index = 0; pg_index < cb->nr_pages; pg_index++) { if (submit) { /* Here we submit bio, but we always have one * extra pending_bios */ refcount_inc(&cb->pending_bios); ret = btrfs_map_bio(); } } /* Submit the last bio */ ret = btrfs_map_bio(); } There are two reasons why we do this: - compressed_bio::pending_bios is a refcount Thus if it's reduced to 0, it can not be increased again. - To ensure the compressed_bio is not freed by some submitted bios If the submitted bio is finished before the next bio submitted, we can free the compressed_bio completely. But the above code is sometimes confusing, and we can do it better by introducing a new member, compressed_bio::pending_sectors. Now we use compressed_bio::pending_sectors to indicate whether we have any pending sectors under IO or not yet submitted. If pending_sectors == 0, we're definitely the last bio of compressed_bio, and is OK to release the compressed bio. Now the workflow looks like this: btrfs_submit_compressed_read/write() { cb = kmalloc() atomic_set(&cb->pending_bios, 0); refcount_set(&cb->pending_sectors, compressed_len >> sectorsize_bits); bio = btrfs_alloc_bio(); for (pg_index = 0; pg_index < cb->nr_pages; pg_index++) { if (submit) { refcount_inc(&cb->pending_bios); ret = btrfs_map_bio(); } } /* Submit the last bio */ refcount_inc(&cb->pending_bios); ret = btrfs_map_bio(); } For now we still need pending_bios for later error handling, but will remove pending_bios eventually after properly handling the errors. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-09-27 15:21:48 +08:00
if (!dec_and_test_compressed_bio(cb, bio))
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
goto out;
/*
* Record the correct mirror_num in cb->orig_bio so that
* read-repair can work properly.
*/
btrfs_bio(cb->orig_bio)->mirror_num = mirror;
cb->mirror_num = mirror;
/*
* Some IO in this cb have failed, just skip checksum as there
* is no way it could be correct.
*/
if (cb->errors == 1)
goto csum_failed;
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
inode = cb->inode;
ret = check_compressed_csum(BTRFS_I(inode), bio,
bio->bi_iter.bi_sector << 9);
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 (ret)
goto csum_failed;
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
/* ok, we're the last bio for this extent, lets start
* the decompression.
*/
ret = btrfs_decompress_bio(cb);
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_failed:
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
if (ret)
cb->errors = 1;
finish_compressed_bio_read(cb, bio);
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
out:
bio_put(bio);
}
/*
* Clear the writeback bits on all of the file
* pages for a compressed write
*/
static noinline void end_compressed_writeback(struct inode *inode,
const struct compressed_bio *cb)
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
{
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
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
unsigned long index = cb->start >> PAGE_SHIFT;
unsigned long end_index = (cb->start + cb->len - 1) >> PAGE_SHIFT;
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
struct page *pages[16];
unsigned long nr_pages = end_index - index + 1;
int i;
int ret;
if (cb->errors)
mapping_set_error(inode->i_mapping, -EIO);
while (nr_pages > 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
ret = find_get_pages_contig(inode->i_mapping, index,
min_t(unsigned long,
nr_pages, ARRAY_SIZE(pages)), pages);
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
if (ret == 0) {
nr_pages -= 1;
index += 1;
continue;
}
for (i = 0; i < ret; i++) {
if (cb->errors)
SetPageError(pages[i]);
btrfs_page_clamp_clear_writeback(fs_info, pages[i],
cb->start, cb->len);
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
put_page(pages[i]);
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
}
nr_pages -= ret;
index += ret;
}
/* the inode may be gone now */
}
static void finish_compressed_bio_write(struct compressed_bio *cb)
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
{
struct inode *inode = cb->inode;
unsigned int index;
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
/*
* Ok, we're the last bio for this extent, step one is to call back
* into the FS and do all the end_io operations.
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_writepage_endio_finish_ordered(BTRFS_I(inode), NULL,
cb->start, cb->start + cb->len - 1,
!cb->errors);
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
end_compressed_writeback(inode, cb);
/* Note, our inode could be gone now */
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
/*
* Release the compressed pages, these came from alloc_page and
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
* are not attached to the inode at all
*/
for (index = 0; index < cb->nr_pages; index++) {
struct page *page = cb->compressed_pages[index];
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
page->mapping = NULL;
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
put_page(page);
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
}
/* Finally free the cb struct */
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
kfree(cb->compressed_pages);
kfree(cb);
}
/*
* Do the cleanup once all the compressed pages hit the disk. This will clear
* writeback on the file pages and free the compressed pages.
*
* This also calls the writeback end hooks for the file pages so that metadata
* and checksums can be updated in the file.
*/
static void end_compressed_bio_write(struct bio *bio)
{
struct compressed_bio *cb = bio->bi_private;
if (!dec_and_test_compressed_bio(cb, bio))
goto out;
btrfs_record_physical_zoned(cb->inode, cb->start, bio);
finish_compressed_bio_write(cb);
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
out:
bio_put(bio);
}
static blk_status_t submit_compressed_bio(struct btrfs_fs_info *fs_info,
struct compressed_bio *cb,
struct bio *bio, int mirror_num)
{
blk_status_t ret;
ASSERT(bio->bi_iter.bi_size);
ret = btrfs_bio_wq_end_io(fs_info, bio, BTRFS_WQ_ENDIO_DATA);
if (ret)
return ret;
ret = btrfs_map_bio(fs_info, bio, mirror_num);
return ret;
}
/*
* Allocate a compressed_bio, which will be used to read/write on-disk
* (aka, compressed) * data.
*
* @cb: The compressed_bio structure, which records all the needed
* information to bind the compressed data to the uncompressed
* page cache.
* @disk_byten: The logical bytenr where the compressed data will be read
* from or written to.
* @endio_func: The endio function to call after the IO for compressed data
* is finished.
* @next_stripe_start: Return value of logical bytenr of where next stripe starts.
* Let the caller know to only fill the bio up to the stripe
* boundary.
*/
static struct bio *alloc_compressed_bio(struct compressed_bio *cb, u64 disk_bytenr,
unsigned int opf, bio_end_io_t endio_func,
u64 *next_stripe_start)
{
struct btrfs_fs_info *fs_info = btrfs_sb(cb->inode->i_sb);
struct btrfs_io_geometry geom;
struct extent_map *em;
struct bio *bio;
int ret;
bio = btrfs_bio_alloc(BIO_MAX_VECS);
bio->bi_iter.bi_sector = disk_bytenr >> SECTOR_SHIFT;
bio->bi_opf = opf;
bio->bi_private = cb;
bio->bi_end_io = endio_func;
em = btrfs_get_chunk_map(fs_info, disk_bytenr, fs_info->sectorsize);
if (IS_ERR(em)) {
bio_put(bio);
return ERR_CAST(em);
}
if (bio_op(bio) == REQ_OP_ZONE_APPEND)
bio_set_dev(bio, em->map_lookup->stripes[0].dev->bdev);
ret = btrfs_get_io_geometry(fs_info, em, btrfs_op(bio), disk_bytenr, &geom);
free_extent_map(em);
if (ret < 0) {
bio_put(bio);
return ERR_PTR(ret);
}
*next_stripe_start = disk_bytenr + geom.len;
return bio;
}
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
/*
* worker function to build and submit bios for previously compressed pages.
* The corresponding pages in the inode should be marked for writeback
* and the compressed pages should have a reference on them for dropping
* when the IO is complete.
*
* This also checksums the file bytes and gets things ready for
* the end io hooks.
*/
blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start,
unsigned int len, u64 disk_start,
unsigned int compressed_len,
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
struct page **compressed_pages,
unsigned int nr_pages,
unsigned int write_flags,
struct cgroup_subsys_state *blkcg_css)
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
{
struct btrfs_fs_info *fs_info = inode->root->fs_info;
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
struct bio *bio = NULL;
struct compressed_bio *cb;
u64 cur_disk_bytenr = disk_start;
u64 next_stripe_start;
blk_status_t ret;
int skip_sum = inode->flags & BTRFS_INODE_NODATASUM;
const bool use_append = btrfs_use_zone_append(inode, disk_start);
const unsigned int bio_op = use_append ? REQ_OP_ZONE_APPEND : REQ_OP_WRITE;
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
ASSERT(IS_ALIGNED(start, fs_info->sectorsize) &&
IS_ALIGNED(len, fs_info->sectorsize));
cb = kmalloc(compressed_bio_size(fs_info, compressed_len), GFP_NOFS);
if (!cb)
return BLK_STS_RESOURCE;
btrfs: introduce compressed_bio::pending_sectors to trace compressed bio For btrfs_submit_compressed_read() and btrfs_submit_compressed_write(), we have a pretty weird dance around compressed_bio::pending_bios: btrfs_submit_compressed_read/write() { cb = kmalloc() refcount_set(&cb->pending_bios, 0); bio = btrfs_alloc_bio(); /* NOTE here, we haven't yet submitted any bio */ refcount_set(&cb->pending_bios, 1); for (pg_index = 0; pg_index < cb->nr_pages; pg_index++) { if (submit) { /* Here we submit bio, but we always have one * extra pending_bios */ refcount_inc(&cb->pending_bios); ret = btrfs_map_bio(); } } /* Submit the last bio */ ret = btrfs_map_bio(); } There are two reasons why we do this: - compressed_bio::pending_bios is a refcount Thus if it's reduced to 0, it can not be increased again. - To ensure the compressed_bio is not freed by some submitted bios If the submitted bio is finished before the next bio submitted, we can free the compressed_bio completely. But the above code is sometimes confusing, and we can do it better by introducing a new member, compressed_bio::pending_sectors. Now we use compressed_bio::pending_sectors to indicate whether we have any pending sectors under IO or not yet submitted. If pending_sectors == 0, we're definitely the last bio of compressed_bio, and is OK to release the compressed bio. Now the workflow looks like this: btrfs_submit_compressed_read/write() { cb = kmalloc() atomic_set(&cb->pending_bios, 0); refcount_set(&cb->pending_sectors, compressed_len >> sectorsize_bits); bio = btrfs_alloc_bio(); for (pg_index = 0; pg_index < cb->nr_pages; pg_index++) { if (submit) { refcount_inc(&cb->pending_bios); ret = btrfs_map_bio(); } } /* Submit the last bio */ refcount_inc(&cb->pending_bios); ret = btrfs_map_bio(); } For now we still need pending_bios for later error handling, but will remove pending_bios eventually after properly handling the errors. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-09-27 15:21:48 +08:00
refcount_set(&cb->pending_sectors, compressed_len >> fs_info->sectorsize_bits);
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
cb->errors = 0;
cb->inode = &inode->vfs_inode;
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
cb->start = start;
cb->len = len;
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
cb->mirror_num = 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
cb->compressed_pages = compressed_pages;
cb->compressed_len = compressed_len;
cb->orig_bio = NULL;
cb->nr_pages = nr_pages;
while (cur_disk_bytenr < disk_start + compressed_len) {
u64 offset = cur_disk_bytenr - disk_start;
unsigned int index = offset >> PAGE_SHIFT;
unsigned int real_size;
unsigned int added;
struct page *page = compressed_pages[index];
bool submit = false;
/* Allocate new bio if submitted or not yet allocated */
if (!bio) {
bio = alloc_compressed_bio(cb, cur_disk_bytenr,
bio_op | write_flags, end_compressed_bio_write,
&next_stripe_start);
if (IS_ERR(bio)) {
ret = errno_to_blk_status(PTR_ERR(bio));
bio = NULL;
goto finish_cb;
}
}
btrfs: fix compressed writes that cross stripe boundary [BUG] When running btrfs/027 with "-o compress" mount option, it always crashes with the following call trace: BTRFS critical (device dm-4): mapping failed logical 298901504 bio len 12288 len 8192 ------------[ cut here ]------------ kernel BUG at fs/btrfs/volumes.c:6651! invalid opcode: 0000 [#1] PREEMPT SMP NOPTI CPU: 5 PID: 31089 Comm: kworker/u24:10 Tainted: G OE 5.13.0-rc2-custom+ #26 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015 Workqueue: btrfs-delalloc btrfs_work_helper [btrfs] RIP: 0010:btrfs_map_bio.cold+0x58/0x5a [btrfs] Call Trace: btrfs_submit_compressed_write+0x2d7/0x470 [btrfs] submit_compressed_extents+0x3b0/0x470 [btrfs] ? mark_held_locks+0x49/0x70 btrfs_work_helper+0x131/0x3e0 [btrfs] process_one_work+0x28f/0x5d0 worker_thread+0x55/0x3c0 ? process_one_work+0x5d0/0x5d0 kthread+0x141/0x160 ? __kthread_bind_mask+0x60/0x60 ret_from_fork+0x22/0x30 ---[ end trace 63113a3a91f34e68 ]--- [CAUSE] The critical message before the crash means we have a bio at logical bytenr 298901504 length 12288, but only 8192 bytes can fit into one stripe, the remaining 4096 bytes go to another stripe. In btrfs, all bios are properly split to avoid cross stripe boundary, but commit 764c7c9a464b ("btrfs: zoned: fix parallel compressed writes") changed the behavior for compressed writes. Previously if we find our new page can't be fitted into current stripe, ie. "submit == 1" case, we submit current bio without adding current page. submit = btrfs_bio_fits_in_stripe(page, PAGE_SIZE, bio, 0); page->mapping = NULL; if (submit || bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) { But after the modification, we will add the page no matter if it crosses stripe boundary, leading to the above crash. submit = btrfs_bio_fits_in_stripe(page, PAGE_SIZE, bio, 0); if (pg_index == 0 && use_append) len = bio_add_zone_append_page(bio, page, PAGE_SIZE, 0); else len = bio_add_page(bio, page, PAGE_SIZE, 0); page->mapping = NULL; if (submit || len < PAGE_SIZE) { [FIX] It's no longer possible to revert to the original code style as we have two different bio_add_*_page() calls now. The new fix is to skip the bio_add_*_page() call if @submit is true. Also to avoid @len to be uninitialized, always initialize it to zero. If @submit is true, @len will not be checked. If @submit is not true, @len will be the return value of bio_add_*_page() call. Either way, the behavior is still the same as the old code. Reported-by: Josef Bacik <josef@toxicpanda.com> Fixes: 764c7c9a464b ("btrfs: zoned: fix parallel compressed writes") Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com> Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-05-25 13:52:43 +08:00
/*
* We should never reach next_stripe_start start as we will
* submit comp_bio when reach the boundary immediately.
