From 102a0743326a03cd1a1202ceda21e175b7d3575c Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Tue, 20 Feb 2024 01:20:52 +0000
Subject: [PATCH] add new system file
---
kernel/fs/btrfs/inode.c | 5243 ++++++++++++++++++++++++++++-------------------------------
1 files changed, 2,479 insertions(+), 2,764 deletions(-)
diff --git a/kernel/fs/btrfs/inode.c b/kernel/fs/btrfs/inode.c
index f314b2c..c900a39 100644
--- a/kernel/fs/btrfs/inode.c
+++ b/kernel/fs/btrfs/inode.c
@@ -3,9 +3,9 @@
* Copyright (C) 2007 Oracle. All rights reserved.
*/
+#include <crypto/hash.h>
#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>
@@ -27,7 +27,12 @@
#include <linux/uio.h>
#include <linux/magic.h>
#include <linux/iversion.h>
+#include <linux/swap.h>
+#include <linux/migrate.h>
+#include <linux/sched/mm.h>
+#include <linux/iomap.h>
#include <asm/unaligned.h>
+#include "misc.h"
#include "ctree.h"
#include "disk-io.h"
#include "transaction.h"
@@ -41,32 +46,31 @@
#include "locking.h"
#include "free-space-cache.h"
#include "inode-map.h"
-#include "backref.h"
#include "props.h"
#include "qgroup.h"
-#include "dedupe.h"
+#include "delalloc-space.h"
+#include "block-group.h"
+#include "space-info.h"
struct btrfs_iget_args {
- struct btrfs_key *location;
+ u64 ino;
struct btrfs_root *root;
};
struct btrfs_dio_data {
u64 reserve;
- u64 unsubmitted_oe_range_start;
- u64 unsubmitted_oe_range_end;
- int overwrite;
+ loff_t length;
+ ssize_t submitted;
+ struct extent_changeset *data_reserved;
+ bool sync;
};
static const struct inode_operations btrfs_dir_inode_operations;
static const struct inode_operations btrfs_symlink_inode_operations;
-static const struct inode_operations btrfs_dir_ro_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 address_space_operations btrfs_symlink_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;
@@ -74,38 +78,26 @@
struct kmem_cache *btrfs_free_space_cachep;
struct kmem_cache *btrfs_free_space_bitmap_cachep;
-#define S_SHIFT 12
-static const unsigned char btrfs_type_by_mode[S_IFMT >> S_SHIFT] = {
- [S_IFREG >> S_SHIFT] = BTRFS_FT_REG_FILE,
- [S_IFDIR >> S_SHIFT] = BTRFS_FT_DIR,
- [S_IFCHR >> S_SHIFT] = BTRFS_FT_CHRDEV,
- [S_IFBLK >> S_SHIFT] = BTRFS_FT_BLKDEV,
- [S_IFIFO >> S_SHIFT] = BTRFS_FT_FIFO,
- [S_IFSOCK >> S_SHIFT] = BTRFS_FT_SOCK,
- [S_IFLNK >> S_SHIFT] = BTRFS_FT_SYMLINK,
-};
-
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,
+static noinline int cow_file_range(struct btrfs_inode *inode,
struct page *locked_page,
- u64 start, u64 end, u64 delalloc_end,
- int *page_started, unsigned long *nr_written,
- int unlock, struct btrfs_dedupe_hash *hash);
-static struct extent_map *create_io_em(struct inode *inode, u64 start, u64 len,
- u64 orig_start, u64 block_start,
+ u64 start, u64 end, int *page_started,
+ unsigned long *nr_written, int unlock);
+static struct extent_map *create_io_em(struct btrfs_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,
+static void __endio_write_update_ordered(struct btrfs_inode *inode,
const u64 offset, const u64 bytes,
const bool uptodate);
/*
* Cleanup all submitted ordered extents in specified range to handle errors
- * from the fill_dellaloc() callback.
+ * 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
@@ -113,7 +105,7 @@
* 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,
+static inline void btrfs_cleanup_ordered_extents(struct btrfs_inode *inode,
struct page *locked_page,
u64 offset, u64 bytes)
{
@@ -125,7 +117,7 @@
struct page *page;
while (index <= end_index) {
- page = find_get_page(inode->i_mapping, index);
+ page = find_get_page(inode->vfs_inode.i_mapping, index);
index++;
if (!page)
continue;
@@ -147,13 +139,6 @@
}
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,
@@ -187,6 +172,9 @@
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;
@@ -241,13 +229,22 @@
start >> PAGE_SHIFT);
btrfs_set_file_extent_compression(leaf, ei, 0);
kaddr = kmap_atomic(page);
- offset = start & (PAGE_SIZE - 1);
+ 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 align size to sectorsize for inline extents just for simplicity
+ * sake.
+ */
+ size = ALIGN(size, root->fs_info->sectorsize);
+ ret = btrfs_inode_set_file_extent_range(BTRFS_I(inode), start, size);
+ if (ret)
+ goto fail;
/*
* we're an inline extent, so nobody can
@@ -271,15 +268,15 @@
* 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,
+static noinline int cow_file_range_inline(struct btrfs_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_root *root = inode->root;
struct btrfs_fs_info *fs_info = root->fs_info;
struct btrfs_trans_handle *trans;
- u64 isize = i_size_read(inode);
+ u64 isize = i_size_read(&inode->vfs_inode);
u64 actual_end = min(end + 1, isize);
u64 inline_len = actual_end - start;
u64 aligned_end = ALIGN(end, fs_info->sectorsize);
@@ -311,7 +308,7 @@
btrfs_free_path(path);
return PTR_ERR(trans);
}
- trans->block_rsv = &BTRFS_I(inode)->block_rsv;
+ trans->block_rsv = &inode->block_rsv;
if (compressed_size && compressed_pages)
extent_item_size = btrfs_file_extent_calc_inline_size(
@@ -320,9 +317,9 @@
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);
+ 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;
@@ -331,7 +328,7 @@
if (isize > actual_end)
inline_len = min_t(u64, isize, actual_end);
ret = insert_inline_extent(trans, path, extent_inserted,
- root, inode, start,
+ root, &inode->vfs_inode, start,
inline_len, compressed_size,
compress_type, compressed_pages);
if (ret && ret != -ENOSPC) {
@@ -342,8 +339,8 @@
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);
+ set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &inode->runtime_flags);
+ btrfs_drop_extent_cache(inode, start, aligned_end - 1, 0);
out:
/*
* Don't forget to free the reserved space, as for inlined extent
@@ -367,18 +364,25 @@
struct list_head list;
};
-struct async_cow {
+struct async_chunk {
struct inode *inode;
- struct btrfs_root *root;
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;
};
-static noinline int add_async_extent(struct async_cow *cow,
+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,
@@ -402,10 +406,10 @@
/*
* Check if the inode has flags compatible with compression
*/
-static inline bool inode_can_compress(struct inode *inode)
+static inline bool inode_can_compress(struct btrfs_inode *inode)
{
- if (BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW ||
- BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)
+ if (inode->flags & BTRFS_INODE_NODATACOW ||
+ inode->flags & BTRFS_INODE_NODATASUM)
return false;
return true;
}
@@ -414,29 +418,30 @@
* 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)
+static inline int inode_need_compress(struct btrfs_inode *inode, u64 start,
+ u64 end)
{
- struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+ struct btrfs_fs_info *fs_info = inode->root->fs_info;
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)));
+ btrfs_ino(inode));
return 0;
}
/* force compress */
if (btrfs_test_opt(fs_info, FORCE_COMPRESS))
return 1;
/* defrag ioctl */
- if (BTRFS_I(inode)->defrag_compress)
+ if (inode->defrag_compress)
return 1;
/* bad compression ratios */
- if (BTRFS_I(inode)->flags & BTRFS_INODE_NOCOMPRESS)
+ if (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);
+ inode->flags & BTRFS_INODE_COMPRESS ||
+ inode->prop_compress)
+ return btrfs_compress_heuristic(&inode->vfs_inode, start, end);
return 0;
}
@@ -466,16 +471,15 @@
* are written in the same order that the flusher thread sent them
* down.
*/
-static noinline void compress_file_range(struct inode *inode,
- struct page *locked_page,
- u64 start, u64 end,
- struct async_cow *async_cow,
- int *num_added)
+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 isize = i_size_read(inode);
+ u64 i_size;
int ret = 0;
struct page **pages = NULL;
unsigned long nr_pages;
@@ -484,12 +488,25 @@
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);
- actual_end = min_t(u64, isize, end + 1);
+ /*
+ * 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;
@@ -530,7 +547,7 @@
* 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)) {
+ if (inode_need_compress(BTRFS_I(inode), start, end)) {
WARN_ON(pages);
pages = kcalloc(nr_pages, sizeof(struct page *), GFP_NOFS);
if (!pages) {
@@ -571,8 +588,7 @@
&total_compressed);
if (!ret) {
- unsigned long offset = total_compressed &
- (PAGE_SIZE - 1);
+ unsigned long offset = offset_in_page(total_compressed);
struct page *page = pages[nr_pages - 1];
char *kaddr;
@@ -595,11 +611,12 @@
/* 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);
+ ret = cow_file_range_inline(BTRFS_I(inode), start, end,
+ 0, BTRFS_COMPRESS_NONE,
+ NULL);
} else {
/* try making a compressed inline extent */
- ret = cow_file_range_inline(inode, start, end,
+ ret = cow_file_range_inline(BTRFS_I(inode), start, end,
total_compressed,
compress_type, pages);
}
@@ -621,8 +638,9 @@
* our outstanding extent for clearing delalloc for this
* range.
*/
- extent_clear_unlock_delalloc(inode, start, end, end,
- NULL, clear_flags,
+ extent_clear_unlock_delalloc(BTRFS_I(inode), start, end,
+ NULL,
+ clear_flags,
PAGE_UNLOCK |
PAGE_CLEAR_DIRTY |
PAGE_SET_WRITEBACK |
@@ -641,8 +659,7 @@
}
kfree(pages);
}
-
- return;
+ return 0;
}
}
@@ -661,14 +678,14 @@
*/
total_in = ALIGN(total_in, PAGE_SIZE);
if (total_compressed + blocksize <= total_in) {
- *num_added += 1;
+ 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_cow, start, total_in,
+ add_async_extent(async_chunk, start, total_in,
total_compressed, pages, nr_pages,
compress_type);
@@ -678,7 +695,7 @@
cond_resched();
goto again;
}
- return;
+ return compressed_extents;
}
}
if (pages) {
@@ -708,18 +725,20 @@
* to our extent and set things up for the async work queue to run
* cow_file_range to do the normal delalloc dance.
*/
- if (page_offset(locked_page) >= start &&
- page_offset(locked_page) <= end)
- __set_page_dirty_nobuffers(locked_page);
+ 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_cow, start, end - start + 1, 0, NULL, 0,
+ add_async_extent(async_chunk, start, end - start + 1, 0, NULL, 0,
BTRFS_COMPRESS_NONE);
- *num_added += 1;
+ compressed_extents++;
- return;
+ return compressed_extents;
}
static void free_async_extent_pages(struct async_extent *async_extent)
@@ -744,45 +763,38 @@
* 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 inode *inode,
- struct async_cow *async_cow)
+static noinline void submit_compressed_extents(struct async_chunk *async_chunk)
{
- struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+ struct btrfs_inode *inode = BTRFS_I(async_chunk->inode);
+ struct btrfs_fs_info *fs_info = inode->root->fs_info;
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;
+ struct btrfs_root *root = inode->root;
+ struct extent_io_tree *io_tree = &inode->io_tree;
int ret = 0;
again:
- while (!list_empty(&async_cow->extents)) {
- async_extent = list_entry(async_cow->extents.next,
+ while (!list_empty(&async_chunk->extents)) {
+ async_extent = list_entry(async_chunk->extents.next,
struct async_extent, list);
list_del(&async_extent->list);
- io_tree = &BTRFS_I(inode)->io_tree;
-
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;
- lock_extent(io_tree, async_extent->start,
- async_extent->start +
- async_extent->ram_size - 1);
-
/* allocate blocks */
- ret = cow_file_range(inode, async_cow->locked_page,
+ ret = cow_file_range(inode, async_chunk->locked_page,
async_extent->start,
async_extent->start +
async_extent->ram_size - 1,
- async_extent->start +
- async_extent->ram_size - 1,
- &page_started, &nr_written, 0,
- NULL);
+ &page_started, &nr_written, 0);
/* JDM XXX */
@@ -793,20 +805,17 @@
* all those pages down to the drive.
*/
if (!page_started && !ret)
- extent_write_locked_range(inode,
+ extent_write_locked_range(&inode->vfs_inode,
async_extent->start,
async_extent->start +
async_extent->ram_size - 1,
WB_SYNC_ALL);
- else if (ret)
- unlock_page(async_cow->locked_page);
+ else if (ret && async_chunk->locked_page)
+ unlock_page(async_chunk->locked_page);
kfree(async_extent);
cond_resched();
continue;
}
-
- lock_extent(io_tree, async_extent->start,
- async_extent->start + async_extent->ram_size - 1);
ret = btrfs_reserve_extent(root, async_extent->ram_size,
async_extent->compressed_size,
@@ -826,7 +835,7 @@
* will not submit these pages down to lower
* layers.
*/
- extent_range_redirty_for_io(inode,
+ extent_range_redirty_for_io(&inode->vfs_inode,
async_extent->start,
async_extent->start +
async_extent->ram_size - 1);
@@ -861,8 +870,7 @@
BTRFS_ORDERED_COMPRESSED,
async_extent->compress_type);
if (ret) {
- btrfs_drop_extent_cache(BTRFS_I(inode),
- async_extent->start,
+ btrfs_drop_extent_cache(inode, async_extent->start,
async_extent->start +
async_extent->ram_size - 1, 0);
goto out_free_reserve;
@@ -875,29 +883,25 @@
extent_clear_unlock_delalloc(inode, async_extent->start,
async_extent->start +
async_extent->ram_size - 1,
- 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,
+ 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_cow->write_flags)) {
- struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree;
+ 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;
- tree->ops->writepage_end_io_hook(p, start, end,
- NULL, 0);
+ p->mapping = inode->vfs_inode.i_mapping;
+ btrfs_writepage_endio_finish_ordered(p, start, end, 0);
+
p->mapping = NULL;
- extent_clear_unlock_delalloc(inode, start, end, end,
- NULL, 0,
+ extent_clear_unlock_delalloc(inode, start, end, NULL, 0,
PAGE_END_WRITEBACK |
PAGE_SET_ERROR);
free_async_extent_pages(async_extent);
@@ -914,8 +918,6 @@
extent_clear_unlock_delalloc(inode, async_extent->start,
async_extent->start +
async_extent->ram_size - 1,
- async_extent->start +
- async_extent->ram_size - 1,
NULL, EXTENT_LOCKED | EXTENT_DELALLOC |
EXTENT_DELALLOC_NEW |
EXTENT_DEFRAG | EXTENT_DO_ACCOUNTING,
@@ -927,10 +929,10 @@
goto again;
}
-static u64 get_extent_allocation_hint(struct inode *inode, u64 start,
+static u64 get_extent_allocation_hint(struct btrfs_inode *inode, u64 start,
u64 num_bytes)
{
- struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
+ struct extent_map_tree *em_tree = &inode->extent_tree;
struct extent_map *em;
u64 alloc_hint = 0;
@@ -972,14 +974,13 @@
* 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,
+static noinline int cow_file_range(struct btrfs_inode *inode,
struct page *locked_page,
- u64 start, u64 end, u64 delalloc_end,
- int *page_started, unsigned long *nr_written,
- int unlock, struct btrfs_dedupe_hash *hash)
+ 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;
+ struct btrfs_root *root = inode->root;
+ struct btrfs_fs_info *fs_info = root->fs_info;
u64 alloc_hint = 0;
u64 num_bytes;
unsigned long ram_size;
@@ -993,8 +994,7 @@
bool extent_reserved = false;
int ret = 0;
- if (btrfs_is_free_space_inode(BTRFS_I(inode))) {
- WARN_ON_ONCE(1);
+ if (btrfs_is_free_space_inode(inode)) {
ret = -EINVAL;
goto out_unlock;
}
@@ -1003,7 +1003,7 @@
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);
+ inode_should_defrag(inode, start, end, num_bytes, SZ_64K);
if (start == 0) {
/* lets try to make an inline extent */
@@ -1016,8 +1016,7 @@
* our outstanding extent for clearing delalloc for this
* range.
*/
- extent_clear_unlock_delalloc(inode, start, end,
- delalloc_end, NULL,
+ extent_clear_unlock_delalloc(inode, start, end, NULL,
EXTENT_LOCKED | EXTENT_DELALLOC |
EXTENT_DELALLOC_NEW | EXTENT_DEFRAG |
EXTENT_DO_ACCOUNTING, PAGE_UNLOCK |
@@ -1033,8 +1032,7 @@
}
alloc_hint = get_extent_allocation_hint(inode, start, num_bytes);
- btrfs_drop_extent_cache(BTRFS_I(inode), start,
- start + num_bytes - 1, 0);
+ btrfs_drop_extent_cache(inode, start, start + num_bytes - 1, 0);
/*
* Relocation relies on the relocated extents to have exactly the same
@@ -1098,7 +1096,7 @@
* skip current ordered extent.
*/
if (ret)
- btrfs_drop_extent_cache(BTRFS_I(inode), start,
+ btrfs_drop_extent_cache(inode, start,
start + ram_size - 1, 0);
}
@@ -1114,9 +1112,8 @@
page_ops = unlock ? PAGE_UNLOCK : 0;
page_ops |= PAGE_SET_PRIVATE2;
- extent_clear_unlock_delalloc(inode, start,
- start + ram_size - 1,
- delalloc_end, locked_page,
+ extent_clear_unlock_delalloc(inode, start, start + ram_size - 1,
+ locked_page,
EXTENT_LOCKED | EXTENT_DELALLOC,
page_ops);
if (num_bytes < cur_alloc_size)
@@ -1139,7 +1136,7 @@
return ret;
out_drop_extent_cache:
- btrfs_drop_extent_cache(BTRFS_I(inode), start, start + ram_size - 1, 0);
+ btrfs_drop_extent_cache(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);
@@ -1161,7 +1158,6 @@
if (extent_reserved) {
extent_clear_unlock_delalloc(inode, start,
start + cur_alloc_size - 1,
- start + cur_alloc_size - 1,
locked_page,
clear_bits,
page_ops);
@@ -1169,8 +1165,7 @@
if (start >= end)
goto out;
}
- extent_clear_unlock_delalloc(inode, start, end, delalloc_end,
- locked_page,
+ extent_clear_unlock_delalloc(inode, start, end, locked_page,
clear_bits | EXTENT_CLEAR_DATA_RESV,
page_ops);
goto out;
@@ -1181,16 +1176,15 @@
*/
static noinline void async_cow_start(struct btrfs_work *work)
{
- struct async_cow *async_cow;
- int num_added = 0;
- async_cow = container_of(work, struct async_cow, work);
+ struct async_chunk *async_chunk;
+ int compressed_extents;
- compress_file_range(async_cow->inode, async_cow->locked_page,
- async_cow->start, async_cow->end, async_cow,
- &num_added);
- if (num_added == 0) {
- btrfs_add_delayed_iput(async_cow->inode);
- async_cow->inode = NULL;
+ 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;
}
}
@@ -1199,77 +1193,153 @@
*/
static noinline void async_cow_submit(struct btrfs_work *work)
{
- struct btrfs_fs_info *fs_info;
- struct async_cow *async_cow;
- struct btrfs_root *root;
+ 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;
- async_cow = container_of(work, struct async_cow, work);
-
- root = async_cow->root;
- fs_info = root->fs_info;
- nr_pages = (async_cow->end - async_cow->start + PAGE_SIZE) >>
+ nr_pages = (async_chunk->end - async_chunk->start + PAGE_SIZE) >>
PAGE_SHIFT;
+
+ /*
+ * ->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);
/* 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);
-
- if (async_cow->inode)
- submit_compressed_extents(async_cow->inode, async_cow);
}
static noinline void async_cow_free(struct btrfs_work *work)
{
- struct async_cow *async_cow;
- async_cow = container_of(work, struct async_cow, work);
- if (async_cow->inode)
- btrfs_add_delayed_iput(async_cow->inode);
- kfree(async_cow);
+ 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 page *locked_page,
+static int cow_file_range_async(struct btrfs_inode *inode,
+ struct writeback_control *wbc,
+ struct page *locked_page,
u64 start, u64 end, int *page_started,
- unsigned long *nr_written,
- unsigned int write_flags)
+ unsigned long *nr_written)
{
- struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
- struct async_cow *async_cow;
- struct btrfs_root *root = BTRFS_I(inode)->root;
+ struct btrfs_fs_info *fs_info = inode->root->fs_info;
+ 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);
- clear_extent_bit(&BTRFS_I(inode)->io_tree, start, end, EXTENT_LOCKED,
- 1, 0, NULL);
- while (start < end) {
- async_cow = kmalloc(sizeof(*async_cow), GFP_NOFS);
- BUG_ON(!async_cow); /* -ENOMEM */
- async_cow->inode = igrab(inode);
- async_cow->root = root;
- async_cow->locked_page = locked_page;
- async_cow->start = start;
- async_cow->write_flags = write_flags;
+ unlock_extent(&inode->io_tree, start, end);
- if (BTRFS_I(inode)->flags & BTRFS_INODE_NOCOMPRESS &&
- !btrfs_test_opt(fs_info, FORCE_COMPRESS))
- cur_end = end;
- else
+ if (inode->flags & BTRFS_INODE_NOCOMPRESS &&
+ !btrfs_test_opt(fs_info, FORCE_COMPRESS)) {
+ num_chunks = 1;
+ should_compress = false;
+ } else {
+ should_compress = true;
+ }
+
+ nofs_flag = memalloc_nofs_save();
+ ctx = kvmalloc(struct_size(ctx, chunks, num_chunks), GFP_KERNEL);
+ memalloc_nofs_restore(nofs_flag);
+
+ if (!ctx) {
+ unsigned clear_bits = EXTENT_LOCKED | EXTENT_DELALLOC |
+ EXTENT_DELALLOC_NEW | EXTENT_DEFRAG |
+ EXTENT_DO_ACCOUNTING;
+ unsigned long page_ops = PAGE_UNLOCK | PAGE_CLEAR_DIRTY |
+ PAGE_SET_WRITEBACK | PAGE_END_WRITEBACK |
+ PAGE_SET_ERROR;
+
+ extent_clear_unlock_delalloc(inode, start, end, locked_page,
+ clear_bits, page_ops);
+ return -ENOMEM;
+ }
+
+ async_chunk = ctx->chunks;
+ atomic_set(&ctx->num_chunks, num_chunks);
+
+ for (i = 0; i < num_chunks; i++) {
+ if (should_compress)
cur_end = min(end, start + SZ_512K - 1);
+ else
+ cur_end = end;
- async_cow->end = cur_end;
- INIT_LIST_HEAD(&async_cow->extents);
+ /*
+ * igrab is called higher up in the call chain, take only the
+ * lightweight reference for the callback lifetime
+ */
+ ihold(&inode->vfs_inode);
+ async_chunk[i].pending = &ctx->num_chunks;
+ async_chunk[i].inode = &inode->vfs_inode;
+ async_chunk[i].start = start;
+ async_chunk[i].end = cur_end;
+ async_chunk[i].write_flags = write_flags;
+ INIT_LIST_HEAD(&async_chunk[i].extents);
- btrfs_init_work(&async_cow->work,
- btrfs_delalloc_helper,
- async_cow_start, async_cow_submit,
- async_cow_free);
+ /*
+ * The locked_page comes all the way from writepage and its
+ * the original page we were actually given. As we spread
+ * this large delalloc region across multiple async_chunk
+ * structs, only the first struct needs a pointer to locked_page
+ *
+ * This way we don't need racey decisions about who is supposed
+ * to unlock it.
+ */
+ if (locked_page) {
+ /*
+ * Depending on the compressibility, the pages might or
+ * might not go through async. We want all of them to
+ * be accounted against wbc once. Let's do it here
+ * before the paths diverge. wbc accounting is used
+ * only for foreign writeback detection and doesn't
+ * need full accuracy. Just account the whole thing
+ * against the first page.
+ */
+ wbc_account_cgroup_owner(wbc, locked_page,
+ cur_end - start);
+ async_chunk[i].locked_page = locked_page;
+ locked_page = NULL;
+ } else {
+ async_chunk[i].locked_page = NULL;
+ }
- nr_pages = (cur_end - start + PAGE_SIZE) >>
- PAGE_SHIFT;
+ if (blkcg_css != blkcg_root_css) {
+ css_get(blkcg_css);
+ async_chunk[i].blkcg_css = blkcg_css;
+ } else {
+ async_chunk[i].blkcg_css = NULL;
+ }
+
+ btrfs_init_work(&async_chunk[i].work, async_cow_start,
+ async_cow_submit, async_cow_free);
+
+ nr_pages = DIV_ROUND_UP(cur_end - start, PAGE_SIZE);
atomic_add(nr_pages, &fs_info->async_delalloc_pages);
- btrfs_queue_work(fs_info->delalloc_workers, &async_cow->work);
+ btrfs_queue_work(fs_info->delalloc_workers, &async_chunk[i].work);
*nr_written += nr_pages;
start = cur_end + 1;
@@ -1300,6 +1370,73 @@
return 1;
}
+static int fallback_to_cow(struct btrfs_inode *inode, struct page *locked_page,
+ const u64 start, const u64 end,
+ int *page_started, unsigned long *nr_written)
+{
+ const bool is_space_ino = btrfs_is_free_space_inode(inode);
+ const bool is_reloc_ino = (inode->root->root_key.objectid ==
+ BTRFS_DATA_RELOC_TREE_OBJECTID);
+ const u64 range_bytes = end + 1 - start;
+ struct extent_io_tree *io_tree = &inode->io_tree;
+ u64 range_start = start;
+ u64 count;
+
+ /*
+ * If EXTENT_NORESERVE is set it means that when the buffered write was
+ * made we had not enough available data space and therefore we did not
+ * reserve data space for it, since we though we could do NOCOW for the
+ * respective file range (either there is prealloc extent or the inode
+ * has the NOCOW bit set).
+ *
+ * However when we need to fallback to COW mode (because for example the
+ * block group for the corresponding extent was turned to RO mode by a
+ * scrub or relocation) we need to do the following:
+ *
+ * 1) We increment the bytes_may_use counter of the data space info.
+ * If COW succeeds, it allocates a new data extent and after doing
+ * that it decrements the space info's bytes_may_use counter and
+ * increments its bytes_reserved counter by the same amount (we do
+ * this at btrfs_add_reserved_bytes()). So we need to increment the
+ * bytes_may_use counter to compensate (when space is reserved at
+ * buffered write time, the bytes_may_use counter is incremented);
+ *
+ * 2) We clear the EXTENT_NORESERVE bit from the range. We do this so
+ * that if the COW path fails for any reason, it decrements (through
+ * extent_clear_unlock_delalloc()) the bytes_may_use counter of the
+ * data space info, which we incremented in the step above.
+ *
+ * If we need to fallback to cow and the inode corresponds to a free
+ * space cache inode or an inode of the data relocation tree, we must
+ * also increment bytes_may_use of the data space_info for the same
+ * reason. Space caches and relocated data extents always get a prealloc
+ * extent for them, however scrub or balance may have set the block
+ * group that contains that extent to RO mode and therefore force COW
+ * when starting writeback.
+ */
+ count = count_range_bits(io_tree, &range_start, end, range_bytes,
+ EXTENT_NORESERVE, 0);
+ if (count > 0 || is_space_ino || is_reloc_ino) {
+ u64 bytes = count;
+ struct btrfs_fs_info *fs_info = inode->root->fs_info;
+ struct btrfs_space_info *sinfo = fs_info->data_sinfo;
+
+ if (is_space_ino || is_reloc_ino)
+ bytes = range_bytes;
+
+ spin_lock(&sinfo->lock);
+ btrfs_space_info_update_bytes_may_use(fs_info, sinfo, bytes);
+ spin_unlock(&sinfo->lock);
+
+ if (count > 0)
+ clear_extent_bit(io_tree, start, end, EXTENT_NORESERVE,
+ 0, 0, NULL);
+ }
+
+ return cow_file_range(inode, locked_page, start, end, page_started,
+ nr_written, 1);
+}
+
/*
* when nowcow writeback call back. This checks for snapshots or COW copies
* of the extents that exist in the file, and COWs the file as required.
@@ -1307,38 +1444,27 @@
* If no cow copies or snapshots exist, we write directly to the existing
* blocks on disk
*/
-static noinline int run_delalloc_nocow(struct inode *inode,
+static noinline int run_delalloc_nocow(struct btrfs_inode *inode,
struct page *locked_page,
- u64 start, u64 end, int *page_started, int force,
- unsigned long *nr_written)
+ const u64 start, const u64 end,
+ int *page_started, int force,
+ unsigned long *nr_written)
{
- struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
- struct btrfs_root *root = BTRFS_I(inode)->root;
- struct extent_buffer *leaf;
+ struct btrfs_fs_info *fs_info = inode->root->fs_info;
+ struct btrfs_root *root = inode->root;
struct btrfs_path *path;
- struct btrfs_file_extent_item *fi;
- struct btrfs_key found_key;
- struct extent_map *em;
- u64 cow_start;
- u64 cur_offset;
- u64 extent_end;
- u64 extent_offset;
- u64 disk_bytenr;
- u64 num_bytes;
- u64 disk_num_bytes;
- u64 ram_bytes;
- int extent_type;
+ u64 cow_start = (u64)-1;
+ u64 cur_offset = start;
int ret;
- int type;
- int nocow;
- int check_prev = 1;
- bool nolock;
- u64 ino = btrfs_ino(BTRFS_I(inode));
+ bool check_prev = true;
+ const bool freespace_inode = btrfs_is_free_space_inode(inode);
+ u64 ino = btrfs_ino(inode);
+ bool nocow = false;
+ u64 disk_bytenr = 0;
path = btrfs_alloc_path();
if (!path) {
- extent_clear_unlock_delalloc(inode, start, end, end,
- locked_page,
+ extent_clear_unlock_delalloc(inode, start, end, locked_page,
EXTENT_LOCKED | EXTENT_DELALLOC |
EXTENT_DO_ACCOUNTING |
EXTENT_DEFRAG, PAGE_UNLOCK |
@@ -1348,15 +1474,29 @@
return -ENOMEM;
}
- nolock = btrfs_is_free_space_inode(BTRFS_I(inode));
-
- cow_start = (u64)-1;
- cur_offset = start;
while (1) {
+ struct btrfs_key found_key;
+ struct btrfs_file_extent_item *fi;
+ struct extent_buffer *leaf;
+ u64 extent_end;
+ u64 extent_offset;
+ u64 num_bytes = 0;
+ u64 disk_num_bytes;
+ u64 ram_bytes;
+ int extent_type;
+
+ nocow = false;
+
ret = btrfs_lookup_file_extent(NULL, root, path, ino,
cur_offset, 0);
if (ret < 0)
goto error;
+
+ /*
+ * If there is no extent for our range when doing the initial
+ * search, then go back to the previous slot as it will be the
+ * one containing the search offset
+ */
if (ret > 0 && path->slots[0] > 0 && check_prev) {
leaf = path->nodes[0];
btrfs_item_key_to_cpu(leaf, &found_key,
@@ -1365,8 +1505,9 @@
found_key.type == BTRFS_EXTENT_DATA_KEY)
path->slots[0]--;
}
- check_prev = 0;
+ check_prev = false;
next_slot:
+ /* Go to next leaf if we have exhausted the current one */
leaf = path->nodes[0];
if (path->slots[0] >= btrfs_header_nritems(leaf)) {
ret = btrfs_next_leaf(root, path);
@@ -1380,28 +1521,40 @@
leaf = path->nodes[0];
}
- nocow = 0;
- disk_bytenr = 0;
- num_bytes = 0;
btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);
+ /* Didn't find anything for our INO */
if (found_key.objectid > ino)
break;
+ /*
+ * Keep searching until we find an EXTENT_ITEM or there are no
+ * more extents for this inode
+ */
if (WARN_ON_ONCE(found_key.objectid < ino) ||
found_key.type < BTRFS_EXTENT_DATA_KEY) {
path->slots[0]++;
goto next_slot;
}
+
+ /* Found key is not EXTENT_DATA_KEY or starts after req range */
if (found_key.type > BTRFS_EXTENT_DATA_KEY ||
found_key.offset > end)
break;
+ /*
+ * If the found extent starts after requested offset, then
+ * adjust extent_end to be right before this extent begins
+ */
if (found_key.offset > cur_offset) {
extent_end = found_key.offset;
extent_type = 0;
goto out_check;
}
+ /*
+ * Found extent which begins before our range and potentially
+ * intersect it
+ */
fi = btrfs_item_ptr(leaf, path->slots[0],
struct btrfs_file_extent_item);
extent_type = btrfs_file_extent_type(leaf, fi);
@@ -1415,31 +1568,41 @@
btrfs_file_extent_num_bytes(leaf, fi);
disk_num_bytes =
btrfs_file_extent_disk_num_bytes(leaf, fi);
- if (extent_end <= start) {
+ /*
+ * If the extent we got ends before our current offset,
+ * skip to the next extent.
+ */
+ if (extent_end <= cur_offset) {
path->slots[0]++;
goto next_slot;
}
+ /* Skip holes */
if (disk_bytenr == 0)
goto out_check;
+ /* Skip compressed/encrypted/encoded extents */
if (btrfs_file_extent_compression(leaf, fi) ||
btrfs_file_extent_encryption(leaf, fi) ||
btrfs_file_extent_other_encoding(leaf, fi))
goto out_check;
/*
- * Do the same check as in btrfs_cross_ref_exist but
- * without the unnecessary search.
+ * If extent is created before the last volume's snapshot
+ * this implies the extent is shared, hence we can't do
+ * nocow. This is the same check as in
+ * btrfs_cross_ref_exist but without calling
+ * btrfs_search_slot.
*/
- if (!nolock &&
+ if (!freespace_inode &&
btrfs_file_extent_generation(leaf, fi) <=
btrfs_root_last_snapshot(&root->root_item))
goto out_check;
if (extent_type == BTRFS_FILE_EXTENT_REG && !force)
goto out_check;
+ /* If extent is RO, we must COW it */
if (btrfs_extent_readonly(fs_info, disk_bytenr))
goto out_check;
ret = btrfs_cross_ref_exist(root, ino,
found_key.offset -
- extent_offset, disk_bytenr);
+ extent_offset, disk_bytenr, false);
if (ret) {
/*
* ret could be -EIO if the above fails to read
@@ -1451,17 +1614,17 @@
goto error;
}
- WARN_ON_ONCE(nolock);
+ WARN_ON_ONCE(freespace_inode);
goto out_check;
}
disk_bytenr += extent_offset;
disk_bytenr += cur_offset - found_key.offset;
num_bytes = min(end + 1, extent_end) - cur_offset;
/*
- * if there are pending snapshots for this root,
- * we fall into common COW way.
