// SPDX-License-Identifier: GPL-2.0/* * f2fs extent cache support * * Copyright (c) 2015 Motorola Mobility * Copyright (c) 2015 Samsung Electronics * Authors: Jaegeuk Kim <jaegeuk@kernel.org> *          Chao Yu <chao2.yu@samsung.com> * * block_age-based extent cache added by: * Copyright (c) 2022 xiaomi Co., Ltd. *             http://www.xiaomi.com/ */ #include <linux/fs.h>#include <linux/f2fs_fs.h> #include "f2fs.h"#include "node.h"#include "segment.h"#include <trace/events/f2fs.h> bool sanity_check_extent_cache(struct inode *inode, struct folio *ifolio){	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);	struct f2fs_extent *i_ext = &F2FS_INODE(ifolio)->i_ext;	struct extent_info ei;	int devi; 	get_read_extent_info(&ei, i_ext); 	if (!ei.len)		return true; 	if (!f2fs_is_valid_blkaddr(sbi, ei.blk, DATA_GENERIC_ENHANCE) ||	    !f2fs_is_valid_blkaddr(sbi, ei.blk + ei.len - 1,					DATA_GENERIC_ENHANCE)) {		f2fs_warn(sbi, "%s: inode (ino=%llx) extent info [%u, %u, %u] is incorrect, run fsck to fix",			  __func__, inode->i_ino,			  ei.blk, ei.fofs, ei.len);		return false;	} 	if (!IS_DEVICE_ALIASING(inode))		return true; 	for (devi = 0; devi < sbi->s_ndevs; devi++) {		if (FDEV(devi).start_blk != ei.blk ||				FDEV(devi).end_blk != ei.blk + ei.len - 1)			continue; 		if (devi == 0) {			f2fs_warn(sbi,			    "%s: inode (ino=%llx) is an alias of meta device",			    __func__, inode->i_ino);			return false;		} 		if (bdev_is_zoned(FDEV(devi).bdev)) {			f2fs_warn(sbi,			    "%s: device alias inode (ino=%llx)'s extent info "			    "[%u, %u, %u] maps to zoned block device",			    __func__, inode->i_ino, ei.blk, ei.fofs, ei.len);			return false;		} 		if ((GET_SEGOFF_FROM_SEG0(sbi, ei.blk) % BLKS_PER_SEC(sbi)) ||		    (ei.len % BLKS_PER_SEC(sbi))) {			f2fs_warn(sbi, "%s: device alias inode (ino=%llx)'s extent info [%u, %u, %u] is not aligned to section size %u",				  __func__, inode->i_ino, ei.blk, ei.fofs, ei.len,				  BLKS_PER_SEC(sbi));			return false;		}		return true;	} 	f2fs_warn(sbi, "%s: device alias inode (ino=%llx)'s extent info "			"[%u, %u, %u] is inconsistent w/ any devices",			__func__, inode->i_ino, ei.blk, ei.fofs, ei.len);	return false;} static void __set_extent_info(struct extent_info *ei,				unsigned int fofs, unsigned int len,				block_t blk, bool keep_clen,				unsigned long age, unsigned long last_blocks,				enum extent_type type){	ei->fofs = fofs;	ei->len = len; 	if (type == EX_READ) {		ei->blk = blk;		if (keep_clen)			return;#ifdef CONFIG_F2FS_FS_COMPRESSION		ei->c_len = 0;#endif	} else if (type == EX_BLOCK_AGE) {		ei->age = age;		ei->last_blocks = last_blocks;	}} static bool __init_may_extent_tree(struct inode *inode, enum extent_type type){	if (type == EX_READ)		return test_opt(F2FS_I_SB(inode), READ_EXTENT_CACHE) &&			S_ISREG(inode->i_mode);	if (type == EX_BLOCK_AGE)		return test_opt(F2FS_I_SB(inode), AGE_EXTENT_CACHE) &&			(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode));	return false;} static bool __may_extent_tree(struct inode *inode, enum extent_type type){	if (IS_DEVICE_ALIASING(inode) && type == EX_READ)		return true; 	/*	 * for recovered files during mount do not create extents	 * if shrinker is not registered.	 */	if (list_empty(&F2FS_I_SB(inode)->s_list))		return false; 	if (!__init_may_extent_tree(inode, type))		return false; 	if (type == EX_READ) {		if (is_inode_flag_set(inode, FI_NO_EXTENT))			return false;		if (is_inode_flag_set(inode, FI_COMPRESSED_FILE) &&				 !f2fs_sb_has_readonly(F2FS_I_SB(inode)))			return false;	} else if (type == EX_BLOCK_AGE) {		if (is_inode_flag_set(inode, FI_COMPRESSED_FILE))			return false;		if (file_is_cold(inode))			return false;	}	return true;} static void __try_update_largest_extent(struct extent_tree *et,						struct extent_node *en){	if (et->type != EX_READ)		return;	if (en->ei.len <= et->largest.len)		return; 	et->largest = en->ei;	et->largest_updated = true;} static bool __is_extent_mergeable(struct extent_info *back,		struct extent_info *front, enum extent_type type){	if (type == EX_READ) {#ifdef CONFIG_F2FS_FS_COMPRESSION		if (back->c_len && back->len != back->c_len)			return false;		if (front->c_len && front->len != front->c_len)			return false;#endif		return (back->fofs + back->len == front->fofs &&				back->blk + back->len == front->blk);	} else if (type == EX_BLOCK_AGE) {		return (back->fofs + back->len == front->fofs &&			abs(back->age - front->age) <= SAME_AGE_REGION &&			abs(back->last_blocks - front->last_blocks) <=							SAME_AGE_REGION);	}	return false;} static bool __is_back_mergeable(struct extent_info *cur,		struct extent_info *back, enum extent_type type){	return __is_extent_mergeable(back, cur, type);} static bool __is_front_mergeable(struct extent_info *cur,		struct extent_info *front, enum extent_type type){	return __is_extent_mergeable(cur, front, type);} static struct extent_node *__lookup_extent_node(struct rb_root_cached *root,			struct extent_node *cached_en, unsigned int fofs){	struct rb_node *node = root->rb_root.rb_node;	struct extent_node *en; 	/* check a cached entry */	if (cached_en && cached_en->ei.fofs <= fofs &&			cached_en->ei.fofs + cached_en->ei.len > fofs)		return cached_en; 	/* check rb_tree */	while (node) {		en = rb_entry(node, struct extent_node, rb_node); 		if (fofs < en->ei.fofs)			node = node->rb_left;		else if (fofs >= en->ei.fofs + en->ei.len)			node = node->rb_right;		else			return en;	}	return NULL;} /* * lookup rb entry in position of @fofs in rb-tree, * if hit, return the entry, otherwise, return NULL * @prev_ex: extent before fofs * @next_ex: extent after fofs * @insert_p: insert point for new extent at fofs * in order to simplify the insertion after. * tree must stay unchanged between lookup and insertion. */static struct extent_node *__lookup_extent_node_ret(struct rb_root_cached *root,				struct extent_node *cached_en,				unsigned int fofs,				struct extent_node **prev_entry,				struct extent_node **next_entry,				struct rb_node ***insert_p,				struct rb_node **insert_parent,				bool *leftmost){	struct rb_node **pnode = &root->rb_root.rb_node;	struct rb_node *parent = NULL, *tmp_node;	struct extent_node *en = cached_en; 	*insert_p = NULL;	*insert_parent = NULL;	*prev_entry = NULL;	*next_entry = NULL; 	if (RB_EMPTY_ROOT(&root->rb_root))		return NULL; 	if (en && en->ei.fofs <= fofs && en->ei.fofs + en->ei.len > fofs)		goto lookup_neighbors; 	*leftmost = true; 	while (*pnode) {		parent = *pnode;		en = rb_entry(*pnode, struct extent_node, rb_node); 		if (fofs < en->ei.fofs) {			pnode = &(*pnode)->rb_left;		} else if (fofs >= en->ei.fofs + en->ei.len) {			pnode = &(*pnode)->rb_right;			*leftmost = false;		} else {			goto lookup_neighbors;		}	} 	*insert_p = pnode;	*insert_parent = parent; 	en = rb_entry(parent, struct extent_node, rb_node);	tmp_node = parent;	if (parent && fofs > en->ei.fofs)		tmp_node = rb_next(parent);	*next_entry = rb_entry_safe(tmp_node, struct extent_node, rb_node); 	tmp_node = parent;	if (parent && fofs < en->ei.fofs)		tmp_node = rb_prev(parent);	*prev_entry = rb_entry_safe(tmp_node, struct extent_node, rb_node);	return NULL; lookup_neighbors:	if (fofs == en->ei.fofs) {		/* lookup prev node for merging backward later */		tmp_node = rb_prev(&en->rb_node);		*prev_entry = rb_entry_safe(tmp_node,					struct extent_node, rb_node);	}	if (fofs == en->ei.fofs + en->ei.len - 1) {		/* lookup next node for merging frontward later */		tmp_node = rb_next(&en->rb_node);		*next_entry = rb_entry_safe(tmp_node,					struct extent_node, rb_node);	}	return en;} static struct kmem_cache *extent_tree_slab;static struct kmem_cache *extent_node_slab; static struct extent_node *__attach_extent_node(struct f2fs_sb_info *sbi,				struct extent_tree *et, struct extent_info *ei,				struct rb_node *parent, struct rb_node **p,				bool leftmost){	struct extent_tree_info *eti = &sbi->extent_tree[et->type];	struct extent_node *en; 	en = f2fs_kmem_cache_alloc(extent_node_slab, GFP_ATOMIC, false, sbi);	if (!en)		return NULL; 	en->ei = *ei;	INIT_LIST_HEAD(&en->list);	en->et = et; 	rb_link_node(&en->rb_node, parent, p);	rb_insert_color_cached(&en->rb_node, &et->root, leftmost);	atomic_inc(&et->node_cnt);	atomic_inc(&eti->total_ext_node);	return en;} static void __detach_extent_node(struct f2fs_sb_info *sbi,				struct extent_tree *et, struct extent_node *en){	struct extent_tree_info *eti = &sbi->extent_tree[et->type]; 	rb_erase_cached(&en->rb_node, &et->root);	atomic_dec(&et->node_cnt);	atomic_dec(&eti->total_ext_node); 	if (et->cached_en == en)		et->cached_en = NULL;	kmem_cache_free(extent_node_slab, en);} /* * Flow to release an extent_node: * 1. list_del_init * 2. __detach_extent_node * 3. kmem_cache_free. */static void __release_extent_node(struct f2fs_sb_info *sbi,			struct extent_tree *et, struct extent_node *en){	struct extent_tree_info *eti = &sbi->extent_tree[et->type]; 	spin_lock(&eti->extent_lock);	f2fs_bug_on(sbi, list_empty(&en->list));	list_del_init(&en->list);	spin_unlock(&eti->extent_lock); 	__detach_extent_node(sbi, et, en);} static struct extent_tree *__grab_extent_tree(struct inode *inode,						enum extent_type type){	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);	struct extent_tree_info *eti = &sbi->extent_tree[type];	struct extent_tree *et;	nid_t ino = inode->i_ino; 	mutex_lock(&eti->extent_tree_lock);	et = radix_tree_lookup(&eti->extent_tree_root, ino);	if (!et) {		et = f2fs_kmem_cache_alloc(extent_tree_slab,					GFP_NOFS, true, NULL);		f2fs_radix_tree_insert(&eti->extent_tree_root, ino, et);		