btrfs: fix compressed writes that cross stripe boundary [BUG] When running btrfs/027 with "-o compress" mount option, it always crashes with the following call trace: BTRFS critical (device dm-4): mapping failed logical 298901504 bio len 12288 len 8192 ------------[ cut here ]------------ kernel BUG at fs/btrfs/volumes.c:6651! invalid opcode: 0000 [#1] PREEMPT SMP NOPTI CPU: 5 PID: 31089 Comm: kworker/u24:10 Tainted: G OE 5.13.0-rc2-custom+ #26 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015 Workqueue: btrfs-delalloc btrfs_work_helper [btrfs] RIP: 0010:btrfs_map_bio.cold+0x58/0x5a [btrfs] Call Trace: btrfs_submit_compressed_write+0x2d7/0x470 [btrfs] submit_compressed_extents+0x3b0/0x470 [btrfs] ? mark_held_locks+0x49/0x70 btrfs_work_helper+0x131/0x3e0 [btrfs] process_one_work+0x28f/0x5d0 worker_thread+0x55/0x3c0 ? process_one_work+0x5d0/0x5d0 kthread+0x141/0x160 ? __kthread_bind_mask+0x60/0x60 ret_from_fork+0x22/0x30 ---[ end trace 63113a3a91f34e68 ]--- [CAUSE] The critical message before the crash means we have a bio at logical bytenr 298901504 length 12288, but only 8192 bytes can fit into one stripe, the remaining 4096 bytes go to another stripe. In btrfs, all bios are properly split to avoid cross stripe boundary, but commit 764c7c9a464b ("btrfs: zoned: fix parallel compressed writes") changed the behavior for compressed writes. Previously if we find our new page can't be fitted into current stripe, ie. "submit == 1" case, we submit current bio without adding current page. submit = btrfs_bio_fits_in_stripe(page, PAGE_SIZE, bio, 0); page->mapping = NULL; if (submit || bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) { But after the modification, we will add the page no matter if it crosses stripe boundary, leading to the above crash. submit = btrfs_bio_fits_in_stripe(page, PAGE_SIZE, bio, 0); if (pg_index == 0 && use_append) len = bio_add_zone_append_page(bio, page, PAGE_SIZE, 0); else len = bio_add_page(bio, page, PAGE_SIZE, 0); page->mapping = NULL; if (submit || len < PAGE_SIZE) { [FIX] It's no longer possible to revert to the original code style as we have two different bio_add_*_page() calls now. The new fix is to skip the bio_add_*_page() call if @submit is true. Also to avoid @len to be uninitialized, always initialize it to zero. If @submit is true, @len will not be checked. If @submit is not true, @len will be the return value of bio_add_*_page() call. Either way, the behavior is still the same as the old code. Reported-by: Josef Bacik <josef@toxicpanda.com> Fixes: 764c7c9a464b ("btrfs: zoned: fix parallel compressed writes") Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com> Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-05-25 13:52:43 +08:00
*/
ASSERT(cur_disk_bytenr != next_stripe_start);
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
/*
* We have various limits on the real read size:
* - stripe boundary
* - page boundary
* - compressed length boundary
*/
real_size = min_t(u64, U32_MAX, next_stripe_start - cur_disk_bytenr);
real_size = min_t(u64, real_size, PAGE_SIZE - offset_in_page(offset));
real_size = min_t(u64, real_size, compressed_len - offset);
ASSERT(IS_ALIGNED(real_size, fs_info->sectorsize));
if (use_append)
added = bio_add_zone_append_page(bio, page, real_size,
offset_in_page(offset));
else
added = bio_add_page(bio, page, real_size,
offset_in_page(offset));
/* Reached zoned boundary */
if (added == 0)
submit = true;
cur_disk_bytenr += added;
/* Reached stripe boundary */
if (cur_disk_bytenr == next_stripe_start)
submit = true;
/* Finished the range */
if (cur_disk_bytenr == disk_start + compressed_len)
submit = true;
if (submit) {
if (!skip_sum) {
ret = btrfs_csum_one_bio(inode, bio, start, 1);
if (ret)
goto finish_cb;
}
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
ret = submit_compressed_bio(fs_info, cb, bio, 0);
if (ret)
goto finish_cb;
bio = NULL;
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
}
cond_resched();
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: fix compressed write bio blkcg attribution Bio attribution is handled at bio_set_dev() as once we have a device, we have a corresponding request_queue and then can derive the current css. In special cases, we want to attribute to bio to someone else. This can be done by calling bio_associate_blkg_from_css() or kthread_associate_blkcg() depending on the scenario. Btrfs does this for compressed writeback as they are handled by kworkers, so the latter can be done here. Commit 1a41802701ec ("btrfs: drop bio_set_dev where not needed") removes early bio_set_dev() calls prior to submit_stripe_bio(). This breaks the above assumption that we'll have a request_queue when we are doing association. To fix this, switch to using kthread_associate_blkcg(). Without this, we crash in btrfs/024: [ 3052.093088] BUG: kernel NULL pointer dereference, address: 0000000000000510 [ 3052.107013] #PF: supervisor read access in kernel mode [ 3052.107014] #PF: error_code(0x0000) - not-present page [ 3052.107015] PGD 0 P4D 0 [ 3052.107021] Oops: 0000 [#1] SMP [ 3052.138904] CPU: 42 PID: 201270 Comm: kworker/u161:0 Kdump: loaded Not tainted 5.5.0-rc1-00062-g4852d8ac90a9 #712 [ 3052.138905] Hardware name: Quanta Tioga Pass Single Side 01-0032211004/Tioga Pass Single Side, BIOS F08_3A18 12/20/2018 [ 3052.138912] Workqueue: btrfs-delalloc btrfs_work_helper [ 3052.191375] RIP: 0010:bio_associate_blkg_from_css+0x1e/0x3c0 [ 3052.191379] RSP: 0018:ffffc900210cfc90 EFLAGS: 00010282 [ 3052.191380] RAX: 0000000000000000 RBX: ffff88bfe5573c00 RCX: 0000000000000000 [ 3052.191382] RDX: ffff889db48ec2f0 RSI: ffff88bfe5573c00 RDI: ffff889db48ec2f0 [ 3052.191386] RBP: 0000000000000800 R08: 0000000000203bb0 R09: ffff889db16b2400 [ 3052.293364] R10: 0000000000000000 R11: ffff88a07fffde80 R12: ffff889db48ec2f0 [ 3052.293365] R13: 0000000000001000 R14: ffff889de82bc000 R15: ffff889e2b7bdcc8 [ 3052.293367] FS: 0000000000000000(0000) GS:ffff889ffba00000(0000) knlGS:0000000000000000 [ 3052.293368] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 3052.293369] CR2: 0000000000000510 CR3: 0000000002611001 CR4: 00000000007606e0 [ 3052.293370] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 3052.293371] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 3052.293372] PKRU: 55555554 [ 3052.293376] Call Trace: [ 3052.402552] btrfs_submit_compressed_write+0x137/0x390 [ 3052.402558] submit_compressed_extents+0x40f/0x4c0 [ 3052.422401] btrfs_work_helper+0x246/0x5a0 [ 3052.422408] process_one_work+0x200/0x570 [ 3052.438601] ? process_one_work+0x180/0x570 [ 3052.438605] worker_thread+0x4c/0x3e0 [ 3052.438614] kthread+0x103/0x140 [ 3052.460735] ? process_one_work+0x570/0x570 [ 3052.460737] ? kthread_mod_delayed_work+0xc0/0xc0 [ 3052.460744] ret_from_fork+0x24/0x30 Fixes: 1a41802701ec ("btrfs: drop bio_set_dev where not needed") Reported-by: Chris Murphy <chris@colorremedies.com> Signed-off-by: Dennis Zhou <dennis@kernel.org> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2019-12-12 07:20:15 +08:00
if (blkcg_css)
kthread_associate_blkcg(NULL);
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
return 0;
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
finish_cb:
if (bio) {
bio->bi_status = ret;
bio_endio(bio);
}
/* Last byte of @cb is submitted, endio will free @cb */
if (cur_disk_bytenr == disk_start + compressed_len)
return ret;
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
wait_var_event(cb, refcount_read(&cb->pending_sectors) ==
(disk_start + compressed_len - cur_disk_bytenr) >>
fs_info->sectorsize_bits);
/*
* Even with previous bio ended, we should still have io not yet
* submitted, thus need to finish manually.
*/
ASSERT(refcount_read(&cb->pending_sectors));
/* Now we are the only one referring @cb, can finish it safely. */
finish_compressed_bio_write(cb);
return ret;
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
}
static u64 bio_end_offset(struct bio *bio)
{
struct bio_vec *last = bio_last_bvec_all(bio);
return page_offset(last->bv_page) + last->bv_len + last->bv_offset;
}
btrfs: subpage: make add_ra_bio_pages() compatible [BUG] If we remove the subpage limitation in add_ra_bio_pages(), then read a compressed extent which has part of its range in next page, like the following inode layout: 0 32K 64K 96K 128K |<--------------|-------------->| Btrfs will trigger ASSERT() in endio function: assertion failed: atomic_read(&subpage->readers) >= nbits ------------[ cut here ]------------ kernel BUG at fs/btrfs/ctree.h:3431! Internal error: Oops - BUG: 0 [#1] SMP Workqueue: btrfs-endio btrfs_work_helper [btrfs] Call trace: assertfail.constprop.0+0x28/0x2c [btrfs] btrfs_subpage_end_reader+0x148/0x14c [btrfs] end_page_read+0x8c/0x100 [btrfs] end_bio_extent_readpage+0x320/0x6b0 [btrfs] bio_endio+0x15c/0x1dc end_workqueue_fn+0x44/0x64 [btrfs] btrfs_work_helper+0x74/0x250 [btrfs] process_one_work+0x1d4/0x47c worker_thread+0x180/0x400 kthread+0x11c/0x120 ret_from_fork+0x10/0x30 ---[ end trace c8b7b552d3bb408c ]--- [CAUSE] When we read the page range [0, 64K), we find it's a compressed extent, and we will try to add extra pages in add_ra_bio_pages() to avoid reading the same compressed extent. But when we add such page into the read bio, it doesn't follow the behavior of btrfs_do_readpage() to properly set subpage::readers. This means, for page [64K, 128K), its subpage::readers is still 0. And when endio is executed on both pages, since page [64K, 128K) has 0 subpage::readers, it triggers above ASSERT() [FIX] Function add_ra_bio_pages() is far from subpage compatible, it always assume PAGE_SIZE == sectorsize, thus when it skip to next range it always just skip PAGE_SIZE. Make it subpage compatible by: - Skip to next page properly when needed If we find there is already a page cache, we need to skip to next page. For that case, we shouldn't just skip PAGE_SIZE bytes, but use @pg_index to calculate the next bytenr and continue. - Only add the page range covered by current extent map We need to calculate which range is covered by current extent map and only add that part into the read bio. - Update subpage::readers before submitting the bio - Use proper cursor other than confusing @last_offset - Calculate the missed threshold based on sector size It's no longer using missed pages, as for 64K page size, we have at most 3 pages to skip. (If aligned only 2 pages) - Add ASSERT() to make sure our bytenr is always aligned - Add comment for the function Add a special note for subpage case, as the function won't really work well for subpage cases. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-09-27 15:21:47 +08:00
/*
* Add extra pages in the same compressed file extent so that we don't need to
* re-read the same extent again and again.
*
* NOTE: this won't work well for subpage, as for subpage read, we lock the
* full page then submit bio for each compressed/regular extents.
*
* This means, if we have several sectors in the same page points to the same
* on-disk compressed data, we will re-read the same extent many times and
* this function can only help for the next page.
*/
static noinline int add_ra_bio_pages(struct inode *inode,
u64 compressed_end,
struct compressed_bio *cb)
{
btrfs: subpage: make add_ra_bio_pages() compatible [BUG] If we remove the subpage limitation in add_ra_bio_pages(), then read a compressed extent which has part of its range in next page, like the following inode layout: 0 32K 64K 96K 128K |<--------------|-------------->| Btrfs will trigger ASSERT() in endio function: assertion failed: atomic_read(&subpage->readers) >= nbits ------------[ cut here ]------------ kernel BUG at fs/btrfs/ctree.h:3431! Internal error: Oops - BUG: 0 [#1] SMP Workqueue: btrfs-endio btrfs_work_helper [btrfs] Call trace: assertfail.constprop.0+0x28/0x2c [btrfs] btrfs_subpage_end_reader+0x148/0x14c [btrfs] end_page_read+0x8c/0x100 [btrfs] end_bio_extent_readpage+0x320/0x6b0 [btrfs] bio_endio+0x15c/0x1dc end_workqueue_fn+0x44/0x64 [btrfs] btrfs_work_helper+0x74/0x250 [btrfs] process_one_work+0x1d4/0x47c worker_thread+0x180/0x400 kthread+0x11c/0x120 ret_from_fork+0x10/0x30 ---[ end trace c8b7b552d3bb408c ]--- [CAUSE] When we read the page range [0, 64K), we find it's a compressed extent, and we will try to add extra pages in add_ra_bio_pages() to avoid reading the same compressed extent. But when we add such page into the read bio, it doesn't follow the behavior of btrfs_do_readpage() to properly set subpage::readers. This means, for page [64K, 128K), its subpage::readers is still 0. And when endio is executed on both pages, since page [64K, 128K) has 0 subpage::readers, it triggers above ASSERT() [FIX] Function add_ra_bio_pages() is far from subpage compatible, it always assume PAGE_SIZE == sectorsize, thus when it skip to next range it always just skip PAGE_SIZE. Make it subpage compatible by: - Skip to next page properly when needed If we find there is already a page cache, we need to skip to next page. For that case, we shouldn't just skip PAGE_SIZE bytes, but use @pg_index to calculate the next bytenr and continue. - Only add the page range covered by current extent map We need to calculate which range is covered by current extent map and only add that part into the read bio. - Update subpage::readers before submitting the bio - Use proper cursor other than confusing @last_offset - Calculate the missed threshold based on sector size It's no longer using missed pages, as for 64K page size, we have at most 3 pages to skip. (If aligned only 2 pages) - Add ASSERT() to make sure our bytenr is always aligned - Add comment for the function Add a special note for subpage case, as the function won't really work well for subpage cases. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-09-27 15:21:47 +08:00
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
unsigned long end_index;
btrfs: subpage: make add_ra_bio_pages() compatible [BUG] If we remove the subpage limitation in add_ra_bio_pages(), then read a compressed extent which has part of its range in next page, like the following inode layout: 0 32K 64K 96K 128K |<--------------|-------------->| Btrfs will trigger ASSERT() in endio function: assertion failed: atomic_read(&subpage->readers) >= nbits ------------[ cut here ]------------ kernel BUG at fs/btrfs/ctree.h:3431! Internal error: Oops - BUG: 0 [#1] SMP Workqueue: btrfs-endio btrfs_work_helper [btrfs] Call trace: assertfail.constprop.0+0x28/0x2c [btrfs] btrfs_subpage_end_reader+0x148/0x14c [btrfs] end_page_read+0x8c/0x100 [btrfs] end_bio_extent_readpage+0x320/0x6b0 [btrfs] bio_endio+0x15c/0x1dc end_workqueue_fn+0x44/0x64 [btrfs] btrfs_work_helper+0x74/0x250 [btrfs] process_one_work+0x1d4/0x47c worker_thread+0x180/0x400 kthread+0x11c/0x120 ret_from_fork+0x10/0x30 ---[ end trace c8b7b552d3bb408c ]--- [CAUSE] When we read the page range [0, 64K), we find it's a compressed extent, and we will try to add extra pages in add_ra_bio_pages() to avoid reading the same compressed extent. But when we add such page into the read bio, it doesn't follow the behavior of btrfs_do_readpage() to properly set subpage::readers. This means, for page [64K, 128K), its subpage::readers is still 0. And when endio is executed on both pages, since page [64K, 128K) has 0 subpage::readers, it triggers above ASSERT() [FIX] Function add_ra_bio_pages() is far from subpage compatible, it always assume PAGE_SIZE == sectorsize, thus when it skip to next range it always just skip PAGE_SIZE. Make it subpage compatible by: - Skip to next page properly when needed If we find there is already a page cache, we need to skip to next page. For that case, we shouldn't just skip PAGE_SIZE bytes, but use @pg_index to calculate the next bytenr and continue. - Only add the page range covered by current extent map We need to calculate which range is covered by current extent map and only add that part into the read bio. - Update subpage::readers before submitting the bio - Use proper cursor other than confusing @last_offset - Calculate the missed threshold based on sector size It's no longer using missed pages, as for 64K page size, we have at most 3 pages to skip. (If aligned only 2 pages) - Add ASSERT() to make sure our bytenr is always aligned - Add comment for the function Add a special note for subpage case, as the function won't really work well for subpage cases. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-09-27 15:21:47 +08:00
u64 cur = bio_end_offset(cb->orig_bio);
u64 isize = i_size_read(inode);
int ret;
struct page *page;
struct extent_map *em;
struct address_space *mapping = inode->i_mapping;
struct extent_map_tree *em_tree;
struct extent_io_tree *tree;
btrfs: subpage: make add_ra_bio_pages() compatible [BUG] If we remove the subpage limitation in add_ra_bio_pages(), then read a compressed extent which has part of its range in next page, like the following inode layout: 0 32K 64K 96K 128K |<--------------|-------------->| Btrfs will trigger ASSERT() in endio function: assertion failed: atomic_read(&subpage->readers) >= nbits ------------[ cut here ]------------ kernel BUG at fs/btrfs/ctree.h:3431! Internal error: Oops - BUG: 0 [#1] SMP Workqueue: btrfs-endio btrfs_work_helper [btrfs] Call trace: assertfail.constprop.0+0x28/0x2c [btrfs] btrfs_subpage_end_reader+0x148/0x14c [btrfs] end_page_read+0x8c/0x100 [btrfs] end_bio_extent_readpage+0x320/0x6b0 [btrfs] bio_endio+0x15c/0x1dc end_workqueue_fn+0x44/0x64 [btrfs] btrfs_work_helper+0x74/0x250 [btrfs] process_one_work+0x1d4/0x47c worker_thread+0x180/0x400 kthread+0x11c/0x120 ret_from_fork+0x10/0x30 ---[ end trace c8b7b552d3bb408c ]--- [CAUSE] When we read the page range [0, 64K), we find it's a compressed extent, and we will try to add extra pages in add_ra_bio_pages() to avoid reading the same compressed extent. But when we add such page into the read bio, it doesn't follow the behavior of btrfs_do_readpage() to properly set subpage::readers. This means, for page [64K, 128K), its subpage::readers is still 0. And when endio is executed on both pages, since page [64K, 128K) has 0 subpage::readers, it triggers above ASSERT() [FIX] Function add_ra_bio_pages() is far from subpage compatible, it always assume PAGE_SIZE == sectorsize, thus when it skip to next range it always just skip PAGE_SIZE. Make it subpage compatible by: - Skip to next page properly when needed If we find there is already a page cache, we need to skip to next page. For that case, we shouldn't just skip PAGE_SIZE bytes, but use @pg_index to calculate the next bytenr and continue. - Only add the page range covered by current extent map We need to calculate which range is covered by current extent map and only add that part into the read bio. - Update subpage::readers before submitting the bio - Use proper cursor other than confusing @last_offset - Calculate the missed threshold based on sector size It's no longer using missed pages, as for 64K page size, we have at most 3 pages to skip. (If aligned only 2 pages) - Add ASSERT() to make sure our bytenr is always aligned - Add comment for the function Add a special note for subpage case, as the function won't really work well for subpage cases. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-09-27 15:21:47 +08:00
int sectors_missed = 0;
em_tree = &BTRFS_I(inode)->extent_tree;
tree = &BTRFS_I(inode)->io_tree;
if (isize == 0)
return 0;
/*
* For current subpage support, we only support 64K page size,
* which means maximum compressed extent size (128K) is just 2x page
* size.
