mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-28 20:02:17 +00:00
![Chao Yu](/assets/img/avatar_default.png)
As Dan Carpenter as below: The patch df634f444ee9: "f2fs: use rb_*_cached friends" from Oct 4, 2018, leads to the following static checker warning: fs/f2fs/extent_cache.c:606 f2fs_update_extent_tree_range() error: uninitialized symbol 'leftmost'. And also Eric Biggers, and Kyungtae Kim reported, there is an UBSAN warning described as below: We report a bug in linux-4.20.2: "UBSAN: Undefined behaviour in fs/f2fs/extent_cache.c" kernel config: https://kt0755.github.io/etc/config_v4.20_stable repro: https://kt0755.github.io/etc/repro.4a3e7.c (f2fs is mounted on /mnt/f2fs/) This arose in f2fs_update_extent_tree_range (fs/f2fs/extent_cache.c:605). It seems that, for some reason, its last argument became "24" although that was supposed to be bool type. ========================================= UBSAN: Undefined behaviour in fs/f2fs/extent_cache.c:605:4 load of value 24 is not a valid value for type '_Bool' CPU: 0 PID: 6774 Comm: syz-executor5 Not tainted 4.20.2 #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0xb1/0x118 lib/dump_stack.c:113 ubsan_epilogue+0x12/0x94 lib/ubsan.c:159 __ubsan_handle_load_invalid_value+0x17a/0x1be lib/ubsan.c:457 f2fs_update_extent_tree_range+0x1d4a/0x1d50 fs/f2fs/extent_cache.c:605 f2fs_update_extent_cache+0x2b6/0x350 fs/f2fs/extent_cache.c:804 f2fs_update_data_blkaddr+0x61/0x70 fs/f2fs/data.c:656 f2fs_outplace_write_data+0x1d6/0x4b0 fs/f2fs/segment.c:3140 f2fs_convert_inline_page+0x86d/0x2060 fs/f2fs/inline.c:163 f2fs_convert_inline_inode+0x6b5/0xad0 fs/f2fs/inline.c:208 f2fs_preallocate_blocks+0x78b/0xb00 fs/f2fs/data.c:982 f2fs_file_write_iter+0x31b/0xf40 fs/f2fs/file.c:3062 call_write_iter include/linux/fs.h:1857 [inline] new_sync_write fs/read_write.c:474 [inline] __vfs_write+0x538/0x6e0 fs/read_write.c:487 vfs_write+0x1b3/0x520 fs/read_write.c:549 ksys_write+0xde/0x1c0 fs/read_write.c:598 __do_sys_write fs/read_write.c:610 [inline] __se_sys_write fs/read_write.c:607 [inline] __x64_sys_write+0x7e/0xc0 fs/read_write.c:607 do_syscall_64+0xbe/0x4f0 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x4497b9 Code: e8 8c 9f 02 00 48 83 c4 18 c3 0f 1f 80 00 00 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 9b 6b fc ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007f1ea15edc68 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 00007f1ea15ee6cc RCX: 00000000004497b9 RDX: 0000000000001000 RSI: 0000000020000140 RDI: 0000000000000013 RBP: 000000000071bea0 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00000000ffffffff R13: 000000000000bb50 R14: 00000000006f4bf0 R15: 00007f1ea15ee700 ========================================= As I checked, this uninitialized variable won't cause extent cache corruption, but in order to avoid such kind of warning of both UBSAN and smatch, fix to initialize related variable. Reported-by: Dan Carpenter <dan.carpenter@oracle.com> Reported-by: Eric Biggers <ebiggers@google.com> Reported-by: Kyungtae Kim <kt0755@gmail.com> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
848 lines
20 KiB
C
