1009 lines · 28.1 KB · C
RawDownload
// SPDX-License-Identifier: GPL-2.0/* * Copyright (C) 2007 Oracle.  All rights reserved. */ #include <linux/slab.h>#include <linux/blkdev.h>#include <linux/writeback.h>#include <linux/sched/mm.h>#include "misc.h"#include "ctree.h"#include "transaction.h"#include "btrfs_inode.h"#include "extent_io.h"#include "disk-io.h"#include "compression.h"#include "delalloc-space.h"#include "qgroup.h" static struct kmem_cache *btrfs_ordered_extent_cache; static u64 entry_end(struct btrfs_ordered_extent *entry){	if (entry->file_offset + entry->num_bytes < entry->file_offset)		return (u64)-1;	return entry->file_offset + entry->num_bytes;} /* returns NULL if the insertion worked, or it returns the node it did find * in the tree */static struct rb_node *tree_insert(struct rb_root *root, u64 file_offset,				   struct rb_node *node){	struct rb_node **p = &root->rb_node;	struct rb_node *parent = NULL;	struct btrfs_ordered_extent *entry; 	while (*p) {		parent = *p;		entry = rb_entry(parent, struct btrfs_ordered_extent, rb_node); 		if (file_offset < entry->file_offset)			p = &(*p)->rb_left;		else if (file_offset >= entry_end(entry))			p = &(*p)->rb_right;		else			return parent;	} 	rb_link_node(node, parent, p);	rb_insert_color(node, root);	return NULL;} /* * look for a given offset in the tree, and if it can't be found return the * first lesser offset */static struct rb_node *__tree_search(struct rb_root *root, u64 file_offset,				     struct rb_node **prev_ret){	struct rb_node *n = root->rb_node;	struct rb_node *prev = NULL;	struct rb_node *test;	struct btrfs_ordered_extent *entry;	struct btrfs_ordered_extent *prev_entry = NULL; 	while (n) {		entry = rb_entry(n, struct btrfs_ordered_extent, rb_node);		prev = n;		prev_entry = entry; 		if (file_offset < entry->file_offset)			n = n->rb_left;		else if (file_offset >= entry_end(entry))			n = n->rb_right;		else			return n;	}	if (!prev_ret)		return NULL; 	while (prev && file_offset >= entry_end(prev_entry)) {		test = rb_next(prev);		if (!test)			break;		prev_entry = rb_entry(test, struct btrfs_ordered_extent,				      rb_node);		if (file_offset < entry_end(prev_entry))			break; 		prev = test;	}	if (prev)		prev_entry = rb_entry(prev, struct btrfs_ordered_extent,				      rb_node);	while (prev && file_offset < entry_end(prev_entry)) {		test = rb_prev(prev);		if (!test)			break;		prev_entry = rb_entry(test, struct btrfs_ordered_extent,				      rb_node);		prev = test;	}	*prev_ret = prev;	return NULL;} static int range_overlaps(struct btrfs_ordered_extent *entry, u64 file_offset,			  u64 len){	if (file_offset + len <= entry->file_offset ||	    entry->file_offset + entry->num_bytes <= file_offset)		return 0;	return 1;} /* * look find the first ordered struct that has this offset, otherwise * the first one less than this offset */static inline struct rb_node *tree_search(struct btrfs_ordered_inode_tree *tree,					  u64 file_offset){	struct rb_root *root = &tree->tree;	struct rb_node *prev = NULL;	struct rb_node *ret;	struct btrfs_ordered_extent *entry; 	if (tree->last) {		entry = rb_entry(tree->last, struct btrfs_ordered_extent,				 rb_node);		if (in_range(file_offset, entry->file_offset, entry->num_bytes))			return tree->last;	}	ret = __tree_search(root, file_offset, &prev);	if (!ret)		ret = prev;	if (ret)		tree->last = ret;	return ret;} /* * Allocate and add a new ordered_extent into the per-inode tree. * * The tree is given a single reference on the ordered extent that was * inserted. */static