* This makes readahead less effective, so here disable readahead for
* subpage for now, until full compressed write is supported.
*/
if (btrfs_sb(inode->i_sb)->sectorsize < PAGE_SIZE)
return 0;
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
end_index = (i_size_read(inode) - 1) >> PAGE_SHIFT;
btrfs: subpage: make add_ra_bio_pages() compatible [BUG] If we remove the subpage limitation in add_ra_bio_pages(), then read a compressed extent which has part of its range in next page, like the following inode layout: 0 32K 64K 96K 128K |<--------------|-------------->| Btrfs will trigger ASSERT() in endio function: assertion failed: atomic_read(&subpage->readers) >= nbits ------------[ cut here ]------------ kernel BUG at fs/btrfs/ctree.h:3431! Internal error: Oops - BUG: 0 [#1] SMP Workqueue: btrfs-endio btrfs_work_helper [btrfs] Call trace: assertfail.constprop.0+0x28/0x2c [btrfs] btrfs_subpage_end_reader+0x148/0x14c [btrfs] end_page_read+0x8c/0x100 [btrfs] end_bio_extent_readpage+0x320/0x6b0 [btrfs] bio_endio+0x15c/0x1dc end_workqueue_fn+0x44/0x64 [btrfs] btrfs_work_helper+0x74/0x250 [btrfs] process_one_work+0x1d4/0x47c worker_thread+0x180/0x400 kthread+0x11c/0x120 ret_from_fork+0x10/0x30 ---[ end trace c8b7b552d3bb408c ]--- [CAUSE] When we read the page range [0, 64K), we find it's a compressed extent, and we will try to add extra pages in add_ra_bio_pages() to avoid reading the same compressed extent. But when we add such page into the read bio, it doesn't follow the behavior of btrfs_do_readpage() to properly set subpage::readers. This means, for page [64K, 128K), its subpage::readers is still 0. And when endio is executed on both pages, since page [64K, 128K) has 0 subpage::readers, it triggers above ASSERT() [FIX] Function add_ra_bio_pages() is far from subpage compatible, it always assume PAGE_SIZE == sectorsize, thus when it skip to next range it always just skip PAGE_SIZE. Make it subpage compatible by: - Skip to next page properly when needed If we find there is already a page cache, we need to skip to next page. For that case, we shouldn't just skip PAGE_SIZE bytes, but use @pg_index to calculate the next bytenr and continue. - Only add the page range covered by current extent map We need to calculate which range is covered by current extent map and only add that part into the read bio. - Update subpage::readers before submitting the bio - Use proper cursor other than confusing @last_offset - Calculate the missed threshold based on sector size It's no longer using missed pages, as for 64K page size, we have at most 3 pages to skip. (If aligned only 2 pages) - Add ASSERT() to make sure our bytenr is always aligned - Add comment for the function Add a special note for subpage case, as the function won't really work well for subpage cases. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-09-27 15:21:47 +08:00
while (cur < compressed_end) {
u64 page_end;
u64 pg_index = cur >> PAGE_SHIFT;
u32 add_size;
if (pg_index > end_index)
break;
page = xa_load(&mapping->i_pages, pg_index);
if (page && !xa_is_value(page)) {
btrfs: subpage: make add_ra_bio_pages() compatible [BUG] If we remove the subpage limitation in add_ra_bio_pages(), then read a compressed extent which has part of its range in next page, like the following inode layout: 0 32K 64K 96K 128K |<--------------|-------------->| Btrfs will trigger ASSERT() in endio function: assertion failed: atomic_read(&subpage->readers) >= nbits ------------[ cut here ]------------ kernel BUG at fs/btrfs/ctree.h:3431! Internal error: Oops - BUG: 0 [#1] SMP Workqueue: btrfs-endio btrfs_work_helper [btrfs] Call trace: assertfail.constprop.0+0x28/0x2c [btrfs] btrfs_subpage_end_reader+0x148/0x14c [btrfs] end_page_read+0x8c/0x100 [btrfs] end_bio_extent_readpage+0x320/0x6b0 [btrfs] bio_endio+0x15c/0x1dc end_workqueue_fn+0x44/0x64 [btrfs] btrfs_work_helper+0x74/0x250 [btrfs] process_one_work+0x1d4/0x47c worker_thread+0x180/0x400 kthread+0x11c/0x120 ret_from_fork+0x10/0x30 ---[ end trace c8b7b552d3bb408c ]--- [CAUSE] When we read the page range [0, 64K), we find it's a compressed extent, and we will try to add extra pages in add_ra_bio_pages() to avoid reading the same compressed extent. But when we add such page into the read bio, it doesn't follow the behavior of btrfs_do_readpage() to properly set subpage::readers. This means, for page [64K, 128K), its subpage::readers is still 0. And when endio is executed on both pages, since page [64K, 128K) has 0 subpage::readers, it triggers above ASSERT() [FIX] Function add_ra_bio_pages() is far from subpage compatible, it always assume PAGE_SIZE == sectorsize, thus when it skip to next range it always just skip PAGE_SIZE. Make it subpage compatible by: - Skip to next page properly when needed If we find there is already a page cache, we need to skip to next page. For that case, we shouldn't just skip PAGE_SIZE bytes, but use @pg_index to calculate the next bytenr and continue. - Only add the page range covered by current extent map We need to calculate which range is covered by current extent map and only add that part into the read bio. - Update subpage::readers before submitting the bio - Use proper cursor other than confusing @last_offset - Calculate the missed threshold based on sector size It's no longer using missed pages, as for 64K page size, we have at most 3 pages to skip. (If aligned only 2 pages) - Add ASSERT() to make sure our bytenr is always aligned - Add comment for the function Add a special note for subpage case, as the function won't really work well for subpage cases. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-09-27 15:21:47 +08:00
sectors_missed += (PAGE_SIZE - offset_in_page(cur)) >>
fs_info->sectorsize_bits;
/* Beyond threshold, no need to continue */
if (sectors_missed > 4)
break;
btrfs: subpage: make add_ra_bio_pages() compatible [BUG] If we remove the subpage limitation in add_ra_bio_pages(), then read a compressed extent which has part of its range in next page, like the following inode layout: 0 32K 64K 96K 128K |<--------------|-------------->| Btrfs will trigger ASSERT() in endio function: assertion failed: atomic_read(&subpage->readers) >= nbits ------------[ cut here ]------------ kernel BUG at fs/btrfs/ctree.h:3431! Internal error: Oops - BUG: 0 [#1] SMP Workqueue: btrfs-endio btrfs_work_helper [btrfs] Call trace: assertfail.constprop.0+0x28/0x2c [btrfs] btrfs_subpage_end_reader+0x148/0x14c [btrfs] end_page_read+0x8c/0x100 [btrfs] end_bio_extent_readpage+0x320/0x6b0 [btrfs] bio_endio+0x15c/0x1dc end_workqueue_fn+0x44/0x64 [btrfs] btrfs_work_helper+0x74/0x250 [btrfs] process_one_work+0x1d4/0x47c worker_thread+0x180/0x400 kthread+0x11c/0x120 ret_from_fork+0x10/0x30 ---[ end trace c8b7b552d3bb408c ]--- [CAUSE] When we read the page range [0, 64K), we find it's a compressed extent, and we will try to add extra pages in add_ra_bio_pages() to avoid reading the same compressed extent. But when we add such page into the read bio, it doesn't follow the behavior of btrfs_do_readpage() to properly set subpage::readers. This means, for page [64K, 128K), its subpage::readers is still 0. And when endio is executed on both pages, since page [64K, 128K) has 0 subpage::readers, it triggers above ASSERT() [FIX] Function add_ra_bio_pages() is far from subpage compatible, it always assume PAGE_SIZE == sectorsize, thus when it skip to next range it always just skip PAGE_SIZE. Make it subpage compatible by: - Skip to next page properly when needed If we find there is already a page cache, we need to skip to next page. For that case, we shouldn't just skip PAGE_SIZE bytes, but use @pg_index to calculate the next bytenr and continue. - Only add the page range covered by current extent map We need to calculate which range is covered by current extent map and only add that part into the read bio. - Update subpage::readers before submitting the bio - Use proper cursor other than confusing @last_offset - Calculate the missed threshold based on sector size It's no longer using missed pages, as for 64K page size, we have at most 3 pages to skip. (If aligned only 2 pages) - Add ASSERT() to make sure our bytenr is always aligned - Add comment for the function Add a special note for subpage case, as the function won't really work well for subpage cases. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-09-27 15:21:47 +08:00
/*
* Jump to next page start as we already have page for
* current offset.
*/
cur = (pg_index << PAGE_SHIFT) + PAGE_SIZE;
continue;
}
page = __page_cache_alloc(mapping_gfp_constraint(mapping,
~__GFP_FS));
if (!page)
break;
if (add_to_page_cache_lru(page, mapping, pg_index, GFP_NOFS)) {
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
put_page(page);
btrfs: subpage: make add_ra_bio_pages() compatible [BUG] If we remove the subpage limitation in add_ra_bio_pages(), then read a compressed extent which has part of its range in next page, like the following inode layout: 0 32K 64K 96K 128K |<--------------|-------------->| Btrfs will trigger ASSERT() in endio function: assertion failed: atomic_read(&subpage->readers) >= nbits ------------[ cut here ]------------ kernel BUG at fs/btrfs/ctree.h:3431! Internal error: Oops - BUG: 0 [#1] SMP Workqueue: btrfs-endio btrfs_work_helper [btrfs] Call trace: assertfail.constprop.0+0x28/0x2c [btrfs] btrfs_subpage_end_reader+0x148/0x14c [btrfs] end_page_read+0x8c/0x100 [btrfs] end_bio_extent_readpage+0x320/0x6b0 [btrfs] bio_endio+0x15c/0x1dc end_workqueue_fn+0x44/0x64 [btrfs] btrfs_work_helper+0x74/0x250 [btrfs] process_one_work+0x1d4/0x47c worker_thread+0x180/0x400 kthread+0x11c/0x120 ret_from_fork+0x10/0x30 ---[ end trace c8b7b552d3bb408c ]--- [CAUSE] When we read the page range [0, 64K), we find it's a compressed extent, and we will try to add extra pages in add_ra_bio_pages() to avoid reading the same compressed extent. But when we add such page into the read bio, it doesn't follow the behavior of btrfs_do_readpage() to properly set subpage::readers. This means, for page [64K, 128K), its subpage::readers is still 0. And when endio is executed on both pages, since page [64K, 128K) has 0 subpage::readers, it triggers above ASSERT() [FIX] Function add_ra_bio_pages() is far from subpage compatible, it always assume PAGE_SIZE == sectorsize, thus when it skip to next range it always just skip PAGE_SIZE. Make it subpage compatible by: - Skip to next page properly when needed If we find there is already a page cache, we need to skip to next page. For that case, we shouldn't just skip PAGE_SIZE bytes, but use @pg_index to calculate the next bytenr and continue. - Only add the page range covered by current extent map We need to calculate which range is covered by current extent map and only add that part into the read bio. - Update subpage::readers before submitting the bio - Use proper cursor other than confusing @last_offset - Calculate the missed threshold based on sector size It's no longer using missed pages, as for 64K page size, we have at most 3 pages to skip. (If aligned only 2 pages) - Add ASSERT() to make sure our bytenr is always aligned - Add comment for the function Add a special note for subpage case, as the function won't really work well for subpage cases. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-09-27 15:21:47 +08:00
/* There is already a page, skip to page end */
cur = (pg_index << PAGE_SHIFT) + PAGE_SIZE;
continue;
}
ret = set_page_extent_mapped(page);
if (ret < 0) {
unlock_page(page);
put_page(page);
break;
}
btrfs: subpage: make add_ra_bio_pages() compatible [BUG] If we remove the subpage limitation in add_ra_bio_pages(), then read a compressed extent which has part of its range in next page, like the following inode layout: 0 32K 64K 96K 128K |<--------------|-------------->| Btrfs will trigger ASSERT() in endio function: assertion failed: atomic_read(&subpage->readers) >= nbits ------------[ cut here ]------------ kernel BUG at fs/btrfs/ctree.h:3431! Internal error: Oops - BUG: 0 [#1] SMP Workqueue: btrfs-endio btrfs_work_helper [btrfs] Call trace: assertfail.constprop.0+0x28/0x2c [btrfs] btrfs_subpage_end_reader+0x148/0x14c [btrfs] end_page_read+0x8c/0x100 [btrfs] end_bio_extent_readpage+0x320/0x6b0 [btrfs] bio_endio+0x15c/0x1dc end_workqueue_fn+0x44/0x64 [btrfs] btrfs_work_helper+0x74/0x250 [btrfs] process_one_work+0x1d4/0x47c worker_thread+0x180/0x400 kthread+0x11c/0x120 ret_from_fork+0x10/0x30 ---[ end trace c8b7b552d3bb408c ]--- [CAUSE] When we read the page range [0, 64K), we find it's a compressed extent, and we will try to add extra pages in add_ra_bio_pages() to avoid reading the same compressed extent. But when we add such page into the read bio, it doesn't follow the behavior of btrfs_do_readpage() to properly set subpage::readers. This means, for page [64K, 128K), its subpage::readers is still 0. And when endio is executed on both pages, since page [64K, 128K) has 0 subpage::readers, it triggers above ASSERT() [FIX] Function add_ra_bio_pages() is far from subpage compatible, it always assume PAGE_SIZE == sectorsize, thus when it skip to next range it always just skip PAGE_SIZE. Make it subpage compatible by: - Skip to next page properly when needed If we find there is already a page cache, we need to skip to next page. For that case, we shouldn't just skip PAGE_SIZE bytes, but use @pg_index to calculate the next bytenr and continue. - Only add the page range covered by current extent map We need to calculate which range is covered by current extent map and only add that part into the read bio. - Update subpage::readers before submitting the bio - Use proper cursor other than confusing @last_offset - Calculate the missed threshold based on sector size It's no longer using missed pages, as for 64K page size, we have at most 3 pages to skip. (If aligned only 2 pages) - Add ASSERT() to make sure our bytenr is always aligned - Add comment for the function Add a special note for subpage case, as the function won't really work well for subpage cases. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-09-27 15:21:47 +08:00
page_end = (pg_index << PAGE_SHIFT) + PAGE_SIZE - 1;
lock_extent(tree, cur, page_end);
read_lock(&em_tree->lock);
