// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (C) 2007 Oracle. All rights reserved.
*/
#include <linux/kernel.h>
#include <linux/bio.h>
#include <linux/buffer_head.h>
#include <linux/file.h>
#include <linux/fs.h>
#include <linux/pagemap.h>
#include <linux/highmem.h>
#include <linux/time.h>
#include <linux/init.h>
#include <linux/string.h>
#include <linux/backing-dev.h>
#include <linux/writeback.h>
#include <linux/compat.h>
#include <linux/xattr.h>
#include <linux/posix_acl.h>
#include <linux/falloc.h>
#include <linux/slab.h>
#include <linux/ratelimit.h>
#include <linux/btrfs.h>
#include <linux/blkdev.h>
#include <linux/posix_acl_xattr.h>
#include <linux/uio.h>
#include <linux/magic.h>
#include <linux/iversion.h>
#include <linux/swap.h>
#include <linux/sched/mm.h>
#include <asm/unaligned.h>
#include "misc.h"
#include "ctree.h"
#include "disk-io.h"
#include "transaction.h"
#include "btrfs_inode.h"
#include "print-tree.h"
#include "ordered-data.h"
#include "xattr.h"
#include "tree-log.h"
#include "volumes.h"
#include "compression.h"
#include "locking.h"
#include "free-space-cache.h"
#include "inode-map.h"
#include "props.h"
#include "qgroup.h"
#include "delalloc-space.h"
#include "block-group.h"
struct btrfs_iget_args {
struct btrfs_key *location;
struct btrfs_root *root;
};
struct btrfs_dio_data {
u64 reserve;
u64 unsubmitted_oe_range_start;
u64 unsubmitted_oe_range_end;
int overwrite;
};
static const struct inode_operations btrfs_dir_inode_operations;
static const struct inode_operations btrfs_symlink_inode_operations;
static const struct inode_operations btrfs_special_inode_operations;
static const struct inode_operations btrfs_file_inode_operations;
static const struct address_space_operations btrfs_aops;
static const struct file_operations btrfs_dir_file_operations;
static const struct extent_io_ops btrfs_extent_io_ops;
static struct kmem_cache *btrfs_inode_cachep;
struct kmem_cache *btrfs_trans_handle_cachep;
struct kmem_cache *btrfs_path_cachep;
struct kmem_cache *btrfs_free_space_cachep;
struct kmem_cache *btrfs_free_space_bitmap_cachep;
static int btrfs_setsize(struct inode *inode, struct iattr *attr);
static int btrfs_truncate(struct inode *inode, bool skip_writeback);
static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent);
static noinline int cow_file_range(struct inode *inode,
struct page *locked_page,
u64 start, u64 end, int *page_started,
unsigned long *nr_written, int unlock);
static struct extent_map *create_io_em(struct inode *inode, u64 start, u64 len,
u64 orig_start, u64 block_start,
u64 block_len, u64 orig_block_len,
u64 ram_bytes, int compress_type,
int type);
static void __endio_write_update_ordered(struct inode *inode,
const u64 offset, const u64 bytes,
const bool uptodate);
/*
* Cleanup all submitted ordered extents in specified range to handle errors
* from the btrfs_run_delalloc_range() callback.
*
* NOTE: caller must ensure that when an error happens, it can not call
* extent_clear_unlock_delalloc() to clear both the bits EXTENT_DO_ACCOUNTING
* and EXTENT_DELALLOC simultaneously, because that causes the reserved metadata
* to be released, which we want to happen only when finishing the ordered
* extent (btrfs_finish_ordered_io()).
