From 23fa18eaa71266feff7ba8d83022d9e1cc83c65a Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Fri, 10 May 2024 07:42:03 +0000
Subject: [PATCH] disable pwm7

---
 kernel/fs/f2fs/extent_cache.c |  780 +++++++++++++++++++++++++++++++++++++++++++++--------------
 1 files changed, 589 insertions(+), 191 deletions(-)

diff --git a/kernel/fs/f2fs/extent_cache.c b/kernel/fs/f2fs/extent_cache.c
index e75f018..dadddb3 100644
--- a/kernel/fs/f2fs/extent_cache.c
+++ b/kernel/fs/f2fs/extent_cache.c
@@ -6,6 +6,10 @@
  * 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>
@@ -14,6 +18,111 @@
 #include "f2fs.h"
 #include "node.h"
 #include <trace/events/f2fs.h>
+
+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)
+{
+	/*
+	 * 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 rb_entry *__lookup_rb_tree_fast(struct rb_entry *cached_re,
 							unsigned int ofs)
@@ -56,6 +165,29 @@
 		return __lookup_rb_tree_slow(root, ofs);
 
 	return re;
+}
+
+struct rb_node **f2fs_lookup_rb_tree_ext(struct f2fs_sb_info *sbi,
+					struct rb_root_cached *root,
+					struct rb_node **parent,
+					unsigned long long key, bool *leftmost)
+{
+	struct rb_node **p = &root->rb_root.rb_node;
+	struct rb_entry *re;
+
+	while (*p) {
+		*parent = *p;
+		re = rb_entry(*parent, struct rb_entry, rb_node);
+
+		if (key < re->key) {
+			p = &(*p)->rb_left;
+		} else {
+			p = &(*p)->rb_right;
+			*leftmost = false;
+		}
+	}
+
+	return p;
 }
 
 struct rb_node **f2fs_lookup_rb_tree_for_insert(struct f2fs_sb_info *sbi,
@@ -166,7 +298,7 @@
 }
 
 bool f2fs_check_rb_tree_consistence(struct f2fs_sb_info *sbi,
-						struct rb_root_cached *root)
+				struct rb_root_cached *root, bool check_key)
 {
 #ifdef CONFIG_F2FS_CHECK_FS
 	struct rb_node *cur = rb_first_cached(root), *next;
@@ -183,13 +315,23 @@
 		cur_re = rb_entry(cur, struct rb_entry, rb_node);
 		next_re = rb_entry(next, struct rb_entry, rb_node);
 
+		if (check_key) {
+			if (cur_re->key > next_re->key) {
+				f2fs_info(sbi, "inconsistent rbtree, "
+					"cur(%llu) next(%llu)",
+					cur_re->key, next_re->key);
+				return false;
+			}
+			goto next;
+		}
+
 		if (cur_re->ofs + cur_re->len > next_re->ofs) {
 			f2fs_info(sbi, "inconsistent rbtree, cur(%u, %u) next(%u, %u)",
 				  cur_re->ofs, cur_re->len,
 				  next_re->ofs, next_re->len);
 			return false;
 		}
-
+next:
 		cur = next;
 	}
 #endif
@@ -204,6 +346,7 @@
 				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 = kmem_cache_alloc(extent_node_slab, GFP_ATOMIC);
@@ -217,16 +360,18 @@
 	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(&sbi->total_ext_node);
+	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(&sbi->total_ext_node);
+	atomic_dec(&eti->total_ext_node);
 
 	if (et->cached_en == en)
 		et->cached_en = NULL;
@@ -242,58 +387,48 @@
 static void __release_extent_node(struct f2fs_sb_info *sbi,
 			struct extent_tree *et, struct extent_node *en)
 {
-	spin_lock(&sbi->extent_lock);
+	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(&sbi->extent_lock);
+	spin_unlock(&eti->extent_lock);
 
 	__detach_extent_node(sbi, et, en);
 }
 
-static struct extent_tree *__grab_extent_tree(struct inode *inode)
+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(&sbi->extent_tree_lock);
-	et = radix_tree_lookup(&sbi->extent_tree_root, 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);
-		f2fs_radix_tree_insert(&sbi->extent_tree_root, ino, et);
+		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(&sbi->total_ext_tree);
+		atomic_inc(&eti->total_ext_tree);
 	} else {
-		atomic_dec(&sbi->total_zombie_tree);
+		atomic_dec(&eti->total_zombie_tree);
 		list_del_init(&et->list);
 	}
-	mutex_unlock(&sbi->extent_tree_lock);
+	mutex_unlock(&eti->extent_tree_lock);
 