btrfs: subpage: make add_ra_bio_pages() compatible [BUG] If we remove the subpage limitation in add_ra_bio_pages(), then read a compressed extent which has part of its range in next page, like the following inode layout: 0 32K 64K 96K 128K |<--------------|-------------->| Btrfs will trigger ASSERT() in endio function: assertion failed: atomic_read(&subpage->readers) >= nbits ------------[ cut here ]------------ kernel BUG at fs/btrfs/ctree.h:3431! Internal error: Oops - BUG: 0 [#1] SMP Workqueue: btrfs-endio btrfs_work_helper [btrfs] Call trace: assertfail.constprop.0+0x28/0x2c [btrfs] btrfs_subpage_end_reader+0x148/0x14c [btrfs] end_page_read+0x8c/0x100 [btrfs] end_bio_extent_readpage+0x320/0x6b0 [btrfs] bio_endio+0x15c/0x1dc end_workqueue_fn+0x44/0x64 [btrfs] btrfs_work_helper+0x74/0x250 [btrfs] process_one_work+0x1d4/0x47c worker_thread+0x180/0x400 kthread+0x11c/0x120 ret_from_fork+0x10/0x30 ---[ end trace c8b7b552d3bb408c ]--- [CAUSE] When we read the page range [0, 64K), we find it's a compressed extent, and we will try to add extra pages in add_ra_bio_pages() to avoid reading the same compressed extent. But when we add such page into the read bio, it doesn't follow the behavior of btrfs_do_readpage() to properly set subpage::readers. This means, for page [64K, 128K), its subpage::readers is still 0. And when endio is executed on both pages, since page [64K, 128K) has 0 subpage::readers, it triggers above ASSERT() [FIX] Function add_ra_bio_pages() is far from subpage compatible, it always assume PAGE_SIZE == sectorsize, thus when it skip to next range it always just skip PAGE_SIZE. Make it subpage compatible by: - Skip to next page properly when needed If we find there is already a page cache, we need to skip to next page. For that case, we shouldn't just skip PAGE_SIZE bytes, but use @pg_index to calculate the next bytenr and continue. - Only add the page range covered by current extent map We need to calculate which range is covered by current extent map and only add that part into the read bio. - Update subpage::readers before submitting the bio - Use proper cursor other than confusing @last_offset - Calculate the missed threshold based on sector size It's no longer using missed pages, as for 64K page size, we have at most 3 pages to skip. (If aligned only 2 pages) - Add ASSERT() to make sure our bytenr is always aligned - Add comment for the function Add a special note for subpage case, as the function won't really work well for subpage cases. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-09-27 15:21:47 +08:00
em = lookup_extent_mapping(em_tree, cur, page_end + 1 - cur);
read_unlock(&em_tree->lock);
btrfs: subpage: make add_ra_bio_pages() compatible [BUG] If we remove the subpage limitation in add_ra_bio_pages(), then read a compressed extent which has part of its range in next page, like the following inode layout: 0 32K 64K 96K 128K |<--------------|-------------->| Btrfs will trigger ASSERT() in endio function: assertion failed: atomic_read(&subpage->readers) >= nbits ------------[ cut here ]------------ kernel BUG at fs/btrfs/ctree.h:3431! Internal error: Oops - BUG: 0 [#1] SMP Workqueue: btrfs-endio btrfs_work_helper [btrfs] Call trace: assertfail.constprop.0+0x28/0x2c [btrfs] btrfs_subpage_end_reader+0x148/0x14c [btrfs] end_page_read+0x8c/0x100 [btrfs] end_bio_extent_readpage+0x320/0x6b0 [btrfs] bio_endio+0x15c/0x1dc end_workqueue_fn+0x44/0x64 [btrfs] btrfs_work_helper+0x74/0x250 [btrfs] process_one_work+0x1d4/0x47c worker_thread+0x180/0x400 kthread+0x11c/0x120 ret_from_fork+0x10/0x30 ---[ end trace c8b7b552d3bb408c ]--- [CAUSE] When we read the page range [0, 64K), we find it's a compressed extent, and we will try to add extra pages in add_ra_bio_pages() to avoid reading the same compressed extent. But when we add such page into the read bio, it doesn't follow the behavior of btrfs_do_readpage() to properly set subpage::readers. This means, for page [64K, 128K), its subpage::readers is still 0. And when endio is executed on both pages, since page [64K, 128K) has 0 subpage::readers, it triggers above ASSERT() [FIX] Function add_ra_bio_pages() is far from subpage compatible, it always assume PAGE_SIZE == sectorsize, thus when it skip to next range it always just skip PAGE_SIZE. Make it subpage compatible by: - Skip to next page properly when needed If we find there is already a page cache, we need to skip to next page. For that case, we shouldn't just skip PAGE_SIZE bytes, but use @pg_index to calculate the next bytenr and continue. - Only add the page range covered by current extent map We need to calculate which range is covered by current extent map and only add that part into the read bio. - Update subpage::readers before submitting the bio - Use proper cursor other than confusing @last_offset - Calculate the missed threshold based on sector size It's no longer using missed pages, as for 64K page size, we have at most 3 pages to skip. (If aligned only 2 pages) - Add ASSERT() to make sure our bytenr is always aligned - Add comment for the function Add a special note for subpage case, as the function won't really work well for subpage cases. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-09-27 15:21:47 +08:00
/*
* At this point, we have a locked page in the page cache for
* these bytes in the file. But, we have to make sure they map
* to this compressed extent on disk.
*/
if (!em || cur < em->start ||
(cur + fs_info->sectorsize > extent_map_end(em)) ||
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
(em->block_start >> 9) != cb->orig_bio->bi_iter.bi_sector) {
free_extent_map(em);
btrfs: subpage: make add_ra_bio_pages() compatible [BUG] If we remove the subpage limitation in add_ra_bio_pages(), then read a compressed extent which has part of its range in next page, like the following inode layout: 0 32K 64K 96K 128K |<--------------|-------------->| Btrfs will trigger ASSERT() in endio function: assertion failed: atomic_read(&subpage->readers) >= nbits ------------[ cut here ]------------ kernel BUG at fs/btrfs/ctree.h:3431! Internal error: Oops - BUG: 0 [#1] SMP Workqueue: btrfs-endio btrfs_work_helper [btrfs] Call trace: assertfail.constprop.0+0x28/0x2c [btrfs] btrfs_subpage_end_reader+0x148/0x14c [btrfs] end_page_read+0x8c/0x100 [btrfs] end_bio_extent_readpage+0x320/0x6b0 [btrfs] bio_endio+0x15c/0x1dc end_workqueue_fn+0x44/0x64 [btrfs] btrfs_work_helper+0x74/0x250 [btrfs] process_one_work+0x1d4/0x47c worker_thread+0x180/0x400 kthread+0x11c/0x120 ret_from_fork+0x10/0x30 ---[ end trace c8b7b552d3bb408c ]--- [CAUSE] When we read the page range [0, 64K), we find it's a compressed extent, and we will try to add extra pages in add_ra_bio_pages() to avoid reading the same compressed extent. But when we add such page into the read bio, it doesn't follow the behavior of btrfs_do_readpage() to properly set subpage::readers. This means, for page [64K, 128K), its subpage::readers is still 0. And when endio is executed on both pages, since page [64K, 128K) has 0 subpage::readers, it triggers above ASSERT() [FIX] Function add_ra_bio_pages() is far from subpage compatible, it always assume PAGE_SIZE == sectorsize, thus when it skip to next range it always just skip PAGE_SIZE. Make it subpage compatible by: - Skip to next page properly when needed If we find there is already a page cache, we need to skip to next page. For that case, we shouldn't just skip PAGE_SIZE bytes, but use @pg_index to calculate the next bytenr and continue. - Only add the page range covered by current extent map We need to calculate which range is covered by current extent map and only add that part into the read bio. - Update subpage::readers before submitting the bio - Use proper cursor other than confusing @last_offset - Calculate the missed threshold based on sector size It's no longer using missed pages, as for 64K page size, we have at most 3 pages to skip. (If aligned only 2 pages) - Add ASSERT() to make sure our bytenr is always aligned - Add comment for the function Add a special note for subpage case, as the function won't really work well for subpage cases. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-09-27 15:21:47 +08:00
unlock_extent(tree, cur, page_end);
unlock_page(page);
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
put_page(page);
break;
}
free_extent_map(em);
if (page->index == end_index) {
size_t zero_offset = offset_in_page(isize);
if (zero_offset) {
int zeros;
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
zeros = PAGE_SIZE - zero_offset;
btrfs: use memzero_page() instead of open coded kmap pattern There are many places where kmap/memset/kunmap patterns occur. Use the newly lifted memzero_page() to eliminate direct uses of kmap and leverage the new core functions use of kmap_local_page(). The development of this patch was aided by the following coccinelle script: // <smpl> // SPDX-License-Identifier: GPL-2.0-only // Find kmap/memset/kunmap pattern and replace with memset*page calls // // NOTE: Offsets and other expressions may be more complex than what the script // will automatically generate. Therefore a catchall rule is provided to find // the pattern which then must be evaluated by hand. // // Confidence: Low // Copyright: (C) 2021 Intel Corporation // URL: http://coccinelle.lip6.fr/ // Comments: // Options: // // Then the memset pattern // @ memset_rule1 @ expression page, V, L, Off; identifier ptr; type VP; @@ ( -VP ptr = kmap(page); | -ptr = kmap(page); | -VP ptr = kmap_atomic(page); | -ptr = kmap_atomic(page); ) <+... ( -memset(ptr, 0, L); +memzero_page(page, 0, L); | -memset(ptr + Off, 0, L); +memzero_page(page, Off, L); | -memset(ptr, V, L); +memset_page(page, V, 0, L); | -memset(ptr + Off, V, L); +memset_page(page, V, Off, L); ) ...+> ( -kunmap(page); | -kunmap_atomic(ptr); ) // Remove any pointers left unused @ depends on memset_rule1 @ identifier memset_rule1.ptr; type VP, VP1; @@ -VP ptr; ... when != ptr; ? VP1 ptr; // // Catch all // @ memset_rule2 @ expression page; identifier ptr; expression GenTo, GenSize, GenValue; type VP; @@ ( -VP ptr = kmap(page); | -ptr = kmap(page); | -VP ptr = kmap_atomic(page); | -ptr = kmap_atomic(page); ) <+... ( // // Some call sites have complex expressions within the memset/memcpy // The follow are catch alls which need to be evaluated by hand. // -memset(GenTo, 0, GenSize); +memzero_pageExtra(page, GenTo, GenSize); | -memset(GenTo, GenValue, GenSize); +memset_pageExtra(page, GenValue, GenTo, GenSize); ) ...+> ( -kunmap(page); | -kunmap_atomic(ptr); ) // Remove any pointers left unused @ depends on memset_rule2 @ identifier memset_rule2.ptr; type VP, VP1; @@ -VP ptr; ... when != ptr; ? VP1 ptr; // </smpl> Link: https://lkml.kernel.org/r/20210309212137.2610186-4-ira.weiny@intel.com Signed-off-by: Ira Weiny <ira.weiny@intel.com> Reviewed-by: David Sterba <dsterba@suse.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com> Cc: Chris Mason <clm@fb.com> Cc: Josef Bacik <josef@toxicpanda.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-05-05 09:40:07 +08:00
memzero_page(page, zero_offset, zeros);
flush_dcache_page(page);
}
}
btrfs: subpage: make add_ra_bio_pages() compatible [BUG] If we remove the subpage limitation in add_ra_bio_pages(), then read a compressed extent which has part of its range in next page, like the following inode layout: 0 32K 64K 96K 128K |<--------------|-------------->| Btrfs will trigger ASSERT() in endio function: assertion failed: atomic_read(&subpage->readers) >= nbits ------------[ cut here ]------------ kernel BUG at fs/btrfs/ctree.h:3431! Internal error: Oops - BUG: 0 [#1] SMP Workqueue: btrfs-endio btrfs_work_helper [btrfs] Call trace: assertfail.constprop.0+0x28/0x2c [btrfs] btrfs_subpage_end_reader+0x148/0x14c [btrfs] end_page_read+0x8c/0x100 [btrfs] end_bio_extent_readpage+0x320/0x6b0 [btrfs] bio_endio+0x15c/0x1dc end_workqueue_fn+0x44/0x64 [btrfs] btrfs_work_helper+0x74/0x250 [btrfs] process_one_work+0x1d4/0x47c worker_thread+0x180/0x400 kthread+0x11c/0x120 ret_from_fork+0x10/0x30 ---[ end trace c8b7b552d3bb408c ]--- [CAUSE] When we read the page range [0, 64K), we find it's a compressed extent, and we will try to add extra pages in add_ra_bio_pages() to avoid reading the same compressed extent. But when we add such page into the read bio, it doesn't follow the behavior of btrfs_do_readpage() to properly set subpage::readers. This means, for page [64K, 128K), its subpage::readers is still 0. And when endio is executed on both pages, since page [64K, 128K) has 0 subpage::readers, it triggers above ASSERT() [FIX] Function add_ra_bio_pages() is far from subpage compatible, it always assume PAGE_SIZE == sectorsize, thus when it skip to next range it always just skip PAGE_SIZE. Make it subpage compatible by: - Skip to next page properly when needed If we find there is already a page cache, we need to skip to next page. For that case, we shouldn't just skip PAGE_SIZE bytes, but use @pg_index to calculate the next bytenr and continue. - Only add the page range covered by current extent map We need to calculate which range is covered by current extent map and only add that part into the read bio. - Update subpage::readers before submitting the bio - Use proper cursor other than confusing @last_offset - Calculate the missed threshold based on sector size It's no longer using missed pages, as for 64K page size, we have at most 3 pages to skip. (If aligned only 2 pages) - Add ASSERT() to make sure our bytenr is always aligned - Add comment for the function Add a special note for subpage case, as the function won't really work well for subpage cases. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-09-27 15:21:47 +08:00
add_size = min(em->start + em->len, page_end + 1) - cur;
ret = bio_add_page(cb->orig_bio, page, add_size, offset_in_page(cur));
if (ret != add_size) {
unlock_extent(tree, cur, page_end);
unlock_page(page);
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
put_page(page);
break;
}
btrfs: subpage: make add_ra_bio_pages() compatible [BUG] If we remove the subpage limitation in add_ra_bio_pages(), then read a compressed extent which has part of its range in next page, like the following inode layout: 0 32K 64K 96K 128K |<--------------|-------------->| Btrfs will trigger ASSERT() in endio function: assertion failed: atomic_read(&subpage->readers) >= nbits ------------[ cut here ]------------ kernel BUG at fs/btrfs/ctree.h:3431! Internal error: Oops - BUG: 0 [#1] SMP Workqueue: btrfs-endio btrfs_work_helper [btrfs] Call trace: assertfail.constprop.0+0x28/0x2c [btrfs] btrfs_subpage_end_reader+0x148/0x14c [btrfs] end_page_read+0x8c/0x100 [btrfs] end_bio_extent_readpage+0x320/0x6b0 [btrfs] bio_endio+0x15c/0x1dc end_workqueue_fn+0x44/0x64 [btrfs] btrfs_work_helper+0x74/0x250 [btrfs] process_one_work+0x1d4/0x47c worker_thread+0x180/0x400 kthread+0x11c/0x120 ret_from_fork+0x10/0x30 ---[ end trace c8b7b552d3bb408c ]--- [CAUSE] When we read the page range [0, 64K), we find it's a compressed extent, and we will try to add extra pages in add_ra_bio_pages() to avoid reading the same compressed extent. But when we add such page into the read bio, it doesn't follow the behavior of btrfs_do_readpage() to properly set subpage::readers. This means, for page [64K, 128K), its subpage::readers is still 0. And when endio is executed on both pages, since page [64K, 128K) has 0 subpage::readers, it triggers above ASSERT() [FIX] Function add_ra_bio_pages() is far from subpage compatible, it always assume PAGE_SIZE == sectorsize, thus when it skip to next range it always just skip PAGE_SIZE. Make it subpage compatible by: - Skip to next page properly when needed If we find there is already a page cache, we need to skip to next page. For that case, we shouldn't just skip PAGE_SIZE bytes, but use @pg_index to calculate the next bytenr and continue. - Only add the page range covered by current extent map We need to calculate which range is covered by current extent map and only add that part into the read bio. - Update subpage::readers before submitting the bio - Use proper cursor other than confusing @last_offset - Calculate the missed threshold based on sector size It's no longer using missed pages, as for 64K page size, we have at most 3 pages to skip. (If aligned only 2 pages) - Add ASSERT() to make sure our bytenr is always aligned - Add comment for the function Add a special note for subpage case, as the function won't really work well for subpage cases. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-09-27 15:21:47 +08:00
/*
* If it's subpage, we also need to increase its
* subpage::readers number, as at endio we will decrease
* subpage::readers and to unlock the page.