*/
static inline void btrfs_cleanup_ordered_extents(struct inode *inode,
struct page *locked_page,
u64 offset, u64 bytes)
{
unsigned long index = offset >> PAGE_SHIFT;
unsigned long end_index = (offset + bytes - 1) >> PAGE_SHIFT;
u64 page_start = page_offset(locked_page);
u64 page_end = page_start + PAGE_SIZE - 1;
struct page *page;
while (index <= end_index) {
page = find_get_page(inode->i_mapping, index);
index++;
if (!page)
continue;
ClearPagePrivate2(page);
put_page(page);
}
/*
* In case this page belongs to the delalloc range being instantiated
* then skip it, since the first page of a range is going to be
* properly cleaned up by the caller of run_delalloc_range
*/
if (page_start >= offset && page_end <= (offset + bytes - 1)) {
offset += PAGE_SIZE;
bytes -= PAGE_SIZE;
}
return __endio_write_update_ordered(inode, offset, bytes, false);
}
static int btrfs_dirty_inode(struct inode *inode);
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
void btrfs_test_inode_set_ops(struct inode *inode)
{
BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
}
#endif
static int btrfs_init_inode_security(struct btrfs_trans_handle *trans,
struct inode *inode, struct inode *dir,
const struct qstr *qstr)
{
int err;
err = btrfs_init_acl(trans, inode, dir);
if (!err)
err = btrfs_xattr_security_init(trans, inode, dir, qstr);
return err;
}
/*
* this does all the hard work for inserting an inline extent into
* the btree. The caller should have done a btrfs_drop_extents so that
* no overlapping inline items exist in the btree
*/
static int insert_inline_extent(struct btrfs_trans_handle *trans,
struct btrfs_path *path, int extent_inserted,
struct btrfs_root *root, struct inode *inode,
u64 start, size_t size, size_t compressed_size,
int compress_type,
struct page **compressed_pages)
{
struct extent_buffer *leaf;
struct page *page = NULL;
char *kaddr;
unsigned long ptr;
struct btrfs_file_extent_item *ei;
int ret;
size_t cur_size = size;
unsigned long offset;
ASSERT((compressed_size > 0 && compressed_pages) ||
(compressed_size == 0 && !compressed_pages));
if (compressed_size && compressed_pages)
cur_size = compressed_size;
inode_add_bytes(inode, size);
if (!extent_inserted) {
struct btrfs_key key;
size_t datasize;
key.objectid = btrfs_ino(BTRFS_I(inode));
key.offset = start;
key.type = BTRFS_EXTENT_DATA_KEY;
datasize = btrfs_file_extent_calc_inline_size(cur_size);
path->leave_spinning = 1;
ret = btrfs_insert_empty_item(trans, root, path, &key,
datasize);
if (ret)
goto fail;
}
leaf = path->nodes[0];
ei = btrfs_item_ptr(leaf, path->slots[0],
struct btrfs_file_extent_item);
btrfs_set_file_extent_generation(leaf, ei, trans->transid);
btrfs_set_file_extent_type(leaf, ei, BTRFS_FILE_EXTENT_INLINE);
btrfs_set_file_extent_encryption(leaf, ei, 0);
btrfs_set_file_extent_other_encoding(leaf, ei, 0);
btrfs_set_file_extent_ram_bytes(leaf, ei, size);
ptr = btrfs_file_extent_inline_start(ei);
if (compress_type != BTRFS_COMPRESS_NONE) {
struct page *cpage;
int i = 0;
while (compressed_size > 0) {
cpage = compressed_pages[i];
cur_size = min_t(unsigned long, compressed_size,
PAGE_SIZE);
kaddr = kmap_atomic(cpage);
write_extent_buffer(leaf, kaddr, ptr, cur_size);
kunmap_atomic(kaddr);
i++;
ptr += cur_size;
compressed_size -= cur_size;
}
btrfs_set_file_extent_compression(leaf, ei,
compress_type);
} else {
page = find_get_page(inode->i_mapping,
start >> PAGE_SHIFT);
btrfs_set_file_extent_compression(leaf, ei, 0);
kaddr = kmap_atomic(page);
offset = offset_in_page(start);
write_extent_buffer(leaf, kaddr + offset, ptr, size);
kunmap_atomic(kaddr);
put_page(page);
}
btrfs_mark_buffer_dirty(leaf);
btrfs_release_path(path);
/*
* we're an inline extent, so nobody can
* extend the file past i_size without locking
* a page we already have locked.
*
* We must do any isize and inode updates
* before we unlock the pages. Otherwise we
* could end up racing with unlink.
*/
BTRFS_I(inode)->disk_i_size = inode->i_size;
ret = btrfs_update_inode(trans, root, inode);
fail:
return ret;
}
/*
* conditionally insert an inline extent into the file. This
* does the checks required to make sure the data is small enough
* to fit as an inline extent.
*/
static noinline int cow_file_range_inline(struct inode *inode, u64 start,
u64 end, size_t compressed_size,
int compress_type,
struct page **compressed_pages)
{
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_fs_info *fs_info = root->fs_info;
struct btrfs_trans_handle *trans;
u64 isize = i_size_read(inode);
u64 actual_end = min(end + 1, isize);
u64 inline_len = actual_end - start;
u64 aligned_end = ALIGN(end, fs_info->sectorsize);
u64 data_len = inline_len;
int ret;
struct btrfs_path *path;
int extent_inserted = 0;
u32 extent_item_size;
if (compressed_size)
data_len = compressed_size;
if (start > 0 ||
actual_end > fs_info->sectorsize ||
data_len > BTRFS_MAX_INLINE_DATA_SIZE(fs_info) ||
(!compressed_size &&
(actual_end & (fs_info->sectorsize - 1)) == 0) ||
end + 1 < isize ||
data_len > fs_info->max_inline) {
return 1;
}
path = btrfs_alloc_path();
if (!path)
return -ENOMEM;
trans = btrfs_join_transaction(root);
if (IS_ERR(trans)) {
btrfs_free_path(path);
return PTR_ERR(trans);
}
trans->block_rsv = &BTRFS_I(inode)->block_rsv;
if (compressed_size && compressed_pages)
extent_item_size = btrfs_file_extent_calc_inline_size(
compressed_size);
else
extent_item_size = btrfs_file_extent_calc_inline_size(
inline_len);
ret = __btrfs_drop_extents(trans, root, inode, path,
start, aligned_end, NULL,
1, 1, extent_item_size, &extent_inserted);
if (ret) {
btrfs_abort_transaction(trans, ret);
goto out;
}
if (isize > actual_end)
inline_len = min_t(u64, isize, actual_end);
ret = insert_inline_extent(trans, path, extent_inserted,
root, inode, start,
inline_len, compressed_size,
compress_type, compressed_pages);
if (ret && ret != -ENOSPC) {
btrfs_abort_transaction(trans, ret);
goto out;
} else if (ret == -ENOSPC) {
ret = 1;
goto out;
}
set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &BTRFS_I(inode)->runtime_flags);
btrfs_drop_extent_cache(BTRFS_I(inode), start, aligned_end - 1, 0);
out:
/*
* Don't forget to free the reserved space, as for inlined extent
* it won't count as data extent, free them directly here.