+ * If there are pending snapshots for this root, we
+ * fall into common COW way
*/
- if (!nolock && atomic_read(&root->snapshot_force_cow))
+ if (!freespace_inode && atomic_read(&root->snapshot_force_cow))
goto out_check;
/*
* force cow if csum exists in the range.
@@ -1480,27 +1643,29 @@
cur_offset = cow_start;
goto error;
}
- WARN_ON_ONCE(nolock);
+ WARN_ON_ONCE(freespace_inode);
goto out_check;
}
if (!btrfs_inc_nocow_writers(fs_info, disk_bytenr))
goto out_check;
- nocow = 1;
+ nocow = true;
} else if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
- extent_end = found_key.offset +
- btrfs_file_extent_ram_bytes(leaf, fi);
- extent_end = ALIGN(extent_end,
- fs_info->sectorsize);
+ extent_end = found_key.offset + ram_bytes;
+ extent_end = ALIGN(extent_end, fs_info->sectorsize);
+ /* Skip extents outside of our requested range */
+ if (extent_end <= start) {
+ path->slots[0]++;
+ goto next_slot;
+ }
} else {
- BUG_ON(1);
+ /* If this triggers then we have a memory corruption */
+ BUG();
}
out_check:
- if (extent_end <= start) {
- path->slots[0]++;
- if (nocow)
- btrfs_dec_nocow_writers(fs_info, disk_bytenr);
- goto next_slot;
- }
+ /*
+ * If nocow is false then record the beginning of the range
+ * that needs to be COWed
+ */
if (!nocow) {
if (cow_start == (u64)-1)
cow_start = cur_offset;
@@ -1512,22 +1677,24 @@
}
btrfs_release_path(path);
+
+ /*
+ * COW range from cow_start to found_key.offset - 1. As the key
+ * will contain the beginning of the first extent that can be
+ * NOCOW, following one which needs to be COW'ed
+ */
if (cow_start != (u64)-1) {
- ret = cow_file_range(inode, locked_page,
- cow_start, found_key.offset - 1,
- end, page_started, nr_written, 1,
- NULL);
- if (ret) {
- if (nocow)
- btrfs_dec_nocow_writers(fs_info,
- disk_bytenr);
+ ret = fallback_to_cow(inode, locked_page,
+ cow_start, found_key.offset - 1,
+ page_started, nr_written);
+ if (ret)
goto error;
- }
cow_start = (u64)-1;
}
if (extent_type == BTRFS_FILE_EXTENT_PREALLOC) {
u64 orig_start = found_key.offset - extent_offset;
+ struct extent_map *em;
em = create_io_em(inode, cur_offset, num_bytes,
orig_start,
@@ -1537,26 +1704,32 @@
ram_bytes, BTRFS_COMPRESS_NONE,
BTRFS_ORDERED_PREALLOC);
if (IS_ERR(em)) {
- if (nocow)
- btrfs_dec_nocow_writers(fs_info,
- disk_bytenr);
ret = PTR_ERR(em);
goto error;
}
free_extent_map(em);
- }
-
- if (extent_type == BTRFS_FILE_EXTENT_PREALLOC) {
- type = BTRFS_ORDERED_PREALLOC;
+ ret = btrfs_add_ordered_extent(inode, cur_offset,
+ disk_bytenr, num_bytes,
+ num_bytes,
+ BTRFS_ORDERED_PREALLOC);
+ if (ret) {
+ btrfs_drop_extent_cache(inode, cur_offset,
+ cur_offset + num_bytes - 1,
+ 0);
+ goto error;
+ }
} else {
- type = BTRFS_ORDERED_NOCOW;
+ ret = btrfs_add_ordered_extent(inode, cur_offset,
+ disk_bytenr, num_bytes,
+ num_bytes,
+ BTRFS_ORDERED_NOCOW);
+ if (ret)
+ goto error;
}
- ret = btrfs_add_ordered_extent(inode, cur_offset, disk_bytenr,
- num_bytes, num_bytes, type);
if (nocow)
btrfs_dec_nocow_writers(fs_info, disk_bytenr);
- BUG_ON(ret); /* -ENOMEM */
+ nocow = false;
if (root->root_key.objectid ==
BTRFS_DATA_RELOC_TREE_OBJECTID)
@@ -1569,7 +1742,7 @@
num_bytes);
extent_clear_unlock_delalloc(inode, cur_offset,
- cur_offset + num_bytes - 1, end,
+ cur_offset + num_bytes - 1,
locked_page, EXTENT_LOCKED |
EXTENT_DELALLOC |
EXTENT_CLEAR_DATA_RESV,
@@ -1594,15 +1767,18 @@
if (cow_start != (u64)-1) {
cur_offset = end;
- ret = cow_file_range(inode, locked_page, cow_start, end, end,
- page_started, nr_written, 1, NULL);
+ ret = fallback_to_cow(inode, locked_page, cow_start, end,
+ page_started, nr_written);
if (ret)
goto error;
}
error:
+ if (nocow)
+ btrfs_dec_nocow_writers(fs_info, disk_bytenr);
+
if (ret && cur_offset < end)
- extent_clear_unlock_delalloc(inode, cur_offset, end, end,
+ extent_clear_unlock_delalloc(inode, cur_offset, end,
locked_page, EXTENT_LOCKED |
EXTENT_DELALLOC | EXTENT_DEFRAG |
EXTENT_DO_ACCOUNTING, PAGE_UNLOCK |
@@ -1613,11 +1789,11 @@
return ret;
}
-static inline int need_force_cow(struct inode *inode, u64 start, u64 end)
+static inline int need_force_cow(struct btrfs_inode *inode, u64 start, u64 end)
{
- if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW) &&
- !(BTRFS_I(inode)->flags & BTRFS_INODE_PREALLOC))
+ if (!(inode->flags & BTRFS_INODE_NODATACOW) &&
+ !(inode->flags & BTRFS_INODE_PREALLOC))
return 0;
/*
@@ -1625,9 +1801,8 @@
* if is not zero, it means the file is defragging.
* Force cow if given extent needs to be defragged.
*/
- if (BTRFS_I(inode)->defrag_bytes &&
- test_range_bit(&BTRFS_I(inode)->io_tree, start, end,
- EXTENT_DEFRAG, 0, NULL))
+ if (inode->defrag_bytes &&
+ test_range_bit(&inode->io_tree, start, end, EXTENT_DEFRAG, 0, NULL))
return 1;
return 0;
@@ -1637,31 +1812,27 @@
* Function to process delayed allocation (create CoW) for ranges which are
* being touched for the first time.
*/
-int btrfs_run_delalloc_range(void *private_data, struct page *locked_page,
+int btrfs_run_delalloc_range(struct btrfs_inode *inode, struct page *locked_page,
u64 start, u64 end, int *page_started, unsigned long *nr_written,
struct writeback_control *wbc)
{
- struct inode *inode = private_data;
int ret;
int force_cow = need_force_cow(inode, start, end);
- unsigned int write_flags = wbc_to_write_flags(wbc);
- if (BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW && !force_cow) {
+ if (inode->flags & BTRFS_INODE_NODATACOW && !force_cow) {
ret = run_delalloc_nocow(inode, locked_page, start, end,
page_started, 1, nr_written);
- } else if (BTRFS_I(inode)->flags & BTRFS_INODE_PREALLOC && !force_cow) {
+ } else if (inode->flags & BTRFS_INODE_PREALLOC && !force_cow) {
ret = run_delalloc_nocow(inode, locked_page, start, end,
page_started, 0, nr_written);
} else if (!inode_can_compress(inode) ||
!inode_need_compress(inode, start, end)) {
- ret = cow_file_range(inode, locked_page, start, end, end,
- page_started, nr_written, 1, NULL);
+ ret = cow_file_range(inode, locked_page, start, end,
+ page_started, nr_written, 1);
} else {
- set_bit(BTRFS_INODE_HAS_ASYNC_EXTENT,
- &BTRFS_I(inode)->runtime_flags);
- ret = cow_file_range_async(inode, locked_page, start, end,
- page_started, nr_written,
- write_flags);
+ set_bit(BTRFS_INODE_HAS_ASYNC_EXTENT, &inode->runtime_flags);
+ ret = cow_file_range_async(inode, wbc, locked_page, start, end,
+ page_started, nr_written);
}
if (ret)
btrfs_cleanup_ordered_extents(inode, locked_page, start,
@@ -1669,10 +1840,9 @@
return ret;
}
-static void btrfs_split_extent_hook(void *private_data,
- struct extent_state *orig, u64 split)
+void btrfs_split_delalloc_extent(struct inode *inode,
+ struct extent_state *orig, u64 split)
{
- struct inode *inode = private_data;
u64 size;
/* not delalloc, ignore it */
@@ -1685,7 +1855,7 @@
u64 new_size;
/*
- * See the explanation in btrfs_merge_extent_hook, the same
+ * See the explanation in btrfs_merge_delalloc_extent, the same
* applies here, just in reverse.
*/
new_size = orig->end - split + 1;
@@ -1702,16 +1872,13 @@
}
/*
- * extent_io.c merge_extent_hook, used to track merged delayed allocation
- * extents so we can keep track of new extents that are just merged onto old
- * extents, such as when we are doing sequential writes, so we can properly
- * account for the metadata space we'll need.
+ * Handle merged delayed allocation extents so we can keep track of new extents
+ * that are just merged onto old extents, such as when we are doing sequential
+ * writes, so we can properly account for the metadata space we'll need.
*/
-static void btrfs_merge_extent_hook(void *private_data,
- struct extent_state *new,
- struct extent_state *other)
+void btrfs_merge_delalloc_extent(struct inode *inode, struct extent_state *new,
+ struct extent_state *other)
{
- struct inode *inode = private_data;
u64 new_size, old_size;
u32 num_extents;
@@ -1815,15 +1982,12 @@
}
/*
- * extent_io.c set_bit_hook, used to track delayed allocation
- * bytes in this file, and to maintain the list of inodes that
- * have pending delalloc work to be done.
+ * Properly track delayed allocation bytes in the inode and to maintain the
+ * list of inodes that have pending delalloc work to be done.
*/
-static void btrfs_set_bit_hook(void *private_data,
- struct extent_state *state, unsigned *bits)
+void btrfs_set_delalloc_extent(struct inode *inode, struct extent_state *state,
+ unsigned *bits)
{
- struct inode *inode = private_data;
-
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
if ((*bits & EXTENT_DEFRAG) && !(*bits & EXTENT_DELALLOC))
@@ -1869,14 +2033,14 @@
}
/*
- * extent_io.c clear_bit_hook, see set_bit_hook for why
+ * Once a range is no longer delalloc this function ensures that proper
+ * accounting happens.
*/
-static void btrfs_clear_bit_hook(void *private_data,
- struct extent_state *state,
- unsigned *bits)
+void btrfs_clear_delalloc_extent(struct inode *vfs_inode,
+ struct extent_state *state, unsigned *bits)
{
- struct btrfs_inode *inode = BTRFS_I((struct inode *)private_data);
- struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+ struct btrfs_inode *inode = BTRFS_I(vfs_inode);
+ struct btrfs_fs_info *fs_info = btrfs_sb(vfs_inode->i_sb);
u64 len = state->end + 1 - state->start;
u32 num_extents = count_max_extents(len);
@@ -1901,7 +2065,7 @@
/*
* We don't reserve metadata space for space cache inodes so we
- * don't need to call dellalloc_release_metadata if there is an
+ * don't need to call delalloc_release_metadata if there is an
* error.
*/
if (*bits & EXTENT_CLEAR_META_RESV &&
@@ -1915,9 +2079,7 @@
if (root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID &&
do_list && !(state->state & EXTENT_NORESERVE) &&
(*bits & EXTENT_CLEAR_DATA_RESV))
- btrfs_free_reserved_data_space_noquota(
- &inode->vfs_inode,
- state->start, len);
+ btrfs_free_reserved_data_space_noquota(fs_info, len);
percpu_counter_add_batch(&fs_info->delalloc_bytes, -len,
fs_info->delalloc_batch);
@@ -1940,16 +2102,21 @@
}
/*
- * Merge bio hook, this must check the chunk tree to make sure we don't create
- * bios that span stripes or chunks
+ * btrfs_bio_fits_in_stripe - Checks whether the size of the given bio will fit
+ * in a chunk's stripe. This function ensures that bios do not span a
+ * stripe/chunk
*
- * return 1 if page cannot be merged to bio
- * return 0 if page can be merged to bio
+ * @page - The page we are about to add to the bio
+ * @size - size we want to add to the bio
+ * @bio - bio we want to ensure is smaller than a stripe
+ * @bio_flags - flags of the bio
+ *
+ * return 1 if page cannot be added to the bio
+ * return 0 if page can be added to the bio
* return error otherwise
*/
-int btrfs_merge_bio_hook(struct page *page, unsigned long offset,
- size_t size, struct bio *bio,
- unsigned long bio_flags)
+int btrfs_bio_fits_in_stripe(struct page *page, size_t size, struct bio *bio,
+ unsigned long bio_flags)
{
struct inode *inode = page->mapping->host;
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
@@ -1957,17 +2124,19 @@
u64 length = 0;
u64 map_length;
int ret;
+ struct btrfs_io_geometry geom;
if (bio_flags & EXTENT_BIO_COMPRESSED)
return 0;
length = bio->bi_iter.bi_size;
map_length = length;
- ret = btrfs_map_block(fs_info, btrfs_op(bio), logical, &map_length,
- NULL, 0);
+ ret = btrfs_get_io_geometry(fs_info, btrfs_op(bio), logical, map_length,
+ &geom);
if (ret < 0)
return ret;
- if (map_length < length + size)
+
+ if (geom.len < length + size)
return 1;
return 0;
}
@@ -1984,34 +2153,8 @@
u64 bio_offset)
{
struct inode *inode = private_data;
- blk_status_t ret = 0;
- ret = btrfs_csum_one_bio(inode, bio, 0, 0);
- BUG_ON(ret); /* -ENOMEM */
- return 0;
-}
-
-/*
- * in order to insert checksums into the metadata in large chunks,
- * we wait until bio submission time. All the pages in the bio are
- * checksummed and sums are attached onto the ordered extent record.
- *
- * At IO completion time the cums attached on the ordered extent record
- * are inserted into the btree
- */
-blk_status_t btrfs_submit_bio_done(void *private_data, struct bio *bio,
- int mirror_num)
-{
- struct inode *inode = private_data;
- struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
- blk_status_t ret;
-
- ret = btrfs_map_bio(fs_info, bio, mirror_num, 1);
- if (ret) {
- bio->bi_status = ret;
- bio_endio(bio);
- }
- return ret;
+ return btrfs_csum_one_bio(BTRFS_I(inode), bio, 0, 0);
}
/*
@@ -2032,11 +2175,10 @@
*
* c-3) otherwise: async submit
*/
-static blk_status_t btrfs_submit_bio_hook(void *private_data, struct bio *bio,
- int mirror_num, unsigned long bio_flags,
- u64 bio_offset)
+blk_status_t btrfs_submit_data_bio(struct inode *inode, struct bio *bio,
+ int mirror_num, unsigned long bio_flags)
+
{
- struct inode *inode = private_data;
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
struct btrfs_root *root = BTRFS_I(inode)->root;
enum btrfs_wq_endio_type metadata = BTRFS_WQ_ENDIO_DATA;
@@ -2060,7 +2202,7 @@
bio_flags);
goto out;
} else if (!skip_sum) {
- ret = btrfs_lookup_bio_sums(inode, bio, NULL);
+ ret = btrfs_lookup_bio_sums(inode, bio, (u64)-1, NULL);
if (ret)
goto out;
}
@@ -2071,17 +2213,16 @@
goto mapit;
/* we're doing a write, do the async checksumming */
ret = btrfs_wq_submit_bio(fs_info, bio, mirror_num, bio_flags,
- bio_offset, inode,
- btrfs_submit_bio_start);
+ 0, inode, btrfs_submit_bio_start);
goto out;
} else if (!skip_sum) {
- ret = btrfs_csum_one_bio(inode, bio, 0, 0);
+ ret = btrfs_csum_one_bio(BTRFS_I(inode), bio, 0, 0);
if (ret)
goto out;
}
mapit:
- ret = btrfs_map_bio(fs_info, bio, mirror_num, 0);
+ ret = btrfs_map_bio(fs_info, bio, mirror_num);
out:
if (ret) {
@@ -2095,16 +2236,15 @@
* given a list of ordered sums record them in the inode. This happens
* at IO completion time based on sums calculated at bio submission time.
*/
-static noinline int add_pending_csums(struct btrfs_trans_handle *trans,
- struct inode *inode, struct list_head *list)
+static int add_pending_csums(struct btrfs_trans_handle *trans,
+ struct list_head *list)
{
struct btrfs_ordered_sum *sum;
int ret;
list_for_each_entry(sum, list, list) {
trans->adding_csums = true;
- ret = btrfs_csum_file_blocks(trans,
- BTRFS_I(inode)->root->fs_info->csum_root, sum);
+ ret = btrfs_csum_file_blocks(trans, trans->fs_info->csum_root, sum);
trans->adding_csums = false;
if (ret)
return ret;
@@ -2112,18 +2252,77 @@
return 0;
}
-int btrfs_set_extent_delalloc(struct inode *inode, u64 start, u64 end,
- unsigned int extra_bits,
- struct extent_state **cached_state, int dedupe)
+static int btrfs_find_new_delalloc_bytes(struct btrfs_inode *inode,
+ const u64 start,
+ const u64 len,
+ struct extent_state **cached_state)
{
- WARN_ON((end & (PAGE_SIZE - 1)) == 0);
- return set_extent_delalloc(&BTRFS_I(inode)->io_tree, start, end,
- extra_bits, cached_state);
+ u64 search_start = start;
+ const u64 end = start + len - 1;
+
+ while (search_start < end) {
+ const u64 search_len = end - search_start + 1;
+ struct extent_map *em;
+ u64 em_len;
+ int ret = 0;
+
+ em = btrfs_get_extent(inode, NULL, 0, search_start, search_len);
+ if (IS_ERR(em))
+ return PTR_ERR(em);
+
+ if (em->block_start != EXTENT_MAP_HOLE)
+ goto next;
+
+ em_len = em->len;
+ if (em->start < search_start)
+ em_len -= search_start - em->start;
+ if (em_len > search_len)
+ em_len = search_len;
+
+ ret = set_extent_bit(&inode->io_tree, search_start,
+ search_start + em_len - 1,
+ EXTENT_DELALLOC_NEW,
+ NULL, cached_state, GFP_NOFS);
+next:
+ search_start = extent_map_end(em);
+ free_extent_map(em);
+ if (ret)
+ return ret;
+ }
+ return 0;
+}
+
+int btrfs_set_extent_delalloc(struct btrfs_inode *inode, u64 start, u64 end,
+ unsigned int extra_bits,
+ struct extent_state **cached_state)
+{
+ WARN_ON(PAGE_ALIGNED(end));
+
+ if (start >= i_size_read(&inode->vfs_inode) &&
+ !(inode->flags & BTRFS_INODE_PREALLOC)) {
+ /*
+ * There can't be any extents following eof in this case so just
+ * set the delalloc new bit for the range directly.
+ */
+ extra_bits |= EXTENT_DELALLOC_NEW;
+ } else {
+ int ret;
+
+ ret = btrfs_find_new_delalloc_bytes(inode, start,
+ end + 1 - start,
+ cached_state);
+ if (ret)
+ return ret;
+ }
+
+ return set_extent_delalloc(&inode->io_tree, start, end, extra_bits,
+ cached_state);
}
/* see btrfs_writepage_start_hook for details on why this is required */
struct btrfs_writepage_fixup {
struct page *page;
+ struct inode *inode;
struct btrfs_work work;
};
@@ -2134,75 +2333,126 @@
struct extent_state *cached_state = NULL;
struct extent_changeset *data_reserved = NULL;
struct page *page;
- struct inode *inode;
+ struct btrfs_inode *inode;
u64 page_start;
u64 page_end;
- int ret;
+ int ret = 0;
+ bool free_delalloc_space = true;
fixup = container_of(work, struct btrfs_writepage_fixup, work);
page = fixup->page;
-again:
- lock_page(page);
- if (!page->mapping || !PageDirty(page) || !PageChecked(page)) {
- ClearPageChecked(page);
- goto out_page;
- }
-
- inode = page->mapping->host;
+ inode = BTRFS_I(fixup->inode);
page_start = page_offset(page);
page_end = page_offset(page) + PAGE_SIZE - 1;
- lock_extent_bits(&BTRFS_I(inode)->io_tree, page_start, page_end,
- &cached_state);
+ /*
+ * This is similar to page_mkwrite, we need to reserve the space before
+ * we take the page lock.
+ */
+ ret = btrfs_delalloc_reserve_space(inode, &data_reserved, page_start,
+ PAGE_SIZE);
+again:
+ lock_page(page);
+
+ /*
+ * Before we queued this fixup, we took a reference on the page.
+ * page->mapping may go NULL, but it shouldn't be moved to a different
+ * address space.
+ */
+ if (!page->mapping || !PageDirty(page) || !PageChecked(page)) {
+ /*
+ * Unfortunately this is a little tricky, either
+ *
+ * 1) We got here and our page had already been dealt with and
+ * we reserved our space, thus ret == 0, so we need to just
+ * drop our space reservation and bail. This can happen the
+ * first time we come into the fixup worker, or could happen
+ * while waiting for the ordered extent.
+ * 2) Our page was already dealt with, but we happened to get an
+ * ENOSPC above from the btrfs_delalloc_reserve_space. In
+ * this case we obviously don't have anything to release, but
+ * because the page was already dealt with we don't want to
+ * mark the page with an error, so make sure we're resetting
+ * ret to 0. This is why we have this check _before_ the ret
+ * check, because we do not want to have a surprise ENOSPC
+ * when the page was already properly dealt with.
+ */
+ if (!ret) {
+ btrfs_delalloc_release_extents(inode, PAGE_SIZE);
+ btrfs_delalloc_release_space(inode, data_reserved,
+ page_start, PAGE_SIZE,
+ true);
+ }
+ ret = 0;
+ goto out_page;
+ }
+
+ /*
+ * We can't mess with the page state unless it is locked, so now that
+ * it is locked bail if we failed to make our space reservation.
+ */
+ if (ret)
+ goto out_page;
+
+ lock_extent_bits(&inode->io_tree, page_start, page_end, &cached_state);
/* already ordered? We're done */
if (PagePrivate2(page))
- goto out;
+ goto out_reserved;
- ordered = btrfs_lookup_ordered_range(BTRFS_I(inode), page_start,
- PAGE_SIZE);
+ ordered = btrfs_lookup_ordered_range(inode, page_start, PAGE_SIZE);
if (ordered) {
- unlock_extent_cached(&BTRFS_I(inode)->io_tree, page_start,
- page_end, &cached_state);
+ unlock_extent_cached(&inode->io_tree, page_start, page_end,
+ &cached_state);
unlock_page(page);
- btrfs_start_ordered_extent(inode, ordered, 1);
+ btrfs_start_ordered_extent(ordered, 1);
btrfs_put_ordered_extent(ordered);
goto again;
}
- ret = btrfs_delalloc_reserve_space(inode, &data_reserved, page_start,
- PAGE_SIZE);
- if (ret) {
- mapping_set_error(page->mapping, ret);
- end_extent_writepage(page, ret, page_start, page_end);
- ClearPageChecked(page);
- goto out;
- }
-
ret = btrfs_set_extent_delalloc(inode, page_start, page_end, 0,
- &cached_state, 0);
- if (ret) {
- mapping_set_error(page->mapping, ret);
- end_extent_writepage(page, ret, page_start, page_end);
- ClearPageChecked(page);
- goto out_reserved;
- }
-
- ClearPageChecked(page);
- set_page_dirty(page);
-out_reserved:
- btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE);
+ &cached_state);
if (ret)
+ goto out_reserved;
+
+ /*
+ * Everything went as planned, we're now the owner of a dirty page with
+ * delayed allocation bits set and space reserved for our COW
+ * destination.
+ *
+ * The page was dirty when we started, nothing should have cleaned it.
+ */
+ BUG_ON(!PageDirty(page));
+ free_delalloc_space = false;
+out_reserved:
+ btrfs_delalloc_release_extents(inode, PAGE_SIZE);
+ if (free_delalloc_space)
btrfs_delalloc_release_space(inode, data_reserved, page_start,
PAGE_SIZE, true);
-out:
- unlock_extent_cached(&BTRFS_I(inode)->io_tree, page_start, page_end,
+ unlock_extent_cached(&inode->io_tree, page_start, page_end,
&cached_state);
out_page:
+ if (ret) {
+ /*
+ * We hit ENOSPC or other errors. Update the mapping and page
+ * to reflect the errors and clean the page.
+ */
+ mapping_set_error(page->mapping, ret);
+ end_extent_writepage(page, ret, page_start, page_end);
+ clear_page_dirty_for_io(page);
+ SetPageError(page);
+ }
+ ClearPageChecked(page);
unlock_page(page);
put_page(page);
kfree(fixup);
extent_changeset_free(data_reserved);
+ /*
+ * As a precaution, do a delayed iput in case it would be the last iput
+ * that could need flushing space. Recursing back to fixup worker would
+ * deadlock.
+ */
+ btrfs_add_delayed_iput(&inode->vfs_inode);
}
/*
@@ -2216,7 +2466,7 @@
* to fix it up. The async helper will wait for ordered extents, set
* the delalloc bit and make it safe to write the page.
*/
-static int btrfs_writepage_start_hook(struct page *page, u64 start, u64 end)
+int btrfs_writepage_cow_fixup(struct page *page, u64 start, u64 end)
{
struct inode *inode = page->mapping->host;
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
@@ -2226,6 +2476,13 @@
if (TestClearPagePrivate2(page))
return 0;
+ /*
+ * PageChecked is set below when we create a fixup worker for this page,
+ * don't try to create another one if we're already PageChecked()
+ *
+ * The extent_io writepage code will redirty the page if we send back
+ * EAGAIN.
+ */
if (PageChecked(page))
return -EAGAIN;
@@ -2233,28 +2490,36 @@
if (!fixup)
return -EAGAIN;
+ /*
+ * We are already holding a reference to this inode from
+ * write_cache_pages. We need to hold it because the space reservation
+ * takes place outside of the page lock, and we can't trust
+ * page->mapping outside of the page lock.
+ */
+ ihold(inode);
SetPageChecked(page);
get_page(page);
- btrfs_init_work(&fixup->work, btrfs_fixup_helper,
- btrfs_writepage_fixup_worker, NULL, NULL);
+ btrfs_init_work(&fixup->work, btrfs_writepage_fixup_worker, NULL, NULL);
fixup->page = page;
+ fixup->inode = inode;
btrfs_queue_work(fs_info->fixup_workers, &fixup->work);
- return -EBUSY;
+
+ return -EAGAIN;
}
static int insert_reserved_file_extent(struct btrfs_trans_handle *trans,
- struct inode *inode, u64 file_pos,
- u64 disk_bytenr, u64 disk_num_bytes,
- u64 num_bytes, u64 ram_bytes,
- u8 compression, u8 encryption,
- u16 other_encoding, int extent_type)
+ struct btrfs_inode *inode, u64 file_pos,
+ struct btrfs_file_extent_item *stack_fi,
+ u64 qgroup_reserved)
{
- struct btrfs_root *root = BTRFS_I(inode)->root;
- struct btrfs_file_extent_item *fi;
+ struct btrfs_root *root = inode->root;
struct btrfs_path *path;
struct extent_buffer *leaf;
struct btrfs_key ins;
- u64 qg_released;
+ u64 disk_num_bytes = btrfs_stack_file_extent_disk_num_bytes(stack_fi);
+ u64 disk_bytenr = btrfs_stack_file_extent_disk_bytenr(stack_fi);
+ u64 num_bytes = btrfs_stack_file_extent_num_bytes(stack_fi);
+ u64 ram_bytes = btrfs_stack_file_extent_ram_bytes(stack_fi);
int extent_inserted = 0;
int ret;
@@ -2273,709 +2538,52 @@
*/
ret = __btrfs_drop_extents(trans, root, inode, path, file_pos,
file_pos + num_bytes, NULL, 0,
- 1, sizeof(*fi), &extent_inserted);
+ 1, sizeof(*stack_fi), &extent_inserted);
if (ret)
goto out;
if (!extent_inserted) {
- ins.objectid = btrfs_ino(BTRFS_I(inode));
+ ins.objectid = btrfs_ino(inode);
ins.offset = file_pos;
ins.type = BTRFS_EXTENT_DATA_KEY;
path->leave_spinning = 1;
ret = btrfs_insert_empty_item(trans, root, path, &ins,
- sizeof(*fi));
+ sizeof(*stack_fi));
if (ret)
goto out;
}
leaf = path->nodes[0];
- fi = btrfs_item_ptr(leaf, path->slots[0],
- struct btrfs_file_extent_item);
- btrfs_set_file_extent_generation(leaf, fi, trans->transid);
- btrfs_set_file_extent_type(leaf, fi, extent_type);
- btrfs_set_file_extent_disk_bytenr(leaf, fi, disk_bytenr);
- btrfs_set_file_extent_disk_num_bytes(leaf, fi, disk_num_bytes);
- btrfs_set_file_extent_offset(leaf, fi, 0);
- btrfs_set_file_extent_num_bytes(leaf, fi, num_bytes);
- btrfs_set_file_extent_ram_bytes(leaf, fi, ram_bytes);
- btrfs_set_file_extent_compression(leaf, fi, compression);
- btrfs_set_file_extent_encryption(leaf, fi, encryption);
- btrfs_set_file_extent_other_encoding(leaf, fi, other_encoding);
+ btrfs_set_stack_file_extent_generation(stack_fi, trans->transid);
+ write_extent_buffer(leaf, stack_fi,
+ btrfs_item_ptr_offset(leaf, path->slots[0]),
+ sizeof(struct btrfs_file_extent_item));
btrfs_mark_buffer_dirty(leaf);
btrfs_release_path(path);
- inode_add_bytes(inode, num_bytes);
+ inode_add_bytes(&inode->vfs_inode, num_bytes);
ins.objectid = disk_bytenr;
ins.offset = disk_num_bytes;
ins.type = BTRFS_EXTENT_ITEM_KEY;
- /*
- * Release the reserved range from inode dirty range map, as it is
- * already moved into delayed_ref_head
- */
- ret = btrfs_qgroup_release_data(inode, file_pos, ram_bytes);
- if (ret < 0)
- goto out;
- qg_released = ret;
- ret = btrfs_alloc_reserved_file_extent(trans, root,
- btrfs_ino(BTRFS_I(inode)),
- file_pos, qg_released, &ins);
-out:
- btrfs_free_path(path);
-
- return ret;
-}
-
-/* snapshot-aware defrag */
-struct sa_defrag_extent_backref {
- struct rb_node node;
- struct old_sa_defrag_extent *old;
- u64 root_id;
- u64 inum;
- u64 file_pos;
- u64 extent_offset;
- u64 num_bytes;
- u64 generation;
-};
-
-struct old_sa_defrag_extent {
- struct list_head list;
- struct new_sa_defrag_extent *new;
-
- u64 extent_offset;
- u64 bytenr;
- u64 offset;
- u64 len;
- int count;
-};
-
-struct new_sa_defrag_extent {
- struct rb_root root;
- struct list_head head;
- struct btrfs_path *path;
- struct inode *inode;
- u64 file_pos;
- u64 len;
- u64 bytenr;
- u64 disk_len;
- u8 compress_type;
-};
-
-static int backref_comp(struct sa_defrag_extent_backref *b1,
- struct sa_defrag_extent_backref *b2)
-{
- if (b1->root_id < b2->root_id)
- return -1;
- else if (b1->root_id > b2->root_id)
- return 1;
-
- if (b1->inum < b2->inum)
- return -1;
- else if (b1->inum > b2->inum)
- return 1;
-
- if (b1->file_pos < b2->file_pos)
- return -1;
- else if (b1->file_pos > b2->file_pos)
- return 1;
-
- /*
- * [------------------------------] ===> (a range of space)
- * |<--->| |<---->| =============> (fs/file tree A)
- * |<---------------------------->| ===> (fs/file tree B)
- *
- * A range of space can refer to two file extents in one tree while
- * refer to only one file extent in another tree.
- *
- * So we may process a disk offset more than one time(two extents in A)
- * and locate at the same extent(one extent in B), then insert two same
- * backrefs(both refer to the extent in B).
- */
- return 0;
-}
-
-static void backref_insert(struct rb_root *root,
- struct sa_defrag_extent_backref *backref)
-{
- struct rb_node **p = &root->rb_node;
- struct rb_node *parent = NULL;
- struct sa_defrag_extent_backref *entry;
- int ret;
-
- while (*p) {
- parent = *p;
- entry = rb_entry(parent, struct sa_defrag_extent_backref, node);
-
- ret = backref_comp(backref, entry);
- if (ret < 0)
- p = &(*p)->rb_left;
- else
- p = &(*p)->rb_right;
- }
-
- rb_link_node(&backref->node, parent, p);
- rb_insert_color(&backref->node, root);
-}
-
-/*
- * Note the backref might has changed, and in this case we just return 0.