*/
if (fs_info->sectorsize < PAGE_SIZE)
btrfs_subpage_start_reader(fs_info, page, cur, add_size);
put_page(page);
cur += add_size;
}
return 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
/*
* for a compressed read, the bio we get passed has all the inode pages
* in it. We don't actually do IO on those pages but allocate new ones
* to hold the compressed pages on disk.
*
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
* bio->bi_iter.bi_sector points to the compressed extent on disk
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
* bio->bi_io_vec points to all of the inode pages
*
* After the compressed pages are read, we copy the bytes into the
* bio we were passed and then call the bio end_io calls
*/
blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
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
int mirror_num, unsigned long bio_flags)
{
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
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
struct extent_map_tree *em_tree;
struct compressed_bio *cb;
unsigned int compressed_len;
unsigned int nr_pages;
unsigned int pg_index;
struct bio *comp_bio = NULL;
const u64 disk_bytenr = bio->bi_iter.bi_sector << SECTOR_SHIFT;
u64 cur_disk_byte = disk_bytenr;
u64 next_stripe_start;
btrfs: grab correct extent map for subpage compressed extent read [BUG] When subpage compressed read write support is enabled, btrfs/038 always fails with EIO. A simplified script can easily trigger the problem: mkfs.btrfs -f -s 4k $dev mount $dev $mnt -o compress=lzo xfs_io -f -c "truncate 118811" $mnt/foo xfs_io -c "pwrite -S 0x0d -b 39987 92267 39987" $mnt/foo > /dev/null sync btrfs subvolume snapshot -r $mnt $mnt/mysnap1 xfs_io -c "pwrite -S 0x3e -b 80000 200000 80000" $mnt/foo > /dev/null sync xfs_io -c "pwrite -S 0xdc -b 10000 250000 10000" $mnt/foo > /dev/null xfs_io -c "pwrite -S 0xff -b 10000 300000 10000" $mnt/foo > /dev/null sync btrfs subvolume snapshot -r $mnt $mnt/mysnap2 cat $mnt/mysnap2/foo # Above cat will fail due to EIO [CAUSE] The problem is in btrfs_submit_compressed_read(). When it tries to grab the extent map of the read range, it uses the following call: em = lookup_extent_mapping(em_tree, page_offset(bio_first_page_all(bio)), fs_info->sectorsize); The problem is in the page_offset(bio_first_page_all(bio)) part. The offending inode has the following file extent layout item 10 key (257 EXTENT_DATA 131072) itemoff 15639 itemsize 53 generation 8 type 1 (regular) extent data disk byte 13680640 nr 4096 extent data offset 0 nr 4096 ram 4096 extent compression 0 (none) item 11 key (257 EXTENT_DATA 135168) itemoff 15586 itemsize 53 generation 8 type 1 (regular) extent data disk byte 0 nr 0 item 12 key (257 EXTENT_DATA 196608) itemoff 15533 itemsize 53 generation 8 type 1 (regular) extent data disk byte 13676544 nr 4096 extent data offset 0 nr 53248 ram 86016 extent compression 2 (lzo) And the bio passed in has the following parameters: page_offset(bio_first_page_all(bio)) = 131072 bio_first_bvec_all(bio)->bv_offset = 65536 If we use page_offset(bio_first_page_all(bio) without adding bv_offset, we will get an extent map for file offset 131072, not 196608. This means we read uncompressed data from disk, and later decompression will definitely fail. [FIX] Take bv_offset into consideration when trying to grab an extent map. And add an ASSERT() to ensure we're really getting a compressed extent. Thankfully this won't affect anything but subpage, thus we only need to ensure this patch get merged before we enabled basic subpage support. Reviewed-by: Anand Jain <anand.jain@oracle.com> Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-05 10:00:56 +08:00
u64 file_offset;
u64 em_len;
u64 em_start;
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
struct extent_map *em;
blk_status_t ret = BLK_STS_RESOURCE;
int faili = 0;
u8 *sums;
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
em_tree = &BTRFS_I(inode)->extent_tree;
btrfs: grab correct extent map for subpage compressed extent read [BUG] When subpage compressed read write support is enabled, btrfs/038 always fails with EIO. A simplified script can easily trigger the problem: mkfs.btrfs -f -s 4k $dev mount $dev $mnt -o compress=lzo xfs_io -f -c "truncate 118811" $mnt/foo xfs_io -c "pwrite -S 0x0d -b 39987 92267 39987" $mnt/foo > /dev/null sync btrfs subvolume snapshot -r $mnt $mnt/mysnap1 xfs_io -c "pwrite -S 0x3e -b 80000 200000 80000" $mnt/foo > /dev/null sync xfs_io -c "pwrite -S 0xdc -b 10000 250000 10000" $mnt/foo > /dev/null xfs_io -c "pwrite -S 0xff -b 10000 300000 10000" $mnt/foo > /dev/null sync btrfs subvolume snapshot -r $mnt $mnt/mysnap2 cat $mnt/mysnap2/foo # Above cat will fail due to EIO [CAUSE] The problem is in btrfs_submit_compressed_read(). When it tries to grab the extent map of the read range, it uses the following call: em = lookup_extent_mapping(em_tree, page_offset(bio_first_page_all(bio)), fs_info->sectorsize); The problem is in the page_offset(bio_first_page_all(bio)) part. The offending inode has the following file extent layout item 10 key (257 EXTENT_DATA 131072) itemoff 15639 itemsize 53 generation 8 type 1 (regular) extent data disk byte 13680640 nr 4096 extent data offset 0 nr 4096 ram 4096 extent compression 0 (none) item 11 key (257 EXTENT_DATA 135168) itemoff 15586 itemsize 53 generation 8 type 1 (regular) extent data disk byte 0 nr 0 item 12 key (257 EXTENT_DATA 196608) itemoff 15533 itemsize 53 generation 8 type 1 (regular) extent data disk byte 13676544 nr 4096 extent data offset 0 nr 53248 ram 86016 extent compression 2 (lzo) And the bio passed in has the following parameters: page_offset(bio_first_page_all(bio)) = 131072 bio_first_bvec_all(bio)->bv_offset = 65536 If we use page_offset(bio_first_page_all(bio) without adding bv_offset, we will get an extent map for file offset 131072, not 196608. This means we read uncompressed data from disk, and later decompression will definitely fail. [FIX] Take bv_offset into consideration when trying to grab an extent map. And add an ASSERT() to ensure we're really getting a compressed extent. Thankfully this won't affect anything but subpage, thus we only need to ensure this patch get merged before we enabled basic subpage support. Reviewed-by: Anand Jain <anand.jain@oracle.com> Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-05 10:00:56 +08:00
file_offset = bio_first_bvec_all(bio)->bv_offset +
page_offset(bio_first_page_all(bio));
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
/* we need the actual starting offset of this extent in the file */
read_lock(&em_tree->lock);
btrfs: grab correct extent map for subpage compressed extent read [BUG] When subpage compressed read write support is enabled, btrfs/038 always fails with EIO. A simplified script can easily trigger the problem: mkfs.btrfs -f -s 4k $dev mount $dev $mnt -o compress=lzo xfs_io -f -c "truncate 118811" $mnt/foo xfs_io -c "pwrite -S 0x0d -b 39987 92267 39987" $mnt/foo > /dev/null sync btrfs subvolume snapshot -r $mnt $mnt/mysnap1 xfs_io -c "pwrite -S 0x3e -b 80000 200000 80000" $mnt/foo > /dev/null sync xfs_io -c "pwrite -S 0xdc -b 10000 250000 10000" $mnt/foo > /dev/null xfs_io -c "pwrite -S 0xff -b 10000 300000 10000" $mnt/foo > /dev/null sync btrfs subvolume snapshot -r $mnt $mnt/mysnap2 cat $mnt/mysnap2/foo # Above cat will fail due to EIO [CAUSE] The problem is in btrfs_submit_compressed_read(). When it tries to grab the extent map of the read range, it uses the following call: em = lookup_extent_mapping(em_tree, page_offset(bio_first_page_all(bio)), fs_info->sectorsize); The problem is in the page_offset(bio_first_page_all(bio)) part. The offending inode has the following file extent layout item 10 key (257 EXTENT_DATA 131072) itemoff 15639 itemsize 53 generation 8 type 1 (regular) extent data disk byte 13680640 nr 4096 extent data offset 0 nr 4096 ram 4096 extent compression 0 (none) item 11 key (257 EXTENT_DATA 135168) itemoff 15586 itemsize 53 generation 8 type 1 (regular) extent data disk byte 0 nr 0 item 12 key (257 EXTENT_DATA 196608) itemoff 15533 itemsize 53 generation 8 type 1 (regular) extent data disk byte 13676544 nr 4096 extent data offset 0 nr 53248 ram 86016 extent compression 2 (lzo) And the bio passed in has the following parameters: page_offset(bio_first_page_all(bio)) = 131072 bio_first_bvec_all(bio)->bv_offset = 65536 If we use page_offset(bio_first_page_all(bio) without adding bv_offset, we will get an extent map for file offset 131072, not 196608. This means we read uncompressed data from disk, and later decompression will definitely fail. [FIX] Take bv_offset into consideration when trying to grab an extent map. And add an ASSERT() to ensure we're really getting a compressed extent. Thankfully this won't affect anything but subpage, thus we only need to ensure this patch get merged before we enabled basic subpage support. Reviewed-by: Anand Jain <anand.jain@oracle.com> Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-05 10:00:56 +08:00
em = lookup_extent_mapping(em_tree, file_offset, fs_info->sectorsize);
read_unlock(&em_tree->lock);
if (!em)
return BLK_STS_IOERR;
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: grab correct extent map for subpage compressed extent read [BUG] When subpage compressed read write support is enabled, btrfs/038 always fails with EIO. A simplified script can easily trigger the problem: mkfs.btrfs -f -s 4k $dev mount $dev $mnt -o compress=lzo xfs_io -f -c "truncate 118811" $mnt/foo xfs_io -c "pwrite -S 0x0d -b 39987 92267 39987" $mnt/foo > /dev/null sync btrfs subvolume snapshot -r $mnt $mnt/mysnap1 xfs_io -c "pwrite -S 0x3e -b 80000 200000 80000" $mnt/foo > /dev/null sync xfs_io -c "pwrite -S 0xdc -b 10000 250000 10000" $mnt/foo > /dev/null xfs_io -c "pwrite -S 0xff -b 10000 300000 10000" $mnt/foo > /dev/null sync btrfs subvolume snapshot -r $mnt $mnt/mysnap2 cat $mnt/mysnap2/foo # Above cat will fail due to EIO [CAUSE] The problem is in btrfs_submit_compressed_read(). When it tries to grab the extent map of the read range, it uses the following call: em = lookup_extent_mapping(em_tree, page_offset(bio_first_page_all(bio)), fs_info->sectorsize); The problem is in the page_offset(bio_first_page_all(bio)) part. The offending inode has the following file extent layout item 10 key (257 EXTENT_DATA 131072) itemoff 15639 itemsize 53 generation 8 type 1 (regular) extent data disk byte 13680640 nr 4096 extent data offset 0 nr 4096 ram 4096 extent compression 0 (none) item 11 key (257 EXTENT_DATA 135168) itemoff 15586 itemsize 53 generation 8 type 1 (regular) extent data disk byte 0 nr 0 item 12 key (257 EXTENT_DATA 196608) itemoff 15533 itemsize 53 generation 8 type 1 (regular) extent data disk byte 13676544 nr 4096 extent data offset 0 nr 53248 ram 86016 extent compression 2 (lzo) And the bio passed in has the following parameters: page_offset(bio_first_page_all(bio)) = 131072 bio_first_bvec_all(bio)->bv_offset = 65536 If we use page_offset(bio_first_page_all(bio) without adding bv_offset, we will get an extent map for file offset 131072, not 196608. This means we read uncompressed data from disk, and later decompression will definitely fail. [FIX] Take bv_offset into consideration when trying to grab an extent map. And add an ASSERT() to ensure we're really getting a compressed extent. Thankfully this won't affect anything but subpage, thus we only need to ensure this patch get merged before we enabled basic subpage support. Reviewed-by: Anand Jain <anand.jain@oracle.com> Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-05 10:00:56 +08:00
ASSERT(em->compress_type != BTRFS_COMPRESS_NONE);
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
compressed_len = em->block_len;
cb = kmalloc(compressed_bio_size(fs_info, compressed_len), GFP_NOFS);
if (!cb)
goto out;
btrfs: introduce compressed_bio::pending_sectors to trace compressed bio For btrfs_submit_compressed_read() and btrfs_submit_compressed_write(), we have a pretty weird dance around compressed_bio::pending_bios: btrfs_submit_compressed_read/write() { cb = kmalloc() refcount_set(&cb->pending_bios, 0); bio = btrfs_alloc_bio(); /* NOTE here, we haven't yet submitted any bio */ refcount_set(&cb->pending_bios, 1); for (pg_index = 0; pg_index < cb->nr_pages; pg_index++) { if (submit) { /* Here we submit bio, but we always have one * extra pending_bios */ refcount_inc(&cb->pending_bios); ret = btrfs_map_bio(); } } /* Submit the last bio */ ret = btrfs_map_bio(); } There are two reasons why we do this: - compressed_bio::pending_bios is a refcount Thus if it's reduced to 0, it can not be increased again. - To ensure the compressed_bio is not freed by some submitted bios If the submitted bio is finished before the next bio submitted, we can free the compressed_bio completely. But the above code is sometimes confusing, and we can do it better by introducing a new member, compressed_bio::pending_sectors. Now we use compressed_bio::pending_sectors to indicate whether we have any pending sectors under IO or not yet submitted. If pending_sectors == 0, we're definitely the last bio of compressed_bio, and is OK to release the compressed bio. Now the workflow looks like this: btrfs_submit_compressed_read/write() { cb = kmalloc() atomic_set(&cb->pending_bios, 0); refcount_set(&cb->pending_sectors, compressed_len >> sectorsize_bits); bio = btrfs_alloc_bio(); for (pg_index = 0; pg_index < cb->nr_pages; pg_index++) { if (submit) { refcount_inc(&cb->pending_bios); ret = btrfs_map_bio(); } } /* Submit the last bio */ refcount_inc(&cb->pending_bios); ret = btrfs_map_bio(); } For now we still need pending_bios for later error handling, but will remove pending_bios eventually after properly handling the errors. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-09-27 15:21:48 +08:00
refcount_set(&cb->pending_sectors, compressed_len >> fs_info->sectorsize_bits);
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
cb->errors = 0;
cb->inode = inode;
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
cb->mirror_num = mirror_num;
sums = cb->sums;
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
cb->start = em->orig_start;
em_len = em->len;
em_start = em->start;
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
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
free_extent_map(em);
em = NULL;
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
cb->len = bio->bi_iter.bi_size;
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
cb->compressed_len = compressed_len;
cb->compress_type = extent_compress_type(bio_flags);
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
cb->orig_bio = bio;
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
nr_pages = DIV_ROUND_UP(compressed_len, PAGE_SIZE);
cb->compressed_pages = kcalloc(nr_pages, sizeof(struct page *),
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
GFP_NOFS);
if (!cb->compressed_pages)
goto fail1;
for (pg_index = 0; pg_index < nr_pages; pg_index++) {
cb->compressed_pages[pg_index] = alloc_page(GFP_NOFS);
if (!cb->compressed_pages[pg_index]) {
faili = pg_index - 1;
ret = BLK_STS_RESOURCE;
goto fail2;
}
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
}
faili = nr_pages - 1;
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
cb->nr_pages = nr_pages;
add_ra_bio_pages(inode, em_start + em_len, cb);
/* include any pages we added in add_ra-bio_pages */
cb->len = bio->bi_iter.bi_size;
while (cur_disk_byte < disk_bytenr + compressed_len) {
u64 offset = cur_disk_byte - disk_bytenr;
unsigned int index = offset >> PAGE_SHIFT;
unsigned int real_size;
unsigned int added;
struct page *page = cb->compressed_pages[index];
bool submit = false;
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
/* Allocate new bio if submitted or not yet allocated */
if (!comp_bio) {
comp_bio = alloc_compressed_bio(cb, cur_disk_byte,
REQ_OP_READ, end_compressed_bio_read,
&next_stripe_start);
if (IS_ERR(comp_bio)) {
ret = errno_to_blk_status(PTR_ERR(comp_bio));
comp_bio = NULL;
goto finish_cb;
}
}
/*
* We should never reach next_stripe_start start as we will
* submit comp_bio when reach the boundary immediately.