848 lines
20 KiB
C
// 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>
|
|
*/
|
|
|
|
#include <linux/fs.h>
|
|
#include <linux/f2fs_fs.h>
|
|
|
|
#include "f2fs.h"
|
|
#include "node.h"
|
|
#include <trace/events/f2fs.h>
|
|
|
|
static struct rb_entry *__lookup_rb_tree_fast(struct rb_entry *cached_re,
|
|
unsigned int ofs)
|
|
{
|
|
if (cached_re) {
|
|
if (cached_re->ofs <= ofs &&
|
|
cached_re->ofs + cached_re->len > ofs) {
|
|
return cached_re;
|
|
}
|
|
}
|
|
return NULL;
|
|
}
|
|
|
|
static struct rb_entry *__lookup_rb_tree_slow(struct rb_root_cached *root,
|
|
unsigned int ofs)
|
|
{
|
|
struct rb_node *node = root->rb_root.rb_node;
|
|
struct rb_entry *re;
|
|
|
|
while (node) {
|
|
re = rb_entry(node, struct rb_entry, rb_node);
|
|
|
|
if (ofs < re->ofs)
|
|
node = node->rb_left;
|
|
else if (ofs >= re->ofs + re->len)
|
|
node = node->rb_right;
|
|
else
|
|
return re;
|
|
}
|
|
return NULL;
|
|
}
|
|
|
|
struct rb_entry *f2fs_lookup_rb_tree(struct rb_root_cached *root,
|
|
struct rb_entry *cached_re, unsigned int ofs)
|
|
{
|
|
struct rb_entry *re;
|
|
|
|
re = __lookup_rb_tree_fast(cached_re, ofs);
|
|
if (!re)
|
|
return __lookup_rb_tree_slow(root, ofs);
|
|
|
|
return re;
|
|
}
|
|
|
|
struct rb_node **f2fs_lookup_rb_tree_for_insert(struct f2fs_sb_info *sbi,
|
|
struct rb_root_cached *root,
|
|
struct rb_node **parent,
|
|
unsigned int ofs, 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 (ofs < re->ofs) {
|
|
p = &(*p)->rb_left;
|
|
} else if (ofs >= re->ofs + re->len) {
|
|
p = &(*p)->rb_right;
|
|
*leftmost = false;
|
|
} else {
|
|
f2fs_bug_on(sbi, 1);
|
|
}
|
|
}
|
|
|
|
return p;
|
|
}
|
|
|
|
/*
|
|
* lookup rb entry in position of @ofs in rb-tree,
|
|
* if hit, return the entry, otherwise, return NULL
|
|
* @prev_ex: extent before ofs
|
|
* @next_ex: extent after ofs
|
|
* @insert_p: insert point for new extent at ofs
|
|
* in order to simpfy the insertion after.
|
|
* tree must stay unchanged between lookup and insertion.
|
|
*/
|
|
struct rb_entry *f2fs_lookup_rb_tree_ret(struct rb_root_cached *root,
|
|
struct rb_entry *cached_re,
|
|
unsigned int ofs,
|
|
struct rb_entry **prev_entry,
|
|
struct rb_entry **next_entry,
|
|
struct rb_node ***insert_p,
|
|
struct rb_node **insert_parent,
|
|
bool force, bool *leftmost)
|
|
{
|
|
struct rb_node **pnode = &root->rb_root.rb_node;
|
|
struct rb_node *parent = NULL, *tmp_node;
|
|
struct rb_entry *re = cached_re;
|
|
|
|
*insert_p = NULL;
|
|
*insert_parent = NULL;
|
|
*prev_entry = NULL;
|
|
*next_entry = NULL;
|
|
|
|
if (RB_EMPTY_ROOT(&root->rb_root))
|
|
return NULL;
|
|
|
|
if (re) {
|
|
if (re->ofs <= ofs && re->ofs + re->len > ofs)
|
|
goto lookup_neighbors;
|
|
}
|
|
|
|
if (leftmost)
|
|
*leftmost = true;
|
|
|
|
while (*pnode) {
|
|
parent = *pnode;
|
|
re = rb_entry(*pnode, struct rb_entry, rb_node);
|
|
|
|
if (ofs < re->ofs) {
|
|
pnode = &(*pnode)->rb_left;
|
|
} else if (ofs >= re->ofs + re->len) {
|
|
pnode = &(*pnode)->rb_right;
|
|
if (leftmost)
|
|
*leftmost = false;
|
|
} else {
|
|
goto lookup_neighbors;
|
|
}
|
|
}
|
|
|
|
*insert_p = pnode;
|
|
*insert_parent = parent;
|
|
|
|