- */
-static noinline int record_one_backref(u64 inum, u64 offset, u64 root_id,
- void *ctx)
-{
- struct btrfs_file_extent_item *extent;
- struct old_sa_defrag_extent *old = ctx;
- struct new_sa_defrag_extent *new = old->new;
- struct btrfs_path *path = new->path;
- struct btrfs_key key;
- struct btrfs_root *root;
- struct sa_defrag_extent_backref *backref;
- struct extent_buffer *leaf;
- struct inode *inode = new->inode;
- struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
- int slot;
- int ret;
- u64 extent_offset;
- u64 num_bytes;
-
- if (BTRFS_I(inode)->root->root_key.objectid == root_id &&
- inum == btrfs_ino(BTRFS_I(inode)))
- return 0;
-
- key.objectid = root_id;
- key.type = BTRFS_ROOT_ITEM_KEY;
- key.offset = (u64)-1;
-
- root = btrfs_read_fs_root_no_name(fs_info, &key);
- if (IS_ERR(root)) {
- if (PTR_ERR(root) == -ENOENT)
- return 0;
- WARN_ON(1);
- btrfs_debug(fs_info, "inum=%llu, offset=%llu, root_id=%llu",
- inum, offset, root_id);
- return PTR_ERR(root);
- }
-
- key.objectid = inum;
- key.type = BTRFS_EXTENT_DATA_KEY;
- if (offset > (u64)-1 << 32)
- key.offset = 0;
- else
- key.offset = offset;
-
- ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
- if (WARN_ON(ret < 0))
- return ret;
- ret = 0;
-
- while (1) {
- cond_resched();
-
- leaf = path->nodes[0];
- slot = path->slots[0];
-
- if (slot >= btrfs_header_nritems(leaf)) {
- ret = btrfs_next_leaf(root, path);
- if (ret < 0) {
- goto out;
- } else if (ret > 0) {
- ret = 0;
- goto out;
- }
- continue;
- }
-
- path->slots[0]++;
-
- btrfs_item_key_to_cpu(leaf, &key, slot);
-
- if (key.objectid > inum)
- goto out;
-
- if (key.objectid < inum || key.type != BTRFS_EXTENT_DATA_KEY)
- continue;
-
- extent = btrfs_item_ptr(leaf, slot,
- struct btrfs_file_extent_item);
-
- if (btrfs_file_extent_disk_bytenr(leaf, extent) != old->bytenr)
- continue;
-
- /*
- * 'offset' refers to the exact key.offset,
- * NOT the 'offset' field in btrfs_extent_data_ref, ie.
- * (key.offset - extent_offset).
- */
- if (key.offset != offset)
- continue;
-
- extent_offset = btrfs_file_extent_offset(leaf, extent);
- num_bytes = btrfs_file_extent_num_bytes(leaf, extent);
-
- if (extent_offset >= old->extent_offset + old->offset +
- old->len || extent_offset + num_bytes <=
- old->extent_offset + old->offset)
- continue;
- break;
- }
-
- backref = kmalloc(sizeof(*backref), GFP_NOFS);
- if (!backref) {
- ret = -ENOENT;
- goto out;
- }
-
- backref->root_id = root_id;
- backref->inum = inum;
- backref->file_pos = offset;
- backref->num_bytes = num_bytes;
- backref->extent_offset = extent_offset;
- backref->generation = btrfs_file_extent_generation(leaf, extent);
- backref->old = old;
- backref_insert(&new->root, backref);
- old->count++;
-out:
- btrfs_release_path(path);
- WARN_ON(ret);
- return ret;
-}
-
-static noinline bool record_extent_backrefs(struct btrfs_path *path,
- struct new_sa_defrag_extent *new)
-{
- struct btrfs_fs_info *fs_info = btrfs_sb(new->inode->i_sb);
- struct old_sa_defrag_extent *old, *tmp;
- int ret;
-
- new->path = path;
-
- list_for_each_entry_safe(old, tmp, &new->head, list) {
- ret = iterate_inodes_from_logical(old->bytenr +
- old->extent_offset, fs_info,
- path, record_one_backref,
- old, false);
- if (ret < 0 && ret != -ENOENT)
- return false;
-
- /* no backref to be processed for this extent */
- if (!old->count) {
- list_del(&old->list);
- kfree(old);
- }
- }
-
- if (list_empty(&new->head))
- return false;
-
- return true;
-}
-
-static int relink_is_mergable(struct extent_buffer *leaf,
- struct btrfs_file_extent_item *fi,
- struct new_sa_defrag_extent *new)
-{
- if (btrfs_file_extent_disk_bytenr(leaf, fi) != new->bytenr)
- return 0;
-
- if (btrfs_file_extent_type(leaf, fi) != BTRFS_FILE_EXTENT_REG)
- return 0;
-
- if (btrfs_file_extent_compression(leaf, fi) != new->compress_type)
- return 0;
-
- if (btrfs_file_extent_encryption(leaf, fi) ||
- btrfs_file_extent_other_encoding(leaf, fi))
- return 0;
-
- return 1;
-}
-
-/*
- * Note the backref might has changed, and in this case we just return 0.
- */
-static noinline int relink_extent_backref(struct btrfs_path *path,
- struct sa_defrag_extent_backref *prev,
- struct sa_defrag_extent_backref *backref)
-{
- struct btrfs_file_extent_item *extent;
- struct btrfs_file_extent_item *item;
- struct btrfs_ordered_extent *ordered;
- struct btrfs_trans_handle *trans;
- struct btrfs_root *root;
- struct btrfs_key key;
- struct extent_buffer *leaf;
- struct old_sa_defrag_extent *old = backref->old;
- struct new_sa_defrag_extent *new = old->new;
- struct btrfs_fs_info *fs_info = btrfs_sb(new->inode->i_sb);
- struct inode *inode;
- struct extent_state *cached = NULL;
- int ret = 0;
- u64 start;
- u64 len;
- u64 lock_start;
- u64 lock_end;
- bool merge = false;
- int index;
-
- if (prev && prev->root_id == backref->root_id &&
- prev->inum == backref->inum &&
- prev->file_pos + prev->num_bytes == backref->file_pos)
- merge = true;
-
- /* step 1: get root */
- key.objectid = backref->root_id;
- key.type = BTRFS_ROOT_ITEM_KEY;
- key.offset = (u64)-1;
-
- index = srcu_read_lock(&fs_info->subvol_srcu);
-
- root = btrfs_read_fs_root_no_name(fs_info, &key);
- if (IS_ERR(root)) {
- srcu_read_unlock(&fs_info->subvol_srcu, index);
- if (PTR_ERR(root) == -ENOENT)
- return 0;
- return PTR_ERR(root);
- }
-
- if (btrfs_root_readonly(root)) {
- srcu_read_unlock(&fs_info->subvol_srcu, index);
- return 0;
- }
-
- /* step 2: get inode */
- key.objectid = backref->inum;
- key.type = BTRFS_INODE_ITEM_KEY;
- key.offset = 0;
-
- inode = btrfs_iget(fs_info->sb, &key, root, NULL);
- if (IS_ERR(inode)) {
- srcu_read_unlock(&fs_info->subvol_srcu, index);
- return 0;
- }
-
- srcu_read_unlock(&fs_info->subvol_srcu, index);
-
- /* step 3: relink backref */
- lock_start = backref->file_pos;
- lock_end = backref->file_pos + backref->num_bytes - 1;
- lock_extent_bits(&BTRFS_I(inode)->io_tree, lock_start, lock_end,
- &cached);
-
- ordered = btrfs_lookup_first_ordered_extent(inode, lock_end);
- if (ordered) {
- btrfs_put_ordered_extent(ordered);
- goto out_unlock;
- }
-
- trans = btrfs_join_transaction(root);
- if (IS_ERR(trans)) {
- ret = PTR_ERR(trans);
- goto out_unlock;
- }
-
- key.objectid = backref->inum;
- key.type = BTRFS_EXTENT_DATA_KEY;
- key.offset = backref->file_pos;
-
- ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
- if (ret < 0) {
- goto out_free_path;
- } else if (ret > 0) {
- ret = 0;
- goto out_free_path;
- }
-
- extent = btrfs_item_ptr(path->nodes[0], path->slots[0],
- struct btrfs_file_extent_item);
-
- if (btrfs_file_extent_generation(path->nodes[0], extent) !=
- backref->generation)
- goto out_free_path;
-
- btrfs_release_path(path);
-
- start = backref->file_pos;
- if (backref->extent_offset < old->extent_offset + old->offset)
- start += old->extent_offset + old->offset -
- backref->extent_offset;
-
- len = min(backref->extent_offset + backref->num_bytes,
- old->extent_offset + old->offset + old->len);
- len -= max(backref->extent_offset, old->extent_offset + old->offset);
-
- ret = btrfs_drop_extents(trans, root, inode, start,
- start + len, 1);
+ ret = btrfs_inode_set_file_extent_range(inode, file_pos, ram_bytes);
if (ret)
- goto out_free_path;
-again:
- key.objectid = btrfs_ino(BTRFS_I(inode));
- key.type = BTRFS_EXTENT_DATA_KEY;
- key.offset = start;
-
- path->leave_spinning = 1;
- if (merge) {
- struct btrfs_file_extent_item *fi;
- u64 extent_len;
- struct btrfs_key found_key;
-
- ret = btrfs_search_slot(trans, root, &key, path, 0, 1);
- if (ret < 0)
- goto out_free_path;
-
- path->slots[0]--;
- leaf = path->nodes[0];
- btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);
-
- fi = btrfs_item_ptr(leaf, path->slots[0],
- struct btrfs_file_extent_item);
- extent_len = btrfs_file_extent_num_bytes(leaf, fi);
-
- if (extent_len + found_key.offset == start &&
- relink_is_mergable(leaf, fi, new)) {
- btrfs_set_file_extent_num_bytes(leaf, fi,
- extent_len + len);
- btrfs_mark_buffer_dirty(leaf);
- inode_add_bytes(inode, len);
-
- ret = 1;
- goto out_free_path;
- } else {
- merge = false;
- btrfs_release_path(path);
- goto again;
- }
- }
-
- ret = btrfs_insert_empty_item(trans, root, path, &key,
- sizeof(*extent));
- if (ret) {
- btrfs_abort_transaction(trans, ret);
- goto out_free_path;
- }
-
- leaf = path->nodes[0];
- item = btrfs_item_ptr(leaf, path->slots[0],
- struct btrfs_file_extent_item);
- btrfs_set_file_extent_disk_bytenr(leaf, item, new->bytenr);
- btrfs_set_file_extent_disk_num_bytes(leaf, item, new->disk_len);
- btrfs_set_file_extent_offset(leaf, item, start - new->file_pos);
- btrfs_set_file_extent_num_bytes(leaf, item, len);
- btrfs_set_file_extent_ram_bytes(leaf, item, new->len);
- btrfs_set_file_extent_generation(leaf, item, trans->transid);
- btrfs_set_file_extent_type(leaf, item, BTRFS_FILE_EXTENT_REG);
- btrfs_set_file_extent_compression(leaf, item, new->compress_type);
- btrfs_set_file_extent_encryption(leaf, item, 0);
- btrfs_set_file_extent_other_encoding(leaf, item, 0);
-
- btrfs_mark_buffer_dirty(leaf);
- inode_add_bytes(inode, len);
- btrfs_release_path(path);
-
- ret = btrfs_inc_extent_ref(trans, root, new->bytenr,
- new->disk_len, 0,
- backref->root_id, backref->inum,
- new->file_pos); /* start - extent_offset */
- if (ret) {
- btrfs_abort_transaction(trans, ret);
- goto out_free_path;
- }
-
- ret = 1;
-out_free_path:
- btrfs_release_path(path);
- path->leave_spinning = 0;
- btrfs_end_transaction(trans);
-out_unlock:
- unlock_extent_cached(&BTRFS_I(inode)->io_tree, lock_start, lock_end,
- &cached);
- iput(inode);
- return ret;
-}
-
-static void free_sa_defrag_extent(struct new_sa_defrag_extent *new)
-{
- struct old_sa_defrag_extent *old, *tmp;
-
- if (!new)
- return;
-
- list_for_each_entry_safe(old, tmp, &new->head, list) {
- kfree(old);
- }
- kfree(new);
-}
-
-static void relink_file_extents(struct new_sa_defrag_extent *new)
-{
- struct btrfs_fs_info *fs_info = btrfs_sb(new->inode->i_sb);
- struct btrfs_path *path;
- struct sa_defrag_extent_backref *backref;
- struct sa_defrag_extent_backref *prev = NULL;
- struct inode *inode;
- struct rb_node *node;
- int ret;
-
- inode = new->inode;
-
- path = btrfs_alloc_path();
- if (!path)
- return;
-
- if (!record_extent_backrefs(path, new)) {
- btrfs_free_path(path);
goto out;
- }
- btrfs_release_path(path);
- while (1) {
- node = rb_first(&new->root);
- if (!node)
- break;
- rb_erase(node, &new->root);
-
- backref = rb_entry(node, struct sa_defrag_extent_backref, node);
-
- ret = relink_extent_backref(path, prev, backref);
- WARN_ON(ret < 0);
-
- kfree(prev);
-
- if (ret == 1)
- prev = backref;
- else
- prev = NULL;
- cond_resched();
- }
- kfree(prev);
-
- btrfs_free_path(path);
+ ret = btrfs_alloc_reserved_file_extent(trans, root, btrfs_ino(inode),
+ file_pos, qgroup_reserved, &ins);
out:
- free_sa_defrag_extent(new);
-
- atomic_dec(&fs_info->defrag_running);
- wake_up(&fs_info->transaction_wait);
-}
-
-static struct new_sa_defrag_extent *
-record_old_file_extents(struct inode *inode,
- struct btrfs_ordered_extent *ordered)
-{
- struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
- struct btrfs_root *root = BTRFS_I(inode)->root;
- struct btrfs_path *path;
- struct btrfs_key key;
- struct old_sa_defrag_extent *old;
- struct new_sa_defrag_extent *new;
- int ret;
-
- new = kmalloc(sizeof(*new), GFP_NOFS);
- if (!new)
- return NULL;
-
- new->inode = inode;
- new->file_pos = ordered->file_offset;
- new->len = ordered->len;
- new->bytenr = ordered->start;
- new->disk_len = ordered->disk_len;
- new->compress_type = ordered->compress_type;
- new->root = RB_ROOT;
- INIT_LIST_HEAD(&new->head);
-
- path = btrfs_alloc_path();
- if (!path)
- goto out_kfree;
-
- key.objectid = btrfs_ino(BTRFS_I(inode));
- key.type = BTRFS_EXTENT_DATA_KEY;
- key.offset = new->file_pos;
-
- ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
- if (ret < 0)
- goto out_free_path;
- if (ret > 0 && path->slots[0] > 0)
- path->slots[0]--;
-
- /* find out all the old extents for the file range */
- while (1) {
- struct btrfs_file_extent_item *extent;
- struct extent_buffer *l;
- int slot;
- u64 num_bytes;
- u64 offset;
- u64 end;
- u64 disk_bytenr;
- u64 extent_offset;
-
- l = path->nodes[0];
- slot = path->slots[0];
-
- if (slot >= btrfs_header_nritems(l)) {
- ret = btrfs_next_leaf(root, path);
- if (ret < 0)
- goto out_free_path;
- else if (ret > 0)
- break;
- continue;
- }
-
- btrfs_item_key_to_cpu(l, &key, slot);
-
- if (key.objectid != btrfs_ino(BTRFS_I(inode)))
- break;
- if (key.type != BTRFS_EXTENT_DATA_KEY)
- break;
- if (key.offset >= new->file_pos + new->len)
- break;
-
- extent = btrfs_item_ptr(l, slot, struct btrfs_file_extent_item);
-
- num_bytes = btrfs_file_extent_num_bytes(l, extent);
- if (key.offset + num_bytes < new->file_pos)
- goto next;
-
- disk_bytenr = btrfs_file_extent_disk_bytenr(l, extent);
- if (!disk_bytenr)
- goto next;
-
- extent_offset = btrfs_file_extent_offset(l, extent);
-
- old = kmalloc(sizeof(*old), GFP_NOFS);
- if (!old)
- goto out_free_path;
-
- offset = max(new->file_pos, key.offset);
- end = min(new->file_pos + new->len, key.offset + num_bytes);
-
- old->bytenr = disk_bytenr;
- old->extent_offset = extent_offset;
- old->offset = offset - key.offset;
- old->len = end - offset;
- old->new = new;
- old->count = 0;
- list_add_tail(&old->list, &new->head);
-next:
- path->slots[0]++;
- cond_resched();
- }
-
btrfs_free_path(path);
- atomic_inc(&fs_info->defrag_running);
- return new;
-
-out_free_path:
- btrfs_free_path(path);
-out_kfree:
- free_sa_defrag_extent(new);
- return NULL;
+ return ret;
}
static void btrfs_release_delalloc_bytes(struct btrfs_fs_info *fs_info,
u64 start, u64 len)
{
- struct btrfs_block_group_cache *cache;
+ struct btrfs_block_group *cache;
cache = btrfs_lookup_block_group(fs_info, start);
ASSERT(cache);
@@ -2987,7 +2595,33 @@
btrfs_put_block_group(cache);
}
-/* as ordered data IO finishes, this gets called so we can finish
+static int insert_ordered_extent_file_extent(struct btrfs_trans_handle *trans,
+ struct btrfs_ordered_extent *oe)
+{
+ struct btrfs_file_extent_item stack_fi;
+ u64 logical_len;
+
+ memset(&stack_fi, 0, sizeof(stack_fi));
+ btrfs_set_stack_file_extent_type(&stack_fi, BTRFS_FILE_EXTENT_REG);
+ btrfs_set_stack_file_extent_disk_bytenr(&stack_fi, oe->disk_bytenr);
+ btrfs_set_stack_file_extent_disk_num_bytes(&stack_fi,
+ oe->disk_num_bytes);
+ if (test_bit(BTRFS_ORDERED_TRUNCATED, &oe->flags))
+ logical_len = oe->truncated_len;
+ else
+ logical_len = oe->num_bytes;
+ btrfs_set_stack_file_extent_num_bytes(&stack_fi, logical_len);
+ btrfs_set_stack_file_extent_ram_bytes(&stack_fi, logical_len);
+ btrfs_set_stack_file_extent_compression(&stack_fi, oe->compress_type);
+ /* Encryption and other encoding is reserved and all 0 */
+
+ return insert_reserved_file_extent(trans, BTRFS_I(oe->inode),
+ oe->file_offset, &stack_fi,
+ oe->qgroup_rsv);
+}
+
+/*
+ * As ordered data IO finishes, this gets called so we can finish
* an ordered extent if the range of bytes in the file it covers are
* fully written.
*/
@@ -2999,32 +2633,33 @@
struct btrfs_trans_handle *trans = NULL;
struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
struct extent_state *cached_state = NULL;
- struct new_sa_defrag_extent *new = NULL;
+ u64 start, end;
int compress_type = 0;
int ret = 0;
- u64 logical_len = ordered_extent->len;
- bool nolock;
+ u64 logical_len = ordered_extent->num_bytes;
+ bool freespace_inode;
bool truncated = false;
bool range_locked = false;
bool clear_new_delalloc_bytes = false;
bool clear_reserved_extent = true;
+ unsigned int clear_bits;
+
+ start = ordered_extent->file_offset;
+ end = start + ordered_extent->num_bytes - 1;
if (!test_bit(BTRFS_ORDERED_NOCOW, &ordered_extent->flags) &&
!test_bit(BTRFS_ORDERED_PREALLOC, &ordered_extent->flags) &&
!test_bit(BTRFS_ORDERED_DIRECT, &ordered_extent->flags))
clear_new_delalloc_bytes = true;
- nolock = btrfs_is_free_space_inode(BTRFS_I(inode));
+ freespace_inode = btrfs_is_free_space_inode(BTRFS_I(inode));
if (test_bit(BTRFS_ORDERED_IOERR, &ordered_extent->flags)) {
ret = -EIO;
goto out;
}
- btrfs_free_io_failure_record(BTRFS_I(inode),
- ordered_extent->file_offset,
- ordered_extent->file_offset +
- ordered_extent->len - 1);
+ btrfs_free_io_failure_record(BTRFS_I(inode), start, end);
if (test_bit(BTRFS_ORDERED_TRUNCATED, &ordered_extent->flags)) {
truncated = true;
@@ -3037,16 +2672,9 @@
if (test_bit(BTRFS_ORDERED_NOCOW, &ordered_extent->flags)) {
BUG_ON(!list_empty(&ordered_extent->list)); /* Logic error */
- /*
- * For mwrite(mmap + memset to write) case, we still reserve
- * space for NOCOW range.
- * As NOCOW won't cause a new delayed ref, just free the space
- */
- btrfs_qgroup_free_data(inode, NULL, ordered_extent->file_offset,
- ordered_extent->len);
- btrfs_ordered_update_i_size(inode, 0, ordered_extent);
- if (nolock)
- trans = btrfs_join_transaction_nolock(root);
+ btrfs_inode_safe_disk_i_size_write(inode, 0);
+ if (freespace_inode)
+ trans = btrfs_join_transaction_spacecache(root);
else
trans = btrfs_join_transaction(root);
if (IS_ERR(trans)) {
@@ -3062,26 +2690,10 @@
}
range_locked = true;
- lock_extent_bits(io_tree, ordered_extent->file_offset,
- ordered_extent->file_offset + ordered_extent->len - 1,
- &cached_state);
+ lock_extent_bits(io_tree, start, end, &cached_state);
- ret = test_range_bit(io_tree, ordered_extent->file_offset,
- ordered_extent->file_offset + ordered_extent->len - 1,
- EXTENT_DEFRAG, 0, cached_state);
- if (ret) {
- u64 last_snapshot = btrfs_root_last_snapshot(&root->root_item);
- if (0 && last_snapshot >= BTRFS_I(inode)->generation)
- /* the inode is shared */
- new = record_old_file_extents(inode, ordered_extent);
-
- clear_extent_bit(io_tree, ordered_extent->file_offset,
- ordered_extent->file_offset + ordered_extent->len - 1,
- EXTENT_DEFRAG, 0, 0, &cached_state);
- }
-
- if (nolock)
- trans = btrfs_join_transaction_nolock(root);
+ if (freespace_inode)
+ trans = btrfs_join_transaction_spacecache(root);
else
trans = btrfs_join_transaction(root);
if (IS_ERR(trans)) {
@@ -3096,43 +2708,35 @@
compress_type = ordered_extent->compress_type;
if (test_bit(BTRFS_ORDERED_PREALLOC, &ordered_extent->flags)) {
BUG_ON(compress_type);
- btrfs_qgroup_free_data(inode, NULL, ordered_extent->file_offset,
- ordered_extent->len);
ret = btrfs_mark_extent_written(trans, BTRFS_I(inode),
ordered_extent->file_offset,
ordered_extent->file_offset +
logical_len);
} else {
BUG_ON(root == fs_info->tree_root);
- ret = insert_reserved_file_extent(trans, inode,
- ordered_extent->file_offset,
- ordered_extent->start,
- ordered_extent->disk_len,
- logical_len, logical_len,
- compress_type, 0, 0,
- BTRFS_FILE_EXTENT_REG);
+ ret = insert_ordered_extent_file_extent(trans, ordered_extent);
if (!ret) {
clear_reserved_extent = false;
btrfs_release_delalloc_bytes(fs_info,
- ordered_extent->start,
- ordered_extent->disk_len);
+ ordered_extent->disk_bytenr,
+ ordered_extent->disk_num_bytes);
}
}
unpin_extent_cache(&BTRFS_I(inode)->extent_tree,
- ordered_extent->file_offset, ordered_extent->len,
- trans->transid);
+ ordered_extent->file_offset,
+ ordered_extent->num_bytes, trans->transid);
if (ret < 0) {
btrfs_abort_transaction(trans, ret);
goto out;
}
- ret = add_pending_csums(trans, inode, &ordered_extent->list);
+ ret = add_pending_csums(trans, &ordered_extent->list);
if (ret) {
btrfs_abort_transaction(trans, ret);
goto out;
}
- btrfs_ordered_update_i_size(inode, 0, ordered_extent);
+ btrfs_inode_safe_disk_i_size_write(inode, 0);
ret = btrfs_update_inode_fallback(trans, root, inode);
if (ret) { /* -ENOMEM or corruption */
btrfs_abort_transaction(trans, ret);
@@ -3140,27 +2744,20 @@
}
ret = 0;
out:
- if (range_locked || clear_new_delalloc_bytes) {
- unsigned int clear_bits = 0;
-
- if (range_locked)
- clear_bits |= EXTENT_LOCKED;
- if (clear_new_delalloc_bytes)
- clear_bits |= EXTENT_DELALLOC_NEW;
- clear_extent_bit(&BTRFS_I(inode)->io_tree,
- ordered_extent->file_offset,
- ordered_extent->file_offset +
- ordered_extent->len - 1,
- clear_bits,
- (clear_bits & EXTENT_LOCKED) ? 1 : 0,
- 0, &cached_state);
- }
+ clear_bits = EXTENT_DEFRAG;
+ if (range_locked)
+ clear_bits |= EXTENT_LOCKED;
+ if (clear_new_delalloc_bytes)
+ clear_bits |= EXTENT_DELALLOC_NEW;
+ clear_extent_bit(&BTRFS_I(inode)->io_tree, start, end, clear_bits,
+ (clear_bits & EXTENT_LOCKED) ? 1 : 0, 0,
+ &cached_state);
if (trans)
btrfs_end_transaction(trans);
if (ret || truncated) {
- u64 start, end;
+ u64 unwritten_start = start;
/*
* If we failed to finish this ordered extent for any reason we
@@ -3175,14 +2772,11 @@
mapping_set_error(ordered_extent->inode->i_mapping, -EIO);
if (truncated)
- start = ordered_extent->file_offset + logical_len;
- else
- start = ordered_extent->file_offset;
- end = ordered_extent->file_offset + ordered_extent->len - 1;
- clear_extent_uptodate(io_tree, start, end, NULL);
+ unwritten_start += logical_len;
+ clear_extent_uptodate(io_tree, unwritten_start, end, NULL);
/* Drop the cache for the part of the extent we didn't write. */
- btrfs_drop_extent_cache(BTRFS_I(inode), start, end, 0);
+ btrfs_drop_extent_cache(BTRFS_I(inode), unwritten_start, end, 0);
/*
* If the ordered extent had an IOERR or something else went
@@ -3197,28 +2791,27 @@
if ((ret || !logical_len) &&
clear_reserved_extent &&
!test_bit(BTRFS_ORDERED_NOCOW, &ordered_extent->flags) &&
- !test_bit(BTRFS_ORDERED_PREALLOC, &ordered_extent->flags))
+ !test_bit(BTRFS_ORDERED_PREALLOC, &ordered_extent->flags)) {
+ /*
+ * Discard the range before returning it back to the
+ * free space pool
+ */
+ if (ret && btrfs_test_opt(fs_info, DISCARD_SYNC))
+ btrfs_discard_extent(fs_info,
+ ordered_extent->disk_bytenr,
+ ordered_extent->disk_num_bytes,
+ NULL);
btrfs_free_reserved_extent(fs_info,
- ordered_extent->start,
- ordered_extent->disk_len, 1);
+ ordered_extent->disk_bytenr,
+ ordered_extent->disk_num_bytes, 1);
+ }
}
-
/*
* This needs to be done to make sure anybody waiting knows we are done
* updating everything for this ordered extent.
*/
- btrfs_remove_ordered_extent(inode, ordered_extent);
-
- /* for snapshot-aware defrag */
- if (new) {
- if (ret) {
- free_sa_defrag_extent(new);
- atomic_dec(&fs_info->defrag_running);
- } else {
- relink_file_extents(new);
- }
- }
+ btrfs_remove_ordered_extent(BTRFS_I(inode), ordered_extent);
/* once for us */
btrfs_put_ordered_extent(ordered_extent);
@@ -3235,14 +2828,13 @@
btrfs_finish_ordered_io(ordered_extent);
}
-static void btrfs_writepage_end_io_hook(struct page *page, u64 start, u64 end,
- struct extent_state *state, int uptodate)
+void btrfs_writepage_endio_finish_ordered(struct page *page, u64 start,
+ u64 end, int uptodate)
{
- struct inode *inode = page->mapping->host;
- struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+ struct btrfs_inode *inode = BTRFS_I(page->mapping->host);
+ struct btrfs_fs_info *fs_info = inode->root->fs_info;
struct btrfs_ordered_extent *ordered_extent = NULL;
struct btrfs_workqueue *wq;
- btrfs_work_func_t func;
trace_btrfs_writepage_end_io_hook(page, start, end, uptodate);
@@ -3251,34 +2843,34 @@
end - start + 1, uptodate))
return;
- if (btrfs_is_free_space_inode(BTRFS_I(inode))) {
+ if (btrfs_is_free_space_inode(inode))
wq = fs_info->endio_freespace_worker;
- func = btrfs_freespace_write_helper;
- } else {
+ else
wq = fs_info->endio_write_workers;
- func = btrfs_endio_write_helper;
- }
- btrfs_init_work(&ordered_extent->work, func, finish_ordered_fn, NULL,
- NULL);
+ btrfs_init_work(&ordered_extent->work, finish_ordered_fn, NULL, NULL);
btrfs_queue_work(wq, &ordered_extent->work);
}
-static int __readpage_endio_check(struct inode *inode,
- struct btrfs_io_bio *io_bio,
- int icsum, struct page *page,
- int pgoff, u64 start, size_t len)
+static int check_data_csum(struct inode *inode, struct btrfs_io_bio *io_bio,
+ int icsum, struct page *page, int pgoff, u64 start,
+ size_t len)
{
+ struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+ SHASH_DESC_ON_STACK(shash, fs_info->csum_shash);
char *kaddr;
- u32 csum_expected;
- u32 csum = ~(u32)0;
+ u16 csum_size = btrfs_super_csum_size(fs_info->super_copy);
+ u8 *csum_expected;
+ u8 csum[BTRFS_CSUM_SIZE];
- csum_expected = *(((u32 *)io_bio->csum) + icsum);
+ csum_expected = ((u8 *)io_bio->csum) + icsum * csum_size;
kaddr = kmap_atomic(page);
- csum = btrfs_csum_data(kaddr + pgoff, csum, len);
- btrfs_csum_final(csum, (u8 *)&csum);
- if (csum != csum_expected)
+ shash->tfm = fs_info->csum_shash;
+
+ crypto_shash_digest(shash, kaddr + pgoff, len, csum);
+
+ if (memcmp(csum, csum_expected, csum_size))
goto zeroit;
kunmap_atomic(kaddr);
@@ -3286,6 +2878,9 @@
zeroit:
btrfs_print_data_csum_error(BTRFS_I(inode), start, csum, csum_expected,
io_bio->mirror_num);
+ if (io_bio->device)
+ btrfs_dev_stat_inc_and_print(io_bio->device,
+ BTRFS_DEV_STAT_CORRUPTION_ERRS);
memset(kaddr + pgoff, 1, len);
flush_dcache_page(page);
kunmap_atomic(kaddr);
@@ -3297,9 +2892,8 @@
* if there's a match, we allow the bio to finish. If not, the code in
* extent_io.c will try to find good copies for us.
*/
-static int btrfs_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
- u64 phy_offset, struct page *page,
- u64 start, u64 end, int mirror)
+int btrfs_verify_data_csum(struct btrfs_io_bio *io_bio, u64 phy_offset,
+ struct page *page, u64 start, u64 end, int mirror)
{
size_t offset = start - page_offset(page);
struct inode *inode = page->mapping->host;
@@ -3321,8 +2915,8 @@
}
phy_offset >>= inode->i_sb->s_blocksize_bits;
- return __readpage_endio_check(inode, io_bio, phy_offset, page, offset,
- start, (size_t)(end - start + 1));
+ return check_data_csum(inode, io_bio, phy_offset, page, offset, start,
+ (size_t)(end - start + 1));
}
/*
@@ -3343,10 +2937,35 @@
if (atomic_add_unless(&inode->i_count, -1, 1))
return;
+ atomic_inc(&fs_info->nr_delayed_iputs);
spin_lock(&fs_info->delayed_iput_lock);
ASSERT(list_empty(&binode->delayed_iput));
list_add_tail(&binode->delayed_iput, &fs_info->delayed_iputs);
spin_unlock(&fs_info->delayed_iput_lock);
+ if (!test_bit(BTRFS_FS_CLEANER_RUNNING, &fs_info->flags))
+ wake_up_process(fs_info->cleaner_kthread);
+}
+
+static void run_delayed_iput_locked(struct btrfs_fs_info *fs_info,
+ struct btrfs_inode *inode)
+{
+ list_del_init(&inode->delayed_iput);
+ spin_unlock(&fs_info->delayed_iput_lock);
+ iput(&inode->vfs_inode);
+ if (atomic_dec_and_test(&fs_info->nr_delayed_iputs))
+ wake_up(&fs_info->delayed_iputs_wait);
+ spin_lock(&fs_info->delayed_iput_lock);
+}
+
+static void btrfs_run_delayed_iput(struct btrfs_fs_info *fs_info,
+ struct btrfs_inode *inode)
+{
+ if (!list_empty(&inode->delayed_iput)) {
+ spin_lock(&fs_info->delayed_iput_lock);
+ if (!list_empty(&inode->delayed_iput))
+ run_delayed_iput_locked(fs_info, inode);
+ spin_unlock(&fs_info->delayed_iput_lock);
+ }
}
void btrfs_run_delayed_iputs(struct btrfs_fs_info *fs_info)
@@ -3358,12 +2977,29 @@
inode = list_first_entry(&fs_info->delayed_iputs,
struct btrfs_inode, delayed_iput);
- list_del_init(&inode->delayed_iput);
- spin_unlock(&fs_info->delayed_iput_lock);
- iput(&inode->vfs_inode);
- spin_lock(&fs_info->delayed_iput_lock);
+ run_delayed_iput_locked(fs_info, inode);
+ cond_resched_lock(&fs_info->delayed_iput_lock);
}
spin_unlock(&fs_info->delayed_iput_lock);
+}
+
+/**
+ * btrfs_wait_on_delayed_iputs - wait on the delayed iputs to be done running
+ * @fs_info - the fs_info for this fs
+ * @return - EINTR if we were killed, 0 if nothing's pending
+ *
+ * This will wait on any delayed iputs that are currently running with KILLABLE
+ * set. Once they are all done running we will return, unless we are killed in
+ * which case we return EINTR. This helps in user operations like fallocate etc
+ * that might get blocked on the iputs.
+ */
+int btrfs_wait_on_delayed_iputs(struct btrfs_fs_info *fs_info)
+{
+ int ret = wait_event_killable(fs_info->delayed_iputs_wait,
+ atomic_read(&fs_info->nr_delayed_iputs) == 0);
+ if (ret)
+ return -EINTR;
+ return 0;
}
/*
@@ -3471,14 +3107,13 @@
found_key.objectid = found_key.offset;
found_key.type = BTRFS_INODE_ITEM_KEY;
found_key.offset = 0;
- inode = btrfs_iget(fs_info->sb, &found_key, root, NULL);
+ inode = btrfs_iget(fs_info->sb, last_objectid, root);
ret = PTR_ERR_OR_ZERO(inode);
if (ret && ret != -ENOENT)
goto out;
if (ret == -ENOENT && root == fs_info->tree_root) {
struct btrfs_root *dead_root;
- struct btrfs_fs_info *fs_info = root->fs_info;
int is_dead_root = 0;
/*
@@ -3490,18 +3125,16 @@
* orphan must not get deleted.