 	/* never died until evict_inode */
-	F2FS_I(inode)->extent_tree = et;
+	F2FS_I(inode)->extent_tree[type] = et;
 
 	return et;
-}
-
-static struct extent_node *__init_extent_tree(struct f2fs_sb_info *sbi,
-				struct extent_tree *et, struct extent_info *ei)
-{
-	struct rb_node **p = &et->root.rb_root.rb_node;
-	struct extent_node *en;
-
-	en = __attach_extent_node(sbi, et, ei, NULL, p, true);
-	if (!en)
-		return NULL;
-
-	et->largest = en->ei;
-	et->cached_en = en;
-	return en;
 }
 
 static unsigned int __free_extent_tree(struct f2fs_sb_info *sbi,
@@ -324,73 +459,89 @@
 	}
 }
 
-/* return true, if inode page is changed */
-static bool __f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext)
+void f2fs_init_read_extent_tree(struct inode *inode, struct page *ipage)
 {
 	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(ipage)->i_ext;
 	struct extent_tree *et;
 	struct extent_node *en;
 	struct extent_info ei;
 
-	if (!f2fs_may_extent_tree(inode)) {
-		/* drop largest extent */
+	if (!__may_extent_tree(inode, EX_READ)) {
+		/* drop largest read extent */
 		if (i_ext && i_ext->len) {
+			f2fs_wait_on_page_writeback(ipage, NODE, true, true);
 			i_ext->len = 0;
-			return true;
+			set_page_dirty(ipage);
 		}
-		return false;
+		goto out;
 	}
 
-	et = __grab_extent_tree(inode);
+	et = __grab_extent_tree(inode, EX_READ);
 
 	if (!i_ext || !i_ext->len)
-		return false;
+		goto out;
 
-	get_extent_info(&ei, i_ext);
+	get_read_extent_info(&ei, i_ext);
 
 	write_lock(&et->lock);
 	if (atomic_read(&et->node_cnt))
-		goto out;
+		goto unlock_out;
 
-	en = __init_extent_tree(sbi, et, &ei);
+	en = __attach_extent_node(sbi, et, &ei, NULL,
+				&et->root.rb_root.rb_node, true);
 	if (en) {
-		spin_lock(&sbi->extent_lock);
-		list_add_tail(&en->list, &sbi->extent_list);
-		spin_unlock(&sbi->extent_lock);
+		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);
 	}
-out:
+unlock_out:
 	write_unlock(&et->lock);
-	return false;
-}
-
-bool f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext)
-{
-	bool ret =  __f2fs_init_extent_tree(inode, i_ext);
-
-	if (!F2FS_I(inode)->extent_tree)
+out:
+	if (!F2FS_I(inode)->extent_tree[EX_READ])
 		set_inode_flag(inode, FI_NO_EXTENT);
-
-	return ret;
 }
 
-static bool f2fs_lookup_extent_tree(struct inode *inode, pgoff_t pgofs,
-							struct extent_info *ei)
+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 *et = F2FS_I(inode)->extent_tree;
+	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;
 
-	f2fs_bug_on(sbi, !et);
-
 	if (!et)
-		return ret;
+		return false;
 
-	trace_f2fs_lookup_extent_tree_start(inode, pgofs);
+	trace_f2fs_lookup_extent_tree_start(inode, pgofs, type);
 
 	read_lock(&et->lock);
 
-	if (et->largest.fofs <= pgofs &&
+	if (type == EX_READ &&
+			et->largest.fofs <= pgofs &&
 			et->largest.fofs + et->largest.len > pgofs) {
 		*ei = et->largest;
 		ret = true;
@@ -404,23 +555,26 @@
 		goto out;
 
 	if (en == et->cached_en)
-		stat_inc_cached_node_hit(sbi);
+		stat_inc_cached_node_hit(sbi, type);
 	else
-		stat_inc_rbtree_node_hit(sbi);
+		stat_inc_rbtree_node_hit(sbi, type);
 
 	*ei = en->ei;
-	spin_lock(&sbi->extent_lock);
+	spin_lock(&eti->extent_lock);
 	if (!list_empty(&en->list)) {
-		list_move_tail(&en->list, &sbi->extent_list);
+		list_move_tail(&en->list, &eti->extent_list);
 		et->cached_en = en;
 	}
-	spin_unlock(&sbi->extent_lock);
+	spin_unlock(&eti->extent_lock);
 	ret = true;
 out:
-	stat_inc_total_hit(sbi);
+	stat_inc_total_hit(sbi, type);
 	read_unlock(&et->lock);
 