re = rb_entry(parent, struct rb_entry, rb_node);
|
|
tmp_node = parent;
|
|
if (parent && ofs > re->ofs)
|
|
tmp_node = rb_next(parent);
|
|
*next_entry = rb_entry_safe(tmp_node, struct rb_entry, rb_node);
|
|
|
|
tmp_node = parent;
|
|
if (parent && ofs < re->ofs)
|
|
tmp_node = rb_prev(parent);
|
|
*prev_entry = rb_entry_safe(tmp_node, struct rb_entry, rb_node);
|
|
return NULL;
|
|
|
|
lookup_neighbors:
|
|
if (ofs == re->ofs || force) {
|
|
/* lookup prev node for merging backward later */
|
|
tmp_node = rb_prev(&re->rb_node);
|
|
*prev_entry = rb_entry_safe(tmp_node, struct rb_entry, rb_node);
|
|
}
|
|
if (ofs == re->ofs + re->len - 1 || force) {
|
|
/* lookup next node for merging frontward later */
|
|
tmp_node = rb_next(&re->rb_node);
|
|
*next_entry = rb_entry_safe(tmp_node, struct rb_entry, rb_node);
|
|
}
|
|
return re;
|
|
}
|
|
|
|
bool f2fs_check_rb_tree_consistence(struct f2fs_sb_info *sbi,
|
|
struct rb_root_cached *root)
|
|
{
|
|
#ifdef CONFIG_F2FS_CHECK_FS
|
|
struct rb_node *cur = rb_first_cached(root), *next;
|
|
struct rb_entry *cur_re, *next_re;
|
|
|
|
if (!cur)
|
|
return true;
|
|
|
|
while (cur) {
|
|
next = rb_next(cur);
|
|
if (!next)
|
|
return true;
|
|
|
|
cur_re = rb_entry(cur, struct rb_entry, rb_node);
|
|
next_re = rb_entry(next, struct rb_entry, rb_node);
|
|
|
|
if (cur_re->ofs + cur_re->len > next_re->ofs) {
|
|
f2fs_msg(sbi->sb, KERN_INFO, "inconsistent rbtree, "
|
|
"cur(%u, %u) next(%u, %u)",
|
|
cur_re->ofs, cur_re->len,
|
|
next_re->ofs, next_re->len);
|
|
return false;
|
|
}
|
|
|
|
cur = next;
|
|
}
|
|
#endif
|
|
return true;
|
|
}
|
|
|
|
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_node *en;
|
|
|
|
en = kmem_cache_alloc(extent_node_slab, GFP_ATOMIC);
|
|
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(&sbi->total_ext_node);
|
|
return en;
|
|
}
|
|
|
|
static void __detach_extent_node(struct f2fs_sb_info *sbi,
|
|
struct extent_tree *et, struct extent_node *en)
|
|
{
|
|
rb_erase_cached(&en->rb_node, &et->root);
|
|
atomic_dec(&et->node_cnt);
|
|
atomic_dec(&sbi->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)
|
|
{
|
|
spin_lock(&sbi->extent_lock);
|
|
f2fs_bug_on(sbi, list_empty(&en->list));
|
|
list_del_init(&en->list);
|
|
spin_unlock(&sbi->extent_lock);
|
|
|
|
__detach_extent_node(sbi, et, en);
|
|
}
|
|
|
|
static struct extent_tree *__grab_extent_tree(struct inode *inode)
|
|
{
|
|
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
|
|
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);
|
|
if (!et) {
|
|
et = f2fs_kmem_cache_alloc(extent_tree_slab, GFP_NOFS);
|
|
f2fs_radix_tree_insert(&sbi->extent_tree_root, ino, et);
|
|
memset(et, 0, sizeof(struct extent_tree));
|
|
et->ino = ino;
|
|
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);
|
|
} else {
|
|
atomic_dec(&sbi->total_zombie_tree);
|
|
list_del_init(&et->list);
|
|
}
|
|
mutex_unlock(&sbi->extent_tree_lock);
|
|
|
|
/* never died until evict_inode */
|
|
F2FS_I(inode)->extent_tree = 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,
|
|
struct extent_tree *et)
|
|
{
|
|
struct rb_node *node, *next;
|
|
struct extent_node *en;