* And at reserve time, it's always aligned to page size, so
* just free one page here.
*/
btrfs_qgroup_free_data(inode, NULL, 0, PAGE_SIZE);
btrfs_free_path(path);
btrfs_end_transaction(trans);
return ret;
}
struct async_extent {
u64 start;
u64 ram_size;
u64 compressed_size;
struct page **pages;
unsigned long nr_pages;
int compress_type;
struct list_head list;
};
struct async_chunk {
struct inode *inode;
struct page *locked_page;
u64 start;
u64 end;
unsigned int write_flags;
struct list_head extents;
struct cgroup_subsys_state *blkcg_css;
struct btrfs_work work;
atomic_t *pending;
};
struct async_cow {
/* Number of chunks in flight; must be first in the structure */
atomic_t num_chunks;
struct async_chunk chunks[];
};
static noinline int add_async_extent(struct async_chunk *cow,
u64 start, u64 ram_size,
u64 compressed_size,
struct page **pages,
unsigned long nr_pages,
int compress_type)
{
struct async_extent *async_extent;
async_extent = kmalloc(sizeof(*async_extent), GFP_NOFS);
BUG_ON(!async_extent); /* -ENOMEM */
async_extent->start = start;
async_extent->ram_size = ram_size;
async_extent->compressed_size = compressed_size;
async_extent->pages = pages;
async_extent->nr_pages = nr_pages;
async_extent->compress_type = compress_type;
list_add_tail(&async_extent->list, &cow->extents);
return 0;
}
/*
* Check if the inode has flags compatible with compression
*/
static inline bool inode_can_compress(struct inode *inode)
{
if (BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW ||
BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)
return false;
return true;
}
/*
* Check if the inode needs to be submitted to compression, based on mount
* options, defragmentation, properties or heuristics.
*/
static inline int inode_need_compress(struct inode *inode, u64 start, u64 end)
{
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
if (!inode_can_compress(inode)) {
WARN(IS_ENABLED(CONFIG_BTRFS_DEBUG),
KERN_ERR "BTRFS: unexpected compression for ino %llu\n",
btrfs_ino(BTRFS_I(inode)));
return 0;
}
/* force compress */
if (btrfs_test_opt(fs_info, FORCE_COMPRESS))
return 1;
/* defrag ioctl */
if (BTRFS_I(inode)->defrag_compress)
return 1;
/* bad compression ratios */
if (BTRFS_I(inode)->flags & BTRFS_INODE_NOCOMPRESS)
return 0;
if (btrfs_test_opt(fs_info, COMPRESS) ||
BTRFS_I(inode)->flags & BTRFS_INODE_COMPRESS ||
BTRFS_I(inode)->prop_compress)
return btrfs_compress_heuristic(inode, start, end);
return 0;
}
static inline void inode_should_defrag(struct btrfs_inode *inode,
u64 start, u64 end, u64 num_bytes, u64 small_write)
{
/* If this is a small write inside eof, kick off a defrag */
if (num_bytes < small_write &&
(start > 0 || end + 1 < inode->disk_i_size))
btrfs_add_inode_defrag(NULL, inode);
}
/*
* we create compressed extents in two phases. The first
* phase compresses a range of pages that have already been
* locked (both pages and state bits are locked).
*
* This is done inside an ordered work queue, and the compression
* is spread across many cpus. The actual IO submission is step
* two, and the ordered work queue takes care of making sure that
* happens in the same order things were put onto the queue by
* writepages and friends.
*
* If this code finds it can't get good compression, it puts an
* entry onto the work queue to write the uncompressed bytes. This
* makes sure that both compressed inodes and uncompressed inodes
* are written in the same order that the flusher thread sent them
* down.