-	trace_f2fs_lookup_extent_tree_end(inode, pgofs, ei);
+	if (type == EX_READ)
+		trace_f2fs_lookup_read_extent_tree_end(inode, pgofs, ei);
+	else if (type == EX_BLOCK_AGE)
+		trace_f2fs_lookup_age_extent_tree_end(inode, pgofs, ei);
 	return ret;
 }
 
@@ -429,18 +583,20 @@
 				struct extent_node *prev_ex,
 				struct extent_node *next_ex)
 {
+	struct extent_tree_info *eti = &sbi->extent_tree[et->type];
 	struct extent_node *en = NULL;
 
-	if (prev_ex && __is_back_mergeable(ei, &prev_ex->ei)) {
+	if (prev_ex && __is_back_mergeable(ei, &prev_ex->ei, et->type)) {
 		prev_ex->ei.len += ei->len;
 		ei = &prev_ex->ei;
 		en = prev_ex;
 	}
 
-	if (next_ex && __is_front_mergeable(ei, &next_ex->ei)) {
+	if (next_ex && __is_front_mergeable(ei, &next_ex->ei, et->type)) {
 		next_ex->ei.fofs = ei->fofs;
-		next_ex->ei.blk = ei->blk;
 		next_ex->ei.len += ei->len;
+		if (et->type == EX_READ)
+			next_ex->ei.blk = ei->blk;
 		if (en)
 			__release_extent_node(sbi, et, prev_ex);
 
@@ -452,12 +608,12 @@
 
 	__try_update_largest_extent(et, en);
 
-	spin_lock(&sbi->extent_lock);
+	spin_lock(&eti->extent_lock);
 	if (!list_empty(&en->list)) {
-		list_move_tail(&en->list, &sbi->extent_list);
+		list_move_tail(&en->list, &eti->extent_list);
 		et->cached_en = en;
 	}
-	spin_unlock(&sbi->extent_lock);
+	spin_unlock(&eti->extent_lock);
 	return en;
 }
 
@@ -467,6 +623,7 @@
 				struct rb_node *insert_parent,
 				bool leftmost)
 {
+	struct extent_tree_info *eti = &sbi->extent_tree[et->type];
 	struct rb_node **p;
 	struct rb_node *parent = NULL;
 	struct extent_node *en = NULL;
@@ -489,47 +646,54 @@
 	__try_update_largest_extent(et, en);
 
 	/* update in global extent list */
-	spin_lock(&sbi->extent_lock);
-	list_add_tail(&en->list, &sbi->extent_list);
+	spin_lock(&eti->extent_lock);
+	list_add_tail(&en->list, &eti->extent_list);
 	et->cached_en = en;
-	spin_unlock(&sbi->extent_lock);
+	spin_unlock(&eti->extent_lock);
 	return en;
 }
 
-static void f2fs_update_extent_tree_range(struct inode *inode,
-				pgoff_t fofs, block_t blkaddr, unsigned int len)
+static void __update_extent_tree_range(struct inode *inode,
+			struct extent_info *tei, enum extent_type type)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	struct extent_tree *et = F2FS_I(inode)->extent_tree;
+	struct extent_tree *et = F2FS_I(inode)->extent_tree[type];
 	struct extent_node *en = NULL, *en1 = NULL;
 	struct extent_node *prev_en = NULL, *next_en = NULL;
 	struct extent_info ei, dei, prev;
 	struct rb_node **insert_p = NULL, *insert_parent = NULL;
+	unsigned int fofs = tei->fofs, len = tei->len;
 	unsigned int end = fofs + len;
-	unsigned int pos = (unsigned int)fofs;
 	bool updated = false;
 	bool leftmost = false;
 
 	if (!et)
 		return;
 
-	trace_f2fs_update_extent_tree_range(inode, fofs, blkaddr, len);
+	if (type == EX_READ)
+		trace_f2fs_update_read_extent_tree_range(inode, fofs, len,
+						tei->blk, 0);
+	else if (type == EX_BLOCK_AGE)
+		trace_f2fs_update_age_extent_tree_range(inode, fofs, len,
+						tei->age, tei->last_blocks);
 
 	write_lock(&et->lock);
 
-	if (is_inode_flag_set(inode, FI_NO_EXTENT)) {
-		write_unlock(&et->lock);
-		return;
+	if (type == EX_READ) {
+		if (is_inode_flag_set(inode, FI_NO_EXTENT)) {
+			write_unlock(&et->lock);
+			return;
+		}
+
+		prev = et->largest;
+		dei.len = 0;
+
+		/*
+		 * drop largest extent before lookup, in case it's already
+		 * been shrunk from extent tree
+		 */
+		__drop_largest_extent(et, fofs, len);
 	}
-
-	prev = et->largest;
-	dei.len = 0;
-
-	/*
-	 * drop largest extent before lookup, in case it's already
-	 * been shrunk from extent tree
-	 */
-	__drop_largest_extent(et, fofs, len);
 