* find_dead_roots already ran before us, so if this
* is a snapshot deletion, we should find the root
- * in the dead_roots list
+ * in the fs_roots radix tree.
*/
- spin_lock(&fs_info->trans_lock);
- list_for_each_entry(dead_root, &fs_info->dead_roots,
- root_list) {
- if (dead_root->root_key.objectid ==
- found_key.objectid) {
- is_dead_root = 1;
- break;
- }
- }
- spin_unlock(&fs_info->trans_lock);
+
+ spin_lock(&fs_info->fs_roots_radix_lock);
+ dead_root = radix_tree_lookup(&fs_info->fs_roots_radix,
+ (unsigned long)found_key.objectid);
+ if (dead_root && btrfs_root_refs(&dead_root->root_item) == 0)
+ is_dead_root = 1;
+ spin_unlock(&fs_info->fs_roots_radix_lock);
+
if (is_dead_root) {
/* prevent this orphan from being found again */
key.offset = found_key.objectid - 1;
@@ -3551,8 +3184,6 @@
/* this will do delete_inode and everything for us */
iput(inode);
- if (ret)
- goto out;
}
/* release the path since we're done with it */
btrfs_release_path(path);
@@ -3694,6 +3325,8 @@
i_uid_write(inode, btrfs_inode_uid(leaf, inode_item));
i_gid_write(inode, btrfs_inode_gid(leaf, inode_item));
btrfs_i_size_write(BTRFS_I(inode), btrfs_inode_size(leaf, inode_item));
+ btrfs_inode_set_file_extent_range(BTRFS_I(inode), 0,
+ round_up(i_size_read(inode), fs_info->sectorsize));
inode->i_atime.tv_sec = btrfs_timespec_sec(leaf, &inode_item->atime);
inode->i_atime.tv_nsec = btrfs_timespec_nsec(leaf, &inode_item->atime);
@@ -3764,21 +3397,14 @@
* inode is not a directory, logging its parent unnecessarily.
*/
BTRFS_I(inode)->last_unlink_trans = BTRFS_I(inode)->last_trans;
+
/*
- * Similar reasoning for last_link_trans, needs to be set otherwise
- * for a case like the following:
- *
- * mkdir A
- * touch foo
- * ln foo A/bar
- * echo 2 > /proc/sys/vm/drop_caches
- * fsync foo
- * <power failure>
- *
- * Would result in link bar and directory A not existing after the power
- * failure.
+ * Same logic as for last_unlink_trans. We don't persist the generation
+ * of the last transaction where this inode was used for a reflink
+ * operation, so after eviction and reloading the inode we must be
+ * pessimistic and assume the last transaction that modified the inode.
*/
- BTRFS_I(inode)->last_link_trans = BTRFS_I(inode)->last_trans;
+ BTRFS_I(inode)->last_reflink_trans = BTRFS_I(inode)->last_trans;
path->slots[0]++;
if (inode->i_nlink != 1 ||
@@ -3827,7 +3453,6 @@
switch (inode->i_mode & S_IFMT) {
case S_IFREG:
inode->i_mapping->a_ops = &btrfs_aops;
- BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
inode->i_fop = &btrfs_file_operations;
inode->i_op = &btrfs_file_inode_operations;
break;
@@ -3838,7 +3463,7 @@
case S_IFLNK:
inode->i_op = &btrfs_symlink_inode_operations;
inode_nohighmem(inode);
- inode->i_mapping->a_ops = &btrfs_symlink_aops;
+ inode->i_mapping->a_ops = &btrfs_aops;
break;
default:
inode->i_op = &btrfs_special_inode_operations;
@@ -3860,45 +3485,42 @@
{
struct btrfs_map_token token;
- btrfs_init_map_token(&token);
+ btrfs_init_map_token(&token, leaf);
- btrfs_set_token_inode_uid(leaf, item, i_uid_read(inode), &token);
- btrfs_set_token_inode_gid(leaf, item, i_gid_read(inode), &token);
- btrfs_set_token_inode_size(leaf, item, BTRFS_I(inode)->disk_i_size,
- &token);
- btrfs_set_token_inode_mode(leaf, item, inode->i_mode, &token);
- btrfs_set_token_inode_nlink(leaf, item, inode->i_nlink, &token);
+ btrfs_set_token_inode_uid(&token, item, i_uid_read(inode));
+ btrfs_set_token_inode_gid(&token, item, i_gid_read(inode));
+ btrfs_set_token_inode_size(&token, item, BTRFS_I(inode)->disk_i_size);
+ btrfs_set_token_inode_mode(&token, item, inode->i_mode);
+ btrfs_set_token_inode_nlink(&token, item, inode->i_nlink);
- btrfs_set_token_timespec_sec(leaf, &item->atime,
- inode->i_atime.tv_sec, &token);
- btrfs_set_token_timespec_nsec(leaf, &item->atime,
- inode->i_atime.tv_nsec, &token);
+ btrfs_set_token_timespec_sec(&token, &item->atime,
+ inode->i_atime.tv_sec);
+ btrfs_set_token_timespec_nsec(&token, &item->atime,
+ inode->i_atime.tv_nsec);
- btrfs_set_token_timespec_sec(leaf, &item->mtime,
- inode->i_mtime.tv_sec, &token);
- btrfs_set_token_timespec_nsec(leaf, &item->mtime,
- inode->i_mtime.tv_nsec, &token);
+ btrfs_set_token_timespec_sec(&token, &item->mtime,
+ inode->i_mtime.tv_sec);
+ btrfs_set_token_timespec_nsec(&token, &item->mtime,
+ inode->i_mtime.tv_nsec);
- btrfs_set_token_timespec_sec(leaf, &item->ctime,
- inode->i_ctime.tv_sec, &token);
- btrfs_set_token_timespec_nsec(leaf, &item->ctime,
- inode->i_ctime.tv_nsec, &token);
+ btrfs_set_token_timespec_sec(&token, &item->ctime,
+ inode->i_ctime.tv_sec);
+ btrfs_set_token_timespec_nsec(&token, &item->ctime,
+ inode->i_ctime.tv_nsec);
- btrfs_set_token_timespec_sec(leaf, &item->otime,
- BTRFS_I(inode)->i_otime.tv_sec, &token);
- btrfs_set_token_timespec_nsec(leaf, &item->otime,
- BTRFS_I(inode)->i_otime.tv_nsec, &token);
+ btrfs_set_token_timespec_sec(&token, &item->otime,
+ BTRFS_I(inode)->i_otime.tv_sec);
+ btrfs_set_token_timespec_nsec(&token, &item->otime,
+ BTRFS_I(inode)->i_otime.tv_nsec);
- btrfs_set_token_inode_nbytes(leaf, item, inode_get_bytes(inode),
- &token);
- btrfs_set_token_inode_generation(leaf, item, BTRFS_I(inode)->generation,
- &token);
- btrfs_set_token_inode_sequence(leaf, item, inode_peek_iversion(inode),
- &token);
- btrfs_set_token_inode_transid(leaf, item, trans->transid, &token);
- btrfs_set_token_inode_rdev(leaf, item, inode->i_rdev, &token);
- btrfs_set_token_inode_flags(leaf, item, BTRFS_I(inode)->flags, &token);
- btrfs_set_token_inode_block_group(leaf, item, 0, &token);
+ btrfs_set_token_inode_nbytes(&token, item, inode_get_bytes(inode));
+ btrfs_set_token_inode_generation(&token, item,
+ BTRFS_I(inode)->generation);
+ btrfs_set_token_inode_sequence(&token, item, inode_peek_iversion(inode));
+ btrfs_set_token_inode_transid(&token, item, trans->transid);
+ btrfs_set_token_inode_rdev(&token, item, inode->i_rdev);
+ btrfs_set_token_inode_flags(&token, item, BTRFS_I(inode)->flags);
+ btrfs_set_token_inode_block_group(&token, item, 0);
}
/*
@@ -3931,7 +3553,7 @@
fill_inode_item(trans, leaf, inode_item, inode);
btrfs_mark_buffer_dirty(leaf);
- btrfs_set_inode_last_trans(trans, inode);
+ btrfs_set_inode_last_trans(trans, BTRFS_I(inode));
ret = 0;
failed:
btrfs_free_path(path);
@@ -3961,7 +3583,7 @@
ret = btrfs_delayed_update_inode(trans, root, inode);
if (!ret)
- btrfs_set_inode_last_trans(trans, inode);
+ btrfs_set_inode_last_trans(trans, BTRFS_I(inode));
return ret;
}
@@ -3994,9 +3616,7 @@
struct btrfs_fs_info *fs_info = root->fs_info;
struct btrfs_path *path;
int ret = 0;
- struct extent_buffer *leaf;
struct btrfs_dir_item *di;
- struct btrfs_key key;
u64 index;
u64 ino = btrfs_ino(inode);
u64 dir_ino = btrfs_ino(dir);
@@ -4010,16 +3630,10 @@
path->leave_spinning = 1;
di = btrfs_lookup_dir_item(trans, root, path, dir_ino,
name, name_len, -1);
- if (IS_ERR(di)) {
- ret = PTR_ERR(di);
+ if (IS_ERR_OR_NULL(di)) {
+ ret = di ? PTR_ERR(di) : -ENOENT;
goto err;
}
- if (!di) {
- ret = -ENOENT;
- goto err;
- }
- leaf = path->nodes[0];
- btrfs_dir_item_key_to_cpu(leaf, di, &key);
ret = btrfs_delete_one_dir_name(trans, root, path, di);
if (ret)
goto err;
@@ -4072,6 +3686,17 @@
ret = 0;
else if (ret)
btrfs_abort_transaction(trans, ret);
+
+ /*
+ * If we have a pending delayed iput we could end up with the final iput
+ * being run in btrfs-cleaner context. If we have enough of these built
+ * up we can end up burning a lot of time in btrfs-cleaner without any
+ * way to throttle the unlinks. Since we're currently holding a ref on
+ * the inode we can run the delayed iput here without any issues as the
+ * final iput won't be done until after we drop the ref we're currently
+ * holding.
+ */
+ btrfs_run_delayed_iput(fs_info, inode);
err:
btrfs_free_path(path);
if (ret)
@@ -4120,7 +3745,7 @@
* 1 for the inode ref
* 1 for the inode
*/
- return btrfs_start_transaction_fallback_global_rsv(root, 5, 5);
+ return btrfs_start_transaction_fallback_global_rsv(root, 5);
}
static int btrfs_unlink(struct inode *dir, struct dentry *dentry)
@@ -4187,10 +3812,7 @@
di = btrfs_lookup_dir_item(trans, root, path, dir_ino,
name, name_len, -1);
if (IS_ERR_OR_NULL(di)) {
- if (!di)
- ret = -ENOENT;
- else
- ret = PTR_ERR(di);
+ ret = di ? PTR_ERR(di) : -ENOENT;
goto out;
}
@@ -4393,18 +4015,24 @@
* again is not run concurrently.
*/
spin_lock(&dest->root_item_lock);
- root_flags = btrfs_root_flags(&dest->root_item);
- if (dest->send_in_progress == 0) {
- btrfs_set_root_flags(&dest->root_item,
- root_flags | BTRFS_ROOT_SUBVOL_DEAD);
- spin_unlock(&dest->root_item_lock);
- } else {
+ if (dest->send_in_progress) {
spin_unlock(&dest->root_item_lock);
btrfs_warn(fs_info,
"attempt to delete subvolume %llu during send",
dest->root_key.objectid);
return -EPERM;
}
+ if (atomic_read(&dest->nr_swapfiles)) {
+ spin_unlock(&dest->root_item_lock);
+ btrfs_warn(fs_info,
+ "attempt to delete subvolume %llu with active swapfile",
+ root->root_key.objectid);
+ return -EPERM;
+ }
+ root_flags = btrfs_root_flags(&dest->root_item);
+ btrfs_set_root_flags(&dest->root_item,
+ root_flags | BTRFS_ROOT_SUBVOL_DEAD);
+ spin_unlock(&dest->root_item_lock);
down_write(&fs_info->subvol_sem);
@@ -4487,7 +4115,7 @@
err = ret;
inode->i_flags |= S_DEAD;
out_release:
- btrfs_subvolume_release_metadata(fs_info, &block_rsv);
+ btrfs_subvolume_release_metadata(root, &block_rsv);
out_up_write:
up_write(&fs_info->subvol_sem);
if (err) {
@@ -4566,31 +4194,6 @@
return err;
}
-static int truncate_space_check(struct btrfs_trans_handle *trans,
- struct btrfs_root *root,
- u64 bytes_deleted)
-{
- struct btrfs_fs_info *fs_info = root->fs_info;
- int ret;
-
- /*
- * This is only used to apply pressure to the enospc system, we don't
- * intend to use this reservation at all.
- */
- bytes_deleted = btrfs_csum_bytes_to_leaves(fs_info, bytes_deleted);
- bytes_deleted *= fs_info->nodesize;
- ret = btrfs_block_rsv_add(root, &fs_info->trans_block_rsv,
- bytes_deleted, BTRFS_RESERVE_NO_FLUSH);
- if (!ret) {
- trace_btrfs_space_reservation(fs_info, "transaction",
- trans->transid,
- bytes_deleted, 1);
- trans->bytes_reserved += bytes_deleted;
- }
- return ret;
-
-}
-
/*
* Return this if we need to call truncate_block for the last bit of the
* truncate.
@@ -4635,16 +4238,18 @@
u64 bytes_deleted = 0;
bool be_nice = false;
bool should_throttle = false;
- bool should_end = false;
+ const u64 lock_start = ALIGN_DOWN(new_size, fs_info->sectorsize);
+ struct extent_state *cached_state = NULL;
BUG_ON(new_size > 0 && min_type != BTRFS_EXTENT_DATA_KEY);
/*
- * for non-free space inodes and ref cows, we want to back off from
- * time to time
+ * For non-free space inodes and non-shareable roots, we want to back
+ * off from time to time. This means all inodes in subvolume roots,
+ * reloc roots, and data reloc roots.
*/
if (!btrfs_is_free_space_inode(BTRFS_I(inode)) &&
- test_bit(BTRFS_ROOT_REF_COWS, &root->state))
+ test_bit(BTRFS_ROOT_SHAREABLE, &root->state))
be_nice = true;
path = btrfs_alloc_path();
@@ -4652,21 +4257,24 @@
return -ENOMEM;
path->reada = READA_BACK;
- /*
- * We want to drop from the next block forward in case this new size is
- * not block aligned since we will be keeping the last block of the
- * extent just the way it is.
- */
- if (test_bit(BTRFS_ROOT_REF_COWS, &root->state) ||
- root == fs_info->tree_root)
+ if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) {
+ lock_extent_bits(&BTRFS_I(inode)->io_tree, lock_start, (u64)-1,
+ &cached_state);
+
+ /*
+ * We want to drop from the next block forward in case this
+ * new size is not block aligned since we will be keeping the
+ * last block of the extent just the way it is.
+ */
btrfs_drop_extent_cache(BTRFS_I(inode), ALIGN(new_size,
fs_info->sectorsize),
(u64)-1, 0);
+ }
/*
* This function is also used to drop the items in the log tree before
* we relog the inode, so if root != BTRFS_I(inode)->root, it means
- * it is used to drop the loged items. So we shouldn't kill the delayed
+ * it is used to drop the logged items. So we shouldn't kill the delayed
* items.
*/
if (min_type == 0 && root == BTRFS_I(inode)->root)
@@ -4688,7 +4296,6 @@
goto out;
}
- path->leave_spinning = 1;
ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
if (ret < 0)
goto out;
@@ -4704,6 +4311,8 @@
}
while (1) {
+ u64 clear_start = 0, clear_len = 0;
+
fi = NULL;
leaf = path->nodes[0];
btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);
@@ -4754,6 +4363,8 @@
if (extent_type != BTRFS_FILE_EXTENT_INLINE) {
u64 num_dec;
+
+ clear_start = found_key.offset;
extent_start = btrfs_file_extent_disk_bytenr(leaf, fi);
if (!del_item) {
u64 orig_num_bytes =
@@ -4761,11 +4372,12 @@
extent_num_bytes = ALIGN(new_size -
found_key.offset,
fs_info->sectorsize);
+ clear_start = ALIGN(new_size, fs_info->sectorsize);
btrfs_set_file_extent_num_bytes(leaf, fi,
extent_num_bytes);
num_dec = (orig_num_bytes -
extent_num_bytes);
- if (test_bit(BTRFS_ROOT_REF_COWS,
+ if (test_bit(BTRFS_ROOT_SHAREABLE,
&root->state) &&
extent_start != 0)
inode_sub_bytes(inode, num_dec);
@@ -4781,11 +4393,12 @@
num_dec = btrfs_file_extent_num_bytes(leaf, fi);
if (extent_start != 0) {
found_extent = 1;
- if (test_bit(BTRFS_ROOT_REF_COWS,
+ if (test_bit(BTRFS_ROOT_SHAREABLE,
&root->state))
inode_sub_bytes(inode, num_dec);
}
}
+ clear_len = num_dec;
} else if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
/*
* we can't truncate inline items that have had
@@ -4799,7 +4412,7 @@
btrfs_set_file_extent_ram_bytes(leaf, fi, size);
size = btrfs_file_extent_calc_inline_size(size);
- btrfs_truncate_item(root->fs_info, path, size, 1);
+ btrfs_truncate_item(path, size, 1);
} else if (!del_item) {
/*
* We have to bail so the last_size is set to
@@ -4807,12 +4420,33 @@
*/
ret = NEED_TRUNCATE_BLOCK;
break;
+ } else {
+ /*
+ * Inline extents are special, we just treat
+ * them as a full sector worth in the file
+ * extent tree just for simplicity sake.
+ */
+ clear_len = fs_info->sectorsize;
}
- if (test_bit(BTRFS_ROOT_REF_COWS, &root->state))
+ if (test_bit(BTRFS_ROOT_SHAREABLE, &root->state))
inode_sub_bytes(inode, item_end + 1 - new_size);
}
delete:
+ /*
+ * We use btrfs_truncate_inode_items() to clean up log trees for
+ * multiple fsyncs, and in this case we don't want to clear the
+ * file extent range because it's just the log.
+ */
+ if (root == BTRFS_I(inode)->root) {
+ ret = btrfs_inode_clear_file_extent_range(BTRFS_I(inode),
+ clear_start, clear_len);
+ if (ret) {
+ btrfs_abort_transaction(trans, ret);
+ break;
+ }
+ }
+
if (del_item)
last_size = found_key.offset;
else
@@ -4836,29 +4470,23 @@
should_throttle = false;
if (found_extent &&
- (test_bit(BTRFS_ROOT_REF_COWS, &root->state) ||
- root == fs_info->tree_root)) {
- btrfs_set_path_blocking(path);
+ root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) {
+ struct btrfs_ref ref = { 0 };
+
bytes_deleted += extent_num_bytes;
- ret = btrfs_free_extent(trans, root, extent_start,
- extent_num_bytes, 0,
- btrfs_header_owner(leaf),
- ino, extent_offset);
+
+ btrfs_init_generic_ref(&ref, BTRFS_DROP_DELAYED_REF,
+ extent_start, extent_num_bytes, 0);
+ ref.real_root = root->root_key.objectid;
+ btrfs_init_data_ref(&ref, btrfs_header_owner(leaf),
+ ino, extent_offset);
+ ret = btrfs_free_extent(trans, &ref);
if (ret) {
btrfs_abort_transaction(trans, ret);
break;
}
- if (btrfs_should_throttle_delayed_refs(trans, fs_info))
- btrfs_async_run_delayed_refs(fs_info,
- trans->delayed_ref_updates * 2,
- trans->transid, 0);
if (be_nice) {
- if (truncate_space_check(trans, root,
- extent_num_bytes)) {
- should_end = true;
- }
- if (btrfs_should_throttle_delayed_refs(trans,
- fs_info))
+ if (btrfs_should_throttle_delayed_refs(trans))
should_throttle = true;
}
}
@@ -4868,7 +4496,7 @@
if (path->slots[0] == 0 ||
path->slots[0] != pending_del_slot ||
- should_throttle || should_end) {
+ should_throttle) {
if (pending_del_nr) {
ret = btrfs_del_items(trans, root, path,
pending_del_slot,
@@ -4880,23 +4508,24 @@
pending_del_nr = 0;
}
btrfs_release_path(path);
- if (should_throttle) {
- unsigned long updates = trans->delayed_ref_updates;
- if (updates) {
- trans->delayed_ref_updates = 0;
- ret = btrfs_run_delayed_refs(trans,
- updates * 2);
- if (ret)
- break;
- }
- }
+
/*
- * if we failed to refill our space rsv, bail out
- * and let the transaction restart
+ * We can generate a lot of delayed refs, so we need to
+ * throttle every once and a while and make sure we're
+ * adding enough space to keep up with the work we are
+ * generating. Since we hold a transaction here we
+ * can't flush, and we don't want to FLUSH_LIMIT because
+ * we could have generated too many delayed refs to
+ * actually allocate, so just bail if we're short and
+ * let the normal reservation dance happen higher up.
*/
- if (should_end) {
- ret = -EAGAIN;
- break;
+ if (should_throttle) {
+ ret = btrfs_delayed_refs_rsv_refill(fs_info,
+ BTRFS_RESERVE_NO_FLUSH);
+ if (ret) {
+ ret = -EAGAIN;
+ break;
+ }
}
goto search_again;
} else {
@@ -4918,22 +4547,12 @@
ASSERT(last_size >= new_size);
if (!ret && last_size > new_size)
last_size = new_size;
- btrfs_ordered_update_i_size(inode, last_size, NULL);
+ btrfs_inode_safe_disk_i_size_write(inode, last_size);
+ unlock_extent_cached(&BTRFS_I(inode)->io_tree, lock_start,
+ (u64)-1, &cached_state);
}
btrfs_free_path(path);
-
- if (be_nice && bytes_deleted > SZ_32M && (ret >= 0 || ret == -EAGAIN)) {
- unsigned long updates = trans->delayed_ref_updates;
- int err;
-
- if (updates) {
- trans->delayed_ref_updates = 0;
- err = btrfs_run_delayed_refs(trans, updates * 2);
- if (err)
- ret = err;
- }
- }
return ret;
}
@@ -4958,11 +4577,13 @@
struct extent_state *cached_state = NULL;
struct extent_changeset *data_reserved = NULL;
char *kaddr;
+ bool only_release_metadata = false;
u32 blocksize = fs_info->sectorsize;
pgoff_t index = from >> PAGE_SHIFT;
unsigned offset = from & (blocksize - 1);
struct page *page;
gfp_t mask = btrfs_alloc_write_mask(mapping);
+ size_t write_bytes = blocksize;
int ret = 0;
u64 block_start;
u64 block_end;
@@ -4974,15 +4595,28 @@
block_start = round_down(from, blocksize);
block_end = block_start + blocksize - 1;
- ret = btrfs_delalloc_reserve_space(inode, &data_reserved,
- block_start, blocksize);
- if (ret)
+ ret = btrfs_check_data_free_space(BTRFS_I(inode), &data_reserved,
+ block_start, blocksize);
+ if (ret < 0) {
+ if (btrfs_check_nocow_lock(BTRFS_I(inode), block_start,
+ &write_bytes) > 0) {
+ /* For nocow case, no need to reserve data space */
+ only_release_metadata = true;
+ } else {
+ goto out;
+ }
+ }
+ ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode), blocksize);
+ if (ret < 0) {
+ if (!only_release_metadata)
+ btrfs_free_reserved_data_space(BTRFS_I(inode),
+ data_reserved, block_start, blocksize);
goto out;
-
+ }
again:
page = find_or_create_page(mapping, index, mask);
if (!page) {
- btrfs_delalloc_release_space(inode, data_reserved,
+ btrfs_delalloc_release_space(BTRFS_I(inode), data_reserved,
block_start, blocksize, true);
btrfs_delalloc_release_extents(BTRFS_I(inode), blocksize);
ret = -ENOMEM;
@@ -5007,24 +4641,23 @@
lock_extent_bits(io_tree, block_start, block_end, &cached_state);
set_page_extent_mapped(page);
- ordered = btrfs_lookup_ordered_extent(inode, block_start);
+ ordered = btrfs_lookup_ordered_extent(BTRFS_I(inode), block_start);
if (ordered) {
unlock_extent_cached(io_tree, block_start, block_end,
&cached_state);
unlock_page(page);
put_page(page);
- btrfs_start_ordered_extent(inode, ordered, 1);
+ btrfs_start_ordered_extent(ordered, 1);
btrfs_put_ordered_extent(ordered);
goto again;
}
clear_extent_bit(&BTRFS_I(inode)->io_tree, block_start, block_end,
- EXTENT_DIRTY | EXTENT_DELALLOC |
- EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG,
- 0, 0, &cached_state);
+ EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG,
+ 0, 0, &cached_state);
- ret = btrfs_set_extent_delalloc(inode, block_start, block_end, 0,
- &cached_state, 0);
+ ret = btrfs_set_extent_delalloc(BTRFS_I(inode), block_start, block_end, 0,
+ &cached_state);
if (ret) {
unlock_extent_cached(io_tree, block_start, block_end,
&cached_state);
@@ -5048,14 +4681,26 @@
set_page_dirty(page);
unlock_extent_cached(io_tree, block_start, block_end, &cached_state);
+ if (only_release_metadata)
+ set_extent_bit(&BTRFS_I(inode)->io_tree, block_start,
+ block_end, EXTENT_NORESERVE, NULL, NULL,
+ GFP_NOFS);
+
out_unlock:
- if (ret)
- btrfs_delalloc_release_space(inode, data_reserved, block_start,
- blocksize, true);
+ if (ret) {
+ if (only_release_metadata)
+ btrfs_delalloc_release_metadata(BTRFS_I(inode),
+ blocksize, true);
+ else
+ btrfs_delalloc_release_space(BTRFS_I(inode), data_reserved,
+ block_start, blocksize, true);
+ }
btrfs_delalloc_release_extents(BTRFS_I(inode), blocksize);
unlock_page(page);
put_page(page);
out:
+ if (only_release_metadata)
+ btrfs_check_nocow_unlock(BTRFS_I(inode));
extent_changeset_free(data_reserved);
return ret;
}
@@ -5137,25 +4782,12 @@
if (size <= hole_start)
return 0;
- while (1) {
- struct btrfs_ordered_extent *ordered;
-
- lock_extent_bits(io_tree, hole_start, block_end - 1,
- &cached_state);
- ordered = btrfs_lookup_ordered_range(BTRFS_I(inode), hole_start,
- block_end - hole_start);
- if (!ordered)
- break;
- unlock_extent_cached(io_tree, hole_start, block_end - 1,
- &cached_state);
- btrfs_start_ordered_extent(inode, ordered, 1);
- btrfs_put_ordered_extent(ordered);
- }
-
+ btrfs_lock_and_flush_ordered_range(BTRFS_I(inode), hole_start,
+ block_end - 1, &cached_state);
cur_offset = hole_start;
while (1) {
em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, cur_offset,
- block_end - cur_offset, 0);
+ block_end - cur_offset);
if (IS_ERR(em)) {
err = PTR_ERR(em);
em = NULL;
@@ -5163,14 +4795,21 @@
}
last_byte = min(extent_map_end(em), block_end);
last_byte = ALIGN(last_byte, fs_info->sectorsize);
+ hole_size = last_byte - cur_offset;
+
if (!test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) {
struct extent_map *hole_em;
- hole_size = last_byte - cur_offset;
err = maybe_insert_hole(root, inode, cur_offset,
hole_size);
if (err)
break;
+
+ err = btrfs_inode_set_file_extent_range(BTRFS_I(inode),
+ cur_offset, hole_size);
+ if (err)
+ break;
+
btrfs_drop_extent_cache(BTRFS_I(inode), cur_offset,
cur_offset + hole_size - 1, 0);
hole_em = alloc_extent_map();
@@ -5187,7 +4826,6 @@
hole_em->block_len = 0;
hole_em->orig_block_len = 0;
hole_em->ram_bytes = hole_size;
- hole_em->bdev = fs_info->fs_devices->latest_bdev;
hole_em->compress_type = BTRFS_COMPRESS_NONE;
hole_em->generation = fs_info->generation;
@@ -5203,6 +4841,11 @@
hole_size - 1, 0);
}
free_extent_map(hole_em);
+ } else {
+ err = btrfs_inode_set_file_extent_range(BTRFS_I(inode),
+ cur_offset, hole_size);
+ if (err)
+ break;
}
next:
free_extent_map(em);
@@ -5246,42 +4889,39 @@
* truncation, it must capture all writes that happened before
* this truncation.
*/
- btrfs_wait_for_snapshot_creation(root);
+ btrfs_drew_write_lock(&root->snapshot_lock);
ret = btrfs_cont_expand(inode, oldsize, newsize);
if (ret) {
- btrfs_end_write_no_snapshotting(root);
+ btrfs_drew_write_unlock(&root->snapshot_lock);
return ret;
}
trans = btrfs_start_transaction(root, 1);
if (IS_ERR(trans)) {
- btrfs_end_write_no_snapshotting(root);
+ btrfs_drew_write_unlock(&root->snapshot_lock);
return PTR_ERR(trans);
}
i_size_write(inode, newsize);
- btrfs_ordered_update_i_size(inode, i_size_read(inode), NULL);
+ btrfs_inode_safe_disk_i_size_write(inode, 0);
pagecache_isize_extended(inode, oldsize, newsize);
ret = btrfs_update_inode(trans, root, inode);
- btrfs_end_write_no_snapshotting(root);
+ btrfs_drew_write_unlock(&root->snapshot_lock);
btrfs_end_transaction(trans);
} else {
/*
* We're truncating a file that used to have good data down to
- * zero. Make sure it gets into the ordered flush list so that
- * any new writes get down to disk quickly.
+ * zero. Make sure any new writes to the file get on disk
+ * on close.
*/
if (newsize == 0)
- set_bit(BTRFS_INODE_ORDERED_DATA_CLOSE,
+ set_bit(BTRFS_INODE_FLUSH_ON_CLOSE,
&BTRFS_I(inode)->runtime_flags);
truncate_setsize(inode, newsize);
- /* Disable nonlocked read DIO to avoid the end less truncate */
- btrfs_inode_block_unlocked_dio(BTRFS_I(inode));
inode_dio_wait(inode);
- btrfs_inode_resume_unlocked_dio(BTRFS_I(inode));
ret = btrfs_truncate(inode, newsize == oldsize);
if (ret && inode->i_nlink) {
@@ -5356,10 +4996,10 @@
truncate_inode_pages_final(&inode->i_data);
write_lock(&map_tree->lock);
- while (!RB_EMPTY_ROOT(&map_tree->map)) {
+ while (!RB_EMPTY_ROOT(&map_tree->map.rb_root)) {
struct extent_map *em;
- node = rb_first(&map_tree->map);
+ node = rb_first_cached(&map_tree->map);
em = rb_entry(node, struct extent_map, rb_node);
clear_bit(EXTENT_FLAG_PINNED, &em->flags);
clear_bit(EXTENT_FLAG_LOGGING, &em->flags);
@@ -5375,8 +5015,8 @@
/*
* Keep looping until we have no more ranges in the io tree.
- * We can have ongoing bios started by readpages (called from readahead)
- * that have their endio callback (extent_io.c:end_bio_extent_readpage)
+ * We can have ongoing bios started by readahead that have
+ * their endio callback (extent_io.c:end_bio_extent_readpage)
* still in progress (unlocked the pages in the bio but did not yet
* unlocked the ranges in the io tree). Therefore this means some
* ranges can still be locked and eviction started because before
@@ -5415,12 +5055,13 @@
* Note, end is the bytenr of last byte, so we need + 1 here.
*/
if (state_flags & EXTENT_DELALLOC)
- btrfs_qgroup_free_data(inode, NULL, start, end - start + 1);
+ btrfs_qgroup_free_data(BTRFS_I(inode), NULL, start,
+ end - start + 1);
clear_extent_bit(io_tree, start, end,
- EXTENT_LOCKED | EXTENT_DIRTY |
- EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING |
- EXTENT_DEFRAG, 1, 1, &cached_state);
+ EXTENT_LOCKED | EXTENT_DELALLOC |
+ EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG, 1, 1,
+ &cached_state);
cond_resched();
spin_lock(&io_tree->lock);
@@ -5429,43 +5070,54 @@
}
static struct btrfs_trans_handle *evict_refill_and_join(struct btrfs_root *root,
- struct btrfs_block_rsv *rsv,
- u64 min_size)
+ struct btrfs_block_rsv *rsv)
{
struct btrfs_fs_info *fs_info = root->fs_info;
struct btrfs_block_rsv *global_rsv = &fs_info->global_block_rsv;
- int failures = 0;
+ struct btrfs_trans_handle *trans;
+ u64 delayed_refs_extra = btrfs_calc_insert_metadata_size(fs_info, 1);
+ int ret;
- for (;;) {
- struct btrfs_trans_handle *trans;
- int ret;
-
- ret = btrfs_block_rsv_refill(root, rsv, min_size,
- BTRFS_RESERVE_FLUSH_LIMIT);
-
- if (ret && ++failures > 2) {
- btrfs_warn(fs_info,
- "could not allocate space for a delete; will truncate on mount");
- return ERR_PTR(-ENOSPC);
- }
-
- trans = btrfs_join_transaction(root);
- if (IS_ERR(trans) || !ret)
- return trans;
-
+ /*
+ * Eviction should be taking place at some place safe because of our
+ * delayed iputs. However the normal flushing code will run delayed
+ * iputs, so we cannot use FLUSH_ALL otherwise we'll deadlock.
+ *
+ * We reserve the delayed_refs_extra here again because we can't use
+ * btrfs_start_transaction(root, 0) for the same deadlocky reason as
+ * above. We reserve our extra bit here because we generate a ton of
+ * delayed refs activity by truncating.
+ *
+ * If we cannot make our reservation we'll attempt to steal from the
+ * global reserve, because we really want to be able to free up space.
+ */
+ ret = btrfs_block_rsv_refill(root, rsv, rsv->size + delayed_refs_extra,
+ BTRFS_RESERVE_FLUSH_EVICT);
+ if (ret) {
/*
* Try to steal from the global reserve if there is space for
* it.