memset(et, 0, sizeof(struct extent_tree));		et->ino = ino;		et->type = type;		et->root = RB_ROOT_CACHED;		et->cached_en = NULL;		rwlock_init(&et->lock);		INIT_LIST_HEAD(&et->list);		atomic_set(&et->node_cnt, 0);		atomic_inc(&eti->total_ext_tree);	} else {		atomic_dec(&eti->total_zombie_tree);		list_del_init(&et->list);	}	mutex_unlock(&eti->extent_tree_lock); 	/* never died until evict_inode */	F2FS_I(inode)->extent_tree[type] = et; 	return et;} static unsigned int __free_extent_tree(struct f2fs_sb_info *sbi,				struct extent_tree *et, unsigned int nr_shrink){	struct rb_node *node, *next;	struct extent_node *en;	unsigned int count; 	node = rb_first_cached(&et->root); 	for (count = 0; node && count < nr_shrink; count++) {		next = rb_next(node);		en = rb_entry(node, struct extent_node, rb_node);		__release_extent_node(sbi, et, en);		node = next;	} 	return count;} static void __drop_largest_extent(struct extent_tree *et,					pgoff_t fofs, unsigned int len){	if (fofs < (pgoff_t)et->largest.fofs + et->largest.len &&			fofs + len > et->largest.fofs) {		et->largest.len = 0;		et->largest_updated = true;	}} void f2fs_init_read_extent_tree(struct inode *inode, struct folio *ifolio){	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);	struct extent_tree_info *eti = &sbi->extent_tree[EX_READ];	struct f2fs_extent *i_ext = &F2FS_INODE(ifolio)->i_ext;	struct extent_tree *et;	struct extent_node *en;	struct extent_info ei = {0}; 	if (!__may_extent_tree(inode, EX_READ)) {		/* drop largest read extent */		if (i_ext->len) {			f2fs_folio_wait_writeback(ifolio, NODE, true, true);			i_ext->len = 0;			folio_mark_dirty(ifolio);		}		set_inode_flag(inode, FI_NO_EXTENT);		return;	} 	et = __grab_extent_tree(inode, EX_READ); 	get_read_extent_info(&ei, i_ext); 	write_lock(&et->lock);	if (atomic_read(&et->node_cnt) || !ei.len)		goto skip; 	if (IS_DEVICE_ALIASING(inode)) {		et->largest = ei;		goto skip;	} 	en = __attach_extent_node(sbi, et, &ei, NULL,				&et->root.rb_root.rb_node, true);	if (en) {		et->largest = en->ei;		et->cached_en = en; 		spin_lock(&eti->extent_lock);		list_add_tail(&en->list, &eti->extent_list);		spin_unlock(&eti->extent_lock);	}skip:	/* Let's drop, if checkpoint got corrupted. */	if (f2fs_cp_error(sbi)) {		et->largest.len = 0;		et->largest_updated = true;	}	write_unlock(&et->lock);} void f2fs_init_age_extent_tree(struct inode *inode){	if (!__init_may_extent_tree(inode, EX_BLOCK_AGE))		return;	__grab_extent_tree(inode, EX_BLOCK_AGE);} void f2fs_init_extent_tree(struct inode *inode){	/* initialize read cache */	if (__init_may_extent_tree(inode, EX_READ))		__grab_extent_tree(inode, EX_READ); 	/* initialize block age cache */	if (__init_may_extent_tree(inode, EX_BLOCK_AGE))		__grab_extent_tree(inode, EX_BLOCK_AGE);} static bool __lookup_extent_tree(struct inode *inode, pgoff_t pgofs,			struct extent_info *ei, enum extent_type type){	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);	struct extent_tree_info *eti = &sbi->extent_tree[type];	struct extent_tree *et = F2FS_I(inode)->extent_tree[type];	struct extent_node *en;	bool ret = false; 	if (!et)		return false; 

Lines 1–500 of 1262. Load more