 	/* 1. lookup first extent node in range [fofs, fofs + len - 1] */
 	en = (struct extent_node *)f2fs_lookup_rb_tree_ret(&et->root,
@@ -550,26 +714,32 @@
 
 		dei = en->ei;
 		org_end = dei.fofs + dei.len;
-		f2fs_bug_on(sbi, pos >= org_end);
+		f2fs_bug_on(sbi, fofs >= org_end);
 
-		if (pos > dei.fofs &&	pos - dei.fofs >= F2FS_MIN_EXTENT_LEN) {
-			en->ei.len = pos - en->ei.fofs;
+		if (fofs > dei.fofs && (type != EX_READ ||
+				fofs - dei.fofs >= F2FS_MIN_EXTENT_LEN)) {
+			en->ei.len = fofs - en->ei.fofs;
 			prev_en = en;
 			parts = 1;
 		}
 
-		if (end < org_end && org_end - end >= F2FS_MIN_EXTENT_LEN) {
+		if (end < org_end && (type != EX_READ ||
+				org_end - end >= F2FS_MIN_EXTENT_LEN)) {
 			if (parts) {
-				set_extent_info(&ei, end,
-						end - dei.fofs + dei.blk,
-						org_end - end);
+				__set_extent_info(&ei,
+					end, org_end - end,
+					end - dei.fofs + dei.blk, false,
+					dei.age, dei.last_blocks,
+					type);
 				en1 = __insert_extent_tree(sbi, et, &ei,
 							NULL, NULL, true);
 				next_en = en1;
 			} else {
-				en->ei.fofs = end;
-				en->ei.blk += end - dei.fofs;
-				en->ei.len -= end - dei.fofs;
+				__set_extent_info(&en->ei,
+					end, en->ei.len - (end - dei.fofs),
+					en->ei.blk + (end - dei.fofs), true,
+					dei.age, dei.last_blocks,
+					type);
 				next_en = en;
 			}
 			parts++;
@@ -599,10 +769,15 @@
 		en = next_en;
 	}
 
-	/* 3. update extent in extent cache */
-	if (blkaddr) {
+	if (type == EX_BLOCK_AGE)
+		goto update_age_extent_cache;
 
-		set_extent_info(&ei, fofs, blkaddr, len);
+	/* 3. update extent in read extent cache */
+	BUG_ON(type != EX_READ);
+
+	if (tei->blk) {
+		__set_extent_info(&ei, fofs, len, tei->blk, false,
+				  0, 0, EX_READ);
 		if (!__try_merge_extent_node(sbi, et, &ei, prev_en, next_en))
 			__insert_extent_tree(sbi, et, &ei,
 					insert_p, insert_parent, leftmost);
@@ -624,31 +799,182 @@
 		et->largest_updated = false;
 		updated = true;
 	}
+	goto out_read_extent_cache;
+update_age_extent_cache:
+	if (!tei->last_blocks)
+		goto out_read_extent_cache;
 
+	__set_extent_info(&ei, fofs, len, 0, false,
+			tei->age, tei->last_blocks, EX_BLOCK_AGE);
+	if (!__try_merge_extent_node(sbi, et, &ei, prev_en, next_en))
+		__insert_extent_tree(sbi, et, &ei,
+					insert_p, insert_parent, leftmost);
+out_read_extent_cache:
 	write_unlock(&et->lock);
 