*/
- if (!btrfs_check_space_for_delayed_refs(trans, fs_info) &&
- !btrfs_block_rsv_migrate(global_rsv, rsv, min_size, 0))
- return trans;
-
- /* If not, commit and try again. */
- ret = btrfs_commit_transaction(trans);
- if (ret)
- return ERR_PTR(ret);
+ if (btrfs_check_space_for_delayed_refs(fs_info) ||
+ btrfs_block_rsv_migrate(global_rsv, rsv, rsv->size, 0)) {
+ btrfs_warn(fs_info,
+ "could not allocate space for delete; will truncate on mount");
+ return ERR_PTR(-ENOSPC);
+ }
+ delayed_refs_extra = 0;
}
+
+ trans = btrfs_join_transaction(root);
+ if (IS_ERR(trans))
+ return trans;
+
+ if (delayed_refs_extra) {
+ trans->block_rsv = &fs_info->trans_block_rsv;
+ trans->bytes_reserved = delayed_refs_extra;
+ btrfs_block_rsv_migrate(rsv, trans->block_rsv,
+ delayed_refs_extra, 1);
+ }
+ return trans;
}
void btrfs_evict_inode(struct inode *inode)
@@ -5474,7 +5126,6 @@
struct btrfs_trans_handle *trans;
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_block_rsv *rsv;
- u64 min_size;
int ret;
trace_btrfs_inode_evict(inode);
@@ -5483,8 +5134,6 @@
clear_inode(inode);
return;
}
-
- min_size = btrfs_calc_trunc_metadata_size(fs_info, 1);
evict_inode_truncate_pages(inode);
@@ -5496,9 +5145,6 @@
if (is_bad_inode(inode))
goto no_delete;
- /* do we really want it for ->i_nlink > 0 and zero btrfs_root_refs? */
- if (!special_file(inode->i_mode))
- btrfs_wait_ordered_range(inode, 0, (u64)-1);
btrfs_free_io_failure_record(BTRFS_I(inode), 0, (u64)-1);
@@ -5518,13 +5164,13 @@
rsv = btrfs_alloc_block_rsv(fs_info, BTRFS_BLOCK_RSV_TEMP);
if (!rsv)
goto no_delete;
- rsv->size = min_size;
+ rsv->size = btrfs_calc_metadata_size(fs_info, 1);
rsv->failfast = 1;
btrfs_i_size_write(BTRFS_I(inode), 0);
while (1) {
- trans = evict_refill_and_join(root, rsv, min_size);
+ trans = evict_refill_and_join(root, rsv);
if (IS_ERR(trans))
goto free_rsv;
@@ -5549,7 +5195,7 @@
* If it turns out that we are dropping too many of these, we might want
* to add a mechanism for retrying these after a commit.
*/
- trans = evict_refill_and_join(root, rsv, min_size);
+ trans = evict_refill_and_join(root, rsv);
if (!IS_ERR(trans)) {
trans->block_rsv = rsv;
btrfs_orphan_del(trans, BTRFS_I(inode));
@@ -5596,12 +5242,8 @@
di = btrfs_lookup_dir_item(NULL, root, path, btrfs_ino(BTRFS_I(dir)),
name, namelen, 0);
- if (!di) {
- ret = -ENOENT;
- goto out;
- }
- if (IS_ERR(di)) {
- ret = PTR_ERR(di);
+ if (IS_ERR_OR_NULL(di)) {
+ ret = di ? PTR_ERR(di) : -ENOENT;
goto out;
}
@@ -5672,7 +5314,7 @@
btrfs_release_path(path);
- new_root = btrfs_read_fs_root_no_name(fs_info, location);
+ new_root = btrfs_get_fs_root(fs_info, location->objectid, true);
if (IS_ERR(new_root)) {
err = PTR_ERR(new_root);
goto out;
@@ -5724,15 +5366,15 @@
spin_unlock(&root->inode_lock);
}
-static void inode_tree_del(struct inode *inode)
+static void inode_tree_del(struct btrfs_inode *inode)
{
- struct btrfs_root *root = BTRFS_I(inode)->root;
+ struct btrfs_root *root = inode->root;
int empty = 0;
spin_lock(&root->inode_lock);
- if (!RB_EMPTY_NODE(&BTRFS_I(inode)->rb_node)) {
- rb_erase(&BTRFS_I(inode)->rb_node, &root->inode_tree);
- RB_CLEAR_NODE(&BTRFS_I(inode)->rb_node);
+ if (!RB_EMPTY_NODE(&inode->rb_node)) {
+ rb_erase(&inode->rb_node, &root->inode_tree);
+ RB_CLEAR_NODE(&inode->rb_node);
empty = RB_EMPTY_ROOT(&root->inode_tree);
}
spin_unlock(&root->inode_lock);
@@ -5750,29 +5392,32 @@
static int btrfs_init_locked_inode(struct inode *inode, void *p)
{
struct btrfs_iget_args *args = p;
- inode->i_ino = args->location->objectid;
- memcpy(&BTRFS_I(inode)->location, args->location,
- sizeof(*args->location));
- BTRFS_I(inode)->root = args->root;
+
+ inode->i_ino = args->ino;
+ BTRFS_I(inode)->location.objectid = args->ino;
+ BTRFS_I(inode)->location.type = BTRFS_INODE_ITEM_KEY;
+ BTRFS_I(inode)->location.offset = 0;
+ BTRFS_I(inode)->root = btrfs_grab_root(args->root);
+ BUG_ON(args->root && !BTRFS_I(inode)->root);
return 0;
}
static int btrfs_find_actor(struct inode *inode, void *opaque)
{
struct btrfs_iget_args *args = opaque;
- return args->location->objectid == BTRFS_I(inode)->location.objectid &&
+
+ return args->ino == BTRFS_I(inode)->location.objectid &&
args->root == BTRFS_I(inode)->root;
}
-static struct inode *btrfs_iget_locked(struct super_block *s,
- struct btrfs_key *location,
+static struct inode *btrfs_iget_locked(struct super_block *s, u64 ino,
struct btrfs_root *root)
{
struct inode *inode;
struct btrfs_iget_args args;
- unsigned long hashval = btrfs_inode_hash(location->objectid, root);
+ unsigned long hashval = btrfs_inode_hash(ino, root);
- args.location = location;
+ args.ino = ino;
args.root = root;
inode = iget5_locked(s, hashval, btrfs_find_actor,
@@ -5781,16 +5426,18 @@
return inode;
}
-/* Get an inode object given its location and corresponding root.
- * Returns in *is_new if the inode was read from disk
+/*
+ * Get an inode object given its inode number and corresponding root.
+ * Path can be preallocated to prevent recursing back to iget through
+ * allocator. NULL is also valid but may require an additional allocation
+ * later.
*/
-struct inode *btrfs_iget_path(struct super_block *s, struct btrfs_key *location,
- struct btrfs_root *root, int *new,
- struct btrfs_path *path)
+struct inode *btrfs_iget_path(struct super_block *s, u64 ino,
+ struct btrfs_root *root, struct btrfs_path *path)
{
struct inode *inode;
- inode = btrfs_iget_locked(s, location, root);
+ inode = btrfs_iget_locked(s, ino, root);
if (!inode)
return ERR_PTR(-ENOMEM);
@@ -5801,8 +5448,6 @@
if (!ret) {
inode_tree_add(inode);
unlock_new_inode(inode);
- if (new)
- *new = 1;
} else {
iget_failed(inode);
/*
@@ -5819,10 +5464,9 @@
return inode;
}
-struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location,
- struct btrfs_root *root, int *new)
+struct inode *btrfs_iget(struct super_block *s, u64 ino, struct btrfs_root *root)
{
- return btrfs_iget_path(s, location, root, new, NULL);
+ return btrfs_iget_path(s, ino, root, NULL);
}
static struct inode *new_simple_dir(struct super_block *s,
@@ -5834,12 +5478,16 @@
if (!inode)
return ERR_PTR(-ENOMEM);
- BTRFS_I(inode)->root = root;
+ BTRFS_I(inode)->root = btrfs_grab_root(root);
memcpy(&BTRFS_I(inode)->location, key, sizeof(*key));
set_bit(BTRFS_INODE_DUMMY, &BTRFS_I(inode)->runtime_flags);
inode->i_ino = BTRFS_EMPTY_SUBVOL_DIR_OBJECTID;
- inode->i_op = &btrfs_dir_ro_inode_operations;
+ /*
+ * We only need lookup, the rest is read-only and there's no inode
+ * associated with the dentry
+ */
+ inode->i_op = &simple_dir_inode_operations;
inode->i_opflags &= ~IOP_XATTR;
inode->i_fop = &simple_dir_operations;
inode->i_mode = S_IFDIR | S_IRUGO | S_IWUSR | S_IXUGO;
@@ -5853,7 +5501,20 @@
static inline u8 btrfs_inode_type(struct inode *inode)
{
- return btrfs_type_by_mode[(inode->i_mode & S_IFMT) >> S_SHIFT];
+ /*
+ * Compile-time asserts that generic FT_* types still match
+ * BTRFS_FT_* types
+ */
+ BUILD_BUG_ON(BTRFS_FT_UNKNOWN != FT_UNKNOWN);
+ BUILD_BUG_ON(BTRFS_FT_REG_FILE != FT_REG_FILE);
+ BUILD_BUG_ON(BTRFS_FT_DIR != FT_DIR);
+ BUILD_BUG_ON(BTRFS_FT_CHRDEV != FT_CHRDEV);
+ BUILD_BUG_ON(BTRFS_FT_BLKDEV != FT_BLKDEV);
+ BUILD_BUG_ON(BTRFS_FT_FIFO != FT_FIFO);
+ BUILD_BUG_ON(BTRFS_FT_SOCK != FT_SOCK);
+ BUILD_BUG_ON(BTRFS_FT_SYMLINK != FT_SYMLINK);
+
+ return fs_umode_to_ftype(inode->i_mode);
}
struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry)
@@ -5864,7 +5525,6 @@
struct btrfs_root *sub_root = root;
struct btrfs_key location;
u8 di_type = 0;
- int index;
int ret = 0;
if (dentry->d_name.len > BTRFS_NAME_LEN)
@@ -5875,7 +5535,7 @@
return ERR_PTR(ret);
if (location.type == BTRFS_INODE_ITEM_KEY) {
- inode = btrfs_iget(dir->i_sb, &location, root, NULL);
+ inode = btrfs_iget(dir->i_sb, location.objectid, root);
if (IS_ERR(inode))
return inode;
@@ -5891,7 +5551,6 @@
return inode;
}
- index = srcu_read_lock(&fs_info->subvol_srcu);
ret = fixup_tree_root_location(fs_info, dir, dentry,
&location, &sub_root);
if (ret < 0) {
@@ -5900,9 +5559,10 @@
else
inode = new_simple_dir(dir->i_sb, &location, sub_root);
} else {
- inode = btrfs_iget(dir->i_sb, &location, sub_root, NULL);
+ inode = btrfs_iget(dir->i_sb, location.objectid, sub_root);
}
- srcu_read_unlock(&fs_info->subvol_srcu, index);
+ if (root != sub_root)
+ btrfs_put_root(sub_root);
if (!IS_ERR(inode) && root != sub_root) {
down_read(&fs_info->cleanup_work_sem);
@@ -5940,22 +5600,12 @@
static struct dentry *btrfs_lookup(struct inode *dir, struct dentry *dentry,
unsigned int flags)
{
- struct inode *inode;
+ struct inode *inode = btrfs_lookup_dentry(dir, dentry);
- inode = btrfs_lookup_dentry(dir, dentry);
- if (IS_ERR(inode)) {
- if (PTR_ERR(inode) == -ENOENT)
- inode = NULL;
- else
- return ERR_CAST(inode);
- }
-
+ if (inode == ERR_PTR(-ENOENT))
+ inode = NULL;
return d_splice_alias(inode, dentry);
}
-
-unsigned char btrfs_filetype_table[] = {
- DT_UNKNOWN, DT_REG, DT_DIR, DT_CHR, DT_BLK, DT_FIFO, DT_SOCK, DT_LNK
-};
/*
* All this infrastructure exists because dir_emit can fault, and we are holding
@@ -6095,7 +5745,7 @@
name_ptr = (char *)(entry + 1);
read_extent_buffer(leaf, name_ptr, (unsigned long)(di + 1),
name_len);
- put_unaligned(btrfs_filetype_table[btrfs_dir_type(leaf, di)],
+ put_unaligned(fs_ftype_to_dtype(btrfs_dir_type(leaf, di)),
&entry->type);
btrfs_dir_item_key_to_cpu(leaf, di, &location);
put_unaligned(location.objectid, &entry->ino);
@@ -6167,7 +5817,7 @@
return PTR_ERR(trans);
ret = btrfs_update_inode(trans, root, inode);
- if (ret && ret == -ENOSPC) {
+ if (ret && (ret == -ENOSPC || ret == -EDQUOT)) {
/* whoops, lets try again with the full transaction */
btrfs_end_transaction(trans);
trans = btrfs_start_transaction(root, 1);
@@ -6290,7 +5940,8 @@
static int btrfs_insert_inode_locked(struct inode *inode)
{
struct btrfs_iget_args args;
- args.location = &BTRFS_I(inode)->location;
+
+ args.ino = BTRFS_I(inode)->location.objectid;
args.root = BTRFS_I(inode)->root;
return insert_inode_locked4(inode,
@@ -6346,13 +5997,16 @@
u32 sizes[2];
int nitems = name ? 2 : 1;
unsigned long ptr;
+ unsigned int nofs_flag;
int ret;
path = btrfs_alloc_path();
if (!path)
return ERR_PTR(-ENOMEM);
+ nofs_flag = memalloc_nofs_save();
inode = new_inode(fs_info->sb);
+ memalloc_nofs_restore(nofs_flag);
if (!inode) {
btrfs_free_path(path);
return ERR_PTR(-ENOMEM);
@@ -6390,7 +6044,7 @@
*/
BTRFS_I(inode)->index_cnt = 2;
BTRFS_I(inode)->dir_index = *index;
- BTRFS_I(inode)->root = root;
+ BTRFS_I(inode)->root = btrfs_grab_root(root);
BTRFS_I(inode)->generation = trans->transid;
inode->i_generation = BTRFS_I(inode)->generation;
@@ -6477,7 +6131,7 @@
inode_tree_add(inode);
trace_btrfs_inode_new(inode);
- btrfs_set_inode_last_trans(trans, inode);
+ btrfs_set_inode_last_trans(trans, BTRFS_I(inode));
btrfs_update_root_times(trans, root);
@@ -6535,8 +6189,7 @@
if (ret)
return ret;
- ret = btrfs_insert_dir_item(trans, root, name, name_len,
- parent_inode, &key,
+ ret = btrfs_insert_dir_item(trans, name, name_len, parent_inode, &key,
btrfs_inode_type(&inode->vfs_inode), index);
if (ret == -EEXIST || ret == -EOVERFLOW)
goto fail_dir_item;
@@ -6620,7 +6273,7 @@
if (IS_ERR(trans))
return PTR_ERR(trans);
- err = btrfs_find_free_ino(root, &objectid);
+ err = btrfs_find_free_objectid(root, &objectid);
if (err)
goto out_unlock;
@@ -6684,7 +6337,7 @@
if (IS_ERR(trans))
return PTR_ERR(trans);
- err = btrfs_find_free_ino(root, &objectid);
+ err = btrfs_find_free_objectid(root, &objectid);
if (err)
goto out_unlock;
@@ -6719,7 +6372,6 @@
if (err)
goto out_unlock;
- BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
d_instantiate_new(dentry, inode);
out_unlock:
@@ -6744,7 +6396,7 @@
int drop_inode = 0;
/* do not allow sys_link's with other subvols of the same device */
- if (root->objectid != BTRFS_I(inode)->root->objectid)
+ if (root->root_key.objectid != BTRFS_I(inode)->root->root_key.objectid)
return -EXDEV;
if (inode->i_nlink >= BTRFS_LINK_MAX)
@@ -6782,7 +6434,6 @@
drop_inode = 1;
} else {
struct dentry *parent = dentry->d_parent;
- int ret;
err = btrfs_update_inode(trans, root, inode);
if (err)
@@ -6796,14 +6447,8 @@
if (err)
goto fail;
}
- BTRFS_I(inode)->last_link_trans = trans->transid;
d_instantiate(dentry, inode);
- ret = btrfs_log_new_name(trans, BTRFS_I(inode), NULL, parent,
- true, NULL);
- if (ret == BTRFS_NEED_TRANS_COMMIT) {
- err = btrfs_commit_transaction(trans);
- trans = NULL;
- }
+ btrfs_log_new_name(trans, BTRFS_I(inode), NULL, parent);
}
fail:
@@ -6824,7 +6469,6 @@
struct btrfs_trans_handle *trans;
struct btrfs_root *root = BTRFS_I(dir)->root;
int err = 0;
- int drop_on_err = 0;
u64 objectid = 0;
u64 index = 0;
@@ -6837,7 +6481,7 @@
if (IS_ERR(trans))
return PTR_ERR(trans);
- err = btrfs_find_free_ino(root, &objectid);
+ err = btrfs_find_free_objectid(root, &objectid);
if (err)
goto out_fail;
@@ -6850,7 +6494,6 @@
goto out_fail;
}
- drop_on_err = 1;
/* these must be set before we unlock the inode */
inode->i_op = &btrfs_dir_inode_operations;
inode->i_fop = &btrfs_dir_file_operations;
@@ -6871,7 +6514,6 @@
goto out_fail;
d_instantiate_new(dentry, inode);
- drop_on_err = 0;
out_fail:
btrfs_end_transaction(trans);
@@ -6929,26 +6571,34 @@
return ret;
}
-/*
- * a bit scary, this does extent mapping from logical file offset to the disk.
- * the ugly parts come from merging extents from the disk with the in-ram
- * representation. This gets more complex because of the data=ordered code,
- * where the in-ram extents might be locked pending data=ordered completion.
+/**
+ * btrfs_get_extent - Lookup the first extent overlapping a range in a file.
+ * @inode: file to search in
+ * @page: page to read extent data into if the extent is inline
+ * @pg_offset: offset into @page to copy to
+ * @start: file offset
+ * @len: length of range starting at @start
*
- * This also copies inline extents directly into the page.
+ * This returns the first &struct extent_map which overlaps with the given
+ * range, reading it from the B-tree and caching it if necessary. Note that
+ * there may be more extents which overlap the given range after the returned
+ * extent_map.
+ *
+ * If @page is not NULL and the extent is inline, this also reads the extent
+ * data directly into the page and marks the extent up to date in the io_tree.
+ *
+ * Return: ERR_PTR on error, non-NULL extent_map on success.
*/
struct extent_map *btrfs_get_extent(struct btrfs_inode *inode,
- struct page *page,
- size_t pg_offset, u64 start, u64 len,
- int create)
+ struct page *page, size_t pg_offset,
+ u64 start, u64 len)
{
struct btrfs_fs_info *fs_info = inode->root->fs_info;
- int ret;
- int err = 0;
+ int ret = 0;
u64 extent_start = 0;
u64 extent_end = 0;
u64 objectid = btrfs_ino(inode);
- u32 found_type;
+ int extent_type = -1;
struct btrfs_path *path = NULL;
struct btrfs_root *root = inode->root;
struct btrfs_file_extent_item *item;
@@ -6957,12 +6607,9 @@
struct extent_map *em = NULL;
struct extent_map_tree *em_tree = &inode->extent_tree;
struct extent_io_tree *io_tree = &inode->io_tree;
- const bool new_inline = !page || create;
read_lock(&em_tree->lock);
em = lookup_extent_mapping(em_tree, start, len);
- if (em)
- em->bdev = fs_info->fs_devices->latest_bdev;
read_unlock(&em_tree->lock);
if (em) {
@@ -6975,48 +6622,47 @@
}
em = alloc_extent_map();
if (!em) {
- err = -ENOMEM;
+ ret = -ENOMEM;
goto out;
}
- em->bdev = fs_info->fs_devices->latest_bdev;
em->start = EXTENT_MAP_HOLE;
em->orig_start = EXTENT_MAP_HOLE;
em->len = (u64)-1;
em->block_len = (u64)-1;
+ path = btrfs_alloc_path();
if (!path) {
- path = btrfs_alloc_path();
- if (!path) {
- err = -ENOMEM;
- goto out;
- }
- /*
- * Chances are we'll be called again, so go ahead and do
- * readahead
- */
- path->reada = READA_FORWARD;
- }
-
- ret = btrfs_lookup_file_extent(NULL, root, path, objectid, start, 0);
- if (ret < 0) {
- err = ret;
+ ret = -ENOMEM;
goto out;
}
- if (ret != 0) {
+ /* Chances are we'll be called again, so go ahead and do readahead */
+ path->reada = READA_FORWARD;
+
+ /*
+ * Unless we're going to uncompress the inline extent, no sleep would
+ * happen.
+ */
+ path->leave_spinning = 1;
+
+ path->recurse = btrfs_is_free_space_inode(inode);
+
+ ret = btrfs_lookup_file_extent(NULL, root, path, objectid, start, 0);
+ if (ret < 0) {
+ goto out;
+ } else if (ret > 0) {
if (path->slots[0] == 0)
goto not_found;
path->slots[0]--;
+ ret = 0;
}
leaf = path->nodes[0];
item = btrfs_item_ptr(leaf, path->slots[0],
struct btrfs_file_extent_item);
- /* are we inside the extent that was found? */
btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);
- found_type = found_key.type;
if (found_key.objectid != objectid ||
- found_type != BTRFS_EXTENT_DATA_KEY) {
+ found_key.type != BTRFS_EXTENT_DATA_KEY) {
/*
* If we backup past the first extent we want to move forward
* and see if there is an extent in front of us, otherwise we'll
@@ -7027,30 +6673,22 @@
goto next;
}
- found_type = btrfs_file_extent_type(leaf, item);
+ extent_type = btrfs_file_extent_type(leaf, item);
extent_start = found_key.offset;
- if (found_type == BTRFS_FILE_EXTENT_REG ||
- found_type == BTRFS_FILE_EXTENT_PREALLOC) {
+ extent_end = btrfs_file_extent_end(path);
+ if (extent_type == BTRFS_FILE_EXTENT_REG ||
+ extent_type == BTRFS_FILE_EXTENT_PREALLOC) {
/* Only regular file could have regular/prealloc extent */
if (!S_ISREG(inode->vfs_inode.i_mode)) {
- err = -EUCLEAN;
+ ret = -EUCLEAN;
btrfs_crit(fs_info,
"regular/prealloc extent found for non-regular inode %llu",
btrfs_ino(inode));
goto out;
}
- extent_end = extent_start +
- btrfs_file_extent_num_bytes(leaf, item);
-
trace_btrfs_get_extent_show_fi_regular(inode, leaf, item,
extent_start);
- } else if (found_type == BTRFS_FILE_EXTENT_INLINE) {
- size_t size;
-
- size = btrfs_file_extent_ram_bytes(leaf, item);
- extent_end = ALIGN(extent_start + size,
- fs_info->sectorsize);
-
+ } else if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
trace_btrfs_get_extent_show_fi_inline(inode, leaf, item,
path->slots[0],
extent_start);
@@ -7060,12 +6698,11 @@
path->slots[0]++;
if (path->slots[0] >= btrfs_header_nritems(leaf)) {
ret = btrfs_next_leaf(root, path);
- if (ret < 0) {
- err = ret;
+ if (ret < 0)
goto out;
- }
- if (ret > 0)
+ else if (ret > 0)
goto not_found;
+
leaf = path->nodes[0];
}
btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);
@@ -7076,26 +6713,28 @@
goto not_found;
if (start > found_key.offset)
goto next;
+
+ /* New extent overlaps with existing one */
em->start = start;
em->orig_start = start;
em->len = found_key.offset - start;
- goto not_found_em;
+ em->block_start = EXTENT_MAP_HOLE;
+ goto insert;
}
- btrfs_extent_item_to_extent_map(inode, path, item,
- new_inline, em);
+ btrfs_extent_item_to_extent_map(inode, path, item, !page, em);
- if (found_type == BTRFS_FILE_EXTENT_REG ||
- found_type == BTRFS_FILE_EXTENT_PREALLOC) {
+ if (extent_type == BTRFS_FILE_EXTENT_REG ||
+ extent_type == BTRFS_FILE_EXTENT_PREALLOC) {
goto insert;
- } else if (found_type == BTRFS_FILE_EXTENT_INLINE) {
+ } else if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
unsigned long ptr;
char *map;
size_t size;
size_t extent_offset;
size_t copy_size;
- if (new_inline)
+ if (!page)
goto out;
size = btrfs_file_extent_ram_bytes(leaf, item);
@@ -7107,15 +6746,15 @@
em->orig_block_len = em->len;
em->orig_start = em->start;
ptr = btrfs_file_extent_inline_start(item) + extent_offset;
+
+ btrfs_set_path_blocking(path);
if (!PageUptodate(page)) {
if (btrfs_file_extent_compression(leaf, item) !=
BTRFS_COMPRESS_NONE) {
ret = uncompress_inline(path, page, pg_offset,
extent_offset, item);
- if (ret) {
- err = ret;
+ if (ret)
goto out;
- }
} else {
map = kmap(page);
read_extent_buffer(leaf, map + pg_offset, ptr,
@@ -7137,49 +6776,45 @@
em->start = start;
em->orig_start = start;
em->len = len;
-not_found_em:
em->block_start = EXTENT_MAP_HOLE;
insert:
+ ret = 0;
btrfs_release_path(path);
if (em->start > start || extent_map_end(em) <= start) {
btrfs_err(fs_info,
"bad extent! em: [%llu %llu] passed [%llu %llu]",
em->start, em->len, start, len);
- err = -EIO;
+ ret = -EIO;
goto out;
}
- err = 0;
write_lock(&em_tree->lock);
- err = btrfs_add_extent_mapping(fs_info, em_tree, &em, start, len);
+ ret = btrfs_add_extent_mapping(fs_info, em_tree, &em, start, len);
write_unlock(&em_tree->lock);
out:
+ btrfs_free_path(path);
trace_btrfs_get_extent(root, inode, em);
- btrfs_free_path(path);
- if (err) {
+ if (ret) {
free_extent_map(em);
- return ERR_PTR(err);
+ return ERR_PTR(ret);
}
- BUG_ON(!em); /* Error is always set */
return em;
}
struct extent_map *btrfs_get_extent_fiemap(struct btrfs_inode *inode,
- struct page *page,
- size_t pg_offset, u64 start, u64 len,
- int create)
+ u64 start, u64 len)
{
struct extent_map *em;
struct extent_map *hole_em = NULL;
- u64 range_start = start;
+ u64 delalloc_start = start;
u64 end;
- u64 found;
- u64 found_end;
+ u64 delalloc_len;
+ u64 delalloc_end;
int err = 0;
- em = btrfs_get_extent(inode, page, pg_offset, start, len, create);
+ em = btrfs_get_extent(inode, NULL, 0, start, len);
if (IS_ERR(em))
return em;
/*
@@ -7204,80 +6839,83 @@
em = NULL;
/* ok, we didn't find anything, lets look for delalloc */
- found = count_range_bits(&inode->io_tree, &range_start,
+ delalloc_len = count_range_bits(&inode->io_tree, &delalloc_start,
end, len, EXTENT_DELALLOC, 1);
- found_end = range_start + found;
- if (found_end < range_start)
- found_end = (u64)-1;
+ delalloc_end = delalloc_start + delalloc_len;
+ if (delalloc_end < delalloc_start)
+ delalloc_end = (u64)-1;
/*
- * we didn't find anything useful, return
- * the original results from get_extent()
+ * We didn't find anything useful, return the original results from
+ * get_extent()
*/
- if (range_start > end || found_end <= start) {
+ if (delalloc_start > end || delalloc_end <= start) {
em = hole_em;
hole_em = NULL;
goto out;
}
- /* adjust the range_start to make sure it doesn't
- * go backwards from the start they passed in
+ /*
+ * Adjust the delalloc_start to make sure it doesn't go backwards from
+ * the start they passed in
*/
- range_start = max(start, range_start);
- found = found_end - range_start;
+ delalloc_start = max(start, delalloc_start);
+ delalloc_len = delalloc_end - delalloc_start;
- if (found > 0) {
- u64 hole_start = start;
- u64 hole_len = len;
+ if (delalloc_len > 0) {
+ u64 hole_start;
+ u64 hole_len;
+ const u64 hole_end = extent_map_end(hole_em);
em = alloc_extent_map();
if (!em) {
err = -ENOMEM;
goto out;
}
- /*
- * when btrfs_get_extent can't find anything it
- * returns one huge hole
- *
- * make sure what it found really fits our range, and
- * adjust to make sure it is based on the start from
- * the caller
- */
- if (hole_em) {
- u64 calc_end = extent_map_end(hole_em);
- if (calc_end <= start || (hole_em->start > end)) {
- free_extent_map(hole_em);
- hole_em = NULL;
- } else {
- hole_start = max(hole_em->start, start);
- hole_len = calc_end - hole_start;
- }
+ ASSERT(hole_em);
+ /*
+ * When btrfs_get_extent can't find anything it returns one
+ * huge hole
+ *
+ * Make sure what it found really fits our range, and adjust to
+ * make sure it is based on the start from the caller
+ */
+ if (hole_end <= start || hole_em->start > end) {
+ free_extent_map(hole_em);
+ hole_em = NULL;
+ } else {
+ hole_start = max(hole_em->start, start);
+ hole_len = hole_end - hole_start;
}
- em->bdev = NULL;
- if (hole_em && range_start > hole_start) {
- /* our hole starts before our delalloc, so we
- * have to return just the parts of the hole
- * that go until the delalloc starts
+
+ if (hole_em && delalloc_start > hole_start) {
+ /*
+ * Our hole starts before our delalloc, so we have to
+ * return just the parts of the hole that go until the
+ * delalloc starts
*/
- em->len = min(hole_len,
- range_start - hole_start);
+ em->len = min(hole_len, delalloc_start - hole_start);
em->start = hole_start;
em->orig_start = hole_start;
/*
- * don't adjust block start at all,
- * it is fixed at EXTENT_MAP_HOLE
+ * Don't adjust block start at all, it is fixed at
+ * EXTENT_MAP_HOLE
*/
em->block_start = hole_em->block_start;
em->block_len = hole_len;
if (test_bit(EXTENT_FLAG_PREALLOC, &hole_em->flags))
set_bit(EXTENT_FLAG_PREALLOC, &em->flags);
} else {
- em->start = range_start;
- em->len = found;
- em->orig_start = range_start;
+ /*
+ * Hole is out of passed range or it starts after
+ * delalloc range
+ */
+ em->start = delalloc_start;
+ em->len = delalloc_len;
+ em->orig_start = delalloc_start;
em->block_start = EXTENT_MAP_DELALLOC;
- em->block_len = found;
+ em->block_len = delalloc_len;
}
} else {
return hole_em;
@@ -7292,7 +6930,7 @@
return em;
}
-static struct extent_map *btrfs_create_dio_extent(struct inode *inode,
+static struct extent_map *btrfs_create_dio_extent(struct btrfs_inode *inode,
const u64 start,
const u64 len,
const u64 orig_start,
@@ -7306,21 +6944,19 @@
int ret;
if (type != BTRFS_ORDERED_NOCOW) {
- em = create_io_em(inode, start, len, orig_start,
- block_start, block_len, orig_block_len,
- ram_bytes,
+ em = create_io_em(inode, start, len, orig_start, block_start,
+ block_len, orig_block_len, ram_bytes,
BTRFS_COMPRESS_NONE, /* compress_type */
type);
if (IS_ERR(em))
goto out;
}
- ret = btrfs_add_ordered_extent_dio(inode, start, block_start,
- len, block_len, type);
+ ret = btrfs_add_ordered_extent_dio(inode, start, block_start, len,
+ block_len, type);
if (ret) {
if (em) {
free_extent_map(em);
- btrfs_drop_extent_cache(BTRFS_I(inode), start,
- start + len - 1, 0);
+ btrfs_drop_extent_cache(inode, start, start + len - 1, 0);
}
em = ERR_PTR(ret);
}
@@ -7329,11 +6965,11 @@
return em;
}
-static struct extent_map *btrfs_new_extent_direct(struct inode *inode,
+static struct extent_map *btrfs_new_extent_direct(struct btrfs_inode *inode,
u64 start, u64 len)
{
- struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
- struct btrfs_root *root = BTRFS_I(inode)->root;
+ struct btrfs_root *root = inode->root;
+ struct btrfs_fs_info *fs_info = root->fs_info;
struct extent_map *em;
struct btrfs_key ins;
u64 alloc_hint;
@@ -7350,19 +6986,38 @@
ins.offset, BTRFS_ORDERED_REGULAR);
btrfs_dec_block_group_reservations(fs_info, ins.objectid);
if (IS_ERR(em))
- btrfs_free_reserved_extent(fs_info, ins.objectid,
- ins.offset, 1);
+ btrfs_free_reserved_extent(fs_info, ins.objectid, ins.offset,
+ 1);
return em;
}
/*
- * returns 1 when the nocow is safe, < 1 on error, 0 if the
- * block must be cow'd
+ * Check if we can do nocow write into the range [@offset, @offset + @len)
+ *
+ * @offset: File offset
+ * @len: The length to write, will be updated to the nocow writeable
+ * range
+ * @orig_start: (optional) Return the original file offset of the file extent
+ * @orig_len: (optional) Return the original on-disk length of the file extent
+ * @ram_bytes: (optional) Return the ram_bytes of the file extent
+ * @strict: if true, omit optimizations that might force us into unnecessary
+ * cow. e.g., don't trust generation number.
+ *
+ * This function will flush ordered extents in the range to ensure proper
+ * nocow checks for (nowait == false) case.
+ *
+ * Return:
+ * >0 and update @len if we can do nocow write
+ * 0 if we can't do nocow write
+ * <0 if error happened
+ *
+ * NOTE: This only checks the file extents, caller is responsible to wait for
+ * any ordered extents.
*/
noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len,
u64 *orig_start, u64 *orig_block_len,
- u64 *ram_bytes)
+ u64 *ram_bytes, bool strict)
{
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
struct btrfs_path *path;
@@ -7440,8 +7095,9 @@
* Do the same check as in btrfs_cross_ref_exist but without the
* unnecessary search.