|
|
unsigned int count = atomic_read(&et->node_cnt);
|
|
|
|
node = rb_first_cached(&et->root);
|
|
while (node) {
|
|
next = rb_next(node);
|
|
en = rb_entry(node, struct extent_node, rb_node);
|
|
__release_extent_node(sbi, et, en);
|
|
node = next;
|
|
}
|
|
|
|
return count - atomic_read(&et->node_cnt);
|
|
}
|
|
|
|
static void __drop_largest_extent(struct extent_tree *et,
|
|
pgoff_t fofs, unsigned int len)
|
|
{
|
|
if (fofs < et->largest.fofs + et->largest.len &&
|
|
fofs + len > et->largest.fofs) {
|
|
et->largest.len = 0;
|
|
et->largest_updated = true;
|
|
}
|
|
}
|
|
|
|
/* return true, if inode page is changed */
|
|
static bool __f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext)
|
|
{
|
|
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
|
|
struct extent_tree *et;
|
|
struct extent_node *en;
|
|
struct extent_info ei;
|
|
|
|
if (!f2fs_may_extent_tree(inode)) {
|
|
/* drop largest extent */
|
|
if (i_ext && i_ext->len) {
|
|
i_ext->len = 0;
|
|
return true;
|
|
}
|
|
return false;
|
|
}
|
|
|
|
et = __grab_extent_tree(inode);
|
|
|
|
if (!i_ext || !i_ext->len)
|
|
return false;
|
|
|
|
get_extent_info(&ei, i_ext);
|
|
|
|
write_lock(&et->lock);
|
|
if (atomic_read(&et->node_cnt))
|
|
goto out;
|
|
|
|
en = __init_extent_tree(sbi, et, &ei);
|
|
if (en) {
|
|
spin_lock(&sbi->extent_lock);
|
|
list_add_tail(&en->list, &sbi->extent_list);
|
|
spin_unlock(&sbi->extent_lock);
|
|
}
|
|
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)
|
|
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)
|
|
{
|
|
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
|
|
struct extent_tree *et = F2FS_I(inode)->extent_tree;
|
|
struct extent_node *en;
|
|
bool ret = false;
|
|
|
|
f2fs_bug_on(sbi, !et);
|
|
|
|
trace_f2fs_lookup_extent_tree_start(inode, pgofs);
|
|
|
|
read_lock(&et->lock);
|
|
|
|
if (et->largest.fofs <= pgofs &&
|
|
et->largest.fofs + et->largest.len > pgofs) {
|
|
*ei = et->largest;
|
|
ret = true;
|
|
stat_inc_largest_node_hit(sbi);
|
|
goto out;
|
|
}
|
|
|
|
en = (struct extent_node *)f2fs_lookup_rb_tree(&et->root,
|
|
(struct rb_entry *)et->cached_en, pgofs);
|
|
if (!en)
|
|
goto out;
|
|
|
|
if (en == et->cached_en)
|
|
stat_inc_cached_node_hit(sbi);
|
|
else
|
|
stat_inc_rbtree_node_hit(sbi);
|
|
|
|
*ei = en->ei;
|
|
spin_lock(&sbi->extent_lock);
|
|
if (!list_empty(&en->list)) {
|
|
list_move_tail(&en->list, &sbi->extent_list);
|
|
et->cached_en = en;
|
|
}
|
|
spin_unlock(&sbi->extent_lock);
|
|
ret = true;
|
|
out:
|
|
stat_inc_total_hit(sbi);
|
|
read_unlock(&et->lock);
|
|
|
|
trace_f2fs_lookup_extent_tree_end(inode, pgofs, ei);
|
|
return ret;
|
|
}
|
|
|
|
static struct extent_node *__try_merge_extent_node(struct f2fs_sb_info *sbi,
|
|
struct extent_tree *et, struct extent_info *ei,
|
|
struct extent_node *prev_ex,
|
|
struct extent_node *next_ex)
|
|
{
|
|
struct extent_node *en = NULL;
|
|
|
|
if (prev_ex && __is_back_mergeable(ei, &prev_ex->ei)) {
|
|
prev_ex->ei.len += ei->len;
|
|
ei = &prev_ex->ei;
|
|
en = prev_ex;
|
|
}
|
|
|
|
if (next_ex && __is_front_mergeable(ei, &next_ex->ei)) {
|
|
next_ex->ei.fofs = ei->fofs;
|