*/
ASSERT(cur_disk_byte != next_stripe_start);
/*
* We have various limit on the real read size:
* - stripe boundary
* - page boundary
* - compressed length boundary
*/
real_size = min_t(u64, U32_MAX, next_stripe_start - cur_disk_byte);
real_size = min_t(u64, real_size, PAGE_SIZE - offset_in_page(offset));
real_size = min_t(u64, real_size, compressed_len - offset);
ASSERT(IS_ALIGNED(real_size, fs_info->sectorsize));
added = bio_add_page(comp_bio, page, real_size, offset_in_page(offset));
/*
* Maximum compressed extent is smaller than bio size limit,
* thus bio_add_page() should always success.
*/
ASSERT(added == real_size);
cur_disk_byte += added;
/* Reached stripe boundary, need to submit */
if (cur_disk_byte == next_stripe_start)
submit = true;
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
/* Has finished the range, need to submit */
if (cur_disk_byte == disk_bytenr + compressed_len)
submit = true;
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
if (submit) {
unsigned int nr_sectors;
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 = btrfs_lookup_bio_sums(inode, comp_bio, sums);
if (ret)
goto finish_cb;
nr_sectors = DIV_ROUND_UP(comp_bio->bi_iter.bi_size,
fs_info->sectorsize);
sums += fs_info->csum_size * nr_sectors;
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
ret = submit_compressed_bio(fs_info, cb, comp_bio, mirror_num);
if (ret)
goto finish_cb;
comp_bio = NULL;
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
}
}
return 0;
fail2:
while (faili >= 0) {
__free_page(cb->compressed_pages[faili]);
faili--;
}
kfree(cb->compressed_pages);
fail1:
kfree(cb);
out:
free_extent_map(em);
return ret;
finish_cb:
if (comp_bio) {
comp_bio->bi_status = ret;
bio_endio(comp_bio);
}
/* All bytes of @cb is submitted, endio will free @cb */
if (cur_disk_byte == disk_bytenr + compressed_len)
return ret;
wait_var_event(cb, refcount_read(&cb->pending_sectors) ==
(disk_bytenr + compressed_len - cur_disk_byte) >>
fs_info->sectorsize_bits);
/*
* Even with previous bio ended, we should still have io not yet
* submitted, thus need to finish @cb manually.
*/
ASSERT(refcount_read(&cb->pending_sectors));
/* Now we are the only one referring @cb, can finish it safely. */
finish_compressed_bio_read(cb, NULL);
return ret;
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
}
/*
* Heuristic uses systematic sampling to collect data from the input data
* range, the logic can be tuned by the following constants:
*
* @SAMPLING_READ_SIZE - how many bytes will be copied from for each sample
* @SAMPLING_INTERVAL - range from which the sampled data can be collected
*/
#define SAMPLING_READ_SIZE (16)
#define SAMPLING_INTERVAL (256)
/*
* For statistical analysis of the input data we consider bytes that form a
* Galois Field of 256 objects. Each object has an attribute count, ie. how
* many times the object appeared in the sample.
*/
#define BUCKET_SIZE (256)
/*
* The size of the sample is based on a statistical sampling rule of thumb.
* The common way is to perform sampling tests as long as the number of
* elements in each cell is at least 5.
*
* Instead of 5, we choose 32 to obtain more accurate results.
* If the data contain the maximum number of symbols, which is 256, we obtain a
* sample size bound by 8192.
*
* For a sample of at most 8KB of data per data range: 16 consecutive bytes
* from up to 512 locations.
*/
#define MAX_SAMPLE_SIZE (BTRFS_MAX_UNCOMPRESSED * \
SAMPLING_READ_SIZE / SAMPLING_INTERVAL)
struct bucket_item {
u32 count;
};
struct heuristic_ws {
/* Partial copy of input data */
u8 *sample;
u32 sample_size;
/* Buckets store counters for each byte value */
struct bucket_item *bucket;
/* Sorting buffer */
struct bucket_item *bucket_b;
struct list_head list;
};
static struct workspace_manager heuristic_wsm;
static void free_heuristic_ws(struct list_head *ws)
{
struct heuristic_ws *workspace;
workspace = list_entry(ws, struct heuristic_ws, list);
kvfree(workspace->sample);
kfree(workspace->bucket);
kfree(workspace->bucket_b);
kfree(workspace);
}
static struct list_head *alloc_heuristic_ws(unsigned int level)
{
struct heuristic_ws *ws;
ws = kzalloc(sizeof(*ws), GFP_KERNEL);
if (!ws)
return ERR_PTR(-ENOMEM);
ws->sample = kvmalloc(MAX_SAMPLE_SIZE, GFP_KERNEL);
if (!ws->sample)
goto fail;
ws->bucket = kcalloc(BUCKET_SIZE, sizeof(*ws->bucket), GFP_KERNEL);
if (!ws->bucket)
goto fail;
ws->bucket_b = kcalloc(BUCKET_SIZE, sizeof(*ws->bucket_b), GFP_KERNEL);
if (!ws->bucket_b)
goto fail;
INIT_LIST_HEAD(&ws->list);
return &ws->list;
fail:
free_heuristic_ws(&ws->list);
return ERR_PTR(-ENOMEM);
}
const struct btrfs_compress_op btrfs_heuristic_compress = {
.workspace_manager = &heuristic_wsm,
};
static const struct btrfs_compress_op * const btrfs_compress_op[] = {
/* The heuristic is represented as compression type 0 */
&btrfs_heuristic_compress,
&btrfs_zlib_compress,
&btrfs_lzo_compress,
btrfs: Add zstd support Add zstd compression and decompression support to BtrFS. zstd at its fastest level compresses almost as well as zlib, while offering much faster compression and decompression, approaching lzo speeds. I benchmarked btrfs with zstd compression against no compression, lzo compression, and zlib compression. I benchmarked two scenarios. Copying a set of files to btrfs, and then reading the files. Copying a tarball to btrfs, extracting it to btrfs, and then reading the extracted files. After every operation, I call `sync` and include the sync time. Between every pair of operations I unmount and remount the filesystem to avoid caching. The benchmark files can be found in the upstream zstd source repository under `contrib/linux-kernel/{btrfs-benchmark.sh,btrfs-extract-benchmark.sh}` [1] [2]. I ran the benchmarks on a Ubuntu 14.04 VM with 2 cores and 4 GiB of RAM. The VM is running on a MacBook Pro with a 3.1 GHz Intel Core i7 processor, 16 GB of RAM, and a SSD. The first compression benchmark is copying 10 copies of the unzipped Silesia corpus [3] into a BtrFS filesystem mounted with `-o compress-force=Method`. The decompression benchmark times how long it takes to `tar` all 10 copies into `/dev/null`. The compression ratio is measured by comparing the output of `df` and `du`. See the benchmark file [1] for details. I benchmarked multiple zstd compression levels, although the patch uses zstd level 1. | Method | Ratio | Compression MB/s | Decompression speed | |---------|-------|------------------|---------------------| | None | 0.99 | 504 | 686 | | lzo | 1.66 | 398 | 442 | | zlib | 2.58 | 65 | 241 | | zstd 1 | 2.57 | 260 | 383 | | zstd 3 | 2.71 | 174 | 408 | | zstd 6 | 2.87 | 70 | 398 | | zstd 9 | 2.92 | 43 | 406 | | zstd 12 | 2.93 | 21 | 408 | | zstd 15 | 3.01 | 11 | 354 | The next benchmark first copies `linux-4.11.6.tar` [4] to btrfs. Then it measures the compression ratio, extracts the tar, and deletes the tar. Then it measures the compression ratio again, and `tar`s the extracted files into `/dev/null`. See the benchmark file [2] for details. | Method | Tar Ratio | Extract Ratio | Copy (s) | Extract (s)| Read (s) | |--------|-----------|---------------|----------|------------|----------| | None | 0.97 | 0.78 | 0.981 | 5.501 | 8.807 | | lzo | 2.06 | 1.38 | 1.631 | 8.458 | 8.585 | | zlib | 3.40 | 1.86 | 7.750 | 21.544 | 11.744 | | zstd 1 | 3.57 | 1.85 | 2.579 | 11.479 | 9.389 | [1] https://github.com/facebook/zstd/blob/dev/contrib/linux-kernel/btrfs-benchmark.sh [2] https://github.com/facebook/zstd/blob/dev/contrib/linux-kernel/btrfs-extract-benchmark.sh [3] http://sun.aei.polsl.pl/~sdeor/index.php?page=silesia [4] https://cdn.kernel.org/pub/linux/kernel/v4.x/linux-4.11.6.tar.xz zstd source repository: https://github.com/facebook/zstd Signed-off-by: Nick Terrell <terrelln@fb.com> Signed-off-by: Chris Mason <clm@fb.com>
2017-08-10 10:39:02 +08:00
&btrfs_zstd_compress,
};
static struct list_head *alloc_workspace(int type, unsigned int level)
{
switch (type) {
case BTRFS_COMPRESS_NONE: return alloc_heuristic_ws(level);
case BTRFS_COMPRESS_ZLIB: return zlib_alloc_workspace(level);
case BTRFS_COMPRESS_LZO: return lzo_alloc_workspace(level);
case BTRFS_COMPRESS_ZSTD: return zstd_alloc_workspace(level);
default:
/*
* This can't happen, the type is validated several times
* before we get here.
*/
BUG();
}
}
static void free_workspace(int type, struct list_head *ws)
{
switch (type) {
case BTRFS_COMPRESS_NONE: return free_heuristic_ws(ws);
case BTRFS_COMPRESS_ZLIB: return zlib_free_workspace(ws);
case BTRFS_COMPRESS_LZO: return lzo_free_workspace(ws);
case BTRFS_COMPRESS_ZSTD: return zstd_free_workspace(ws);
default:
/*
* This can't happen, the type is validated several times
* before we get here.
*/
BUG();
}
}
static void btrfs_init_workspace_manager(int type)
{
struct workspace_manager *wsm;
struct list_head *workspace;
wsm = btrfs_compress_op[type]->workspace_manager;
INIT_LIST_HEAD(&wsm->idle_ws);
spin_lock_init(&wsm->ws_lock);
atomic_set(&wsm->total_ws, 0);
init_waitqueue_head(&wsm->ws_wait);
/*
* Preallocate one workspace for each compression type so we can
* guarantee forward progress in the worst case
*/
workspace = alloc_workspace(type, 0);
if (IS_ERR(workspace)) {
pr_warn(
"BTRFS: cannot preallocate compression workspace, will try later\n");
} else {
atomic_set(&wsm->total_ws, 1);
wsm->free_ws = 1;
list_add(workspace, &wsm->idle_ws);
}
}
static void btrfs_cleanup_workspace_manager(int type)
{
struct workspace_manager *wsman;
struct list_head *ws;
wsman = btrfs_compress_op[type]->workspace_manager;
while (!list_empty(&wsman->idle_ws)) {
ws = wsman->idle_ws.next;
list_del(ws);
free_workspace(type, ws);
atomic_dec(&wsman->total_ws);
}
}
/*
* This finds an available workspace or allocates a new one.
* If it's not possible to allocate a new one, waits until there's one.
* Preallocation makes a forward progress guarantees and we do not return
* errors.
*/
struct list_head *btrfs_get_workspace(int type, unsigned int level)
{
struct workspace_manager *wsm;
struct list_head *workspace;
int cpus = num_online_cpus();
unsigned nofs_flag;
struct list_head *idle_ws;
spinlock_t *ws_lock;
atomic_t *total_ws;
wait_queue_head_t *ws_wait;
int *free_ws;
wsm = btrfs_compress_op[type]->workspace_manager;
idle_ws = &wsm->idle_ws;
ws_lock = &wsm->ws_lock;
total_ws = &wsm->total_ws;
ws_wait = &wsm->ws_wait;
free_ws = &wsm->free_ws;
again:
spin_lock(ws_lock);
if (!list_empty(idle_ws)) {
workspace = idle_ws->next;
list_del(workspace);
(*free_ws)--;
spin_unlock(ws_lock);
return workspace;
}
if (atomic_read(total_ws) > cpus) {
DEFINE_WAIT(wait);
spin_unlock(ws_lock);
prepare_to_wait(ws_wait, &wait, TASK_UNINTERRUPTIBLE);
if (atomic_read(total_ws) > cpus && !*free_ws)
schedule();
finish_wait(ws_wait, &wait);
goto again;
}
atomic_inc(total_ws);
spin_unlock(ws_lock);
/*
* Allocation helpers call vmalloc that can't use GFP_NOFS, so we have
* to turn it off here because we might get called from the restricted
* context of btrfs_compress_bio/btrfs_compress_pages
*/
nofs_flag = memalloc_nofs_save();
workspace = alloc_workspace(type, level);
memalloc_nofs_restore(nofs_flag);
if (IS_ERR(workspace)) {
atomic_dec(total_ws);
wake_up(ws_wait);
/*
* Do not return the error but go back to waiting. There's a
* workspace preallocated for each type and the compression
* time is bounded so we get to a workspace eventually. This
* makes our caller's life easier.
*
* To prevent silent and low-probability deadlocks (when the
* initial preallocation fails), check if there are any
* workspaces at all.
*/
if (atomic_read(total_ws) == 0) {
static DEFINE_RATELIMIT_STATE(_rs,
/* once per minute */ 60 * HZ,
/* no burst */ 1);
if (__ratelimit(&_rs)) {
pr_warn("BTRFS: no compression workspaces, low memory, retrying\n");
}
}
goto again;
}
return workspace;
}
static struct list_head *get_workspace(int type, int level)
{
switch (type) {
case BTRFS_COMPRESS_NONE: return btrfs_get_workspace(type, level);
case BTRFS_COMPRESS_ZLIB: return zlib_get_workspace(level);
case BTRFS_COMPRESS_LZO: return btrfs_get_workspace(type, level);
case BTRFS_COMPRESS_ZSTD: return zstd_get_workspace(level);
default:
/*
* This can't happen, the type is validated several times
* before we get here.
*/
BUG();
}
}
/*
* put a workspace struct back on the list or free it if we have enough
* idle ones sitting around
*/
void btrfs_put_workspace(int type, struct list_head *ws)
{
struct workspace_manager *wsm;
struct list_head *idle_ws;
spinlock_t *ws_lock;
atomic_t *total_ws;
wait_queue_head_t *ws_wait;
int *free_ws;
wsm = btrfs_compress_op[type]->workspace_manager;
idle_ws = &wsm->idle_ws;
ws_lock = &wsm->ws_lock;
total_ws = &wsm->total_ws;
ws_wait = &wsm->ws_wait;
free_ws = &wsm->free_ws;
spin_lock(ws_lock);
if (*free_ws <= num_online_cpus()) {
list_add(ws, idle_ws);
(*free_ws)++;
spin_unlock(ws_lock);
goto wake;
}
spin_unlock(ws_lock);
free_workspace(type, ws);
atomic_dec(total_ws);
wake:
cond_wake_up(ws_wait);
}
static void put_workspace(int type, struct list_head *ws)
{
switch (type) {
case BTRFS_COMPRESS_NONE: return btrfs_put_workspace(type, ws);
case BTRFS_COMPRESS_ZLIB: return btrfs_put_workspace(type, ws);
case BTRFS_COMPRESS_LZO: return btrfs_put_workspace(type, ws);
case BTRFS_COMPRESS_ZSTD: return zstd_put_workspace(ws);
default:
/*
* This can't happen, the type is validated several times
* before we get here.