*/
- if (btrfs_file_extent_generation(leaf, fi) <=
- btrfs_root_last_snapshot(&root->root_item))
+ if (!strict &&
+ (btrfs_file_extent_generation(leaf, fi) <=
+ btrfs_root_last_snapshot(&root->root_item)))
goto out;
backref_offset = btrfs_file_extent_offset(leaf, fi);
@@ -7477,7 +7133,8 @@
*/
ret = btrfs_cross_ref_exist(root, btrfs_ino(BTRFS_I(inode)),
- key.offset - backref_offset, disk_bytenr);
+ key.offset - backref_offset, disk_bytenr,
+ strict);
if (ret) {
ret = 0;
goto out;
@@ -7505,7 +7162,7 @@
}
static int lock_extent_direct(struct inode *inode, u64 lockstart, u64 lockend,
- struct extent_state **cached_state, int writing)
+ struct extent_state **cached_state, bool writing)
{
struct btrfs_ordered_extent *ordered;
int ret = 0;
@@ -7554,7 +7211,7 @@
*/
if (writing ||
test_bit(BTRFS_ORDERED_DIRECT, &ordered->flags))
- btrfs_start_ordered_extent(inode, ordered, 1);
+ btrfs_start_ordered_extent(ordered, 1);
else
ret = -ENOTBLK;
btrfs_put_ordered_extent(ordered);
@@ -7564,11 +7221,11 @@
* for it to complete) and then invalidate the pages for
* this range (through invalidate_inode_pages2_range()),
* but that can lead us to a deadlock with a concurrent
- * call to readpages() (a buffered read or a defrag call
+ * call to readahead (a buffered read or a defrag call
* triggered a readahead) on a page lock due to an
* ordered dio extent we created before but did not have
* yet a corresponding bio submitted (whence it can not
- * complete), which makes readpages() wait for that
+ * complete), which makes readahead wait for that
* ordered extent to complete while holding a lock on
* that page.
*/
@@ -7585,15 +7242,14 @@
}
/* The callers of this must take lock_extent() */
-static struct extent_map *create_io_em(struct inode *inode, u64 start, u64 len,
- u64 orig_start, u64 block_start,
+static struct extent_map *create_io_em(struct btrfs_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)
{
struct extent_map_tree *em_tree;
struct extent_map *em;
- struct btrfs_root *root = BTRFS_I(inode)->root;
int ret;
ASSERT(type == BTRFS_ORDERED_PREALLOC ||
@@ -7601,7 +7257,7 @@
type == BTRFS_ORDERED_NOCOW ||
type == BTRFS_ORDERED_REGULAR);
- em_tree = &BTRFS_I(inode)->extent_tree;
+ em_tree = &inode->extent_tree;
em = alloc_extent_map();
if (!em)
return ERR_PTR(-ENOMEM);
@@ -7611,7 +7267,6 @@
em->len = len;
em->block_len = block_len;
em->block_start = block_start;
- em->bdev = root->fs_info->fs_devices->latest_bdev;
em->orig_block_len = orig_block_len;
em->ram_bytes = ram_bytes;
em->generation = -1;
@@ -7624,8 +7279,8 @@
}
do {
- btrfs_drop_extent_cache(BTRFS_I(inode), em->start,
- em->start + em->len - 1, 0);
+ btrfs_drop_extent_cache(inode, em->start,
+ em->start + em->len - 1, 0);
write_lock(&em_tree->lock);
ret = add_extent_mapping(em_tree, em, 1);
write_unlock(&em_tree->lock);
@@ -7645,28 +7300,7 @@
}
-static int btrfs_get_blocks_direct_read(struct extent_map *em,
- struct buffer_head *bh_result,
- struct inode *inode,
- u64 start, u64 len)
-{
- if (em->block_start == EXTENT_MAP_HOLE ||
- test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
- return -ENOENT;
-
- len = min(len, em->len - (start - em->start));
-
- bh_result->b_blocknr = (em->block_start + (start - em->start)) >>
- inode->i_blkbits;
- bh_result->b_size = len;
- bh_result->b_bdev = em->bdev;
- set_buffer_mapped(bh_result);
-
- return 0;
-}
-
static int btrfs_get_blocks_direct_write(struct extent_map **map,
- struct buffer_head *bh_result,
struct inode *inode,
struct btrfs_dio_data *dio_data,
u64 start, u64 len)
@@ -7698,11 +7332,11 @@
block_start = em->block_start + (start - em->start);
if (can_nocow_extent(inode, start, &len, &orig_start,
- &orig_block_len, &ram_bytes) == 1 &&
+ &orig_block_len, &ram_bytes, false) == 1 &&
btrfs_inc_nocow_writers(fs_info, block_start)) {
struct extent_map *em2;
- em2 = btrfs_create_dio_extent(inode, start, len,
+ em2 = btrfs_create_dio_extent(BTRFS_I(inode), start, len,
orig_start, block_start,
len, orig_block_len,
ram_bytes, type);
@@ -7721,16 +7355,14 @@
* use the existing or preallocated extent, so does not
* need to adjust btrfs_space_info's bytes_may_use.
*/
- btrfs_free_reserved_data_space_noquota(inode, start,
- len);
+ btrfs_free_reserved_data_space_noquota(fs_info, len);
goto skip_cow;
}
}
/* this will cow the extent */
- len = bh_result->b_size;
free_extent_map(em);
- *map = em = btrfs_new_extent_direct(inode, start, len);
+ *map = em = btrfs_new_extent_direct(BTRFS_I(inode), start, len);
if (IS_ERR(em)) {
ret = PTR_ERR(em);
goto out;
@@ -7739,72 +7371,93 @@
len = min(len, em->len - (start - em->start));
skip_cow:
- bh_result->b_blocknr = (em->block_start + (start - em->start)) >>
- inode->i_blkbits;
- bh_result->b_size = len;
- bh_result->b_bdev = em->bdev;
- set_buffer_mapped(bh_result);
-
- if (!test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
- set_buffer_new(bh_result);
-
/*
* Need to update the i_size under the extent lock so buffered
* readers will get the updated i_size when we unlock.
*/
- if (!dio_data->overwrite && start + len > i_size_read(inode))
+ if (start + len > i_size_read(inode))
i_size_write(inode, start + len);
- WARN_ON(dio_data->reserve < len);
dio_data->reserve -= len;
- dio_data->unsubmitted_oe_range_end = start + len;
- current->journal_info = dio_data;
out:
return ret;
}
-static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
- struct buffer_head *bh_result, int create)
+static int btrfs_dio_iomap_begin(struct inode *inode, loff_t start,
+ loff_t length, unsigned int flags, struct iomap *iomap,
+ struct iomap *srcmap)
{
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
struct extent_map *em;
struct extent_state *cached_state = NULL;
struct btrfs_dio_data *dio_data = NULL;
- u64 start = iblock << inode->i_blkbits;
u64 lockstart, lockend;
- u64 len = bh_result->b_size;
- int unlock_bits = EXTENT_LOCKED;
+ const bool write = !!(flags & IOMAP_WRITE);
int ret = 0;
+ u64 len = length;
+ bool unlock_extents = false;
+ bool sync = (current->journal_info == BTRFS_DIO_SYNC_STUB);
- if (create)
- unlock_bits |= EXTENT_DIRTY;
- else
+ /*
+ * We used current->journal_info here to see if we were sync, but
+ * there's a lot of tests in the enospc machinery to not do flushing if
+ * we have a journal_info set, so we need to clear this out and re-set
+ * it in iomap_end.
+ */
+ ASSERT(current->journal_info == NULL ||
+ current->journal_info == BTRFS_DIO_SYNC_STUB);
+ current->journal_info = NULL;
+
+ if (!write)
len = min_t(u64, len, fs_info->sectorsize);
lockstart = start;
lockend = start + len - 1;
- if (current->journal_info) {
- /*
- * Need to pull our outstanding extents and set journal_info to NULL so
- * that anything that needs to check if there's a transaction doesn't get
- * confused.
- */
- dio_data = current->journal_info;
- current->journal_info = NULL;
+ /*
+ * The generic stuff only does filemap_write_and_wait_range, which
+ * isn't enough if we've written compressed pages to this area, so we
+ * need to flush the dirty pages again to make absolutely sure that any
+ * outstanding dirty pages are on disk.
+ */
+ if (test_bit(BTRFS_INODE_HAS_ASYNC_EXTENT,
+ &BTRFS_I(inode)->runtime_flags)) {
+ ret = filemap_fdatawrite_range(inode->i_mapping, start,
+ start + length - 1);
+ if (ret)
+ return ret;
}
+
+ dio_data = kzalloc(sizeof(*dio_data), GFP_NOFS);
+ if (!dio_data)
+ return -ENOMEM;
+
+ dio_data->sync = sync;
+ dio_data->length = length;
+ if (write) {
+ dio_data->reserve = round_up(length, fs_info->sectorsize);
+ ret = btrfs_delalloc_reserve_space(BTRFS_I(inode),
+ &dio_data->data_reserved,
+ start, dio_data->reserve);
+ if (ret) {
+ extent_changeset_free(dio_data->data_reserved);
+ kfree(dio_data);
+ return ret;
+ }
+ }
+ iomap->private = dio_data;
+
/*
* If this errors out it's because we couldn't invalidate pagecache for
* this range and we need to fallback to buffered.
*/
- if (lock_extent_direct(inode, lockstart, lockend, &cached_state,
- create)) {
+ if (lock_extent_direct(inode, lockstart, lockend, &cached_state, write)) {
ret = -ENOTBLK;
goto err;
}
- em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, start, len, 0);
+ em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, start, len);
if (IS_ERR(em)) {
ret = PTR_ERR(em);
goto unlock_err;
@@ -7827,443 +7480,253 @@
if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags) ||
em->block_start == EXTENT_MAP_INLINE) {
free_extent_map(em);
- ret = -ENOTBLK;
+ /*
+ * If we are in a NOWAIT context, return -EAGAIN in order to
+ * fallback to buffered IO. This is not only because we can
+ * block with buffered IO (no support for NOWAIT semantics at
+ * the moment) but also to avoid returning short reads to user
+ * space - this happens if we were able to read some data from
+ * previous non-compressed extents and then when we fallback to
+ * buffered IO, at btrfs_file_read_iter() by calling
+ * filemap_read(), we fail to fault in pages for the read buffer,
+ * in which case filemap_read() returns a short read (the number
+ * of bytes previously read is > 0, so it does not return -EFAULT).
+ */
+ ret = (flags & IOMAP_NOWAIT) ? -EAGAIN : -ENOTBLK;
goto unlock_err;
}
- if (create) {
- ret = btrfs_get_blocks_direct_write(&em, bh_result, inode,
- dio_data, start, len);
+ len = min(len, em->len - (start - em->start));
+ if (write) {
+ ret = btrfs_get_blocks_direct_write(&em, inode, dio_data,
+ start, len);
if (ret < 0)
goto unlock_err;
-
- /* clear and unlock the entire range */
- clear_extent_bit(&BTRFS_I(inode)->io_tree, lockstart, lockend,
- unlock_bits, 1, 0, &cached_state);
+ unlock_extents = true;
+ /* Recalc len in case the new em is smaller than requested */
+ len = min(len, em->len - (start - em->start));
} else {
- ret = btrfs_get_blocks_direct_read(em, bh_result, inode,
- start, len);
- /* Can be negative only if we read from a hole */
- if (ret < 0) {
- ret = 0;
- free_extent_map(em);
- goto unlock_err;
- }
/*
* We need to unlock only the end area that we aren't using.
* The rest is going to be unlocked by the endio routine.
*/
- lockstart = start + bh_result->b_size;
- if (lockstart < lockend) {
- clear_extent_bit(&BTRFS_I(inode)->io_tree, lockstart,
- lockend, unlock_bits, 1, 0,
- &cached_state);
- } else {
- free_extent_state(cached_state);
- }
+ lockstart = start + len;
+ if (lockstart < lockend)
+ unlock_extents = true;
}
+
+ if (unlock_extents)
+ unlock_extent_cached(&BTRFS_I(inode)->io_tree,
+ lockstart, lockend, &cached_state);
+ else
+ free_extent_state(cached_state);
+
+ /*
+ * Translate extent map information to iomap.
+ * We trim the extents (and move the addr) even though iomap code does
+ * that, since we have locked only the parts we are performing I/O in.
+ */
+ if ((em->block_start == EXTENT_MAP_HOLE) ||
+ (test_bit(EXTENT_FLAG_PREALLOC, &em->flags) && !write)) {
+ iomap->addr = IOMAP_NULL_ADDR;
+ iomap->type = IOMAP_HOLE;
+ } else {
+ iomap->addr = em->block_start + (start - em->start);
+ iomap->type = IOMAP_MAPPED;
+ }
+ iomap->offset = start;
+ iomap->bdev = fs_info->fs_devices->latest_bdev;
+ iomap->length = len;
free_extent_map(em);
return 0;
unlock_err:
- clear_extent_bit(&BTRFS_I(inode)->io_tree, lockstart, lockend,
- unlock_bits, 1, 0, &cached_state);
+ unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart, lockend,
+ &cached_state);
err:
- if (dio_data)
- current->journal_info = dio_data;
+ if (dio_data) {
+ btrfs_delalloc_release_space(BTRFS_I(inode),
+ dio_data->data_reserved, start,
+ dio_data->reserve, true);
+ btrfs_delalloc_release_extents(BTRFS_I(inode), dio_data->reserve);
+ extent_changeset_free(dio_data->data_reserved);
+ kfree(dio_data);
+ }
return ret;
}
-static inline blk_status_t submit_dio_repair_bio(struct inode *inode,
- struct bio *bio,
- int mirror_num)
+static int btrfs_dio_iomap_end(struct inode *inode, loff_t pos, loff_t length,
+ ssize_t written, unsigned int flags, struct iomap *iomap)
{
+ int ret = 0;
+ struct btrfs_dio_data *dio_data = iomap->private;
+ size_t submitted = dio_data->submitted;
+ const bool write = !!(flags & IOMAP_WRITE);
+
+ if (!write && (iomap->type == IOMAP_HOLE)) {
+ /* If reading from a hole, unlock and return */
+ unlock_extent(&BTRFS_I(inode)->io_tree, pos, pos + length - 1);
+ goto out;
+ }
+
+ if (submitted < length) {
+ pos += submitted;
+ length -= submitted;
+ if (write)
+ __endio_write_update_ordered(BTRFS_I(inode), pos,
+ length, false);
+ else
+ unlock_extent(&BTRFS_I(inode)->io_tree, pos,
+ pos + length - 1);
+ ret = -ENOTBLK;
+ }
+
+ if (write) {
+ if (dio_data->reserve)
+ btrfs_delalloc_release_space(BTRFS_I(inode),
+ dio_data->data_reserved, pos,
+ dio_data->reserve, true);
+ btrfs_delalloc_release_extents(BTRFS_I(inode), dio_data->length);
+ extent_changeset_free(dio_data->data_reserved);
+ }
+out:
+ /*
+ * We're all done, we can re-set the current->journal_info now safely
+ * for our endio.
+ */
+ if (dio_data->sync) {
+ ASSERT(current->journal_info == NULL);
+ current->journal_info = BTRFS_DIO_SYNC_STUB;
+ }
+ kfree(dio_data);
+ iomap->private = NULL;
+
+ return ret;
+}
+
+static void btrfs_dio_private_put(struct btrfs_dio_private *dip)
+{
+ /*
+ * This implies a barrier so that stores to dio_bio->bi_status before
+ * this and loads of dio_bio->bi_status after this are fully ordered.
+ */
+ if (!refcount_dec_and_test(&dip->refs))
+ return;
+
+ if (bio_op(dip->dio_bio) == REQ_OP_WRITE) {
+ __endio_write_update_ordered(BTRFS_I(dip->inode),
+ dip->logical_offset,
+ dip->bytes,
+ !dip->dio_bio->bi_status);
+ } else {
+ unlock_extent(&BTRFS_I(dip->inode)->io_tree,
+ dip->logical_offset,
+ dip->logical_offset + dip->bytes - 1);
+ }
+
+ bio_endio(dip->dio_bio);
+ kfree(dip);
+}
+
+static blk_status_t submit_dio_repair_bio(struct inode *inode, struct bio *bio,
+ int mirror_num,
+ unsigned long bio_flags)
+{
+ struct btrfs_dio_private *dip = bio->bi_private;
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
blk_status_t ret;
BUG_ON(bio_op(bio) == REQ_OP_WRITE);
- ret = btrfs_bio_wq_end_io(fs_info, bio, BTRFS_WQ_ENDIO_DIO_REPAIR);
+ 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, 0);
-
+ refcount_inc(&dip->refs);
+ ret = btrfs_map_bio(fs_info, bio, mirror_num);
+ if (ret)
+ refcount_dec(&dip->refs);
return ret;
}
-static int btrfs_check_dio_repairable(struct inode *inode,
- struct bio *failed_bio,
- struct io_failure_record *failrec,
- int failed_mirror)
+static blk_status_t btrfs_check_read_dio_bio(struct inode *inode,
+ struct btrfs_io_bio *io_bio,
+ const bool uptodate)
{
- struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
- int num_copies;
-
- num_copies = btrfs_num_copies(fs_info, failrec->logical, failrec->len);
- if (num_copies == 1) {
- /*
- * we only have a single copy of the data, so don't bother with
- * all the retry and error correction code that follows. no
- * matter what the error is, it is very likely to persist.
- */
- btrfs_debug(fs_info,
- "Check DIO Repairable: cannot repair, num_copies=%d, next_mirror %d, failed_mirror %d",
- num_copies, failrec->this_mirror, failed_mirror);
- return 0;
- }
-
- failrec->failed_mirror = failed_mirror;
- failrec->this_mirror++;
- if (failrec->this_mirror == failed_mirror)
- failrec->this_mirror++;
-
- if (failrec->this_mirror > num_copies) {
- btrfs_debug(fs_info,
- "Check DIO Repairable: (fail) num_copies=%d, next_mirror %d, failed_mirror %d",
- num_copies, failrec->this_mirror, failed_mirror);
- return 0;
- }
-
- return 1;
-}
-
-static blk_status_t dio_read_error(struct inode *inode, struct bio *failed_bio,
- struct page *page, unsigned int pgoff,
- u64 start, u64 end, int failed_mirror,
- bio_end_io_t *repair_endio, void *repair_arg)
-{
- struct io_failure_record *failrec;
- struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
+ struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info;
+ const u32 sectorsize = fs_info->sectorsize;
struct extent_io_tree *failure_tree = &BTRFS_I(inode)->io_failure_tree;
- struct bio *bio;
- int isector;
- unsigned int read_mode = 0;
- int segs;
- int ret;
- blk_status_t status;
- struct bio_vec bvec;
-
- BUG_ON(bio_op(failed_bio) == REQ_OP_WRITE);
-
- ret = btrfs_get_io_failure_record(inode, start, end, &failrec);
- if (ret)
- return errno_to_blk_status(ret);
-
- ret = btrfs_check_dio_repairable(inode, failed_bio, failrec,
- failed_mirror);
- if (!ret) {
- free_io_failure(failure_tree, io_tree, failrec);
- return BLK_STS_IOERR;
- }
-
- segs = bio_segments(failed_bio);
- bio_get_first_bvec(failed_bio, &bvec);
- if (segs > 1 ||
- (bvec.bv_len > btrfs_inode_sectorsize(inode)))
- read_mode |= REQ_FAILFAST_DEV;
-
- isector = start - btrfs_io_bio(failed_bio)->logical;
- isector >>= inode->i_sb->s_blocksize_bits;
- bio = btrfs_create_repair_bio(inode, failed_bio, failrec, page,
- pgoff, isector, repair_endio, repair_arg);
- bio->bi_opf = REQ_OP_READ | read_mode;
-
- btrfs_debug(BTRFS_I(inode)->root->fs_info,
- "repair DIO read error: submitting new dio read[%#x] to this_mirror=%d, in_validation=%d",
- read_mode, failrec->this_mirror, failrec->in_validation);
-
- status = submit_dio_repair_bio(inode, bio, failrec->this_mirror);
- if (status) {
- free_io_failure(failure_tree, io_tree, failrec);
- bio_put(bio);
- }
-
- return status;
-}
-
-struct btrfs_retry_complete {
- struct completion done;
- struct inode *inode;
- u64 start;
- int uptodate;
-};
-
-static void btrfs_retry_endio_nocsum(struct bio *bio)
-{
- struct btrfs_retry_complete *done = bio->bi_private;
- struct inode *inode = done->inode;
- struct bio_vec *bvec;
- struct extent_io_tree *io_tree, *failure_tree;
- int i;
-
- if (bio->bi_status)
- goto end;
-
- ASSERT(bio->bi_vcnt == 1);
- io_tree = &BTRFS_I(inode)->io_tree;
- failure_tree = &BTRFS_I(inode)->io_failure_tree;
- ASSERT(bio_first_bvec_all(bio)->bv_len == btrfs_inode_sectorsize(inode));
-
- done->uptodate = 1;
- ASSERT(!bio_flagged(bio, BIO_CLONED));
- bio_for_each_segment_all(bvec, bio, i)
- clean_io_failure(BTRFS_I(inode)->root->fs_info, failure_tree,
- io_tree, done->start, bvec->bv_page,
- btrfs_ino(BTRFS_I(inode)), 0);
-end:
- complete(&done->done);
- bio_put(bio);
-}
-
-static blk_status_t __btrfs_correct_data_nocsum(struct inode *inode,
- struct btrfs_io_bio *io_bio)
-{
- struct btrfs_fs_info *fs_info;
+ struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
+ const bool csum = !(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM);
struct bio_vec bvec;
struct bvec_iter iter;
- struct btrfs_retry_complete done;
- u64 start;
- unsigned int pgoff;
- u32 sectorsize;
- int nr_sectors;
- blk_status_t ret;
+ u64 start = io_bio->logical;
+ int icsum = 0;
blk_status_t err = BLK_STS_OK;
- fs_info = BTRFS_I(inode)->root->fs_info;
- sectorsize = fs_info->sectorsize;
+ __bio_for_each_segment(bvec, &io_bio->bio, iter, io_bio->iter) {
+ unsigned int i, nr_sectors, pgoff;
- start = io_bio->logical;
- done.inode = inode;
- io_bio->bio.bi_iter = io_bio->iter;
-
- bio_for_each_segment(bvec, &io_bio->bio, iter) {
nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info, bvec.bv_len);
pgoff = bvec.bv_offset;
-
-next_block_or_try_again:
- done.uptodate = 0;
- done.start = start;
- init_completion(&done.done);
-
- ret = dio_read_error(inode, &io_bio->bio, bvec.bv_page,
- pgoff, start, start + sectorsize - 1,
- io_bio->mirror_num,
- btrfs_retry_endio_nocsum, &done);
- if (ret) {
- err = ret;
- goto next;
- }
-
- wait_for_completion_io(&done.done);
-
- if (!done.uptodate) {
- /* We might have another mirror, so try again */
- goto next_block_or_try_again;
- }
-
-next:
- start += sectorsize;
-
- nr_sectors--;
- if (nr_sectors) {
- pgoff += sectorsize;
+ for (i = 0; i < nr_sectors; i++) {
ASSERT(pgoff < PAGE_SIZE);
- goto next_block_or_try_again;
+ if (uptodate &&
+ (!csum || !check_data_csum(inode, io_bio, icsum,
+ bvec.bv_page, pgoff,
+ start, sectorsize))) {
+ clean_io_failure(fs_info, failure_tree, io_tree,
+ start, bvec.bv_page,
+ btrfs_ino(BTRFS_I(inode)),
+ pgoff);
+ } else {
+ blk_status_t status;
+
+ status = btrfs_submit_read_repair(inode,
+ &io_bio->bio,
+ start - io_bio->logical,
+ bvec.bv_page, pgoff,
+ start,
+ start + sectorsize - 1,
+ io_bio->mirror_num,
+ submit_dio_repair_bio);
+ if (status)
+ err = status;
+ }
+ start += sectorsize;
+ icsum++;
+ pgoff += sectorsize;
}
}
-
return err;
}
-static void btrfs_retry_endio(struct bio *bio)
-{
- struct btrfs_retry_complete *done = bio->bi_private;
- struct btrfs_io_bio *io_bio = btrfs_io_bio(bio);
- struct extent_io_tree *io_tree, *failure_tree;
- struct inode *inode = done->inode;
- struct bio_vec *bvec;
- int uptodate;
- int ret;
- int i;
-
- if (bio->bi_status)
- goto end;
-
- uptodate = 1;
-
- ASSERT(bio->bi_vcnt == 1);
- ASSERT(bio_first_bvec_all(bio)->bv_len == btrfs_inode_sectorsize(done->inode));
-
- io_tree = &BTRFS_I(inode)->io_tree;
- failure_tree = &BTRFS_I(inode)->io_failure_tree;
-
- ASSERT(!bio_flagged(bio, BIO_CLONED));
- bio_for_each_segment_all(bvec, bio, i) {
- ret = __readpage_endio_check(inode, io_bio, i, bvec->bv_page,
- bvec->bv_offset, done->start,
- bvec->bv_len);
- if (!ret)
- clean_io_failure(BTRFS_I(inode)->root->fs_info,
- failure_tree, io_tree, done->start,
- bvec->bv_page,
- btrfs_ino(BTRFS_I(inode)),
- bvec->bv_offset);
- else
- uptodate = 0;
- }
-
- done->uptodate = uptodate;
-end:
- complete(&done->done);
- bio_put(bio);
-}
-
-static blk_status_t __btrfs_subio_endio_read(struct inode *inode,
- struct btrfs_io_bio *io_bio, blk_status_t err)
-{
- struct btrfs_fs_info *fs_info;
- struct bio_vec bvec;
- struct bvec_iter iter;
- struct btrfs_retry_complete done;
- u64 start;
- u64 offset = 0;
- u32 sectorsize;
- int nr_sectors;
- unsigned int pgoff;
- int csum_pos;
- bool uptodate = (err == 0);
- int ret;
- blk_status_t status;
-
- fs_info = BTRFS_I(inode)->root->fs_info;
- sectorsize = fs_info->sectorsize;
-
- err = BLK_STS_OK;
- start = io_bio->logical;
- done.inode = inode;
- io_bio->bio.bi_iter = io_bio->iter;
-
- bio_for_each_segment(bvec, &io_bio->bio, iter) {
- nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info, bvec.bv_len);
-
- pgoff = bvec.bv_offset;
-next_block:
- if (uptodate) {
- csum_pos = BTRFS_BYTES_TO_BLKS(fs_info, offset);
- ret = __readpage_endio_check(inode, io_bio, csum_pos,
- bvec.bv_page, pgoff, start, sectorsize);
- if (likely(!ret))
- goto next;
- }
-try_again:
- done.uptodate = 0;
- done.start = start;
- init_completion(&done.done);
-
- status = dio_read_error(inode, &io_bio->bio, bvec.bv_page,
- pgoff, start, start + sectorsize - 1,
- io_bio->mirror_num, btrfs_retry_endio,
- &done);
- if (status) {
- err = status;
- goto next;
- }
-
- wait_for_completion_io(&done.done);
-
- if (!done.uptodate) {
- /* We might have another mirror, so try again */
- goto try_again;
- }
-next:
- offset += sectorsize;
- start += sectorsize;
-
- ASSERT(nr_sectors);
-
- nr_sectors--;
- if (nr_sectors) {
- pgoff += sectorsize;
- ASSERT(pgoff < PAGE_SIZE);
- goto next_block;
- }
- }
-
- return err;
-}
-
-static blk_status_t btrfs_subio_endio_read(struct inode *inode,
- struct btrfs_io_bio *io_bio, blk_status_t err)
-{
- bool skip_csum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM;
-
- if (skip_csum) {
- if (unlikely(err))
- return __btrfs_correct_data_nocsum(inode, io_bio);
- else
- return BLK_STS_OK;
- } else {
- return __btrfs_subio_endio_read(inode, io_bio, err);
- }
-}
-
-static void btrfs_endio_direct_read(struct bio *bio)
-{
- struct btrfs_dio_private *dip = bio->bi_private;
- struct inode *inode = dip->inode;
- struct bio *dio_bio;
- struct btrfs_io_bio *io_bio = btrfs_io_bio(bio);
- blk_status_t err = bio->bi_status;
-
- if (dip->flags & BTRFS_DIO_ORIG_BIO_SUBMITTED)
- err = btrfs_subio_endio_read(inode, io_bio, err);
-
- unlock_extent(&BTRFS_I(inode)->io_tree, dip->logical_offset,
- dip->logical_offset + dip->bytes - 1);
- dio_bio = dip->dio_bio;
-
- kfree(dip);
-
- dio_bio->bi_status = err;
- dio_end_io(dio_bio);
-
- if (io_bio->end_io)
- io_bio->end_io(io_bio, blk_status_to_errno(err));
- bio_put(bio);
-}
-
-static void __endio_write_update_ordered(struct inode *inode,
+static void __endio_write_update_ordered(struct btrfs_inode *inode,
const u64 offset, const u64 bytes,
const bool uptodate)
{
- struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+ struct btrfs_fs_info *fs_info = inode->root->fs_info;
struct btrfs_ordered_extent *ordered = NULL;
struct btrfs_workqueue *wq;
- btrfs_work_func_t func;
u64 ordered_offset = offset;
u64 ordered_bytes = bytes;
u64 last_offset;
- if (btrfs_is_free_space_inode(BTRFS_I(inode))) {
+ if (btrfs_is_free_space_inode(inode))
wq = fs_info->endio_freespace_worker;
- func = btrfs_freespace_write_helper;
- } else {
+ else
wq = fs_info->endio_write_workers;
- func = btrfs_endio_write_helper;
- }
while (ordered_offset < offset + bytes) {
last_offset = ordered_offset;
if (btrfs_dec_test_first_ordered_pending(inode, &ordered,
- &ordered_offset,
- ordered_bytes,
- uptodate)) {
- btrfs_init_work(&ordered->work, func,
- finish_ordered_fn,
- NULL, NULL);
+ &ordered_offset,
+ ordered_bytes,
+ uptodate)) {
+ btrfs_init_work(&ordered->work, finish_ordered_fn, NULL,
+ NULL);
btrfs_queue_work(wq, &ordered->work);
}
/*
@@ -8274,7 +7737,7 @@
return;
/*
* Our bio might span multiple ordered extents. In this case
- * we keep goin until we have accounted the whole dio.
+ * we keep going until we have accounted the whole dio.
*/
if (ordered_offset < offset + bytes) {
ordered_bytes = offset + bytes - ordered_offset;
@@ -8283,29 +7746,12 @@
}
}
-static void btrfs_endio_direct_write(struct bio *bio)
-{
- struct btrfs_dio_private *dip = bio->bi_private;
- struct bio *dio_bio = dip->dio_bio;
-
- __endio_write_update_ordered(dip->inode, dip->logical_offset,
- dip->bytes, !bio->bi_status);
-
- kfree(dip);
-
- dio_bio->bi_status = bio->bi_status;
- dio_end_io(dio_bio);
- bio_put(bio);
-}
-
static blk_status_t btrfs_submit_bio_start_direct_io(void *private_data,
struct bio *bio, u64 offset)
{
struct inode *inode = private_data;
- blk_status_t ret;
- ret = btrfs_csum_one_bio(inode, bio, offset, 1);
- BUG_ON(ret); /* -ENOMEM */
- return 0;
+
+ return btrfs_csum_one_bio(BTRFS_I(inode), bio, offset, 1);
}
static void btrfs_end_dio_bio(struct bio *bio)
@@ -8321,62 +7767,16 @@
(unsigned long long)bio->bi_iter.bi_sector,
bio->bi_iter.bi_size, err);
- if (dip->subio_endio)
- err = dip->subio_endio(dip->inode, btrfs_io_bio(bio), err);
-
- if (err) {
- /*
- * We want to perceive the errors flag being set before
- * decrementing the reference count. We don't need a barrier
- * since atomic operations with a return value are fully
- * ordered as per atomic_t.txt
- */
- dip->errors = 1;
+ if (bio_op(bio) == REQ_OP_READ) {
+ err = btrfs_check_read_dio_bio(dip->inode, btrfs_io_bio(bio),
+ !err);
}
- /* if there are more bios still pending for this dio, just exit */
- if (!atomic_dec_and_test(&dip->pending_bios))
- goto out;
+ if (err)
+ dip->dio_bio->bi_status = err;
- if (dip->errors) {
- bio_io_error(dip->orig_bio);
- } else {
- dip->dio_bio->bi_status = BLK_STS_OK;
- bio_endio(dip->orig_bio);
- }
-out:
bio_put(bio);
-}
-
-static inline blk_status_t btrfs_lookup_and_bind_dio_csum(struct inode *inode,
- struct btrfs_dio_private *dip,
- struct bio *bio,
- u64 file_offset)
-{
- struct btrfs_io_bio *io_bio = btrfs_io_bio(bio);
- struct btrfs_io_bio *orig_io_bio = btrfs_io_bio(dip->orig_bio);
- blk_status_t ret;
-
- /*
- * We load all the csum data we need when we submit
- * the first bio to reduce the csum tree search and
- * contention.
- */
- if (dip->logical_offset == file_offset) {
- ret = btrfs_lookup_bio_sums_dio(inode, dip->orig_bio,
- file_offset);
- if (ret)
- return ret;
- }
-
- if (bio == dip->orig_bio)
- return 0;
-
- file_offset -= dip->logical_offset;
- file_offset >>= inode->i_sb->s_blocksize_bits;
- io_bio->csum = (u8 *)(((u32 *)orig_io_bio->csum) + file_offset);
-
- return 0;
+ btrfs_dio_private_put(dip);
}
static inline blk_status_t btrfs_submit_dio_bio(struct bio *bio,
@@ -8410,222 +7810,169 @@
* If we aren't doing async submit, calculate the csum of the
* bio now.
*/
- ret = btrfs_csum_one_bio(inode, bio, file_offset, 1);
+ ret = btrfs_csum_one_bio(BTRFS_I(inode), bio, file_offset, 1);
if (ret)
goto err;
} else {
- ret = btrfs_lookup_and_bind_dio_csum(inode, dip, bio,
- file_offset);
- if (ret)
- goto err;
+ u64 csum_offset;
+
+ csum_offset = file_offset - dip->logical_offset;
+ csum_offset >>= inode->i_sb->s_blocksize_bits;
+ csum_offset *= btrfs_super_csum_size(fs_info->super_copy);
+ btrfs_io_bio(bio)->csum = dip->csums + csum_offset;
}
map:
- ret = btrfs_map_bio(fs_info, bio, 0, 0);
+ ret = btrfs_map_bio(fs_info, bio, 0);
err:
return ret;
}
-static int btrfs_submit_direct_hook(struct btrfs_dio_private *dip)
+/*
+ * If this succeeds, the btrfs_dio_private is responsible for cleaning up locked
+ * or ordered extents whether or not we submit any bios.