|
next_ex->ei.blk = ei->blk;
|
|
next_ex->ei.len += ei->len;
|
|
if (en)
|
|
__release_extent_node(sbi, et, prev_ex);
|
|
|
|
en = next_ex;
|
|
}
|
|
|
|
if (!en)
|
|
return NULL;
|
|
|
|
__try_update_largest_extent(et, en);
|
|
|
|
spin_lock(&sbi->extent_lock);
|
|
if (!list_empty(&en->list)) {
|
|
list_move_tail(&en->list, &sbi->extent_list);
|
|
et->cached_en = en;
|
|
}
|
|
spin_unlock(&sbi->extent_lock);
|
|
return en;
|
|
}
|
|
|
|
static struct extent_node *__insert_extent_tree(struct f2fs_sb_info *sbi,
|
|
struct extent_tree *et, struct extent_info *ei,
|
|
struct rb_node **insert_p,
|
|
struct rb_node *insert_parent,
|
|
bool leftmost)
|
|
{
|
|
struct rb_node **p;
|
|
struct rb_node *parent = NULL;
|
|
struct extent_node *en = NULL;
|
|
|
|
if (insert_p && insert_parent) {
|
|
parent = insert_parent;
|
|
p = insert_p;
|
|
goto do_insert;
|
|
}
|
|
|
|
leftmost = true;
|
|
|
|
p = f2fs_lookup_rb_tree_for_insert(sbi, &et->root, &parent,
|
|
ei->fofs, &leftmost);
|
|
do_insert:
|
|
en = __attach_extent_node(sbi, et, ei, parent, p, leftmost);
|
|
if (!en)
|
|
return NULL;
|
|
|
|
__try_update_largest_extent(et, en);
|
|
|
|
/* update in global extent list */
|
|
spin_lock(&sbi->extent_lock);
|
|
list_add_tail(&en->list, &sbi->extent_list);
|
|
et->cached_en = en;
|
|
spin_unlock(&sbi->extent_lock);
|
|
return en;
|
|
}
|
|
|
|
static void f2fs_update_extent_tree_range(struct inode *inode,
|
|
pgoff_t fofs, block_t blkaddr, unsigned int len)
|
|
{
|
|
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
|
|
struct extent_tree *et = F2FS_I(inode)->extent_tree;
|
|
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 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);
|
|
|
|
write_lock(&et->lock);
|
|
|
|
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);
|
|
|
|
/* 1. lookup first extent node in range [fofs, fofs + len - 1] */
|
|
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)
|
|
en = next_en;
|
|
|
|
/* 2. invlidate all extent nodes in range [fofs, fofs + len - 1] */
|
|
while (en && en->ei.fofs < end) {
|
|
unsigned int org_end;
|
|
int parts = 0; /* # of parts current extent split into */
|
|
|
|
next_en = en1 = NULL;
|
|
|
|
dei = en->ei;
|
|
org_end = dei.fofs + dei.len;
|
|
f2fs_bug_on(sbi, pos >= org_end);
|
|
|
|
if (pos > dei.fofs && pos - dei.fofs >= F2FS_MIN_EXTENT_LEN) {
|
|
en->ei.len = pos - en->ei.fofs;
|
|
prev_en = en;
|
|
parts = 1;
|
|
}
|
|
|
|
if (end < org_end && org_end - end >= F2FS_MIN_EXTENT_LEN) {
|
|
if (parts) {
|
|
set_extent_info(&ei, end,
|
|
end - dei.fofs + dei.blk,
|
|
org_end - end);
|
|
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;
|
|
next_en = en;
|
|
}
|
|
parts++;
|
|
}
|
|
|
|
if (!next_en) {
|
|
struct rb_node *node = rb_next(&en->rb_node);
|
|
|
|
next_en = rb_entry_safe(node, struct extent_node,
|
|
rb_node);
|
|
}
|
|
|
|
if (parts)
|
|
__try_update_largest_extent(et, en);
|
|
else
|
|
__release_extent_node(sbi, et, en);
|
|
|
|
/*
|
|
* if original extent is split into zero or two parts, extent
|
|
* tree has been altered by deletion or insertion, therefore
|
|
* invalidate pointers regard to tree.