*/
BUG();
}
}
/*
* Adjust @level according to the limits of the compression algorithm or
* fallback to default
*/
static unsigned int btrfs_compress_set_level(int type, unsigned level)
{
const struct btrfs_compress_op *ops = btrfs_compress_op[type];
if (level == 0)
level = ops->default_level;
else
level = min(level, ops->max_level);
return level;
}
/*
* Given an address space and start and length, compress the bytes into @pages
* that are allocated on demand.
*
* @type_level is encoded algorithm and level, where level 0 means whatever
* default the algorithm chooses and is opaque here;
* - compression algo are 0-3
* - the level are bits 4-7
*
* @out_pages is an in/out parameter, holds maximum number of pages to allocate
* and returns number of actually allocated pages
*
* @total_in is used to return the number of bytes actually read. It
* may be smaller than the input length if we had to exit early because we
* ran out of room in the pages array or because we cross the
* max_out threshold.
*
* @total_out is an in/out parameter, must be set to the input length and will
* be also used to return the total number of compressed bytes
*/
int btrfs_compress_pages(unsigned int type_level, struct address_space *mapping,
u64 start, struct page **pages,
unsigned long *out_pages,
unsigned long *total_in,
unsigned long *total_out)
{
int type = btrfs_compress_type(type_level);
int level = btrfs_compress_level(type_level);
struct list_head *workspace;
int ret;
level = btrfs_compress_set_level(type, level);
workspace = get_workspace(type, level);
ret = compression_compress_pages(type, workspace, mapping, start, pages,
out_pages, total_in, total_out);
put_workspace(type, workspace);
return ret;
}
static int btrfs_decompress_bio(struct compressed_bio *cb)
{
struct list_head *workspace;
int ret;
int type = cb->compress_type;
workspace = get_workspace(type, 0);
ret = compression_decompress_bio(type, workspace, cb);
put_workspace(type, workspace);
return ret;
}
/*
* a less complex decompression routine. Our compressed data fits in a
* single page, and we want to read a single page out of it.
* start_byte tells us the offset into the compressed data we're interested in
*/
int btrfs_decompress(int type, unsigned char *data_in, struct page *dest_page,
unsigned long start_byte, size_t srclen, size_t destlen)
{
struct list_head *workspace;
int ret;
workspace = get_workspace(type, 0);
ret = compression_decompress(type, workspace, data_in, dest_page,
start_byte, srclen, destlen);
put_workspace(type, workspace);
return ret;
}
void __init btrfs_init_compress(void)
{
btrfs_init_workspace_manager(BTRFS_COMPRESS_NONE);
btrfs_init_workspace_manager(BTRFS_COMPRESS_ZLIB);
btrfs_init_workspace_manager(BTRFS_COMPRESS_LZO);
zstd_init_workspace_manager();
}
void __cold btrfs_exit_compress(void)
{
btrfs_cleanup_workspace_manager(BTRFS_COMPRESS_NONE);
btrfs_cleanup_workspace_manager(BTRFS_COMPRESS_ZLIB);
btrfs_cleanup_workspace_manager(BTRFS_COMPRESS_LZO);
zstd_cleanup_workspace_manager();
}
/*
btrfs: rework btrfs_decompress_buf2page() There are several bugs inside the function btrfs_decompress_buf2page() - @start_byte doesn't take bvec.bv_offset into consideration Thus it can't handle case where the target range is not page aligned. - Too many helper variables There are tons of helper variables, @buf_offset, @current_buf_start, @start_byte, @prev_start_byte, @working_bytes, @bytes. This hurts anyone who wants to read the function. - No obvious main cursor for the iteartion A new problem caused by previous problem. - Comments for parameter list makes no sense Like @buf_start is the offset to @buf, or offset inside the full decompressed extent? (Spoiler alert, the later case) And @total_out acts more like @buf_start + @size_of_buf. The worst is @disk_start. The real meaning of it is the file offset of the full decompressed extent. This patch will rework the whole function by: - Add a proper comment with ASCII art to explain the parameter list - Rework parameter list The old @buf_start is renamed to @decompressed, to show how many bytes are already decompressed inside the full decompressed extent. The old @total_out is replaced by @buf_len, which is the decompressed data size. For old @disk_start and @bio, just pass @compressed_bio in. - Use single main cursor The main cursor will be @cur_file_offset, to show what's the current file offset. Other helper variables will be declared inside the main loop, and only minimal amount of helper variables: * offset_inside_decompressed_buf: The only real helper * copy_start_file_offset: File offset we start memcpy * bvec_file_offset: File offset of current bvec Even with all these extensive comments, the final function is still smaller than the original function, which is definitely a win. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-05 10:00:58 +08:00
* Copy decompressed data from working buffer to pages.
*
btrfs: rework btrfs_decompress_buf2page() There are several bugs inside the function btrfs_decompress_buf2page() - @start_byte doesn't take bvec.bv_offset into consideration Thus it can't handle case where the target range is not page aligned. - Too many helper variables There are tons of helper variables, @buf_offset, @current_buf_start, @start_byte, @prev_start_byte, @working_bytes, @bytes. This hurts anyone who wants to read the function. - No obvious main cursor for the iteartion A new problem caused by previous problem. - Comments for parameter list makes no sense Like @buf_start is the offset to @buf, or offset inside the full decompressed extent? (Spoiler alert, the later case) And @total_out acts more like @buf_start + @size_of_buf. The worst is @disk_start. The real meaning of it is the file offset of the full decompressed extent. This patch will rework the whole function by: - Add a proper comment with ASCII art to explain the parameter list - Rework parameter list The old @buf_start is renamed to @decompressed, to show how many bytes are already decompressed inside the full decompressed extent. The old @total_out is replaced by @buf_len, which is the decompressed data size. For old @disk_start and @bio, just pass @compressed_bio in. - Use single main cursor The main cursor will be @cur_file_offset, to show what's the current file offset. Other helper variables will be declared inside the main loop, and only minimal amount of helper variables: * offset_inside_decompressed_buf: The only real helper * copy_start_file_offset: File offset we start memcpy * bvec_file_offset: File offset of current bvec Even with all these extensive comments, the final function is still smaller than the original function, which is definitely a win. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-05 10:00:58 +08:00
* @buf: The decompressed data buffer
* @buf_len: The decompressed data length
* @decompressed: Number of bytes that are already decompressed inside the
* compressed extent
* @cb: The compressed extent descriptor
* @orig_bio: The original bio that the caller wants to read for
*
btrfs: rework btrfs_decompress_buf2page() There are several bugs inside the function btrfs_decompress_buf2page() - @start_byte doesn't take bvec.bv_offset into consideration Thus it can't handle case where the target range is not page aligned. - Too many helper variables There are tons of helper variables, @buf_offset, @current_buf_start, @start_byte, @prev_start_byte, @working_bytes, @bytes. This hurts anyone who wants to read the function. - No obvious main cursor for the iteartion A new problem caused by previous problem. - Comments for parameter list makes no sense Like @buf_start is the offset to @buf, or offset inside the full decompressed extent? (Spoiler alert, the later case) And @total_out acts more like @buf_start + @size_of_buf. The worst is @disk_start. The real meaning of it is the file offset of the full decompressed extent. This patch will rework the whole function by: - Add a proper comment with ASCII art to explain the parameter list - Rework parameter list The old @buf_start is renamed to @decompressed, to show how many bytes are already decompressed inside the full decompressed extent. The old @total_out is replaced by @buf_len, which is the decompressed data size. For old @disk_start and @bio, just pass @compressed_bio in. - Use single main cursor The main cursor will be @cur_file_offset, to show what's the current file offset. Other helper variables will be declared inside the main loop, and only minimal amount of helper variables: * offset_inside_decompressed_buf: The only real helper * copy_start_file_offset: File offset we start memcpy * bvec_file_offset: File offset of current bvec Even with all these extensive comments, the final function is still smaller than the original function, which is definitely a win. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-05 10:00:58 +08:00
* An easier to understand graph is like below:
*
* |<- orig_bio ->| |<- orig_bio->|
* |<------- full decompressed extent ----->|
* |<----------- @cb range ---->|
* | |<-- @buf_len -->|
* |<--- @decompressed --->|
*
* Note that, @cb can be a subpage of the full decompressed extent, but
* @cb->start always has the same as the orig_file_offset value of the full
* decompressed extent.
*
* When reading compressed extent, we have to read the full compressed extent,
* while @orig_bio may only want part of the range.
* Thus this function will ensure only data covered by @orig_bio will be copied
* to.
*
* Return 0 if we have copied all needed contents for @orig_bio.
* Return >0 if we need continue decompress.
*/
btrfs: rework btrfs_decompress_buf2page() There are several bugs inside the function btrfs_decompress_buf2page() - @start_byte doesn't take bvec.bv_offset into consideration Thus it can't handle case where the target range is not page aligned. - Too many helper variables There are tons of helper variables, @buf_offset, @current_buf_start, @start_byte, @prev_start_byte, @working_bytes, @bytes. This hurts anyone who wants to read the function. - No obvious main cursor for the iteartion A new problem caused by previous problem. - Comments for parameter list makes no sense Like @buf_start is the offset to @buf, or offset inside the full decompressed extent? (Spoiler alert, the later case) And @total_out acts more like @buf_start + @size_of_buf. The worst is @disk_start. The real meaning of it is the file offset of the full decompressed extent. This patch will rework the whole function by: - Add a proper comment with ASCII art to explain the parameter list - Rework parameter list The old @buf_start is renamed to @decompressed, to show how many bytes are already decompressed inside the full decompressed extent. The old @total_out is replaced by @buf_len, which is the decompressed data size. For old @disk_start and @bio, just pass @compressed_bio in. - Use single main cursor The main cursor will be @cur_file_offset, to show what's the current file offset. Other helper variables will be declared inside the main loop, and only minimal amount of helper variables: * offset_inside_decompressed_buf: The only real helper * copy_start_file_offset: File offset we start memcpy * bvec_file_offset: File offset of current bvec Even with all these extensive comments, the final function is still smaller than the original function, which is definitely a win. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-05 10:00:58 +08:00
int btrfs_decompress_buf2page(const char *buf, u32 buf_len,
struct compressed_bio *cb, u32 decompressed)
{
btrfs: rework btrfs_decompress_buf2page() There are several bugs inside the function btrfs_decompress_buf2page() - @start_byte doesn't take bvec.bv_offset into consideration Thus it can't handle case where the target range is not page aligned. - Too many helper variables There are tons of helper variables, @buf_offset, @current_buf_start, @start_byte, @prev_start_byte, @working_bytes, @bytes. This hurts anyone who wants to read the function. - No obvious main cursor for the iteartion A new problem caused by previous problem. - Comments for parameter list makes no sense Like @buf_start is the offset to @buf, or offset inside the full decompressed extent? (Spoiler alert, the later case) And @total_out acts more like @buf_start + @size_of_buf. The worst is @disk_start. The real meaning of it is the file offset of the full decompressed extent. This patch will rework the whole function by: - Add a proper comment with ASCII art to explain the parameter list - Rework parameter list The old @buf_start is renamed to @decompressed, to show how many bytes are already decompressed inside the full decompressed extent. The old @total_out is replaced by @buf_len, which is the decompressed data size. For old @disk_start and @bio, just pass @compressed_bio in. - Use single main cursor The main cursor will be @cur_file_offset, to show what's the current file offset. Other helper variables will be declared inside the main loop, and only minimal amount of helper variables: * offset_inside_decompressed_buf: The only real helper * copy_start_file_offset: File offset we start memcpy * bvec_file_offset: File offset of current bvec Even with all these extensive comments, the final function is still smaller than the original function, which is definitely a win. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-05 10:00:58 +08:00
struct bio *orig_bio = cb->orig_bio;
/* Offset inside the full decompressed extent */
u32 cur_offset;
cur_offset = decompressed;
/* The main loop to do the copy */
while (cur_offset < decompressed + buf_len) {
struct bio_vec bvec;
size_t copy_len;
u32 copy_start;
/* Offset inside the full decompressed extent */
u32 bvec_offset;
bvec = bio_iter_iovec(orig_bio, orig_bio->bi_iter);
/*
* cb->start may underflow, but subtracting that value can still
* give us correct offset inside the full decompressed extent.
*/
bvec_offset = page_offset(bvec.bv_page) + bvec.bv_offset - cb->start;
btrfs: rework btrfs_decompress_buf2page() There are several bugs inside the function btrfs_decompress_buf2page() - @start_byte doesn't take bvec.bv_offset into consideration Thus it can't handle case where the target range is not page aligned. - Too many helper variables There are tons of helper variables, @buf_offset, @current_buf_start, @start_byte, @prev_start_byte, @working_bytes, @bytes. This hurts anyone who wants to read the function. - No obvious main cursor for the iteartion A new problem caused by previous problem. - Comments for parameter list makes no sense Like @buf_start is the offset to @buf, or offset inside the full decompressed extent? (Spoiler alert, the later case) And @total_out acts more like @buf_start + @size_of_buf. The worst is @disk_start. The real meaning of it is the file offset of the full decompressed extent. This patch will rework the whole function by: - Add a proper comment with ASCII art to explain the parameter list - Rework parameter list The old @buf_start is renamed to @decompressed, to show how many bytes are already decompressed inside the full decompressed extent. The old @total_out is replaced by @buf_len, which is the decompressed data size. For old @disk_start and @bio, just pass @compressed_bio in. - Use single main cursor The main cursor will be @cur_file_offset, to show what's the current file offset. Other helper variables will be declared inside the main loop, and only minimal amount of helper variables: * offset_inside_decompressed_buf: The only real helper * copy_start_file_offset: File offset we start memcpy * bvec_file_offset: File offset of current bvec Even with all these extensive comments, the final function is still smaller than the original function, which is definitely a win. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-05 10:00:58 +08:00
/* Haven't reached the bvec range, exit */
if (decompressed + buf_len <= bvec_offset)
return 1;
btrfs: rework btrfs_decompress_buf2page() There are several bugs inside the function btrfs_decompress_buf2page() - @start_byte doesn't take bvec.bv_offset into consideration Thus it can't handle case where the target range is not page aligned. - Too many helper variables There are tons of helper variables, @buf_offset, @current_buf_start, @start_byte, @prev_start_byte, @working_bytes, @bytes. This hurts anyone who wants to read the function. - No obvious main cursor for the iteartion A new problem caused by previous problem. - Comments for parameter list makes no sense Like @buf_start is the offset to @buf, or offset inside the full decompressed extent? (Spoiler alert, the later case) And @total_out acts more like @buf_start + @size_of_buf. The worst is @disk_start. The real meaning of it is the file offset of the full decompressed extent. This patch will rework the whole function by: - Add a proper comment with ASCII art to explain the parameter list - Rework parameter list The old @buf_start is renamed to @decompressed, to show how many bytes are already decompressed inside the full decompressed extent. The old @total_out is replaced by @buf_len, which is the decompressed data size. For old @disk_start and @bio, just pass @compressed_bio in. - Use single main cursor The main cursor will be @cur_file_offset, to show what's the current file offset. Other helper variables will be declared inside the main loop, and only minimal amount of helper variables: * offset_inside_decompressed_buf: The only real helper * copy_start_file_offset: File offset we start memcpy * bvec_file_offset: File offset of current bvec Even with all these extensive comments, the final function is still smaller than the original function, which is definitely a win. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-05 10:00:58 +08:00
copy_start = max(cur_offset, bvec_offset);
copy_len = min(bvec_offset + bvec.bv_len,
decompressed + buf_len) - copy_start;
ASSERT(copy_len);
/*
btrfs: rework btrfs_decompress_buf2page() There are several bugs inside the function btrfs_decompress_buf2page() - @start_byte doesn't take bvec.bv_offset into consideration Thus it can't handle case where the target range is not page aligned. - Too many helper variables There are tons of helper variables, @buf_offset, @current_buf_start, @start_byte, @prev_start_byte, @working_bytes, @bytes. This hurts anyone who wants to read the function. - No obvious main cursor for the iteartion A new problem caused by previous problem. - Comments for parameter list makes no sense Like @buf_start is the offset to @buf, or offset inside the full decompressed extent? (Spoiler alert, the later case) And @total_out acts more like @buf_start + @size_of_buf. The worst is @disk_start. The real meaning of it is the file offset of the full decompressed extent. This patch will rework the whole function by: - Add a proper comment with ASCII art to explain the parameter list - Rework parameter list The old @buf_start is renamed to @decompressed, to show how many bytes are already decompressed inside the full decompressed extent. The old @total_out is replaced by @buf_len, which is the decompressed data size. For old @disk_start and @bio, just pass @compressed_bio in. - Use single main cursor The main cursor will be @cur_file_offset, to show what's the current file offset. Other helper variables will be declared inside the main loop, and only minimal amount of helper variables: * offset_inside_decompressed_buf: The only real helper * copy_start_file_offset: File offset we start memcpy * bvec_file_offset: File offset of current bvec Even with all these extensive comments, the final function is still smaller than the original function, which is definitely a win. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-05 10:00:58 +08:00
* Extra range check to ensure we didn't go beyond
* @buf + @buf_len.