 	if (updated)
 		f2fs_mark_inode_dirty_sync(inode, true);
 }
 
-unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink)
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+void f2fs_update_read_extent_tree_range_compressed(struct inode *inode,
+				pgoff_t fofs, block_t blkaddr, unsigned int llen,
+				unsigned int c_len)
 {
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	struct extent_tree *et = F2FS_I(inode)->extent_tree[EX_READ];
+	struct extent_node *en = NULL;
+	struct extent_node *prev_en = NULL, *next_en = NULL;
+	struct extent_info ei;
+	struct rb_node **insert_p = NULL, *insert_parent = NULL;
+	bool leftmost = false;
+
+	trace_f2fs_update_read_extent_tree_range(inode, fofs, llen,
+						blkaddr, c_len);
+
+	/* it is safe here to check FI_NO_EXTENT w/o et->lock in ro image */
+	if (is_inode_flag_set(inode, FI_NO_EXTENT))
+		return;
+
+	write_lock(&et->lock);
+
+	en = (struct extent_node *)f2fs_lookup_rb_tree_ret(&et->root,
+				(struct rb_entry *)et->cached_en, fofs,
+				(struct rb_entry **)&prev_en,
+				(struct rb_entry **)&next_en,
+				&insert_p, &insert_parent, false,
+				&leftmost);
+	if (en)
+		goto unlock_out;
+
+	__set_extent_info(&ei, fofs, llen, blkaddr, true, 0, 0, EX_READ);
+	ei.c_len = c_len;
+
+	if (!__try_merge_extent_node(sbi, et, &ei, prev_en, next_en))
+		__insert_extent_tree(sbi, et, &ei,
+				insert_p, insert_parent, leftmost);
+unlock_out:
+	write_unlock(&et->lock);
+}
+#endif
+
+static unsigned long long __calculate_block_age(struct f2fs_sb_info *sbi,
+						unsigned long long new,
+						unsigned long long old)
+{
+	unsigned int rem_old, rem_new;
+	unsigned long long res;
+	unsigned int weight = sbi->last_age_weight;
+
+	res = div_u64_rem(new, 100, &rem_new) * (100 - weight)
+		+ div_u64_rem(old, 100, &rem_old) * weight;
+
+	if (rem_new)
+		res += rem_new * (100 - weight) / 100;
+	if (rem_old)
+		res += rem_old * weight / 100;
+
+	return res;
+}
+
+/* This returns a new age and allocated blocks in ei */
+static int __get_new_block_age(struct inode *inode, struct extent_info *ei,
+						block_t blkaddr)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	loff_t f_size = i_size_read(inode);
+	unsigned long long cur_blocks =
+				atomic64_read(&sbi->allocated_data_blocks);
+	struct extent_info tei = *ei;	/* only fofs and len are valid */
+
+	/*
+	 * When I/O is not aligned to a PAGE_SIZE, update will happen to the last
+	 * file block even in seq write. So don't record age for newly last file
+	 * block here.
+	 */
+	if ((f_size >> PAGE_SHIFT) == ei->fofs && f_size & (PAGE_SIZE - 1) &&
+			blkaddr == NEW_ADDR)
+		return -EINVAL;
+
+	if (__lookup_extent_tree(inode, ei->fofs, &tei, EX_BLOCK_AGE)) {
+		unsigned long long cur_age;
+
+		if (cur_blocks >= tei.last_blocks)
+			cur_age = cur_blocks - tei.last_blocks;
+		else
+			/* allocated_data_blocks overflow */
+			cur_age = ULLONG_MAX - tei.last_blocks + cur_blocks;
+
+		if (tei.age)
+			ei->age = __calculate_block_age(sbi, cur_age, tei.age);
+		else
+			ei->age = cur_age;
+		ei->last_blocks = cur_blocks;
+		WARN_ON(ei->age > cur_blocks);
+		return 0;
+	}
+
+	f2fs_bug_on(sbi, blkaddr == NULL_ADDR);
+
+	/* the data block was allocated for the first time */
+	if (blkaddr == NEW_ADDR)
+		goto out;
+
+	if (__is_valid_data_blkaddr(blkaddr) &&
+	    !f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC_ENHANCE)) {
+		f2fs_bug_on(sbi, 1);
+		return -EINVAL;
+	}
+out:
+	/*
+	 * init block age with zero, this can happen when the block age extent
+	 * was reclaimed due to memory constraint or system reboot
+	 */
+	ei->age = 0;
+	ei->last_blocks = cur_blocks;
+	return 0;
+}
+
+static void __update_extent_cache(struct dnode_of_data *dn, enum extent_type type)
+{
+	struct extent_info ei = {};
+
+	if (!__may_extent_tree(dn->inode, type))
+		return;
+
+	ei.fofs = f2fs_start_bidx_of_node(ofs_of_node(dn->node_page), dn->inode) +
+								dn->ofs_in_node;
+	ei.len = 1;
+
+	if (type == EX_READ) {
+		if (dn->data_blkaddr == NEW_ADDR)
+			ei.blk = NULL_ADDR;
+		else
+			ei.blk = dn->data_blkaddr;
+	} else if (type == EX_BLOCK_AGE) {
+		if (__get_new_block_age(dn->inode, &ei, dn->data_blkaddr))
+			return;
+	}
+	__update_extent_tree_range(dn->inode, &ei, type);
+}
+
+static unsigned int __shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink,
+					enum extent_type type)
+{
+	struct extent_tree_info *eti = &sbi->extent_tree[type];
 	struct extent_tree *et, *next;
 	struct extent_node *en;
 	unsigned int node_cnt = 0, tree_cnt = 0;
 	int remained;
 