int __btrfs_add_ordered_extent(struct btrfs_inode *inode, u64 file_offset,				      u64 disk_bytenr, u64 num_bytes,				      u64 disk_num_bytes, int type, int dio,				      int compress_type){	struct btrfs_root *root = inode->root;	struct btrfs_fs_info *fs_info = root->fs_info;	struct btrfs_ordered_inode_tree *tree = &inode->ordered_tree;	struct rb_node *node;	struct btrfs_ordered_extent *entry;	int ret; 	if (type == BTRFS_ORDERED_NOCOW || type == BTRFS_ORDERED_PREALLOC) {		/* For nocow write, we can release the qgroup rsv right now */		ret = btrfs_qgroup_free_data(inode, NULL, file_offset, num_bytes);		if (ret < 0)			return ret;		ret = 0;	} else {		/*		 * The ordered extent has reserved qgroup space, release now		 * and pass the reserved number for qgroup_record to free.		 */		ret = btrfs_qgroup_release_data(inode, file_offset, num_bytes);		if (ret < 0)			return ret;	}	entry = kmem_cache_zalloc(btrfs_ordered_extent_cache, GFP_NOFS);	if (!entry)		return -ENOMEM; 	entry->file_offset = file_offset;	entry->disk_bytenr = disk_bytenr;	entry->num_bytes = num_bytes;	entry->disk_num_bytes = disk_num_bytes;	entry->bytes_left = num_bytes;	entry->inode = igrab(&inode->vfs_inode);	entry->compress_type = compress_type;	entry->truncated_len = (u64)-1;	entry->qgroup_rsv = ret;	entry->physical = (u64)-1;	entry->disk = NULL;	entry->partno = (u8)-1; 	ASSERT(type == BTRFS_ORDERED_REGULAR ||	       type == BTRFS_ORDERED_NOCOW ||	       type == BTRFS_ORDERED_PREALLOC ||	       type == BTRFS_ORDERED_COMPRESSED);	set_bit(type, &entry->flags); 	percpu_counter_add_batch(&fs_info->ordered_bytes, num_bytes,				 fs_info->delalloc_batch); 	if (dio)		set_bit(BTRFS_ORDERED_DIRECT, &entry->flags); 	/* one ref for the tree */	refcount_set(&entry->refs, 1);	init_waitqueue_head(&entry->wait);	INIT_LIST_HEAD(&entry->list);	INIT_LIST_HEAD(&entry->log_list);	INIT_LIST_HEAD(&entry->root_extent_list);	INIT_LIST_HEAD(&entry->work_list);	init_completion(&entry->completion); 	trace_btrfs_ordered_extent_add(inode, entry); 	spin_lock_irq(&tree->lock);	node = tree_insert(&tree->tree, file_offset,			   &entry->rb_node);	if (node)		btrfs_panic(fs_info, -EEXIST,				"inconsistency in ordered tree at offset %llu",				file_offset);	spin_unlock_irq(&tree->lock); 	spin_lock(&root->ordered_extent_lock);	list_add_tail(&entry->root_extent_list,		      &root->ordered_extents);	root->nr_ordered_extents++;	if (root->nr_ordered_extents == 1) {		spin_lock(&fs_info->ordered_root_lock);		BUG_ON(!list_empty(&root->ordered_root));		list_add_tail(&root->ordered_root, &fs_info->ordered_roots);		spin_unlock(&fs_info->ordered_root_lock);	}	spin_unlock(&root->ordered_extent_lock); 	/*	 * We don't need the count_max_extents here, we can assume that all of	 * that work has been done at higher layers, so this is truly the	 * smallest the extent is going to get.	 */	spin_lock(&inode->lock);	btrfs_mod_outstanding_extents(inode, 1);	spin_unlock(&inode->lock); 	return 0;} int btrfs_add_ordered_extent(struct btrfs_inode *inode, u64 file_offset,			     u64 disk_bytenr, u64 num_bytes, u64 disk_num_bytes,			     int type){	ASSERT(type == BTRFS_ORDERED_REGULAR ||	       type == BTRFS_ORDERED_NOCOW ||	       type == BTRFS_ORDERED_PREALLOC);	return __btrfs_add_ordered_extent(inode, file_offset, disk_bytenr,					  num_bytes, disk_num_bytes, type, 0,					  BTRFS_COMPRESS_NONE);} int btrfs_add_ordered_extent_dio(struct btrfs_inode *inode, u64 file_offset,				 u64 disk_bytenr, u64 num_bytes,				 u64 disk_num_bytes, int type){	ASSERT(type == BTRFS_ORDERED_REGULAR ||	       type == BTRFS_ORDERED_NOCOW ||	       type == BTRFS_ORDERED_PREALLOC);	return __btrfs_add_ordered_extent(inode, file_offset, disk_bytenr,					  num_bytes, disk_num_bytes, type, 1,					  BTRFS_COMPRESS_NONE);} int btrfs_add_ordered_extent_compress(struct btrfs_inode *inode, u64 file_offset,				      u64 disk_bytenr, u64 num_bytes,				      u64 disk_num_bytes, int compress_type){	ASSERT(compress_type != BTRFS_COMPRESS_NONE);	return __btrfs_add_ordered_extent(inode, file_offset, disk_bytenr,					  num_bytes, disk_num_bytes,					  BTRFS_ORDERED_COMPRESSED, 0,					  compress_type);} /* * Add a struct btrfs_ordered_sum into the list of checksums to be inserted * when an ordered extent is finished.  If the list covers more than one * ordered extent, it is split across multiples. */void btrfs_add_ordered_sum(struct btrfs_ordered_extent *entry,			   struct btrfs_ordered_sum *sum){	struct btrfs_ordered_inode_tree *tree; 	tree = &BTRFS_I(entry->inode)->ordered_tree;	spin_lock_irq(&tree->lock);	list_add_tail(&sum->list, &entry->list);	spin_unlock_irq(&tree->lock);} /* * Finish IO for one ordered extent across a given range.  The range can * contain several ordered extents. * * @found_ret:	 Return the finished ordered extent * @file_offset: File offset for the finished IO * 		 Will also be updated to one byte past the range that is * 		 recordered as finished. This allows caller to walk forward. * @io_size:	 Length of the finish IO range * @uptodate:	 If the IO finished without problem * * Return true if any ordered extent is finished in the range, and update * @found_ret and @file_offset. * Return false otherwise. * * NOTE: Although The range can cross multiple ordered extents, only one * ordered extent will be updated during one call. The caller is responsible to * iterate all ordered extents in the range. */bool btrfs_dec_test_first_ordered_pending(struct btrfs_inode *inode,				   struct btrfs_ordered_extent **finished_ret,				   u64 *file_offset, u64 io_size, int uptodate){	struct btrfs_fs_info *fs_info = inode->root->fs_info;	struct btrfs_ordered_inode_tree *tree = &inode->ordered_tree;	struct rb_node *node;	struct btrfs_ordered_extent *entry = NULL;	bool finished = false;	unsigned long flags;	u64 dec_end;	u64 dec_start;	u64 to_dec; 	spin_lock_irqsave(&tree->lock, flags);	node = tree_search(tree, *file_offset);	if (!node)		goto out; 	entry = rb_entry(node, struct btrfs_ordered_extent, rb_node);	if (!in_range(*file_offset, entry->file_offset, entry->num_bytes))		goto out; 	dec_start = max(*file_offset, entry->file_offset);	dec_end = min(*file_offset + io_size,		      entry->file_offset + entry->num_bytes);	*file_offset = dec_end;	if (dec_start > dec_end) {		btrfs_crit(fs_info, "bad ordering dec_start %llu end %llu",			   dec_start, dec_end);	}	to_dec = dec_end - dec_start;	if (to_dec > entry->bytes_left) {		btrfs_crit(fs_info,			   "bad ordered accounting left %llu size %llu",			   entry->bytes_left, to_dec);	}	entry->bytes_left -= to_dec;	if (!uptodate)		set_bit(BTRFS_ORDERED_IOERR, &entry->flags); 	if (entry->bytes_left == 0) {		/*		 * Ensure only one caller can set the flag and finished_ret		 * accordingly		 */		finished = !test_and_set_bit(BTRFS_ORDERED_IO_DONE, &entry->flags);		/* test_and_set_bit implies a barrier */		cond_wake_up_nomb(&entry->wait);	}out:	if (finished && finished_ret && entry) {		*finished_ret = entry;		refcount_inc(&entry->refs);	}	spin_unlock_irqrestore(&tree->lock, flags);	return finished;} /* * Finish IO for one ordered extent across a given range.  