*/
btrfs: rework btrfs_decompress_buf2page() There are several bugs inside the function btrfs_decompress_buf2page() - @start_byte doesn't take bvec.bv_offset into consideration Thus it can't handle case where the target range is not page aligned. - Too many helper variables There are tons of helper variables, @buf_offset, @current_buf_start, @start_byte, @prev_start_byte, @working_bytes, @bytes. This hurts anyone who wants to read the function. - No obvious main cursor for the iteartion A new problem caused by previous problem. - Comments for parameter list makes no sense Like @buf_start is the offset to @buf, or offset inside the full decompressed extent? (Spoiler alert, the later case) And @total_out acts more like @buf_start + @size_of_buf. The worst is @disk_start. The real meaning of it is the file offset of the full decompressed extent. This patch will rework the whole function by: - Add a proper comment with ASCII art to explain the parameter list - Rework parameter list The old @buf_start is renamed to @decompressed, to show how many bytes are already decompressed inside the full decompressed extent. The old @total_out is replaced by @buf_len, which is the decompressed data size. For old @disk_start and @bio, just pass @compressed_bio in. - Use single main cursor The main cursor will be @cur_file_offset, to show what's the current file offset. Other helper variables will be declared inside the main loop, and only minimal amount of helper variables: * offset_inside_decompressed_buf: The only real helper * copy_start_file_offset: File offset we start memcpy * bvec_file_offset: File offset of current bvec Even with all these extensive comments, the final function is still smaller than the original function, which is definitely a win. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-05 10:00:58 +08:00
ASSERT(copy_start - decompressed < buf_len);
memcpy_to_page(bvec.bv_page, bvec.bv_offset,
buf + copy_start - decompressed, copy_len);
flush_dcache_page(bvec.bv_page);
cur_offset += copy_len;
btrfs: rework btrfs_decompress_buf2page() There are several bugs inside the function btrfs_decompress_buf2page() - @start_byte doesn't take bvec.bv_offset into consideration Thus it can't handle case where the target range is not page aligned. - Too many helper variables There are tons of helper variables, @buf_offset, @current_buf_start, @start_byte, @prev_start_byte, @working_bytes, @bytes. This hurts anyone who wants to read the function. - No obvious main cursor for the iteartion A new problem caused by previous problem. - Comments for parameter list makes no sense Like @buf_start is the offset to @buf, or offset inside the full decompressed extent? (Spoiler alert, the later case) And @total_out acts more like @buf_start + @size_of_buf. The worst is @disk_start. The real meaning of it is the file offset of the full decompressed extent. This patch will rework the whole function by: - Add a proper comment with ASCII art to explain the parameter list - Rework parameter list The old @buf_start is renamed to @decompressed, to show how many bytes are already decompressed inside the full decompressed extent. The old @total_out is replaced by @buf_len, which is the decompressed data size. For old @disk_start and @bio, just pass @compressed_bio in. - Use single main cursor The main cursor will be @cur_file_offset, to show what's the current file offset. Other helper variables will be declared inside the main loop, and only minimal amount of helper variables: * offset_inside_decompressed_buf: The only real helper * copy_start_file_offset: File offset we start memcpy * bvec_file_offset: File offset of current bvec Even with all these extensive comments, the final function is still smaller than the original function, which is definitely a win. Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-05 10:00:58 +08:00
bio_advance(orig_bio, copy_len);
/* Finished the bio */
if (!orig_bio->bi_iter.bi_size)
return 0;
}
return 1;
}
/*
* Shannon Entropy calculation
*
* Pure byte distribution analysis fails to determine compressibility of data.
* Try calculating entropy to estimate the average minimum number of bits
* needed to encode the sampled data.
*
* For convenience, return the percentage of needed bits, instead of amount of
* bits directly.
*
* @ENTROPY_LVL_ACEPTABLE - below that threshold, sample has low byte entropy
* and can be compressible with high probability
*
* @ENTROPY_LVL_HIGH - data are not compressible with high probability
*
* Use of ilog2() decreases precision, we lower the LVL to 5 to compensate.
*/
#define ENTROPY_LVL_ACEPTABLE (65)
#define ENTROPY_LVL_HIGH (80)
/*
* For increasead precision in shannon_entropy calculation,
* let's do pow(n, M) to save more digits after comma:
*
* - maximum int bit length is 64
* - ilog2(MAX_SAMPLE_SIZE) -> 13
* - 13 * 4 = 52 < 64 -> M = 4
*
* So use pow(n, 4).
*/
static inline u32 ilog2_w(u64 n)
{
return ilog2(n * n * n * n);
}
static u32 shannon_entropy(struct heuristic_ws *ws)
{
const u32 entropy_max = 8 * ilog2_w(2);
u32 entropy_sum = 0;
u32 p, p_base, sz_base;
u32 i;
sz_base = ilog2_w(ws->sample_size);
for (i = 0; i < BUCKET_SIZE && ws->bucket[i].count > 0; i++) {
p = ws->bucket[i].count;
p_base = ilog2_w(p);
entropy_sum += p * (sz_base - p_base);
}
entropy_sum /= ws->sample_size;
return entropy_sum * 100 / entropy_max;
}
#define RADIX_BASE 4U
#define COUNTERS_SIZE (1U << RADIX_BASE)
static u8 get4bits(u64 num, int shift) {
u8 low4bits;
num >>= shift;
/* Reverse order */
low4bits = (COUNTERS_SIZE - 1) - (num % COUNTERS_SIZE);
return low4bits;
}
/*
* Use 4 bits as radix base
* Use 16 u32 counters for calculating new position in buf array
*
* @array - array that will be sorted
* @array_buf - buffer array to store sorting results
* must be equal in size to @array
* @num - array size
*/
static void radix_sort(struct bucket_item *array, struct bucket_item *array_buf,
int num)
{
u64 max_num;
u64 buf_num;
u32 counters[COUNTERS_SIZE];
u32 new_addr;
u32 addr;
int bitlen;
int shift;
int i;
/*
* Try avoid useless loop iterations for small numbers stored in big
* counters. Example: 48 33 4 ... in 64bit array
*/
max_num = array[0].count;
for (i = 1; i < num; i++) {
buf_num = array[i].count;
if (buf_num > max_num)
max_num = buf_num;
}
buf_num = ilog2(max_num);
bitlen = ALIGN(buf_num, RADIX_BASE * 2);
shift = 0;
while (shift < bitlen) {
memset(counters, 0, sizeof(counters));
for (i = 0; i < num; i++) {
buf_num = array[i].count;
addr = get4bits(buf_num, shift);
counters[addr]++;
}
for (i = 1; i < COUNTERS_SIZE; i++)
counters[i] += counters[i - 1];
for (i = num - 1; i >= 0; i--) {
buf_num = array[i].count;
addr = get4bits(buf_num, shift);
counters[addr]--;
new_addr = counters[addr];
array_buf[new_addr] = array[i];
}
shift += RADIX_BASE;
/*
* Normal radix expects to move data from a temporary array, to
* the main one. But that requires some CPU time. Avoid that
* by doing another sort iteration to original array instead of
* memcpy()
*/
memset(counters, 0, sizeof(counters));
for (i = 0; i < num; i ++) {
buf_num = array_buf[i].count;
addr = get4bits(buf_num, shift);
counters[addr]++;
}
for (i = 1; i < COUNTERS_SIZE; i++)
counters[i] += counters[i - 1];
for (i = num - 1; i >= 0; i--) {
buf_num = array_buf[i].count;
addr = get4bits(buf_num, shift);
counters[addr]--;
new_addr = counters[addr];
array[new_addr] = array_buf[i];
}
shift += RADIX_BASE;
}
}
/*
* Size of the core byte set - how many bytes cover 90% of the sample
*
* There are several types of structured binary data that use nearly all byte
* values. The distribution can be uniform and counts in all buckets will be
* nearly the same (eg. encrypted data). Unlikely to be compressible.
*
* Other possibility is normal (Gaussian) distribution, where the data could
* be potentially compressible, but we have to take a few more steps to decide
* how much.
*
* @BYTE_CORE_SET_LOW - main part of byte values repeated frequently,
* compression algo can easy fix that
* @BYTE_CORE_SET_HIGH - data have uniform distribution and with high
* probability is not compressible
*/
#define BYTE_CORE_SET_LOW (64)
#define BYTE_CORE_SET_HIGH (200)
static int byte_core_set_size(struct heuristic_ws *ws)
{
u32 i;
u32 coreset_sum = 0;
const u32 core_set_threshold = ws->sample_size * 90 / 100;
struct bucket_item *bucket = ws->bucket;
/* Sort in reverse order */
radix_sort(ws->bucket, ws->bucket_b, BUCKET_SIZE);
for (i = 0; i < BYTE_CORE_SET_LOW; i++)
coreset_sum += bucket[i].count;
if (coreset_sum > core_set_threshold)
return i;
for (; i < BYTE_CORE_SET_HIGH && bucket[i].count > 0; i++) {
coreset_sum += bucket[i].count;
if (coreset_sum > core_set_threshold)
break;
}
return i;
}
/*
* Count byte values in buckets.
* This heuristic can detect textual data (configs, xml, json, html, etc).
* Because in most text-like data byte set is restricted to limited number of
* possible characters, and that restriction in most cases makes data easy to
* compress.
*
* @BYTE_SET_THRESHOLD - consider all data within this byte set size:
* less - compressible
* more - need additional analysis
*/
#define BYTE_SET_THRESHOLD (64)
static u32 byte_set_size(const struct heuristic_ws *ws)
{
u32 i;
u32 byte_set_size = 0;
for (i = 0; i < BYTE_SET_THRESHOLD; i++) {
if (ws->bucket[i].count > 0)
byte_set_size++;
}
/*
* Continue collecting count of byte values in buckets. If the byte
* set size is bigger then the threshold, it's pointless to continue,
* the detection technique would fail for this type of data.
*/
for (; i < BUCKET_SIZE; i++) {
if (ws->bucket[i].count > 0) {
byte_set_size++;
if (byte_set_size > BYTE_SET_THRESHOLD)
return byte_set_size;
}
}
return byte_set_size;
}
static bool sample_repeated_patterns(struct heuristic_ws *ws)
{
const u32 half_of_sample = ws->sample_size / 2;
const u8 *data = ws->sample;
return memcmp(&data[0], &data[half_of_sample], half_of_sample) == 0;
}
static void heuristic_collect_sample(struct inode *inode, u64 start, u64 end,
struct heuristic_ws *ws)
{
struct page *page;
u64 index, index_end;
u32 i, curr_sample_pos;
u8 *in_data;
/*
* Compression handles the input data by chunks of 128KiB
* (defined by BTRFS_MAX_UNCOMPRESSED)
*
* We do the same for the heuristic and loop over the whole range.
*
* MAX_SAMPLE_SIZE - calculated under assumption that heuristic will
* process no more than BTRFS_MAX_UNCOMPRESSED at a time.
*/
if (end - start > BTRFS_MAX_UNCOMPRESSED)
end = start + BTRFS_MAX_UNCOMPRESSED;
index = start >> PAGE_SHIFT;
index_end = end >> PAGE_SHIFT;
/* Don't miss unaligned end */
if (!IS_ALIGNED(end, PAGE_SIZE))
index_end++;
curr_sample_pos = 0;
while (index < index_end) {
page = find_get_page(inode->i_mapping, index);
in_data = kmap_local_page(page);
/* Handle case where the start is not aligned to PAGE_SIZE */
i = start % PAGE_SIZE;
while (i < PAGE_SIZE - SAMPLING_READ_SIZE) {
/* Don't sample any garbage from the last page */
if (start > end - SAMPLING_READ_SIZE)
break;
memcpy(&ws->sample[curr_sample_pos], &in_data[i],
SAMPLING_READ_SIZE);
i += SAMPLING_INTERVAL;
start += SAMPLING_INTERVAL;
curr_sample_pos += SAMPLING_READ_SIZE;
}
kunmap_local(in_data);
put_page(page);
index++;
}
ws->sample_size = curr_sample_pos;
}
/*
* Compression heuristic.
*
* For now is's a naive and optimistic 'return true', we'll extend the logic to
* quickly (compared to direct compression) detect data characteristics
* (compressible/uncompressible) to avoid wasting CPU time on uncompressible
* data.
*
* The following types of analysis can be performed:
* - detect mostly zero data
* - detect data with low "byte set" size (text, etc)
* - detect data with low/high "core byte" set
*
* Return non-zero if the compression should be done, 0 otherwise.
*/
int btrfs_compress_heuristic(struct inode *inode, u64 start, u64 end)
{
struct list_head *ws_list = get_workspace(0, 0);
struct heuristic_ws *ws;
u32 i;
u8 byte;
int ret = 0;
ws = list_entry(ws_list, struct heuristic_ws, list);
heuristic_collect_sample(inode, start, end, ws);
if (sample_repeated_patterns(ws)) {
ret = 1;
goto out;
}
memset(ws->bucket, 0, sizeof(*ws->bucket)*BUCKET_SIZE);
for (i = 0; i < ws->sample_size; i++) {
byte = ws->sample[i];
ws->bucket[byte].count++;
}
i = byte_set_size(ws);
if (i < BYTE_SET_THRESHOLD) {
ret = 2;
goto out;
}
i = byte_core_set_size(ws);
if (i <= BYTE_CORE_SET_LOW) {
ret = 3;
goto out;
}
if (i >= BYTE_CORE_SET_HIGH) {
ret = 0;
goto out;
}
i = shannon_entropy(ws);
if (i <= ENTROPY_LVL_ACEPTABLE) {
ret = 4;
goto out;
}
/*
* For the levels below ENTROPY_LVL_HIGH, additional analysis would be
* needed to give green light to compression.
*
* For now just assume that compression at that level is not worth the
* resources because:
*
* 1. it is possible to defrag the data later
*
* 2. the data would turn out to be hardly compressible, eg. 150 byte
* values, every bucket has counter at level ~54. The heuristic would
* be confused. This can happen when data have some internal repeated
* patterns like "abbacbbc...". This can be detected by analyzing
* pairs of bytes, which is too costly.
*/
if (i < ENTROPY_LVL_HIGH) {
ret = 5;
goto out;
} else {
ret = 0;
goto out;
}
out:
put_workspace(0, ws_list);
return ret;
}
/*
* Convert the compression suffix (eg. after "zlib" starting with ":") to
* level, unrecognized string will set the default level
*/
unsigned int btrfs_compress_str2level(unsigned int type, const char *str)
{
unsigned int level = 0;
int ret;
if (!type)
return 0;
if (str[0] == ':') {
ret = kstrtouint(str + 1, 10, &level);
if (ret)
level = 0;
}
level = btrfs_compress_set_level(type, level);
return level;
}