-	if (!test_opt(sbi, EXTENT_CACHE))
-		return 0;
-
-	if (!atomic_read(&sbi->total_zombie_tree))
+	if (!atomic_read(&eti->total_zombie_tree))
 		goto free_node;
 
-	if (!mutex_trylock(&sbi->extent_tree_lock))
+	if (!mutex_trylock(&eti->extent_tree_lock))
 		goto out;
 
 	/* 1. remove unreferenced extent tree */
-	list_for_each_entry_safe(et, next, &sbi->zombie_list, list) {
+	list_for_each_entry_safe(et, next, &eti->zombie_list, list) {
 		if (atomic_read(&et->node_cnt)) {
 			write_lock(&et->lock);
 			node_cnt += __free_extent_tree(sbi, et);
@@ -656,61 +982,137 @@
 		}
 		f2fs_bug_on(sbi, atomic_read(&et->node_cnt));
 		list_del_init(&et->list);
-		radix_tree_delete(&sbi->extent_tree_root, et->ino);
+		radix_tree_delete(&eti->extent_tree_root, et->ino);
 		kmem_cache_free(extent_tree_slab, et);
-		atomic_dec(&sbi->total_ext_tree);
-		atomic_dec(&sbi->total_zombie_tree);
+		atomic_dec(&eti->total_ext_tree);
+		atomic_dec(&eti->total_zombie_tree);
 		tree_cnt++;
 
 		if (node_cnt + tree_cnt >= nr_shrink)
 			goto unlock_out;
 		cond_resched();
 	}
-	mutex_unlock(&sbi->extent_tree_lock);
+	mutex_unlock(&eti->extent_tree_lock);
 
 free_node:
 	/* 2. remove LRU extent entries */
-	if (!mutex_trylock(&sbi->extent_tree_lock))
+	if (!mutex_trylock(&eti->extent_tree_lock))
 		goto out;
 
 	remained = nr_shrink - (node_cnt + tree_cnt);
 
-	spin_lock(&sbi->extent_lock);
+	spin_lock(&eti->extent_lock);
 	for (; remained > 0; remained--) {
-		if (list_empty(&sbi->extent_list))
+		if (list_empty(&eti->extent_list))
 			break;
-		en = list_first_entry(&sbi->extent_list,
+		en = list_first_entry(&eti->extent_list,
 					struct extent_node, list);
 		et = en->et;
 		if (!write_trylock(&et->lock)) {
 			/* refresh this extent node's position in extent list */
-			list_move_tail(&en->list, &sbi->extent_list);
+			list_move_tail(&en->list, &eti->extent_list);
 			continue;
 		}
 
 		list_del_init(&en->list);
-		spin_unlock(&sbi->extent_lock);
+		spin_unlock(&eti->extent_lock);
 
 		__detach_extent_node(sbi, et, en);
 
 		write_unlock(&et->lock);
 		node_cnt++;
-		spin_lock(&sbi->extent_lock);
+		spin_lock(&eti->extent_lock);
 	}
-	spin_unlock(&sbi->extent_lock);
+	spin_unlock(&eti->extent_lock);
 
 unlock_out:
-	mutex_unlock(&sbi->extent_tree_lock);
+	mutex_unlock(&eti->extent_tree_lock);
 out:
-	trace_f2fs_shrink_extent_tree(sbi, node_cnt, tree_cnt);
+	trace_f2fs_shrink_extent_tree(sbi, node_cnt, tree_cnt, type);
 