The range can only * contain one ordered extent. * * @cached:	 The cached ordered extent. If not NULL, we can skip the tree *               search and use the ordered extent directly. * 		 Will be also used to store the finished ordered extent. * @file_offset: File offset for the finished IO * @io_size:	 Length of the finish IO range * @uptodate:	 If the IO finishes without problem * * Return true if the ordered extent is finished in the range, and update * @cached. * Return false otherwise. * * NOTE: The range can NOT cross multiple ordered extents. * Thus caller should ensure the range doesn't cross ordered extents. */bool btrfs_dec_test_ordered_pending(struct btrfs_inode *inode,				    struct btrfs_ordered_extent **cached,				    u64 file_offset, u64 io_size, int uptodate){	struct btrfs_ordered_inode_tree *tree = &inode->ordered_tree;	struct rb_node *node;	struct btrfs_ordered_extent *entry = NULL;	unsigned long flags;	bool finished = false; 	spin_lock_irqsave(&tree->lock, flags);	if (cached && *cached) {		entry = *cached;		goto have_entry;	} 	node = tree_search(tree, file_offset);	if (!node)		goto out; 	entry = rb_entry(node, struct btrfs_ordered_extent, rb_node);have_entry:	if (!in_range(file_offset, entry->file_offset, entry->num_bytes))		goto out; 	if (io_size > entry->bytes_left)		btrfs_crit(inode->root->fs_info,			   "bad ordered accounting left %llu size %llu",		       entry->bytes_left, io_size); 	entry->bytes_left -= io_size;	if (!uptodate)		set_bit(BTRFS_ORDERED_IOERR, &entry->flags); 	if (entry->bytes_left == 0) {		/*		 * Ensure only one caller can set the flag and finished_ret		 * accordingly		 */		finished = !test_and_set_bit(BTRFS_ORDERED_IO_DONE, &entry->flags);		/* test_and_set_bit implies a barrier */		cond_wake_up_nomb(&entry->wait);	}out:	if (finished && cached && entry) {		*cached = entry;		refcount_inc(&entry->refs);	}	spin_unlock_irqrestore(&tree->lock, flags);	return finished;} /* * used to drop a reference on an ordered extent.  This will free * the extent if the last reference is dropped */void btrfs_put_ordered_extent(struct btrfs_ordered_extent *entry){	struct list_head *cur;	struct btrfs_ordered_sum *sum; 	trace_btrfs_ordered_extent_put(BTRFS_I(entry->inode), entry); 	if (refcount_dec_and_test(&entry->refs)) {		ASSERT(list_empty(&entry->root_extent_list));		ASSERT(list_empty(&entry->log_list));		ASSERT(RB_EMPTY_NODE(&entry->rb_node));		if (entry->inode)			btrfs_add_delayed_iput(entry->inode);		while (!list_empty(&entry->list)) {			cur = entry->list.next;			sum = list_entry(cur, struct btrfs_ordered_sum, list);			list_del(&sum->list);			kvfree(sum);		}		kmem_cache_free(btrfs_ordered_extent_cache, entry);	}} /* * remove an ordered extent from the tree.  No references are dropped * and waiters are woken up. */void btrfs_remove_ordered_extent(struct btrfs_inode *btrfs_inode,				 struct btrfs_ordered_extent *entry){	struct btrfs_ordered_inode_tree *tree;	struct btrfs_root *root = btrfs_inode->root;	struct btrfs_fs_info *fs_info = root->fs_info;	struct rb_node *node;	bool pending; 	/* This is paired with btrfs_add_ordered_extent. */	spin_lock(&btrfs_inode->lock);	btrfs_mod_outstanding_extents(btrfs_inode, -1);	spin_unlock(&btrfs_inode->lock);	if (root != fs_info->tree_root)		btrfs_delalloc_release_metadata(btrfs_inode, entry->num_bytes,						false); 	percpu_counter_add_batch(&fs_info->ordered_bytes, -entry->num_bytes,				 fs_info->delalloc_batch); 

Lines 1–500 of 1009.