*/
static noinline int compress_file_range(struct async_chunk *async_chunk)
{
struct inode *inode = async_chunk->inode;
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
u64 blocksize = fs_info->sectorsize;
u64 start = async_chunk->start;
u64 end = async_chunk->end;
u64 actual_end;
u64 i_size;
int ret = 0;
struct page **pages = NULL;
unsigned long nr_pages;
unsigned long total_compressed = 0;
unsigned long total_in = 0;
int i;
int will_compress;
int compress_type = fs_info->compress_type;
int compressed_extents = 0;
int redirty = 0;
inode_should_defrag(BTRFS_I(inode), start, end, end - start + 1,
SZ_16K);
/*
* We need to save i_size before now because it could change in between
* us evaluating the size and assigning it. This is because we lock and
* unlock the page in truncate and fallocate, and then modify the i_size
* later on.
*
* The barriers are to emulate READ_ONCE, remove that once i_size_read
* does that for us.
*/
barrier();
i_size = i_size_read(inode);
barrier();
actual_end = min_t(u64, i_size, end + 1);
again:
will_compress = 0;
nr_pages = (end >> PAGE_SHIFT) - (start >> PAGE_SHIFT) + 1;
BUILD_BUG_ON((BTRFS_MAX_COMPRESSED % PAGE_SIZE) != 0);
nr_pages = min_t(unsigned long, nr_pages,
BTRFS_MAX_COMPRESSED / PAGE_SIZE);
/*
* we don't want to send crud past the end of i_size through
* compression, that's just a waste of CPU time. So, if the
* end of the file is before the start of our current
* requested range of bytes, we bail out to the uncompressed
* cleanup code that can deal with all of this.
*
* It isn't really the fastest way to fix things, but this is a
* very uncommon corner.
*/
if (actual_end <= start)
goto cleanup_and_bail_uncompressed;
total_compressed = actual_end - start;
/*
* skip compression for a small file range(<=blocksize) that
* isn't an inline extent, since it doesn't save disk space at all.
*/
if (total_compressed <= blocksize &&
(start > 0 || end + 1 < BTRFS_I(inode)->disk_i_size))
goto cleanup_and_bail_uncompressed;
total_compressed = min_t(unsigned long, total_compressed,
BTRFS_MAX_UNCOMPRESSED);
total_in = 0;
ret = 0;
/*
* we do compression for mount -o compress and when the
* inode has not been flagged as nocompress. This flag can
* change at any time if we discover bad compression ratios.
*/
if (inode_need_compress(inode, start, end)) {
WARN_ON(pages);
pages = kcalloc(nr_pages, sizeof(struct page *), GFP_NOFS);
if (!pages) {
/* just bail out to the uncompressed code */
nr_pages = 0;
goto cont;
}
if (BTRFS_I(inode)->defrag_compress)
compress_type = BTRFS_I(inode)->defrag_compress;
else if (BTRFS_I(inode)->prop_compress)
compress_type = BTRFS_I(inode)->prop_compress;
/*
* we need to call clear_page_dirty_for_io on each
* page in the range. Otherwise applications with the file
* mmap'd can wander in and change the page contents while
* we are compressing them.
*
* If the compression fails for any reason, we set the pages
* dirty again later on.
*
* Note that the remaining part is redirtied, the start pointer
* has moved, the end is the original one.
*/
if (!redirty) {
extent_range_clear_dirty_for_io(inode, start, end);
redirty = 1;
}
/* Compression level is applied here and only here */
ret = btrfs_compress_pages(
compress_type | (fs_info->compress_level << 4),
inode->i_mapping, start,
pages,
&nr_pages,
&total_in,
&total_compressed);
if (!ret) {
unsigned long offset = offset_in_page(total_compressed);
struct page *page = pages[nr_pages - 1];
char *kaddr;
/* zero the tail end of the last page, we might be
* sending it down to disk
*/
if (offset) {
kaddr = kmap_atomic(page);
memset(kaddr + offset, 0,
PAGE_SIZE - offset);
kunmap_atomic(kaddr);
}
will_compress = 1;
}
}
cont:
if (start == 0) {
/* lets try to make an inline extent */
if (ret || total_in < actual_end) {
/* we didn't compress the entire range, try
* to make an uncompressed inline extent.
*/
ret = cow_file_range_inline(inode, start, end, 0,
BTRFS_COMPRESS_NONE, NULL);
} else {
/* try making a compressed inline extent */
ret = cow_file_range_inline(inode, start, end,
total_compressed,
compress_type, pages);
}
if (ret <= 0) {
unsigned long clear_flags = EXTENT_DELALLOC |
EXTENT_DELALLOC_NEW | EXTENT_DEFRAG |
EXTENT_DO_ACCOUNTING;
unsigned long page_error_op;
page_error_op = ret < 0 ? PAGE_SET_ERROR : 0;
/*
* inline extent creation worked or returned error,
* we don't need to create any more async work items.
* Unlock and free up our temp pages.