+ */
+static struct btrfs_dio_private *btrfs_create_dio_private(struct bio *dio_bio,
+ struct inode *inode,
+ loff_t file_offset)
{
- struct inode *inode = dip->inode;
+ const bool write = (bio_op(dio_bio) == REQ_OP_WRITE);
+ const bool csum = !(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM);
+ size_t dip_size;
+ struct btrfs_dio_private *dip;
+
+ dip_size = sizeof(*dip);
+ if (!write && csum) {
+ struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+ const u16 csum_size = btrfs_super_csum_size(fs_info->super_copy);
+ size_t nblocks;
+
+ nblocks = dio_bio->bi_iter.bi_size >> inode->i_sb->s_blocksize_bits;
+ dip_size += csum_size * nblocks;
+ }
+
+ dip = kzalloc(dip_size, GFP_NOFS);
+ if (!dip)
+ return NULL;
+
+ dip->inode = inode;
+ dip->logical_offset = file_offset;
+ dip->bytes = dio_bio->bi_iter.bi_size;
+ dip->disk_bytenr = (u64)dio_bio->bi_iter.bi_sector << 9;
+ dip->dio_bio = dio_bio;
+ refcount_set(&dip->refs, 1);
+ return dip;
+}
+
+static blk_qc_t btrfs_submit_direct(struct inode *inode, struct iomap *iomap,
+ struct bio *dio_bio, loff_t file_offset)
+{
+ const bool write = (bio_op(dio_bio) == REQ_OP_WRITE);
+ const bool csum = !(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM);
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+ const bool raid56 = (btrfs_data_alloc_profile(fs_info) &
+ BTRFS_BLOCK_GROUP_RAID56_MASK);
+ struct btrfs_dio_private *dip;
struct bio *bio;
- struct bio *orig_bio = dip->orig_bio;
- u64 start_sector = orig_bio->bi_iter.bi_sector;
- u64 file_offset = dip->logical_offset;
- u64 map_length;
+ u64 start_sector;
int async_submit = 0;
u64 submit_len;
int clone_offset = 0;
int clone_len;
int ret;
blk_status_t status;
+ struct btrfs_io_geometry geom;
+ struct btrfs_dio_data *dio_data = iomap->private;
- map_length = orig_bio->bi_iter.bi_size;
- submit_len = map_length;
- ret = btrfs_map_block(fs_info, btrfs_op(orig_bio), start_sector << 9,
- &map_length, NULL, 0);
- if (ret)
- return -EIO;
-
- if (map_length >= submit_len) {
- bio = orig_bio;
- dip->flags |= BTRFS_DIO_ORIG_BIO_SUBMITTED;
- goto submit;
+ dip = btrfs_create_dio_private(dio_bio, inode, file_offset);
+ if (!dip) {
+ if (!write) {
+ unlock_extent(&BTRFS_I(inode)->io_tree, file_offset,
+ file_offset + dio_bio->bi_iter.bi_size - 1);
+ }
+ dio_bio->bi_status = BLK_STS_RESOURCE;
+ bio_endio(dio_bio);
+ return BLK_QC_T_NONE;
}
- /* async crcs make it difficult to collect full stripe writes. */
- if (btrfs_data_alloc_profile(fs_info) & BTRFS_BLOCK_GROUP_RAID56_MASK)
- async_submit = 0;
- else
- async_submit = 1;
+ if (!write && csum) {
+ /*
+ * Load the csums up front to reduce csum tree searches and
+ * contention when submitting bios.
+ */
+ status = btrfs_lookup_bio_sums(inode, dio_bio, file_offset,
+ dip->csums);
+ if (status != BLK_STS_OK)
+ goto out_err;
+ }
- /* bio split */
- ASSERT(map_length <= INT_MAX);
+ start_sector = dio_bio->bi_iter.bi_sector;
+ submit_len = dio_bio->bi_iter.bi_size;
+
do {
- clone_len = min_t(int, submit_len, map_length);
+ ret = btrfs_get_io_geometry(fs_info, btrfs_op(dio_bio),
+ start_sector << 9, submit_len,
+ &geom);
+ if (ret) {
+ status = errno_to_blk_status(ret);
+ goto out_err;
+ }
+ ASSERT(geom.len <= INT_MAX);
+
+ clone_len = min_t(int, submit_len, geom.len);
/*
* This will never fail as it's passing GPF_NOFS and
* the allocation is backed by btrfs_bioset.
*/
- bio = btrfs_bio_clone_partial(orig_bio, clone_offset,
- clone_len);
+ bio = btrfs_bio_clone_partial(dio_bio, clone_offset, clone_len);
bio->bi_private = dip;
bio->bi_end_io = btrfs_end_dio_bio;
btrfs_io_bio(bio)->logical = file_offset;
ASSERT(submit_len >= clone_len);
submit_len -= clone_len;
- if (submit_len == 0)
- break;
/*
* Increase the count before we submit the bio so we know
* the end IO handler won't happen before we increase the
* count. Otherwise, the dip might get freed before we're
* done setting it up.
+ *
+ * We transfer the initial reference to the last bio, so we
+ * don't need to increment the reference count for the last one.
*/
- atomic_inc(&dip->pending_bios);
+ if (submit_len > 0) {
+ refcount_inc(&dip->refs);
+ /*
+ * If we are submitting more than one bio, submit them
+ * all asynchronously. The exception is RAID 5 or 6, as
+ * asynchronous checksums make it difficult to collect
+ * full stripe writes.
+ */
+ if (!raid56)
+ async_submit = 1;
+ }
status = btrfs_submit_dio_bio(bio, inode, file_offset,
async_submit);
if (status) {
bio_put(bio);
- atomic_dec(&dip->pending_bios);
+ if (submit_len > 0)
+ refcount_dec(&dip->refs);
goto out_err;
}
+ dio_data->submitted += clone_len;
clone_offset += clone_len;
start_sector += clone_len >> 9;
file_offset += clone_len;
-
- map_length = submit_len;
- ret = btrfs_map_block(fs_info, btrfs_op(orig_bio),
- start_sector << 9, &map_length, NULL, 0);
- if (ret)
- goto out_err;
} while (submit_len > 0);
+ return BLK_QC_T_NONE;
-submit:
- status = btrfs_submit_dio_bio(bio, inode, file_offset, async_submit);
- if (!status)
- return 0;
-
- if (bio != orig_bio)
- bio_put(bio);
out_err:
- dip->errors = 1;
- /*
- * Before atomic variable goto zero, we must make sure dip->errors is
- * perceived to be set. This ordering is ensured by the fact that an
- * atomic operations with a return value are fully ordered as per
- * atomic_t.txt
- */
- if (atomic_dec_and_test(&dip->pending_bios))
- bio_io_error(dip->orig_bio);
-
- /* bio_end_io() will handle error, so we needn't return it */
- return 0;
-}
-
-static void btrfs_submit_direct(struct bio *dio_bio, struct inode *inode,
- loff_t file_offset)
-{
- struct btrfs_dio_private *dip = NULL;
- struct bio *bio = NULL;
- struct btrfs_io_bio *io_bio;
- bool write = (bio_op(dio_bio) == REQ_OP_WRITE);
- int ret = 0;
-
- bio = btrfs_bio_clone(dio_bio);
-
- dip = kzalloc(sizeof(*dip), GFP_NOFS);
- if (!dip) {
- ret = -ENOMEM;
- goto free_ordered;
- }
-
- dip->private = dio_bio->bi_private;
- dip->inode = inode;
- dip->logical_offset = file_offset;
- dip->bytes = dio_bio->bi_iter.bi_size;
- dip->disk_bytenr = (u64)dio_bio->bi_iter.bi_sector << 9;
- bio->bi_private = dip;
- dip->orig_bio = bio;
- dip->dio_bio = dio_bio;
- atomic_set(&dip->pending_bios, 1);
- io_bio = btrfs_io_bio(bio);
- io_bio->logical = file_offset;
-
- if (write) {
- bio->bi_end_io = btrfs_endio_direct_write;
- } else {
- bio->bi_end_io = btrfs_endio_direct_read;
- dip->subio_endio = btrfs_subio_endio_read;
- }
-
- /*
- * Reset the range for unsubmitted ordered extents (to a 0 length range)
- * even if we fail to submit a bio, because in such case we do the
- * corresponding error handling below and it must not be done a second
- * time by btrfs_direct_IO().
- */
- if (write) {
- struct btrfs_dio_data *dio_data = current->journal_info;
-
- dio_data->unsubmitted_oe_range_end = dip->logical_offset +
- dip->bytes;
- dio_data->unsubmitted_oe_range_start =
- dio_data->unsubmitted_oe_range_end;
- }
-
- ret = btrfs_submit_direct_hook(dip);
- if (!ret)
- return;
-
- if (io_bio->end_io)
- io_bio->end_io(io_bio, ret);
-
-free_ordered:
- /*
- * If we arrived here it means either we failed to submit the dip
- * or we either failed to clone the dio_bio or failed to allocate the
- * dip. If we cloned the dio_bio and allocated the dip, we can just
- * call bio_endio against our io_bio so that we get proper resource
- * cleanup if we fail to submit the dip, otherwise, we must do the
- * same as btrfs_endio_direct_[write|read] because we can't call these
- * callbacks - they require an allocated dip and a clone of dio_bio.
- */
- if (bio && dip) {
- bio_io_error(bio);
- /*
- * The end io callbacks free our dip, do the final put on bio
- * and all the cleanup and final put for dio_bio (through
- * dio_end_io()).
- */
- dip = NULL;
- bio = NULL;
- } else {
- if (write)
- __endio_write_update_ordered(inode,
- file_offset,
- dio_bio->bi_iter.bi_size,
- false);
- else
- unlock_extent(&BTRFS_I(inode)->io_tree, file_offset,
- file_offset + dio_bio->bi_iter.bi_size - 1);
-
- dio_bio->bi_status = BLK_STS_IOERR;
- /*
- * Releases and cleans up our dio_bio, no need to bio_put()
- * nor bio_endio()/bio_io_error() against dio_bio.
- */
- dio_end_io(dio_bio);
- }
- if (bio)
- bio_put(bio);
- kfree(dip);
+ dip->dio_bio->bi_status = status;
+ btrfs_dio_private_put(dip);
+ return BLK_QC_T_NONE;
}
static ssize_t check_direct_IO(struct btrfs_fs_info *fs_info,
@@ -8661,37 +8008,63 @@
return retval;
}
-static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
+static inline int btrfs_maybe_fsync_end_io(struct kiocb *iocb, ssize_t size,
+ int error, unsigned flags)
+{
+ /*
+ * Now if we're still in the context of our submitter we know we can't
+ * safely run generic_write_sync(), so clear our flag here so that the
+ * caller knows to follow up with a sync.
+ */
+ if (current->journal_info == BTRFS_DIO_SYNC_STUB) {
+ current->journal_info = NULL;
+ return error;
+ }
+
+ if (error)
+ return error;
+
+ if (size) {
+ iocb->ki_flags |= IOCB_DSYNC;
+ return generic_write_sync(iocb, size);
+ }
+
+ return 0;
+}
+
+static const struct iomap_ops btrfs_dio_iomap_ops = {
+ .iomap_begin = btrfs_dio_iomap_begin,
+ .iomap_end = btrfs_dio_iomap_end,
+};
+
+static const struct iomap_dio_ops btrfs_dio_ops = {
+ .submit_io = btrfs_submit_direct,
+};
+
+static const struct iomap_dio_ops btrfs_sync_dops = {
+ .submit_io = btrfs_submit_direct,
+ .end_io = btrfs_maybe_fsync_end_io,
+};
+
+ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
- struct btrfs_dio_data dio_data = { 0 };
struct extent_changeset *data_reserved = NULL;
loff_t offset = iocb->ki_pos;
size_t count = 0;
- int flags = 0;
- bool wakeup = true;
bool relock = false;
ssize_t ret;
- if (check_direct_IO(fs_info, iter, offset))
+ if (check_direct_IO(fs_info, iter, offset)) {
+ ASSERT(current->journal_info == NULL ||
+ current->journal_info == BTRFS_DIO_SYNC_STUB);
+ current->journal_info = NULL;
return 0;
+ }
- inode_dio_begin(inode);
-
- /*
- * The generic stuff only does filemap_write_and_wait_range, which
- * isn't enough if we've written compressed pages to this area, so
- * we need to flush the dirty pages again to make absolutely sure
- * that any outstanding dirty pages are on disk.
- */
count = iov_iter_count(iter);
- if (test_bit(BTRFS_INODE_HAS_ASYNC_EXTENT,
- &BTRFS_I(inode)->runtime_flags))
- filemap_fdatawrite_range(inode->i_mapping, offset,
- offset + count - 1);
-
if (iov_iter_rw(iter) == WRITE) {
/*
* If the write DIO is beyond the EOF, we need update
@@ -8699,65 +8072,29 @@
* not unlock the i_mutex at this case.
*/
if (offset + count <= inode->i_size) {
- dio_data.overwrite = 1;
inode_unlock(inode);
relock = true;
}
- ret = btrfs_delalloc_reserve_space(inode, &data_reserved,
- offset, count);
- if (ret)
- goto out;
-
- /*
- * We need to know how many extents we reserved so that we can
- * do the accounting properly if we go over the number we
- * originally calculated. Abuse current->journal_info for this.
- */
- dio_data.reserve = round_up(count,
- fs_info->sectorsize);
- dio_data.unsubmitted_oe_range_start = (u64)offset;
- dio_data.unsubmitted_oe_range_end = (u64)offset;
- current->journal_info = &dio_data;
down_read(&BTRFS_I(inode)->dio_sem);
- } else if (test_bit(BTRFS_INODE_READDIO_NEED_LOCK,
- &BTRFS_I(inode)->runtime_flags)) {
- inode_dio_end(inode);
- flags = DIO_LOCKING | DIO_SKIP_HOLES;
- wakeup = false;
}
- ret = __blockdev_direct_IO(iocb, inode,
- fs_info->fs_devices->latest_bdev,
- iter, btrfs_get_blocks_direct, NULL,
- btrfs_submit_direct, flags);
- if (iov_iter_rw(iter) == WRITE) {
+ /*
+ * We have are actually a sync iocb, so we need our fancy endio to know
+ * if we need to sync.
+ */
+ if (current->journal_info)
+ ret = iomap_dio_rw(iocb, iter, &btrfs_dio_iomap_ops,
+ &btrfs_sync_dops, is_sync_kiocb(iocb));
+ else
+ ret = iomap_dio_rw(iocb, iter, &btrfs_dio_iomap_ops,
+ &btrfs_dio_ops, is_sync_kiocb(iocb));
+
+ if (ret == -ENOTBLK)
+ ret = 0;
+
+ if (iov_iter_rw(iter) == WRITE)
up_read(&BTRFS_I(inode)->dio_sem);
- current->journal_info = NULL;
- if (ret < 0 && ret != -EIOCBQUEUED) {
- if (dio_data.reserve)
- btrfs_delalloc_release_space(inode, data_reserved,
- offset, dio_data.reserve, true);
- /*
- * On error we might have left some ordered extents
- * without submitting corresponding bios for them, so
- * cleanup them up to avoid other tasks getting them
- * and waiting for them to complete forever.
- */
- if (dio_data.unsubmitted_oe_range_start <
- dio_data.unsubmitted_oe_range_end)
- __endio_write_update_ordered(inode,
- dio_data.unsubmitted_oe_range_start,
- dio_data.unsubmitted_oe_range_end -
- dio_data.unsubmitted_oe_range_start,
- false);
- } else if (ret >= 0 && (size_t)ret < count)
- btrfs_delalloc_release_space(inode, data_reserved,
- offset, count - (size_t)ret, true);
- btrfs_delalloc_release_extents(BTRFS_I(inode), count);
- }
-out:
- if (wakeup)
- inode_dio_end(inode);
+
if (relock)
inode_lock(inode);
@@ -8765,25 +8102,33 @@
return ret;
}
-#define BTRFS_FIEMAP_FLAGS (FIEMAP_FLAG_SYNC)
-
static int btrfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
- __u64 start, __u64 len)
+ u64 start, u64 len)
{
int ret;
- ret = fiemap_check_flags(fieinfo, BTRFS_FIEMAP_FLAGS);
+ ret = fiemap_prep(inode, fieinfo, start, &len, 0);
if (ret)
return ret;
- return extent_fiemap(inode, fieinfo, start, len);
+ return extent_fiemap(BTRFS_I(inode), fieinfo, start, len);
}
int btrfs_readpage(struct file *file, struct page *page)
{
- struct extent_io_tree *tree;
- tree = &BTRFS_I(page->mapping->host)->io_tree;
- return extent_read_full_page(tree, page, btrfs_get_extent, 0);
+ struct btrfs_inode *inode = BTRFS_I(page->mapping->host);
+ u64 start = page_offset(page);
+ u64 end = start + PAGE_SIZE - 1;
+ unsigned long bio_flags = 0;
+ struct bio *bio = NULL;
+ int ret;
+
+ btrfs_lock_and_flush_ordered_range(inode, start, end, NULL);
+
+ ret = btrfs_do_readpage(page, NULL, &bio, &bio_flags, 0, NULL);
+ if (bio)
+ ret = submit_one_bio(bio, 0, bio_flags);
+ return ret;
}
static int btrfs_writepage(struct page *page, struct writeback_control *wbc)
@@ -8817,21 +8162,16 @@
return extent_writepages(mapping, wbc);
}
-static int
-btrfs_readpages(struct file *file, struct address_space *mapping,
- struct list_head *pages, unsigned nr_pages)
+static void btrfs_readahead(struct readahead_control *rac)
{
- return extent_readpages(mapping, pages, nr_pages);
+ extent_readahead(rac);
}
static int __btrfs_releasepage(struct page *page, gfp_t gfp_flags)
{
int ret = try_release_extent_mapping(page, gfp_flags);
- if (ret == 1) {
- ClearPagePrivate(page);
- set_page_private(page, 0);
- put_page(page);
- }
+ if (ret == 1)
+ detach_page_private(page);
return ret;
}
@@ -8842,18 +8182,45 @@
return __btrfs_releasepage(page, gfp_flags);
}
+#ifdef CONFIG_MIGRATION
+static int btrfs_migratepage(struct address_space *mapping,
+ struct page *newpage, struct page *page,
+ enum migrate_mode mode)
+{
+ int ret;
+
+ ret = migrate_page_move_mapping(mapping, newpage, page, 0);
+ if (ret != MIGRATEPAGE_SUCCESS)
+ return ret;
+
+ if (page_has_private(page))
+ attach_page_private(newpage, detach_page_private(page));
+
+ if (PagePrivate2(page)) {
+ ClearPagePrivate2(page);
+ SetPagePrivate2(newpage);
+ }
+
+ if (mode != MIGRATE_SYNC_NO_COPY)
+ migrate_page_copy(newpage, page);
+ else
+ migrate_page_states(newpage, page);
+ return MIGRATEPAGE_SUCCESS;
+}
+#endif
+
static void btrfs_invalidatepage(struct page *page, unsigned int offset,
unsigned int length)
{
- struct inode *inode = page->mapping->host;
- struct extent_io_tree *tree;
+ struct btrfs_inode *inode = BTRFS_I(page->mapping->host);
+ struct extent_io_tree *tree = &inode->io_tree;
struct btrfs_ordered_extent *ordered;
struct extent_state *cached_state = NULL;
u64 page_start = page_offset(page);
u64 page_end = page_start + PAGE_SIZE - 1;
u64 start;
u64 end;
- int inode_evicting = inode->i_state & I_FREEING;
+ int inode_evicting = inode->vfs_inode.i_state & I_FREEING;
/*
* we have the page locked, so new writeback can't start,
@@ -8864,28 +8231,39 @@
*/
wait_on_page_writeback(page);
- tree = &BTRFS_I(inode)->io_tree;
- if (offset) {
+ /*
+ * For subpage case, we have call sites like
+ * btrfs_punch_hole_lock_range() which passes range not aligned to
+ * sectorsize.
+ * If the range doesn't cover the full page, we don't need to and
+ * shouldn't clear page extent mapped, as page->private can still
+ * record subpage dirty bits for other part of the range.
+ *
+ * For cases that can invalidate the full even the range doesn't
+ * cover the full page, like invalidating the last page, we're
+ * still safe to wait for ordered extent to finish.
+ */
+ if (!(offset == 0 && length == PAGE_SIZE)) {
btrfs_releasepage(page, GFP_NOFS);
return;
}
if (!inode_evicting)
lock_extent_bits(tree, page_start, page_end, &cached_state);
-again:
+
start = page_start;
- ordered = btrfs_lookup_ordered_range(BTRFS_I(inode), start,
- page_end - start + 1);
+again:
+ ordered = btrfs_lookup_ordered_range(inode, start, page_end - start + 1);
if (ordered) {
- end = min(page_end, ordered->file_offset + ordered->len - 1);
+ end = min(page_end,
+ ordered->file_offset + ordered->num_bytes - 1);
/*
* IO on this page will never be started, so we need
* to account for any ordered extents now
*/
if (!inode_evicting)
clear_extent_bit(tree, start, end,
- EXTENT_DIRTY | EXTENT_DELALLOC |
- EXTENT_DELALLOC_NEW |
+ EXTENT_DELALLOC | EXTENT_DELALLOC_NEW |
EXTENT_LOCKED | EXTENT_DO_ACCOUNTING |
EXTENT_DEFRAG, 1, 0, &cached_state);
/*
@@ -8896,7 +8274,7 @@
struct btrfs_ordered_inode_tree *tree;
u64 new_len;
- tree = &BTRFS_I(inode)->ordered_tree;
+ tree = &inode->ordered_tree;
spin_lock_irq(&tree->lock);
set_bit(BTRFS_ORDERED_TRUNCATED, &ordered->flags);
@@ -8937,8 +8315,7 @@
*/
btrfs_qgroup_free_data(inode, NULL, page_start, PAGE_SIZE);
if (!inode_evicting) {
- clear_extent_bit(tree, page_start, page_end,
- EXTENT_LOCKED | EXTENT_DIRTY |
+ clear_extent_bit(tree, page_start, page_end, EXTENT_LOCKED |
EXTENT_DELALLOC | EXTENT_DELALLOC_NEW |
EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG, 1, 1,
&cached_state);
@@ -8947,11 +8324,7 @@
}
ClearPageChecked(page);
- if (PagePrivate(page)) {
- ClearPagePrivate(page);
- set_page_private(page, 0);
- put_page(page);
- }
+ detach_page_private(page);
}
/*
@@ -9004,8 +8377,8 @@
* end up waiting indefinitely to get a lock on the page currently
* being processed by btrfs_page_mkwrite() function.
*/
- ret2 = btrfs_delalloc_reserve_space(inode, &data_reserved, page_start,
- reserved_space);
+ ret2 = btrfs_delalloc_reserve_space(BTRFS_I(inode), &data_reserved,
+ page_start, reserved_space);
if (!ret2) {
ret2 = file_update_time(vmf->vma->vm_file);
reserved = 1;
@@ -9042,7 +8415,7 @@
unlock_extent_cached(io_tree, page_start, page_end,
&cached_state);
unlock_page(page);
- btrfs_start_ordered_extent(inode, ordered, 1);
+ btrfs_start_ordered_extent(ordered, 1);
btrfs_put_ordered_extent(ordered);
goto again;
}
@@ -9052,9 +8425,9 @@
fs_info->sectorsize);
if (reserved_space < PAGE_SIZE) {
end = page_start + reserved_space - 1;
- btrfs_delalloc_release_space(inode, data_reserved,
- page_start, PAGE_SIZE - reserved_space,
- true);
+ btrfs_delalloc_release_space(BTRFS_I(inode),
+ data_reserved, page_start,
+ PAGE_SIZE - reserved_space, true);
}
}
@@ -9066,23 +8439,21 @@
* reserve data&meta space before lock_page() (see above comments).
*/
clear_extent_bit(&BTRFS_I(inode)->io_tree, page_start, end,
- EXTENT_DIRTY | EXTENT_DELALLOC |
- EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG,
- 0, 0, &cached_state);
+ EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING |
+ EXTENT_DEFRAG, 0, 0, &cached_state);
- ret2 = btrfs_set_extent_delalloc(inode, page_start, end, 0,
- &cached_state, 0);
+ ret2 = btrfs_set_extent_delalloc(BTRFS_I(inode), page_start, end, 0,
+ &cached_state);
if (ret2) {
unlock_extent_cached(io_tree, page_start, page_end,
&cached_state);
ret = VM_FAULT_SIGBUS;
goto out_unlock;
}
- ret2 = 0;
/* page is wholly or partially inside EOF */
if (page_start + PAGE_SIZE > size)
- zero_start = size & ~PAGE_MASK;
+ zero_start = offset_in_page(size);
else
zero_start = PAGE_SIZE;
@@ -9096,24 +8467,20 @@
set_page_dirty(page);
SetPageUptodate(page);
- BTRFS_I(inode)->last_trans = fs_info->generation;
- BTRFS_I(inode)->last_sub_trans = BTRFS_I(inode)->root->log_transid;
- BTRFS_I(inode)->last_log_commit = BTRFS_I(inode)->root->last_log_commit;
+ btrfs_set_inode_last_sub_trans(BTRFS_I(inode));
unlock_extent_cached(io_tree, page_start, page_end, &cached_state);
- if (!ret2) {
- btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE);
- sb_end_pagefault(inode->i_sb);
- extent_changeset_free(data_reserved);
- return VM_FAULT_LOCKED;
- }
+ btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE);
+ sb_end_pagefault(inode->i_sb);
+ extent_changeset_free(data_reserved);
+ return VM_FAULT_LOCKED;
out_unlock:
unlock_page(page);
out:
btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE);
- btrfs_delalloc_release_space(inode, data_reserved, page_start,
+ btrfs_delalloc_release_space(BTRFS_I(inode), data_reserved, page_start,
reserved_space, (ret != 0));
out_noreserve:
sb_end_pagefault(inode->i_sb);
@@ -9129,7 +8496,7 @@
int ret;
struct btrfs_trans_handle *trans;
u64 mask = fs_info->sectorsize - 1;
- u64 min_size = btrfs_calc_trunc_metadata_size(fs_info, 1);
+ u64 min_size = btrfs_calc_metadata_size(fs_info, 1);
if (!skip_writeback) {
ret = btrfs_wait_ordered_range(inode, inode->i_size & (~mask),
@@ -9184,7 +8551,7 @@
/* Migrate the slack space for the truncate to our reserve */
ret = btrfs_block_rsv_migrate(&fs_info->trans_block_rsv, rsv,
- min_size, 0);
+ min_size, false);
BUG_ON(ret);
/*
@@ -9219,9 +8586,9 @@
break;
}
- btrfs_block_rsv_release(fs_info, rsv, -1);
+ btrfs_block_rsv_release(fs_info, rsv, -1, NULL);
ret = btrfs_block_rsv_migrate(&fs_info->trans_block_rsv,
- rsv, min_size, 0);
+ rsv, min_size, false);
BUG_ON(ret); /* shouldn't happen */
trans->block_rsv = rsv;
}
@@ -9244,7 +8611,7 @@
ret = PTR_ERR(trans);
goto out;
}
- btrfs_ordered_update_i_size(inode, inode->i_size, NULL);
+ btrfs_inode_safe_disk_i_size_write(inode, 0);
}
if (trans) {
@@ -9327,7 +8694,7 @@
ei->index_cnt = (u64)-1;
ei->dir_index = 0;
ei->last_unlink_trans = 0;
- ei->last_link_trans = 0;
+ ei->last_reflink_trans = 0;
ei->last_log_commit = 0;
spin_lock_init(&ei->lock);
@@ -9346,13 +8713,15 @@
inode = &ei->vfs_inode;
extent_map_tree_init(&ei->extent_tree);
- extent_io_tree_init(&ei->io_tree, inode);
- extent_io_tree_init(&ei->io_failure_tree, inode);
- ei->io_tree.track_uptodate = 1;
- ei->io_failure_tree.track_uptodate = 1;
+ extent_io_tree_init(fs_info, &ei->io_tree, IO_TREE_INODE_IO, inode);
+ extent_io_tree_init(fs_info, &ei->io_failure_tree,
+ IO_TREE_INODE_IO_FAILURE, inode);
+ extent_io_tree_init(fs_info, &ei->file_extent_tree,
+ IO_TREE_INODE_FILE_EXTENT, inode);
+ ei->io_tree.track_uptodate = true;
+ ei->io_failure_tree.track_uptodate = true;
atomic_set(&ei->sync_writers, 0);
mutex_init(&ei->log_mutex);
- mutex_init(&ei->delalloc_mutex);
btrfs_ordered_inode_tree_init(&ei->ordered_tree);
INIT_LIST_HEAD(&ei->delalloc_inodes);
INIT_LIST_HEAD(&ei->delayed_iput);
@@ -9370,27 +8739,26 @@
}
#endif
-static void btrfs_i_callback(struct rcu_head *head)
+void btrfs_free_inode(struct inode *inode)
{
- struct inode *inode = container_of(head, struct inode, i_rcu);
kmem_cache_free(btrfs_inode_cachep, BTRFS_I(inode));
}
-void btrfs_destroy_inode(struct inode *inode)
+void btrfs_destroy_inode(struct inode *vfs_inode)
{
- struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
struct btrfs_ordered_extent *ordered;
- struct btrfs_root *root = BTRFS_I(inode)->root;
+ struct btrfs_inode *inode = BTRFS_I(vfs_inode);
+ struct btrfs_root *root = inode->root;
- WARN_ON(!hlist_empty(&inode->i_dentry));
- WARN_ON(inode->i_data.nrpages);
- WARN_ON(BTRFS_I(inode)->block_rsv.reserved);
- WARN_ON(BTRFS_I(inode)->block_rsv.size);
- WARN_ON(BTRFS_I(inode)->outstanding_extents);
- WARN_ON(BTRFS_I(inode)->delalloc_bytes);
- WARN_ON(BTRFS_I(inode)->new_delalloc_bytes);
- WARN_ON(BTRFS_I(inode)->csum_bytes);
- WARN_ON(BTRFS_I(inode)->defrag_bytes);
+ WARN_ON(!hlist_empty(&vfs_inode->i_dentry));
+ WARN_ON(vfs_inode->i_data.nrpages);
+ WARN_ON(inode->block_rsv.reserved);
+ WARN_ON(inode->block_rsv.size);
+ WARN_ON(inode->outstanding_extents);
+ WARN_ON(inode->delalloc_bytes);
+ WARN_ON(inode->new_delalloc_bytes);
+ WARN_ON(inode->csum_bytes);
+ WARN_ON(inode->defrag_bytes);
/*
* This can happen where we create an inode, but somebody else also
@@ -9398,16 +8766,16 @@
* created.
*/
if (!root)
- goto free;
+ return;
while (1) {
ordered = btrfs_lookup_first_ordered_extent(inode, (u64)-1);
if (!ordered)
break;
else {
- btrfs_err(fs_info,
+ btrfs_err(root->fs_info,
"found ordered extent %llu %llu on inode cleanup",
- ordered->file_offset, ordered->len);
+ ordered->file_offset, ordered->num_bytes);
btrfs_remove_ordered_extent(inode, ordered);
btrfs_put_ordered_extent(ordered);
btrfs_put_ordered_extent(ordered);
@@ -9415,9 +8783,9 @@
}
btrfs_qgroup_check_reserved_leak(inode);
inode_tree_del(inode);
- btrfs_drop_extent_cache(BTRFS_I(inode), 0, (u64)-1, 0);
-free:
- call_rcu(&inode->i_rcu, btrfs_i_callback);
+ btrfs_drop_extent_cache(inode, 0, (u64)-1, 0);
+ btrfs_inode_clear_file_extent_range(inode, 0, (u64)-1);
+ btrfs_put_root(inode->root);
}
int btrfs_drop_inode(struct inode *inode)
@@ -9542,19 +8910,15 @@
struct inode *new_inode = new_dentry->d_inode;
struct inode *old_inode = old_dentry->d_inode;
struct timespec64 ctime = current_time(old_inode);
- struct dentry *parent;
u64 old_ino = btrfs_ino(BTRFS_I(old_inode));
u64 new_ino = btrfs_ino(BTRFS_I(new_inode));
u64 old_idx = 0;
u64 new_idx = 0;
int ret;
+ int ret2;
bool root_log_pinned = false;
bool dest_log_pinned = false;
- struct btrfs_log_ctx ctx_root;
- struct btrfs_log_ctx ctx_dest;
- bool sync_log_root = false;
- bool sync_log_dest = false;
- bool commit_transaction = false;
+ bool need_abort = false;
/*
* For non-subvolumes allow exchange only within one subvolume, in the
@@ -9565,9 +8929,6 @@
(old_ino != BTRFS_FIRST_FREE_OBJECTID ||
new_ino != BTRFS_FIRST_FREE_OBJECTID))
return -EXDEV;
-
- btrfs_init_log_ctx(&ctx_root, old_inode);
- btrfs_init_log_ctx(&ctx_dest, new_inode);
/* close the race window with snapshot create/destroy ioctl */
if (old_ino == BTRFS_FIRST_FREE_OBJECTID ||
@@ -9608,7 +8969,7 @@
/* Reference for the source. */
if (old_ino == BTRFS_FIRST_FREE_OBJECTID) {
/* force full log commit if subvolume involved. */
- btrfs_set_log_full_commit(fs_info, trans);
+ btrfs_set_log_full_commit(trans);
} else {
btrfs_pin_log_trans(root);
root_log_pinned = true;
@@ -9620,12 +8981,13 @@
old_idx);
if (ret)
goto out_fail;
+ need_abort = true;
}
/* And now for the dest. */
if (new_ino == BTRFS_FIRST_FREE_OBJECTID) {
/* force full log commit if subvolume involved. */
- btrfs_set_log_full_commit(fs_info, trans);
+ btrfs_set_log_full_commit(trans);
} else {
btrfs_pin_log_trans(dest);
dest_log_pinned = true;
@@ -9635,8 +8997,11 @@
new_ino,
btrfs_ino(BTRFS_I(old_dir)),
new_idx);
- if (ret)
+ if (ret) {
+ if (need_abort)
+ btrfs_abort_transaction(trans, ret);
goto out_fail;
+ }
}
/* Update inode version and ctime/mtime. */
@@ -9710,30 +9075,14 @@
BTRFS_I(new_inode)->dir_index = new_idx;
if (root_log_pinned) {
- parent = new_dentry->d_parent;
- ret = btrfs_log_new_name(trans, BTRFS_I(old_inode),
- BTRFS_I(old_dir), parent,
- false, &ctx_root);
- if (ret == BTRFS_NEED_LOG_SYNC)
- sync_log_root = true;
- else if (ret == BTRFS_NEED_TRANS_COMMIT)
- commit_transaction = true;
- ret = 0;
+ btrfs_log_new_name(trans, BTRFS_I(old_inode), BTRFS_I(old_dir),
+ new_dentry->d_parent);
btrfs_end_log_trans(root);
root_log_pinned = false;
}
if (dest_log_pinned) {
- if (!commit_transaction) {
- parent = old_dentry->d_parent;
- ret = btrfs_log_new_name(trans, BTRFS_I(new_inode),
- BTRFS_I(new_dir), parent,
- false, &ctx_dest);
- if (ret == BTRFS_NEED_LOG_SYNC)
- sync_log_dest = true;
- else if (ret == BTRFS_NEED_TRANS_COMMIT)
- commit_transaction = true;
- ret = 0;
- }
+ btrfs_log_new_name(trans, BTRFS_I(new_inode), BTRFS_I(new_dir),
+ old_dentry->d_parent);
btrfs_end_log_trans(dest);
dest_log_pinned = false;
}
@@ -9755,7 +9104,7 @@
btrfs_inode_in_log(BTRFS_I(old_inode), fs_info->generation) ||
(new_inode &&
btrfs_inode_in_log(BTRFS_I(new_inode), fs_info->generation)))
- btrfs_set_log_full_commit(fs_info, trans);
+ btrfs_set_log_full_commit(trans);
if (root_log_pinned) {
btrfs_end_log_trans(root);
@@ -9766,45 +9115,12 @@
dest_log_pinned = false;
}
}
- if (!ret && sync_log_root && !commit_transaction) {
- ret = btrfs_sync_log(trans, BTRFS_I(old_inode)->root,
- &ctx_root);
- if (ret)
- commit_transaction = true;
- }
- if (!ret && sync_log_dest && !commit_transaction) {
- ret = btrfs_sync_log(trans, BTRFS_I(new_inode)->root,
- &ctx_dest);
- if (ret)
- commit_transaction = true;
- }
- if (commit_transaction) {
- /*
- * We may have set commit_transaction when logging the new name
- * in the destination root, in which case we left the source
- * root context in the list of log contextes. So make sure we
- * remove it to avoid invalid memory accesses, since the context
- * was allocated in our stack frame.