|
|
*/
|
|
if (parts != 1) {
|
|
insert_p = NULL;
|
|
insert_parent = NULL;
|
|
}
|
|
en = next_en;
|
|
}
|
|
|
|
/* 3. update extent in extent cache */
|
|
if (blkaddr) {
|
|
|
|
set_extent_info(&ei, fofs, blkaddr, len);
|
|
if (!__try_merge_extent_node(sbi, et, &ei, prev_en, next_en))
|
|
__insert_extent_tree(sbi, et, &ei,
|
|
insert_p, insert_parent, leftmost);
|
|
|
|
/* give up extent_cache, if split and small updates happen */
|
|
if (dei.len >= 1 &&
|
|
prev.len < F2FS_MIN_EXTENT_LEN &&
|
|
et->largest.len < F2FS_MIN_EXTENT_LEN) {
|
|
et->largest.len = 0;
|
|
et->largest_updated = true;
|
|
set_inode_flag(inode, FI_NO_EXTENT);
|
|
}
|
|
}
|
|
|
|
if (is_inode_flag_set(inode, FI_NO_EXTENT))
|
|
__free_extent_tree(sbi, et);
|
|
|
|
if (et->largest_updated) {
|
|
et->largest_updated = false;
|
|
updated = true;
|
|
}
|
|
|
|
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)
|
|
{
|
|
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))
|
|
goto free_node;
|
|
|
|
if (!mutex_trylock(&sbi->extent_tree_lock))
|
|
goto out;
|
|
|
|
/* 1. remove unreferenced extent tree */
|
|
list_for_each_entry_safe(et, next, &sbi->zombie_list, list) {
|
|
if (atomic_read(&et->node_cnt)) {
|
|
write_lock(&et->lock);
|
|
node_cnt += __free_extent_tree(sbi, et);
|
|
write_unlock(&et->lock);
|
|
}
|
|
f2fs_bug_on(sbi, atomic_read(&et->node_cnt));
|
|
list_del_init(&et->list);
|
|
radix_tree_delete(&sbi->extent_tree_root, et->ino);
|
|
kmem_cache_free(extent_tree_slab, et);
|
|
atomic_dec(&sbi->total_ext_tree);
|
|
atomic_dec(&sbi->total_zombie_tree);
|
|
tree_cnt++;
|
|
|
|
if (node_cnt + tree_cnt >= nr_shrink)
|
|
goto unlock_out;
|
|
cond_resched();
|
|
}
|
|
mutex_unlock(&sbi->extent_tree_lock);
|
|
|
|
free_node:
|
|
/* 2. remove LRU extent entries */
|
|
if (!mutex_trylock(&sbi->extent_tree_lock))
|
|
goto out;
|
|
|
|
remained = nr_shrink - (node_cnt + tree_cnt);
|
|
|
|
spin_lock(&sbi->extent_lock);
|
|
for (; remained > 0; remained--) {
|
|
if (list_empty(&sbi->extent_list))
|
|
break;
|
|
en = list_first_entry(&sbi->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);
|
|
continue;
|
|
}
|
|
|
|
list_del_init(&en->list);
|
|
spin_unlock(&sbi->extent_lock);
|
|
|
|
__detach_extent_node(sbi, et, en);
|
|
|
|
write_unlock(&et->lock);
|
|
node_cnt++;
|
|
spin_lock(&sbi->extent_lock);
|
|
}
|
|
spin_unlock(&sbi->extent_lock);
|
|
|
|
unlock_out:
|
|
mutex_unlock(&sbi->extent_tree_lock);
|
|
out:
|
|
trace_f2fs_shrink_extent_tree(sbi, node_cnt, tree_cnt);
|
|
|
|
return node_cnt + tree_cnt;
|
|
}
|
|
|
|