*
* We use DO_ACCOUNTING here because we need the
* delalloc_release_metadata to be done _after_ we drop
* our outstanding extent for clearing delalloc for this
* range.
*/
extent_clear_unlock_delalloc(inode, start, end, NULL,
clear_flags,
PAGE_UNLOCK |
PAGE_CLEAR_DIRTY |
PAGE_SET_WRITEBACK |
page_error_op |
PAGE_END_WRITEBACK);
for (i = 0; i < nr_pages; i++) {
WARN_ON(pages[i]->mapping);
put_page(pages[i]);
}
kfree(pages);
return 0;
}
}
if (will_compress) {
/*
* we aren't doing an inline extent round the compressed size
* up to a block size boundary so the allocator does sane
* things
*/
total_compressed = ALIGN(total_compressed, blocksize);
/*
* one last check to make sure the compression is really a
* win, compare the page count read with the blocks on disk,
* compression must free at least one sector size
*/
total_in = ALIGN(total_in, PAGE_SIZE);
if (total_compressed + blocksize <= total_in) {
compressed_extents++;
/*
* The async work queues will take care of doing actual
* allocation on disk for these compressed pages, and
* will submit them to the elevator.
*/
add_async_extent(async_chunk, start, total_in,
total_compressed, pages, nr_pages,
compress_type);
if (start + total_in < end) {
start += total_in;
pages = NULL;
cond_resched();
goto again;
}
return compressed_extents;
}
}
if (pages) {
/*
* the compression code ran but failed to make things smaller,
* free any pages it allocated and our page pointer array
*/
for (i = 0; i < nr_pages; i++) {
WARN_ON(pages[i]->mapping);
put_page(pages[i]);
}
kfree(pages);
pages = NULL;
total_compressed = 0;
nr_pages = 0;
/* flag the file so we don't compress in the future */
if (!btrfs_test_opt(fs_info, FORCE_COMPRESS) &&
!(BTRFS_I(inode)->prop_compress)) {
BTRFS_I(inode)->flags |= BTRFS_INODE_NOCOMPRESS;
}
}
cleanup_and_bail_uncompressed:
/*
* No compression, but we still need to write the pages in the file
* we've been given so far. redirty the locked page if it corresponds
* to our extent and set things up for the async work queue to run
* cow_file_range to do the normal delalloc dance.
*/
if (async_chunk->locked_page &&
(page_offset(async_chunk->locked_page) >= start &&
page_offset(async_chunk->locked_page)) <= end) {
__set_page_dirty_nobuffers(async_chunk->locked_page);
/* unlocked later on in the async handlers */
}
if (redirty)
extent_range_redirty_for_io(inode, start, end);
add_async_extent(async_chunk, start, end - start + 1, 0, NULL, 0,
BTRFS_COMPRESS_NONE);
compressed_extents++;
return compressed_extents;
}
static void free_async_extent_pages(struct async_extent *async_extent)
{
int i;
if (!async_extent->pages)
return;
for (i = 0; i < async_extent->nr_pages; i++) {
WARN_ON(async_extent->pages[i]->mapping);
put_page(async_extent->pages[i]);
}
kfree(async_extent->pages);
async_extent->nr_pages = 0;
async_extent->pages = NULL;
}
/*
* phase two of compressed writeback. This is the ordered portion
* of the code, which only gets called in the order the work was
* queued. We walk all the async extents created by compress_file_range
* and send them down to the disk.
*/
static noinline void submit_compressed_extents(struct async_chunk *async_chunk)
{
struct inode *inode = async_chunk->inode;
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
struct async_extent *async_extent;
u64 alloc_hint = 0;
struct btrfs_key ins;
struct extent_map *em;
struct btrfs_root *root = BTRFS_I(inode)->root;
struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
int ret = 0;
again:
while (!list_empty(&async_chunk->extents)) {
async_extent = list_entry(async_chunk->extents.next,
struct async_extent, list);
list_del(&async_extent->list);
retry:
lock_extent(io_tree, async_extent->start,
async_extent->start + async_extent->ram_size - 1);
/* did the compression code fall back to uncompressed IO? */
if (!async_extent->pages) {
int page_started = 0;
unsigned long nr_written = 0;
/* allocate blocks */
ret = cow_file_range(inode, async_chunk->locked_page,
async_extent->start,
async_extent->start +
async_extent->ram_size - 1,
&page_started, &nr_written, 0);
/* JDM XXX */
/*
* if page_started, cow_file_range inserted an
* inline extent and took care of all the unlocking
* and IO for us. Otherwise, we need to submit
* all those pages down to the drive.