 	return node_cnt + tree_cnt;
 }
 
-unsigned int f2fs_destroy_extent_node(struct inode *inode)
+/* read extent cache operations */
+bool f2fs_lookup_read_extent_cache(struct inode *inode, pgoff_t pgofs,
+				struct extent_info *ei)
+{
+	if (!__may_extent_tree(inode, EX_READ))
+		return false;
+
+	return __lookup_extent_tree(inode, pgofs, ei, EX_READ);
+}
+
+void f2fs_update_read_extent_cache(struct dnode_of_data *dn)
+{
+	return __update_extent_cache(dn, EX_READ);
+}
+
+void f2fs_update_read_extent_cache_range(struct dnode_of_data *dn,
+				pgoff_t fofs, block_t blkaddr, unsigned int len)
+{
+	struct extent_info ei = {
+		.fofs = fofs,
+		.len = len,
+		.blk = blkaddr,
+	};
+
+	if (!__may_extent_tree(dn->inode, EX_READ))
+		return;
+
+	__update_extent_tree_range(dn->inode, &ei, EX_READ);
+}
+
+unsigned int f2fs_shrink_read_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink)
+{
+	if (!test_opt(sbi, READ_EXTENT_CACHE))
+		return 0;
+
+	return __shrink_extent_tree(sbi, nr_shrink, EX_READ);
+}
+
+/* block age extent cache operations */
+bool f2fs_lookup_age_extent_cache(struct inode *inode, pgoff_t pgofs,
+				struct extent_info *ei)
+{
+	if (!__may_extent_tree(inode, EX_BLOCK_AGE))
+		return false;
+
+	return __lookup_extent_tree(inode, pgofs, ei, EX_BLOCK_AGE);
+}
+
+void f2fs_update_age_extent_cache(struct dnode_of_data *dn)
+{
+	return __update_extent_cache(dn, EX_BLOCK_AGE);
+}
+
+void f2fs_update_age_extent_cache_range(struct dnode_of_data *dn,
+				pgoff_t fofs, unsigned int len)
+{
+	struct extent_info ei = {
+		.fofs = fofs,
+		.len = len,
+	};
+
+	if (!__may_extent_tree(dn->inode, EX_BLOCK_AGE))
+		return;
+
+	__update_extent_tree_range(dn->inode, &ei, EX_BLOCK_AGE);
+}
+
+unsigned int f2fs_shrink_age_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink)
+{
+	if (!test_opt(sbi, AGE_EXTENT_CACHE))
+		return 0;
+
+	return __shrink_extent_tree(sbi, nr_shrink, EX_BLOCK_AGE);
+}
+
+static unsigned int __destroy_extent_node(struct inode *inode,
+					enum extent_type type)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	struct extent_tree *et = F2FS_I(inode)->extent_tree;
+	struct extent_tree *et = F2FS_I(inode)->extent_tree[type];
 	unsigned int node_cnt = 0;
 
 	if (!et || !atomic_read(&et->node_cnt))
@@ -723,32 +1125,47 @@
 	return node_cnt;
 }
 
-void f2fs_drop_extent_tree(struct inode *inode)
+void f2fs_destroy_extent_node(struct inode *inode)
+{
+	__destroy_extent_node(inode, EX_READ);
+	__destroy_extent_node(inode, EX_BLOCK_AGE);
+}
+
+static void __drop_extent_tree(struct inode *inode, enum extent_type type)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	struct extent_tree *et = F2FS_I(inode)->extent_tree;
+	struct extent_tree *et = F2FS_I(inode)->extent_tree[type];
 	bool updated = false;
 
-	if (!f2fs_may_extent_tree(inode))
+	if (!__may_extent_tree(inode, type))
 		return;
 
-	set_inode_flag(inode, FI_NO_EXTENT);
-
 	write_lock(&et->lock);
+	set_inode_flag(inode, FI_NO_EXTENT);
 	__free_extent_tree(sbi, et);
-	if (et->largest.len) {
-		et->largest.len = 0;
-		updated = true;
+	if (type == EX_READ) {
+		set_inode_flag(inode, FI_NO_EXTENT);
+		if (et->largest.len) {
+			et->largest.len = 0;
+			updated = true;
+		}
 	}
 	write_unlock(&et->lock);
 	if (updated)
 		f2fs_mark_inode_dirty_sync(inode, true);
 }
 
-void f2fs_destroy_extent_tree(struct inode *inode)
+void f2fs_drop_extent_tree(struct inode *inode)
+{
+	__drop_extent_tree(inode, EX_READ);
+	__drop_extent_tree(inode, EX_BLOCK_AGE);
+}
+
+static void __destroy_extent_tree(struct inode *inode, enum extent_type type)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	struct extent_tree *et = F2FS_I(inode)->extent_tree;
+	struct extent_tree_info *eti = &sbi->extent_tree[type];
+	struct extent_tree *et = F2FS_I(inode)->extent_tree[type];
 	unsigned int node_cnt = 0;
 
 	if (!et)
@@ -756,76 +1173,57 @@
 
 	if (inode->i_nlink && !is_bad_inode(inode) &&
 					atomic_read(&et->node_cnt)) {
-		mutex_lock(&sbi->extent_tree_lock);
-		list_add_tail(&et->list, &sbi->zombie_list);
-		atomic_inc(&sbi->total_zombie_tree);
-		mutex_unlock(&sbi->extent_tree_lock);
+		mutex_lock(&eti->extent_tree_lock);
+		list_add_tail(&et->list, &eti->zombie_list);
+		atomic_inc(&eti->total_zombie_tree);
+		mutex_unlock(&eti->extent_tree_lock);
 		return;
 	}
 