unsigned int f2fs_destroy_extent_node(struct inode *inode)
|
|
{
|
|
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
|
|
struct extent_tree *et = F2FS_I(inode)->extent_tree;
|
|
unsigned int node_cnt = 0;
|
|
|
|
if (!et || !atomic_read(&et->node_cnt))
|
|
return 0;
|
|
|
|
write_lock(&et->lock);
|
|
node_cnt = __free_extent_tree(sbi, et);
|
|
write_unlock(&et->lock);
|
|
|
|
return node_cnt;
|
|
}
|
|
|
|
void f2fs_drop_extent_tree(struct inode *inode)
|
|
{
|
|
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
|
|
struct extent_tree *et = F2FS_I(inode)->extent_tree;
|
|
bool updated = false;
|
|
|
|
if (!f2fs_may_extent_tree(inode))
|
|
return;
|
|
|
|
set_inode_flag(inode, FI_NO_EXTENT);
|
|
|
|
write_lock(&et->lock);
|
|
__free_extent_tree(sbi, et);
|
|
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)
|
|
{
|
|
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
|
|
struct extent_tree *et = F2FS_I(inode)->extent_tree;
|
|
unsigned int node_cnt = 0;
|
|
|
|
if (!et)
|
|
return;
|
|
|
|
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);
|
|
return;
|
|
}
|
|
|
|
/* free all extent info belong to this extent tree */
|
|
node_cnt = f2fs_destroy_extent_node(inode);
|
|
|
|
/* delete extent tree entry in radix tree */
|
|
mutex_lock(&sbi->extent_tree_lock);
|
|
f2fs_bug_on(sbi, atomic_read(&et->node_cnt));
|
|
radix_tree_delete(&sbi->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);
|
|
|
|
F2FS_I(inode)->extent_tree = NULL;
|
|
|
|
trace_f2fs_destroy_extent_tree(inode, node_cnt);
|
|
}
|
|
|
|
bool f2fs_lookup_extent_cache(struct inode *inode, pgoff_t pgofs,
|
|
struct extent_info *ei)
|
|
{
|
|
if (!f2fs_may_extent_tree(inode))
|
|
return false;
|
|
|
|
return f2fs_lookup_extent_tree(inode, pgofs, ei);
|
|
}
|
|
|
|
void f2fs_update_extent_cache(struct dnode_of_data *dn)
|
|
{
|
|
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);
|
|
}
|
|
|
|
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);
|
|
}
|
|
|
|
int __init f2fs_create_extent_cache(void)
|
|
{
|
|
extent_tree_slab = f2fs_kmem_cache_create("f2fs_extent_tree",
|
|
sizeof(struct extent_tree));
|
|
if (!extent_tree_slab)
|
|
return -ENOMEM;
|
|
extent_node_slab = f2fs_kmem_cache_create("f2fs_extent_node",
|
|
sizeof(struct extent_node));
|
|
if (!extent_node_slab) {
|
|
kmem_cache_destroy(extent_tree_slab);
|
|
return -ENOMEM;
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
void f2fs_destroy_extent_cache(void)
|
|
{
|
|
kmem_cache_destroy(extent_node_slab);
|
|
kmem_cache_destroy(extent_tree_slab);
|
|
}
|