*/
if (!page_started && !ret)
extent_write_locked_range(inode,
async_extent->start,
async_extent->start +
async_extent->ram_size - 1,
WB_SYNC_ALL);
else if (ret && async_chunk->locked_page)
unlock_page(async_chunk->locked_page);
kfree(async_extent);
cond_resched();
continue;
}
ret = btrfs_reserve_extent(root, async_extent->ram_size,
async_extent->compressed_size,
async_extent->compressed_size,
0, alloc_hint, &ins, 1, 1);
if (ret) {
free_async_extent_pages(async_extent);
if (ret == -ENOSPC) {
unlock_extent(io_tree, async_extent->start,
async_extent->start +
async_extent->ram_size - 1);
/*
* we need to redirty the pages if we decide to
* fallback to uncompressed IO, otherwise we
* will not submit these pages down to lower
* layers.
*/
extent_range_redirty_for_io(inode,
async_extent->start,
async_extent->start +
async_extent->ram_size - 1);
goto retry;
}
goto out_free;
}
/*
* here we're doing allocation and writeback of the
* compressed pages
*/
em = create_io_em(inode, async_extent->start,
async_extent->ram_size, /* len */
async_extent->start, /* orig_start */
ins.objectid, /* block_start */
ins.offset, /* block_len */
ins.offset, /* orig_block_len */
async_extent->ram_size, /* ram_bytes */
async_extent->compress_type,
BTRFS_ORDERED_COMPRESSED);
if (IS_ERR(em))
/* ret value is not necessary due to void function */
goto out_free_reserve;
free_extent_map(em);
ret = btrfs_add_ordered_extent_compress(inode,
async_extent->start,
ins.objectid,
async_extent->ram_size,
ins.offset,
BTRFS_ORDERED_COMPRESSED,
async_extent->compress_type);
if (ret) {
btrfs_drop_extent_cache(BTRFS_I(inode),
async_extent->start,
async_extent->start +
async_extent->ram_size - 1, 0);
goto out_free_reserve;
}
btrfs_dec_block_group_reservations(fs_info, ins.objectid);
/*
* clear dirty, set writeback and unlock the pages.
*/
extent_clear_unlock_delalloc(inode, async_extent->start,
async_extent->start +
async_extent->ram_size - 1,
NULL, EXTENT_LOCKED | EXTENT_DELALLOC,
PAGE_UNLOCK | PAGE_CLEAR_DIRTY |
PAGE_SET_WRITEBACK);
if (btrfs_submit_compressed_write(inode,
async_extent->start,
async_extent->ram_size,
ins.objectid,
ins.offset, async_extent->pages,
async_extent->nr_pages,
async_chunk->write_flags,
async_chunk->blkcg_css)) {
struct page *p = async_extent->pages[0];
const u64 start = async_extent->start;
const u64 end = start + async_extent->ram_size - 1;
p->mapping = inode->i_mapping;
btrfs_writepage_endio_finish_ordered(p, start, end, 0);
p->mapping = NULL;
extent_clear_unlock_delalloc(inode, start, end,
NULL, 0,
PAGE_END_WRITEBACK |
PAGE_SET_ERROR);
free_async_extent_pages(async_extent);
}
alloc_hint = ins.objectid + ins.offset;
kfree(async_extent);
cond_resched();
}
return;
out_free_reserve:
btrfs_dec_block_group_reservations(fs_info, ins.objectid);
btrfs_free_reserved_extent(fs_info, ins.objectid, ins.offset, 1);
out_free:
extent_clear_unlock_delalloc(inode, async_extent->start,
async_extent->start +
async_extent->ram_size - 1,
NULL, EXTENT_LOCKED | EXTENT_DELALLOC |
EXTENT_DELALLOC_NEW |
EXTENT_DEFRAG | EXTENT_DO_ACCOUNTING,
PAGE_UNLOCK | PAGE_CLEAR_DIRTY |
PAGE_SET_WRITEBACK | PAGE_END_WRITEBACK |
PAGE_SET_ERROR);
free_async_extent_pages(async_extent);
kfree(async_extent);
goto again;
}
static u64 get_extent_allocation_hint(struct inode *inode, u64 start,
u64 num_bytes)
{
struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
struct extent_map *em;
u64 alloc_hint = 0;
read_lock(&em_tree->lock);
em = search_extent_mapping(em_tree, start, num_bytes);
if (em) {
/*
* if block start isn't an actual block number then find the
* first block in this inode and use that as a hint. If that
* block is also bogus then just don't worry about it.
*/
if (em->block_start >= EXTENT_MAP_LAST_BYTE) {
free_extent_map(em);
em = search_extent_mapping(em_tree, 0, 0);
if (em && em->block_start < EXTENT_MAP_LAST_BYTE)
alloc_hint = em->block_start;
if (em)
free_extent_map(em);
} else {
alloc_hint = em->block_start;
free_extent_map(em);
}
}
read_unlock(&em_tree->lock);
return alloc_hint;
}
/*
* when extent_io.c finds a delayed allocation range in the file,
* the call backs end up in this code. The basic idea is to
* allocate extents on disk for the range, and create ordered data structs
* in ram to track those extents.