 	/* free all extent info belong to this extent tree */
-	node_cnt = f2fs_destroy_extent_node(inode);
+	node_cnt = __destroy_extent_node(inode, type);
 
 	/* delete extent tree entry in radix tree */
-	mutex_lock(&sbi->extent_tree_lock);
+	mutex_lock(&eti->extent_tree_lock);
 	f2fs_bug_on(sbi, atomic_read(&et->node_cnt));
-	radix_tree_delete(&sbi->extent_tree_root, inode->i_ino);
+	radix_tree_delete(&eti->extent_tree_root, inode->i_ino);
 	kmem_cache_free(extent_tree_slab, et);
-	atomic_dec(&sbi->total_ext_tree);
-	mutex_unlock(&sbi->extent_tree_lock);
+	atomic_dec(&eti->total_ext_tree);
+	mutex_unlock(&eti->extent_tree_lock);
 
-	F2FS_I(inode)->extent_tree = NULL;
+	F2FS_I(inode)->extent_tree[type] = NULL;
 
-	trace_f2fs_destroy_extent_tree(inode, node_cnt);
+	trace_f2fs_destroy_extent_tree(inode, node_cnt, type);
 }
 
-bool f2fs_lookup_extent_cache(struct inode *inode, pgoff_t pgofs,
-					struct extent_info *ei)
+void f2fs_destroy_extent_tree(struct inode *inode)
 {
-	if (!f2fs_may_extent_tree(inode))
-		return false;
-
-	return f2fs_lookup_extent_tree(inode, pgofs, ei);
+	__destroy_extent_tree(inode, EX_READ);
+	__destroy_extent_tree(inode, EX_BLOCK_AGE);
 }
 
-void f2fs_update_extent_cache(struct dnode_of_data *dn)
+static void __init_extent_tree_info(struct extent_tree_info *eti)
 {
-	pgoff_t fofs;
-	block_t blkaddr;
-
-	if (!f2fs_may_extent_tree(dn->inode))
-		return;
-
-	if (dn->data_blkaddr == NEW_ADDR)
-		blkaddr = NULL_ADDR;
-	else
-		blkaddr = dn->data_blkaddr;
-
-	fofs = f2fs_start_bidx_of_node(ofs_of_node(dn->node_page), dn->inode) +
-								dn->ofs_in_node;
-	f2fs_update_extent_tree_range(dn->inode, fofs, blkaddr, 1);
-}
-
-void f2fs_update_extent_cache_range(struct dnode_of_data *dn,
-				pgoff_t fofs, block_t blkaddr, unsigned int len)
-
-{
-	if (!f2fs_may_extent_tree(dn->inode))
-		return;
-
-	f2fs_update_extent_tree_range(dn->inode, fofs, blkaddr, len);
+	INIT_RADIX_TREE(&eti->extent_tree_root, GFP_NOIO);
+	mutex_init(&eti->extent_tree_lock);
+	INIT_LIST_HEAD(&eti->extent_list);
+	spin_lock_init(&eti->extent_lock);
+	atomic_set(&eti->total_ext_tree, 0);
+	INIT_LIST_HEAD(&eti->zombie_list);
+	atomic_set(&eti->total_zombie_tree, 0);
+	atomic_set(&eti->total_ext_node, 0);
 }
 
 void f2fs_init_extent_cache_info(struct f2fs_sb_info *sbi)
 {
-	INIT_RADIX_TREE(&sbi->extent_tree_root, GFP_NOIO);
-	mutex_init(&sbi->extent_tree_lock);
-	INIT_LIST_HEAD(&sbi->extent_list);
-	spin_lock_init(&sbi->extent_lock);
-	atomic_set(&sbi->total_ext_tree, 0);
-	INIT_LIST_HEAD(&sbi->zombie_list);
-	atomic_set(&sbi->total_zombie_tree, 0);
-	atomic_set(&sbi->total_ext_node, 0);
+	__init_extent_tree_info(&sbi->extent_tree[EX_READ]);
+	__init_extent_tree_info(&sbi->extent_tree[EX_BLOCK_AGE]);
+
+	/* initialize for block age extents */
+	atomic64_set(&sbi->allocated_data_blocks, 0);
+	sbi->hot_data_age_threshold = DEF_HOT_DATA_AGE_THRESHOLD;
+	sbi->warm_data_age_threshold = DEF_WARM_DATA_AGE_THRESHOLD;
+	sbi->last_age_weight = LAST_AGE_WEIGHT;
 }
 
 int __init f2fs_create_extent_cache(void)

--
Gitblit v1.6.2