- */
- if (sync_log_root) {
- mutex_lock(&root->log_mutex);
- list_del_init(&ctx_root.list);
- mutex_unlock(&root->log_mutex);
- }
- ret = btrfs_commit_transaction(trans);
- } else {
- int ret2;
-
- ret2 = btrfs_end_transaction(trans);
- ret = ret ? ret : ret2;
- }
+ ret2 = btrfs_end_transaction(trans);
+ ret = ret ? ret : ret2;
out_notrans:
if (new_ino == BTRFS_FIRST_FREE_OBJECTID ||
old_ino == BTRFS_FIRST_FREE_OBJECTID)
up_read(&fs_info->subvol_sem);
-
- ASSERT(list_empty(&ctx_root.list));
- ASSERT(list_empty(&ctx_dest.list));
return ret;
}
@@ -9819,7 +9135,7 @@
u64 objectid;
u64 index;
- ret = btrfs_find_free_ino(root, &objectid);
+ ret = btrfs_find_free_objectid(root, &objectid);
if (ret)
return ret;
@@ -9873,11 +9189,9 @@
struct inode *old_inode = d_inode(old_dentry);
u64 index = 0;
int ret;
+ int ret2;
u64 old_ino = btrfs_ino(BTRFS_I(old_inode));
bool log_pinned = false;
- struct btrfs_log_ctx ctx;
- bool sync_log = false;
- bool commit_transaction = false;
if (btrfs_ino(BTRFS_I(new_dir)) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)
return -EPERM;
@@ -9954,7 +9268,7 @@
BTRFS_I(old_inode)->dir_index = 0ULL;
if (unlikely(old_ino == BTRFS_FIRST_FREE_OBJECTID)) {
/* force full log commit if subvolume involved. */
- btrfs_set_log_full_commit(fs_info, trans);
+ btrfs_set_log_full_commit(trans);
} else {
btrfs_pin_log_trans(root);
log_pinned = true;
@@ -10027,17 +9341,8 @@
BTRFS_I(old_inode)->dir_index = index;
if (log_pinned) {
- struct dentry *parent = new_dentry->d_parent;
-
- btrfs_init_log_ctx(&ctx, old_inode);
- ret = btrfs_log_new_name(trans, BTRFS_I(old_inode),
- BTRFS_I(old_dir), parent,
- false, &ctx);
- if (ret == BTRFS_NEED_LOG_SYNC)
- sync_log = true;
- else if (ret == BTRFS_NEED_TRANS_COMMIT)
- commit_transaction = true;
- ret = 0;
+ btrfs_log_new_name(trans, BTRFS_I(old_inode), BTRFS_I(old_dir),
+ new_dentry->d_parent);
btrfs_end_log_trans(root);
log_pinned = false;
}
@@ -10069,28 +9374,13 @@
btrfs_inode_in_log(BTRFS_I(old_inode), fs_info->generation) ||
(new_inode &&
btrfs_inode_in_log(BTRFS_I(new_inode), fs_info->generation)))
- btrfs_set_log_full_commit(fs_info, trans);
+ btrfs_set_log_full_commit(trans);
btrfs_end_log_trans(root);
log_pinned = false;
}
- if (!ret && sync_log) {
- ret = btrfs_sync_log(trans, BTRFS_I(old_inode)->root, &ctx);
- if (ret)
- commit_transaction = true;
- } else if (sync_log) {
- mutex_lock(&root->log_mutex);
- list_del(&ctx.list);
- mutex_unlock(&root->log_mutex);
- }
- if (commit_transaction) {
- ret = btrfs_commit_transaction(trans);
- } else {
- int ret2;
-
- ret2 = btrfs_end_transaction(trans);
- ret = ret ? ret : ret2;
- }
+ ret2 = btrfs_end_transaction(trans);
+ ret = ret ? ret : ret2;
out_notrans:
if (old_ino == BTRFS_FIRST_FREE_OBJECTID)
up_read(&fs_info->subvol_sem);
@@ -10147,9 +9437,7 @@
init_completion(&work->completion);
INIT_LIST_HEAD(&work->list);
work->inode = inode;
- WARN_ON_ONCE(!inode);
- btrfs_init_work(&work->work, btrfs_flush_delalloc_helper,
- btrfs_run_delalloc_work, NULL, NULL);
+ btrfs_init_work(&work->work, btrfs_run_delalloc_work, NULL, NULL);
return work;
}
@@ -10158,7 +9446,9 @@
* some fairly slow code that needs optimization. This walks the list
* of all the inodes with pending delalloc and forces them to disk.
*/
-static int start_delalloc_inodes(struct btrfs_root *root, int nr, bool snapshot)
+static int start_delalloc_inodes(struct btrfs_root *root,
+ struct writeback_control *wbc, bool snapshot,
+ bool in_reclaim_context)
{
struct btrfs_inode *binode;
struct inode *inode;
@@ -10166,6 +9456,7 @@
struct list_head works;
struct list_head splice;
int ret = 0;
+ bool full_flush = wbc->nr_to_write == LONG_MAX;
INIT_LIST_HEAD(&works);
INIT_LIST_HEAD(&splice);
@@ -10179,6 +9470,11 @@
list_move_tail(&binode->delalloc_inodes,
&root->delalloc_inodes);
+
+ if (in_reclaim_context &&
+ test_bit(BTRFS_INODE_NO_DELALLOC_FLUSH, &binode->runtime_flags))
+ continue;
+
inode = igrab(&binode->vfs_inode);
if (!inode) {
cond_resched_lock(&root->delalloc_lock);
@@ -10189,18 +9485,26 @@
if (snapshot)
set_bit(BTRFS_INODE_SNAPSHOT_FLUSH,
&binode->runtime_flags);
- work = btrfs_alloc_delalloc_work(inode);
- if (!work) {
- iput(inode);
- ret = -ENOMEM;
- goto out;
+ if (full_flush) {
+ work = btrfs_alloc_delalloc_work(inode);
+ if (!work) {
+ iput(inode);
+ ret = -ENOMEM;
+ goto out;
+ }
+ list_add_tail(&work->list, &works);
+ btrfs_queue_work(root->fs_info->flush_workers,
+ &work->work);
+ } else {
+ ret = sync_inode(inode, wbc);
+ if (!ret &&
+ test_bit(BTRFS_INODE_HAS_ASYNC_EXTENT,
+ &BTRFS_I(inode)->runtime_flags))
+ ret = sync_inode(inode, wbc);
+ btrfs_add_delayed_iput(inode);
+ if (ret || wbc->nr_to_write <= 0)
+ goto out;
}
- list_add_tail(&work->list, &works);
- btrfs_queue_work(root->fs_info->flush_workers,
- &work->work);
- ret++;
- if (nr != -1 && ret >= nr)
- goto out;
cond_resched();
spin_lock(&root->delalloc_lock);
}
@@ -10224,20 +9528,29 @@
int btrfs_start_delalloc_snapshot(struct btrfs_root *root)
{
+ struct writeback_control wbc = {
+ .nr_to_write = LONG_MAX,
+ .sync_mode = WB_SYNC_NONE,
+ .range_start = 0,
+ .range_end = LLONG_MAX,
+ };
struct btrfs_fs_info *fs_info = root->fs_info;
- int ret;
if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state))
return -EROFS;
- ret = start_delalloc_inodes(root, -1, true);
- if (ret > 0)
- ret = 0;
- return ret;
+ return start_delalloc_inodes(root, &wbc, true, false);
}
-int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, int nr)
+int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, u64 nr,
+ bool in_reclaim_context)
{
+ struct writeback_control wbc = {
+ .nr_to_write = (nr == U64_MAX) ? LONG_MAX : (unsigned long)nr,
+ .sync_mode = WB_SYNC_NONE,
+ .range_start = 0,
+ .range_end = LLONG_MAX,
+ };
struct btrfs_root *root;
struct list_head splice;
int ret;
@@ -10251,23 +9564,25 @@
spin_lock(&fs_info->delalloc_root_lock);
list_splice_init(&fs_info->delalloc_roots, &splice);
while (!list_empty(&splice) && nr) {
+ /*
+ * Reset nr_to_write here so we know that we're doing a full
+ * flush.
+ */
+ if (nr == U64_MAX)
+ wbc.nr_to_write = LONG_MAX;
+
root = list_first_entry(&splice, struct btrfs_root,
delalloc_root);
- root = btrfs_grab_fs_root(root);
+ root = btrfs_grab_root(root);
BUG_ON(!root);
list_move_tail(&root->delalloc_root,
&fs_info->delalloc_roots);
spin_unlock(&fs_info->delalloc_root_lock);
- ret = start_delalloc_inodes(root, nr, false);
- btrfs_put_fs_root(root);
- if (ret < 0)
+ ret = start_delalloc_inodes(root, &wbc, false, in_reclaim_context);
+ btrfs_put_root(root);
+ if (ret < 0 || wbc.nr_to_write <= 0)
goto out;
-
- if (nr != -1) {
- nr -= ret;
- WARN_ON(nr < 0);
- }
spin_lock(&fs_info->delalloc_root_lock);
}
spin_unlock(&fs_info->delalloc_root_lock);
@@ -10316,7 +9631,7 @@
if (IS_ERR(trans))
return PTR_ERR(trans);
- err = btrfs_find_free_ino(root, &objectid);
+ err = btrfs_find_free_objectid(root, &objectid);
if (err)
goto out_unlock;
@@ -10338,7 +9653,6 @@
inode->i_fop = &btrfs_file_operations;
inode->i_op = &btrfs_file_inode_operations;
inode->i_mapping->a_ops = &btrfs_aops;
- BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
err = btrfs_init_inode_security(trans, inode, dir, &dentry->d_name);
if (err)
@@ -10377,7 +9691,6 @@
inode->i_op = &btrfs_symlink_inode_operations;
inode_nohighmem(inode);
- inode->i_mapping->a_ops = &btrfs_symlink_aops;
inode_set_bytes(inode, name_len);
btrfs_i_size_write(BTRFS_I(inode), name_len);
err = btrfs_update_inode(trans, root, inode);
@@ -10404,6 +9717,65 @@
return err;
}
+static struct btrfs_trans_handle *insert_prealloc_file_extent(
+ struct btrfs_trans_handle *trans_in,
+ struct inode *inode, struct btrfs_key *ins,
+ u64 file_offset)
+{
+ struct btrfs_file_extent_item stack_fi;
+ struct btrfs_replace_extent_info extent_info;
+ struct btrfs_trans_handle *trans = trans_in;
+ struct btrfs_path *path;
+ u64 start = ins->objectid;
+ u64 len = ins->offset;
+ int ret;
+
+ memset(&stack_fi, 0, sizeof(stack_fi));
+
+ btrfs_set_stack_file_extent_type(&stack_fi, BTRFS_FILE_EXTENT_PREALLOC);
+ btrfs_set_stack_file_extent_disk_bytenr(&stack_fi, start);
+ btrfs_set_stack_file_extent_disk_num_bytes(&stack_fi, len);
+ btrfs_set_stack_file_extent_num_bytes(&stack_fi, len);
+ btrfs_set_stack_file_extent_ram_bytes(&stack_fi, len);
+ btrfs_set_stack_file_extent_compression(&stack_fi, BTRFS_COMPRESS_NONE);
+ /* Encryption and other encoding is reserved and all 0 */
+
+ ret = btrfs_qgroup_release_data(BTRFS_I(inode), file_offset, len);
+ if (ret < 0)
+ return ERR_PTR(ret);
+
+ if (trans) {
+ ret = insert_reserved_file_extent(trans, BTRFS_I(inode),
+ file_offset, &stack_fi, ret);
+ if (ret)
+ return ERR_PTR(ret);
+ return trans;
+ }
+
+ extent_info.disk_offset = start;
+ extent_info.disk_len = len;
+ extent_info.data_offset = 0;
+ extent_info.data_len = len;
+ extent_info.file_offset = file_offset;
+ extent_info.extent_buf = (char *)&stack_fi;
+ extent_info.is_new_extent = true;
+ extent_info.qgroup_reserved = ret;
+ extent_info.insertions = 0;
+
+ path = btrfs_alloc_path();
+ if (!path)
+ return ERR_PTR(-ENOMEM);
+
+ ret = btrfs_replace_file_extents(inode, path, file_offset,
+ file_offset + len - 1, &extent_info,
+ &trans);
+ btrfs_free_path(path);
+ if (ret)
+ return ERR_PTR(ret);
+
+ return trans;
+}
+
static int __btrfs_prealloc_file_range(struct inode *inode, int mode,
u64 start, u64 num_bytes, u64 min_size,
loff_t actual_len, u64 *alloc_hint,
@@ -10426,14 +9798,6 @@
if (trans)
own_trans = false;
while (num_bytes > 0) {
- if (own_trans) {
- trans = btrfs_start_transaction(root, 3);
- if (IS_ERR(trans)) {
- ret = PTR_ERR(trans);
- break;
- }
- }
-
cur_bytes = min_t(u64, num_bytes, SZ_256M);
cur_bytes = max(cur_bytes, min_size);
/*
@@ -10445,11 +9809,8 @@
cur_bytes = min(cur_bytes, last_alloc);
ret = btrfs_reserve_extent(root, cur_bytes, cur_bytes,
min_size, 0, *alloc_hint, &ins, 1, 0);
- if (ret) {
- if (own_trans)
- btrfs_end_transaction(trans);
+ if (ret)
break;
- }
/*
* We've reserved this space, and thus converted it from
@@ -10459,20 +9820,20 @@
* clear_offset by our extent size.
*/
clear_offset += ins.offset;
- btrfs_dec_block_group_reservations(fs_info, ins.objectid);
last_alloc = ins.offset;
- ret = insert_reserved_file_extent(trans, inode,
- cur_offset, ins.objectid,
- ins.offset, ins.offset,
- ins.offset, 0, 0, 0,
- BTRFS_FILE_EXTENT_PREALLOC);
- if (ret) {
+ trans = insert_prealloc_file_extent(trans, inode, &ins, cur_offset);
+ /*
+ * Now that we inserted the prealloc extent we can finally
+ * decrement the number of reservations in the block group.
+ * If we did it before, we could race with relocation and have
+ * relocation miss the reserved extent, making it fail later.
+ */
+ btrfs_dec_block_group_reservations(fs_info, ins.objectid);
+ if (IS_ERR(trans)) {
+ ret = PTR_ERR(trans);
btrfs_free_reserved_extent(fs_info, ins.objectid,
ins.offset, 0);
- btrfs_abort_transaction(trans, ret);
- if (own_trans)
- btrfs_end_transaction(trans);
break;
}
@@ -10493,7 +9854,6 @@
em->block_len = ins.offset;
em->orig_block_len = ins.offset;
em->ram_bytes = ins.offset;
- em->bdev = fs_info->fs_devices->latest_bdev;
set_bit(EXTENT_FLAG_PREALLOC, &em->flags);
em->generation = trans->transid;
@@ -10524,7 +9884,7 @@
else
i_size = cur_offset;
i_size_write(inode, i_size);
- btrfs_ordered_update_i_size(inode, i_size, NULL);
+ btrfs_inode_safe_disk_i_size_write(inode, 0);
}
ret = btrfs_update_inode(trans, root, inode);
@@ -10536,11 +9896,13 @@
break;
}
- if (own_trans)
+ if (own_trans) {
btrfs_end_transaction(trans);
+ trans = NULL;
+ }
}
if (clear_offset < end)
- btrfs_free_reserved_data_space(inode, NULL, clear_offset,
+ btrfs_free_reserved_data_space(BTRFS_I(inode), NULL, clear_offset,
end - clear_offset + 1);
return ret;
}
@@ -10600,7 +9962,7 @@
if (IS_ERR(trans))
return PTR_ERR(trans);
- ret = btrfs_find_free_ino(root, &objectid);
+ ret = btrfs_find_free_objectid(root, &objectid);
if (ret)
goto out;
@@ -10616,7 +9978,6 @@
inode->i_op = &btrfs_file_inode_operations;
inode->i_mapping->a_ops = &btrfs_aops;
- BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
ret = btrfs_init_inode_security(trans, inode, dir, NULL);
if (ret)
@@ -10648,26 +10009,6 @@
return ret;
}
-__attribute__((const))
-static int btrfs_readpage_io_failed_hook(struct page *page, int failed_mirror)
-{
- return -EAGAIN;
-}
-
-static void btrfs_check_extent_io_range(void *private_data, const char *caller,
- u64 start, u64 end)
-{
- struct inode *inode = private_data;
- u64 isize;
-
- isize = i_size_read(inode);
- if (end >= PAGE_SIZE && (end % 2) == 0 && end != isize - 1) {
- btrfs_debug_rl(BTRFS_I(inode)->root->fs_info,
- "%s: ino %llu isize %llu odd range [%llu,%llu]",
- caller, btrfs_ino(BTRFS_I(inode)), isize, start, end);
- }
-}
-
void btrfs_set_range_writeback(struct extent_io_tree *tree, u64 start, u64 end)
{
struct inode *inode = tree->private_data;
@@ -10683,6 +10024,403 @@
index++;
}
}
+
+#ifdef CONFIG_SWAP
+/*
+ * Add an entry indicating a block group or device which is pinned by a
+ * swapfile. Returns 0 on success, 1 if there is already an entry for it, or a
+ * negative errno on failure.
+ */
+static int btrfs_add_swapfile_pin(struct inode *inode, void *ptr,
+ bool is_block_group)
+{
+ struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info;
+ struct btrfs_swapfile_pin *sp, *entry;
+ struct rb_node **p;
+ struct rb_node *parent = NULL;
+
+ sp = kmalloc(sizeof(*sp), GFP_NOFS);
+ if (!sp)
+ return -ENOMEM;
+ sp->ptr = ptr;
+ sp->inode = inode;
+ sp->is_block_group = is_block_group;
+ sp->bg_extent_count = 1;
+
+ spin_lock(&fs_info->swapfile_pins_lock);
+ p = &fs_info->swapfile_pins.rb_node;
+ while (*p) {
+ parent = *p;
+ entry = rb_entry(parent, struct btrfs_swapfile_pin, node);
+ if (sp->ptr < entry->ptr ||
+ (sp->ptr == entry->ptr && sp->inode < entry->inode)) {
+ p = &(*p)->rb_left;
+ } else if (sp->ptr > entry->ptr ||
+ (sp->ptr == entry->ptr && sp->inode > entry->inode)) {
+ p = &(*p)->rb_right;
+ } else {
+ if (is_block_group)
+ entry->bg_extent_count++;
+ spin_unlock(&fs_info->swapfile_pins_lock);
+ kfree(sp);
+ return 1;
+ }
+ }
+ rb_link_node(&sp->node, parent, p);
+ rb_insert_color(&sp->node, &fs_info->swapfile_pins);
+ spin_unlock(&fs_info->swapfile_pins_lock);
+ return 0;
+}
+
+/* Free all of the entries pinned by this swapfile. */
+static void btrfs_free_swapfile_pins(struct inode *inode)
+{
+ struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info;
+ struct btrfs_swapfile_pin *sp;
+ struct rb_node *node, *next;
+
+ spin_lock(&fs_info->swapfile_pins_lock);
+ node = rb_first(&fs_info->swapfile_pins);
+ while (node) {
+ next = rb_next(node);
+ sp = rb_entry(node, struct btrfs_swapfile_pin, node);
+ if (sp->inode == inode) {
+ rb_erase(&sp->node, &fs_info->swapfile_pins);
+ if (sp->is_block_group) {
+ btrfs_dec_block_group_swap_extents(sp->ptr,
+ sp->bg_extent_count);
+ btrfs_put_block_group(sp->ptr);
+ }
+ kfree(sp);
+ }
+ node = next;
+ }
+ spin_unlock(&fs_info->swapfile_pins_lock);
+}
+
+struct btrfs_swap_info {
+ u64 start;
+ u64 block_start;
+ u64 block_len;
+ u64 lowest_ppage;
+ u64 highest_ppage;
+ unsigned long nr_pages;
+ int nr_extents;
+};
+
+static int btrfs_add_swap_extent(struct swap_info_struct *sis,
+ struct btrfs_swap_info *bsi)
+{
+ unsigned long nr_pages;
+ unsigned long max_pages;
+ u64 first_ppage, first_ppage_reported, next_ppage;
+ int ret;
+
+ /*
+ * Our swapfile may have had its size extended after the swap header was
+ * written. In that case activating the swapfile should not go beyond
+ * the max size set in the swap header.
+ */
+ if (bsi->nr_pages >= sis->max)
+ return 0;
+
+ max_pages = sis->max - bsi->nr_pages;
+ first_ppage = ALIGN(bsi->block_start, PAGE_SIZE) >> PAGE_SHIFT;
+ next_ppage = ALIGN_DOWN(bsi->block_start + bsi->block_len,
+ PAGE_SIZE) >> PAGE_SHIFT;
+
+ if (first_ppage >= next_ppage)
+ return 0;
+ nr_pages = next_ppage - first_ppage;
+ nr_pages = min(nr_pages, max_pages);
+
+ first_ppage_reported = first_ppage;
+ if (bsi->start == 0)
+ first_ppage_reported++;
+ if (bsi->lowest_ppage > first_ppage_reported)
+ bsi->lowest_ppage = first_ppage_reported;
+ if (bsi->highest_ppage < (next_ppage - 1))
+ bsi->highest_ppage = next_ppage - 1;
+
+ ret = add_swap_extent(sis, bsi->nr_pages, nr_pages, first_ppage);
+ if (ret < 0)
+ return ret;
+ bsi->nr_extents += ret;
+ bsi->nr_pages += nr_pages;
+ return 0;
+}
+
+static void btrfs_swap_deactivate(struct file *file)
+{
+ struct inode *inode = file_inode(file);
+
+ btrfs_free_swapfile_pins(inode);
+ atomic_dec(&BTRFS_I(inode)->root->nr_swapfiles);
+}
+
+static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file,
+ sector_t *span)
+{
+ struct inode *inode = file_inode(file);
+ struct btrfs_root *root = BTRFS_I(inode)->root;
+ struct btrfs_fs_info *fs_info = root->fs_info;
+ struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
+ struct extent_state *cached_state = NULL;
+ struct extent_map *em = NULL;
+ struct btrfs_device *device = NULL;
+ struct btrfs_swap_info bsi = {
+ .lowest_ppage = (sector_t)-1ULL,
+ };
+ int ret = 0;
+ u64 isize;
+ u64 start;
+
+ /*
+ * If the swap file was just created, make sure delalloc is done. If the
+ * file changes again after this, the user is doing something stupid and
+ * we don't really care.
+ */
+ ret = btrfs_wait_ordered_range(inode, 0, (u64)-1);
+ if (ret)
+ return ret;
+
+ /*
+ * The inode is locked, so these flags won't change after we check them.
+ */
+ if (BTRFS_I(inode)->flags & BTRFS_INODE_COMPRESS) {
+ btrfs_warn(fs_info, "swapfile must not be compressed");
+ return -EINVAL;
+ }
+ if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW)) {
+ btrfs_warn(fs_info, "swapfile must not be copy-on-write");
+ return -EINVAL;
+ }
+ if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)) {
+ btrfs_warn(fs_info, "swapfile must not be checksummed");
+ return -EINVAL;
+ }
+
+ /*
+ * Balance or device remove/replace/resize can move stuff around from
+ * under us. The exclop protection makes sure they aren't running/won't
+ * run concurrently while we are mapping the swap extents, and
+ * fs_info->swapfile_pins prevents them from running while the swap
+ * file is active and moving the extents. Note that this also prevents
+ * a concurrent device add which isn't actually necessary, but it's not
+ * really worth the trouble to allow it.
+ */
+ if (!btrfs_exclop_start(fs_info, BTRFS_EXCLOP_SWAP_ACTIVATE)) {
+ btrfs_warn(fs_info,
+ "cannot activate swapfile while exclusive operation is running");
+ return -EBUSY;
+ }
+
+ /*
+ * Prevent snapshot creation while we are activating the swap file.
+ * We do not want to race with snapshot creation. If snapshot creation
+ * already started before we bumped nr_swapfiles from 0 to 1 and
+ * completes before the first write into the swap file after it is
+ * activated, than that write would fallback to COW.
+ */
+ if (!btrfs_drew_try_write_lock(&root->snapshot_lock)) {
+ btrfs_exclop_finish(fs_info);
+ btrfs_warn(fs_info,
+ "cannot activate swapfile because snapshot creation is in progress");
+ return -EINVAL;
+ }
+ /*
+ * Snapshots can create extents which require COW even if NODATACOW is
+ * set. We use this counter to prevent snapshots. We must increment it
+ * before walking the extents because we don't want a concurrent
+ * snapshot to run after we've already checked the extents.
+ *
+ * It is possible that subvolume is marked for deletion but still not
+ * removed yet. To prevent this race, we check the root status before
+ * activating the swapfile.
+ */
+ spin_lock(&root->root_item_lock);
+ if (btrfs_root_dead(root)) {
+ spin_unlock(&root->root_item_lock);
+
+ btrfs_exclop_finish(fs_info);
+ btrfs_warn(fs_info,
+ "cannot activate swapfile because subvolume %llu is being deleted",
+ root->root_key.objectid);
+ return -EPERM;
+ }
+ atomic_inc(&root->nr_swapfiles);
+ spin_unlock(&root->root_item_lock);
+
+ isize = ALIGN_DOWN(inode->i_size, fs_info->sectorsize);
+
+ lock_extent_bits(io_tree, 0, isize - 1, &cached_state);
+ start = 0;
+ while (start < isize) {
+ u64 logical_block_start, physical_block_start;
+ struct btrfs_block_group *bg;
+ u64 len = isize - start;
+
+ em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, start, len);
+ if (IS_ERR(em)) {
+ ret = PTR_ERR(em);
+ goto out;
+ }
+
+ if (em->block_start == EXTENT_MAP_HOLE) {
+ btrfs_warn(fs_info, "swapfile must not have holes");
+ ret = -EINVAL;
+ goto out;
+ }
+ if (em->block_start == EXTENT_MAP_INLINE) {
+ /*
+ * It's unlikely we'll ever actually find ourselves
+ * here, as a file small enough to fit inline won't be
+ * big enough to store more than the swap header, but in
+ * case something changes in the future, let's catch it
+ * here rather than later.
+ */
+ btrfs_warn(fs_info, "swapfile must not be inline");
+ ret = -EINVAL;
+ goto out;
+ }
+ if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags)) {
+ btrfs_warn(fs_info, "swapfile must not be compressed");
+ ret = -EINVAL;
+ goto out;
+ }
+
+ logical_block_start = em->block_start + (start - em->start);
+ len = min(len, em->len - (start - em->start));
+ free_extent_map(em);
+ em = NULL;
+
+ ret = can_nocow_extent(inode, start, &len, NULL, NULL, NULL, true);
+ if (ret < 0) {
+ goto out;
+ } else if (ret) {
+ ret = 0;
+ } else {
+ btrfs_warn(fs_info,
+ "swapfile must not be copy-on-write");
+ ret = -EINVAL;
+ goto out;
+ }
+
+ em = btrfs_get_chunk_map(fs_info, logical_block_start, len);
+ if (IS_ERR(em)) {
+ ret = PTR_ERR(em);
+ goto out;
+ }
+
+ if (em->map_lookup->type & BTRFS_BLOCK_GROUP_PROFILE_MASK) {
+ btrfs_warn(fs_info,
+ "swapfile must have single data profile");
+ ret = -EINVAL;
+ goto out;
+ }
+
+ if (device == NULL) {
+ device = em->map_lookup->stripes[0].dev;
+ ret = btrfs_add_swapfile_pin(inode, device, false);
+ if (ret == 1)
+ ret = 0;
+ else if (ret)
+ goto out;
+ } else if (device != em->map_lookup->stripes[0].dev) {
+ btrfs_warn(fs_info, "swapfile must be on one device");
+ ret = -EINVAL;
+ goto out;
+ }
+
+ physical_block_start = (em->map_lookup->stripes[0].physical +
+ (logical_block_start - em->start));
+ len = min(len, em->len - (logical_block_start - em->start));
+ free_extent_map(em);
+ em = NULL;
+
+ bg = btrfs_lookup_block_group(fs_info, logical_block_start);
+ if (!bg) {
+ btrfs_warn(fs_info,
+ "could not find block group containing swapfile");
+ ret = -EINVAL;
+ goto out;
+ }
+
+ if (!btrfs_inc_block_group_swap_extents(bg)) {
+ btrfs_warn(fs_info,
+ "block group for swapfile at %llu is read-only%s",
+ bg->start,
+ atomic_read(&fs_info->scrubs_running) ?
+ " (scrub running)" : "");
+ btrfs_put_block_group(bg);
+ ret = -EINVAL;
+ goto out;
+ }
+
+ ret = btrfs_add_swapfile_pin(inode, bg, true);
+ if (ret) {
+ btrfs_put_block_group(bg);
+ if (ret == 1)
+ ret = 0;
+ else
+ goto out;
+ }
+
+ if (bsi.block_len &&
+ bsi.block_start + bsi.block_len == physical_block_start) {
+ bsi.block_len += len;
+ } else {
+ if (bsi.block_len) {
+ ret = btrfs_add_swap_extent(sis, &bsi);
+ if (ret)
+ goto out;
+ }
+ bsi.start = start;
+ bsi.block_start = physical_block_start;
+ bsi.block_len = len;
+ }
+
+ start += len;
+ }
+
+ if (bsi.block_len)
+ ret = btrfs_add_swap_extent(sis, &bsi);
+
+out:
+ if (!IS_ERR_OR_NULL(em))
+ free_extent_map(em);
+
+ unlock_extent_cached(io_tree, 0, isize - 1, &cached_state);
+
+ if (ret)
+ btrfs_swap_deactivate(file);
+
+ btrfs_drew_write_unlock(&root->snapshot_lock);
+
+ btrfs_exclop_finish(fs_info);
+
+ if (ret)
+ return ret;
+
+ if (device)
+ sis->bdev = device->bdev;
+ *span = bsi.highest_ppage - bsi.lowest_ppage + 1;
+ sis->max = bsi.nr_pages;
+ sis->pages = bsi.nr_pages - 1;
+ sis->highest_bit = bsi.nr_pages - 1;
+ return bsi.nr_extents;
+}
+#else
+static void btrfs_swap_deactivate(struct file *file)
+{
+}
+
+static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file,
+ sector_t *span)
+{
+ return -EOPNOTSUPP;
+}
+#endif
static const struct inode_operations btrfs_dir_inode_operations = {
.getattr = btrfs_getattr,
@@ -10703,11 +10441,6 @@
.update_time = btrfs_update_time,
.tmpfile = btrfs_tmpfile,
};
-static const struct inode_operations btrfs_dir_ro_inode_operations = {
- .lookup = btrfs_lookup,
- .permission = btrfs_permission,
- .update_time = btrfs_update_time,
-};
static const struct file_operations btrfs_dir_file_operations = {
.llseek = generic_file_llseek,
@@ -10720,22 +10453,6 @@
#endif
.release = btrfs_release_file,
.fsync = btrfs_sync_file,
-};
-
-static const struct extent_io_ops btrfs_extent_io_ops = {
- /* mandatory callbacks */
- .submit_bio_hook = btrfs_submit_bio_hook,
- .readpage_end_io_hook = btrfs_readpage_end_io_hook,
- .readpage_io_failed_hook = btrfs_readpage_io_failed_hook,
-
- /* optional callbacks */
- .writepage_end_io_hook = btrfs_writepage_end_io_hook,
- .writepage_start_hook = btrfs_writepage_start_hook,
- .set_bit_hook = btrfs_set_bit_hook,
- .clear_bit_hook = btrfs_clear_bit_hook,
- .merge_extent_hook = btrfs_merge_extent_hook,
- .split_extent_hook = btrfs_split_extent_hook,
- .check_extent_io_range = btrfs_check_extent_io_range,
};
/*
@@ -10754,19 +10471,17 @@
.readpage = btrfs_readpage,
.writepage = btrfs_writepage,
.writepages = btrfs_writepages,
- .readpages = btrfs_readpages,
- .direct_IO = btrfs_direct_IO,
+ .readahead = btrfs_readahead,
+ .direct_IO = noop_direct_IO,
.invalidatepage = btrfs_invalidatepage,
.releasepage = btrfs_releasepage,
+#ifdef CONFIG_MIGRATION
+ .migratepage = btrfs_migratepage,
+#endif
.set_page_dirty = btrfs_set_page_dirty,
.error_remove_page = generic_error_remove_page,
-};
-
-static const struct address_space_operations btrfs_symlink_aops = {
- .readpage = btrfs_readpage,
- .writepage = btrfs_writepage,
- .invalidatepage = btrfs_invalidatepage,
- .releasepage = btrfs_releasepage,
+ .swap_activate = btrfs_swap_activate,
+ .swap_deactivate = btrfs_swap_deactivate,
};
static const struct inode_operations btrfs_file_inode_operations = {
--
Gitblit v1.6.2