*
* locked_page is the page that writepage had locked already. We use
* it to make sure we don't do extra locks or unlocks.
*
* *page_started is set to one if we unlock locked_page and do everything
* required to start IO on it. It may be clean and already done with
* IO when we return.
*/
static noinline int cow_file_range(struct inode *inode,
struct page *locked_page,
u64 start, u64 end, int *page_started,
unsigned long *nr_written, int unlock)
{
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
struct btrfs_root *root = BTRFS_I(inode)->root;
u64 alloc_hint = 0;
u64 num_bytes;
unsigned long ram_size;
u64 cur_alloc_size = 0;
u64 blocksize = fs_info->sectorsize;
struct btrfs_key ins;
struct extent_map *em;
unsigned clear_bits;
unsigned long page_ops;
bool extent_reserved = false;
int ret = 0;
if (btrfs_is_free_space_inode(BTRFS_I(inode))) {
WARN_ON_ONCE(1);
ret = -EINVAL;
goto out_unlock;
}
num_bytes = ALIGN(end - start + 1, blocksize);
num_bytes = max(blocksize, num_bytes);
ASSERT(num_bytes <= btrfs_super_total_bytes(fs_info->super_copy));
inode_should_defrag(BTRFS_I(inode), start, end, num_bytes, SZ_64K);
if (start == 0) {
/* lets try to make an inline extent */
ret = cow_file_range_inline(inode, start, end, 0,
BTRFS_COMPRESS_NONE, NULL);
if (ret == 0) {
/*
* We use DO_ACCOUNTING here because we need the
* delalloc_release_metadata to be run _after_ we drop
* our outstanding extent for clearing delalloc for this
* range.
*/
extent_clear_unlock_delalloc(inode, start, end, NULL,
EXTENT_LOCKED | EXTENT_DELALLOC |
EXTENT_DELALLOC_NEW | EXTENT_DEFRAG |
EXTENT_DO_ACCOUNTING, PAGE_UNLOCK |
PAGE_CLEAR_DIRTY | PAGE_SET_WRITEBACK |
PAGE_END_WRITEBACK);
*nr_written = *nr_written +
(end - start + PAGE_SIZE) / PAGE_SIZE;
*page_started = 1;
goto out;
} else if (ret < 0) {
goto out_unlock;
}
}
alloc_hint = get_extent_allocation_hint(inode, start, num_bytes);
btrfs_drop_extent_cache(BTRFS_I(inode), start,
start + num_bytes - 1, 0);
while (num_bytes > 0) {
cur_alloc_size = num_bytes;
ret = btrfs_reserve_extent(root, cur_alloc_size, cur_alloc_size,
fs_info->sectorsize, 0, alloc_hint,
&ins, 1, 1);
if (ret < 0)
goto out_unlock;
cur_alloc_size = ins.offset;
extent_reserved = true;
ram_size = ins.offset;
em = create_io_em(inode, start, ins.offset, /* len */
start, /* orig_start */
ins.objectid, /* block_start */
ins.offset, /* block_len */
ins.offset, /* orig_block_len */
ram_size, /* ram_bytes */
BTRFS_COMPRESS_NONE, /* compress_type */
BTRFS_ORDERED_REGULAR /* type */);
if (IS_ERR(em)) {
ret = PTR_ERR(em);
goto out_reserve;
}
free_extent_map(em);
ret = btrfs_add_ordered_extent(inode, start, ins.objectid,
ram_size, cur_alloc_size, 0);
if (ret)
goto out_drop_extent_cache;
if (root->root_key.objectid ==
BTRFS_DATA_RELOC_TREE_OBJECTID) {
ret = btrfs_reloc_clone_csums(inode, start,
cur_alloc_size);
/*
* Only drop cache here, and process as normal.
*
* We must not allow extent_clear_unlock_delalloc()
* at out_unlock label to free meta of this ordered
* extent, as its meta should be freed by
* btrfs_finish_ordered_io().
*
* So we must continue until @start is increased to
* skip current ordered extent.
*/
if (ret)
btrfs_drop_extent_cache(BTRFS_I(inode), start,
start + ram_size - 1, 0);
}
btrfs_dec_block_group_reservations(fs_info, ins.objectid);
/* we're not doing compressed IO, don't unlock the first
* page (which the caller expects to stay locked), don't
* clear any dirty bits and don't set any writeback bits
*
* Do set the Private2 bit so we know this page was properly
* setup for writepage
*/
page_ops = unlock ? PAGE_UNLOCK : 0;
page_ops |= PAGE_SET_PRIVATE2;
extent_clear_unlock_delalloc(inode, start,
start + ram_size - 1,
locked_page,
EXTENT_LOCKED | EXTENT_DELALLOC,
page_ops);
if (num_bytes < cur_alloc_size)
num_bytes = 0;
else
num_bytes -= cur_alloc_size;
alloc_hint = ins.objectid + ins.offset;
start += cur_alloc_size;
extent_reserved = false;
/*
* btrfs_reloc_clone_csums() error, since start is increased
* extent_clear_unlock_delalloc() at out_unlock label won't
* free metadata of current ordered extent, we're OK to exit.
*/
if (ret)
goto out_unlock;
}
out:
return ret;
out_drop_extent_cache:
btrfs_drop_extent_cache(BTRFS_I(inode), start, start + ram_size - 1, 0);
out_reserve:
btrfs_dec_block_group_reservations(fs_info, ins.objectid);
btrfs_free_reserved_extent(fs_info, ins.objectid, ins.offset, 1);
out_unlock:
clear_bits = EXTENT_LOCKED | EXTENT_DELALLOC | EXTENT_DELALLOC_NEW |
EXTENT_DEFRAG | EXTENT_CLEAR_META_RESV;
page_ops = PAGE_UNLOCK | PAGE_CLEAR_DIRTY | PAGE_SET_WRITEBACK |
PAGE_END_WRITEBACK;
/*
* If we reserved an extent for our delalloc range (or a subrange) and
* failed to create the respective ordered extent, then it means that
* when we reserved the extent we decremented the extent's size from
* the data space_info's bytes_may_use counter and incremented the
* space_info's bytes_reserved counter by the same amount. We must make
* sure extent_clear_unlock_delalloc() does not try to decrement again
* the data space_info's bytes_may_use counter, therefore we do not pass
* it the flag EXTENT_CLEAR_DATA_RESV.
*/
if (extent_reserved) {
extent_clear_unlock_delalloc(inode, start,
start + cur_alloc_size,
locked_page,
clear_bits,
page_ops);
start += cur_alloc_size;
if (start >= end)
goto out;
}
extent_clear_unlock_delalloc(inode, start, end, locked_page,
clear_bits | EXTENT_CLEAR_DATA_RESV,
page_ops);
goto out;
}
/*
* work queue call back to started compression on a file and pages
*/
static noinline void async_cow_start(struct btrfs_work *work)
{
struct async_chunk *async_chunk;
int compressed_extents;
async_chunk = container_of(work, struct async_chunk, work);
compressed_extents = compress_file_range(async_chunk);
if (compressed_extents == 0) {
btrfs_add_delayed_iput(async_chunk->inode);
async_chunk->inode = NULL;
}
}
/*
* work queue call back to submit previously compressed pages
*/
static noinline void async_cow_submit(struct btrfs_work *work)
{
struct async_chunk *async_chunk = container_of(work, struct async_chunk,
work);
struct btrfs_fs_info *fs_info = btrfs_work_owner(work);
unsigned long nr_pages;
nr_pages = (async_chunk->end - async_chunk->start + PAGE_SIZE) >>
PAGE_SHIFT;
/* atomic_sub_return implies a barrier */
if (atomic_sub_return(nr_pages, &fs_info->async_delalloc_pages) <
5 * SZ_1M)
cond_wake_up_nomb(&fs_info->async_submit_wait);
/*
* ->inode could be NULL if async_chunk_start has failed to compress,
* in which case we don't have anything to submit, yet we need to
* always adjust ->async_delalloc_pages as its paired with the init
* happening in cow_file_range_async
*/
if (async_chunk->inode)
submit_compressed_extents(async_chunk);
}
static noinline void async_cow_free(struct btrfs_work *work)
{
struct async_chunk *async_chunk;
async_chunk = container_of(work, struct async_chunk, work);
if (async_chunk->inode)
btrfs_add_delayed_iput(async_chunk->inode);
if (async_chunk->blkcg_css)
css_put(async_chunk->blkcg_css);
/*
* Since the pointer to 'pending' is at the beginning of the array of
* async_chunk's, freeing it ensures the whole array has been freed.
*/
if (atomic_dec_and_test(async_chunk->pending))
kvfree(async_chunk->pending);
}
static int cow_file_range_async(struct inode *inode,
struct writeback_control *wbc,
struct page *locked_page,
u64 start, u64 end, int *page_started,
unsigned long *nr_written)
{
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
struct cgroup_subsys_state *blkcg_css = wbc_blkcg_css(wbc);
struct async_cow *ctx;
struct async_chunk *async_chunk;
unsigned long nr_pages;
u64 cur_end;
u64 num_chunks = DIV_ROUND_UP(end - start, SZ_512K);
int i;
bool should_compress;
unsigned nofs_flag;
const unsigned int write_flags = wbc_to_write_flags(wbc);
unlock_extent(&BTRFS_I(inode)->io_tree, start, end);
if (BTRFS_I(inode)->flags & BTRFS_INODE_NOCOMPRESS &&
!btrfs_test_opt(fs_info, FORCE_COMPRESS)) {
num_chunks = 1;
should_compress = false;
} else {
should_compress = true;
}
nofs_flag