UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity
OpenCloudOS-Kernel/fs/f2fs/data.c

2306 lines
54 KiB
C
Raw Blame History

/*
* fs/f2fs/data.c
*
* Copyright (c) 2012 Samsung Electronics Co., Ltd.
* http://www.samsung.com/
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#include <linux/fs.h>
#include <linux/f2fs_fs.h>
#include <linux/buffer_head.h>
#include <linux/mpage.h>
#include <linux/writeback.h>
#include <linux/backing-dev.h>
#include <linux/pagevec.h>
#include <linux/blkdev.h>
#include <linux/bio.h>
#include <linux/prefetch.h>
#include <linux/uio.h>
#include <linux/mm.h>
#include <linux/memcontrol.h>
#include <linux/cleancache.h>
#include <linux/sched/signal.h>
#include "f2fs.h"
#include "node.h"
#include "segment.h"
#include "trace.h"
#include <trace/events/f2fs.h>
static bool __is_cp_guaranteed(struct page *page)
{
struct address_space *mapping = page->mapping;
struct inode *inode;
struct f2fs_sb_info *sbi;
if (!mapping)
return false;
inode = mapping->host;
sbi = F2FS_I_SB(inode);
if (inode->i_ino == F2FS_META_INO(sbi) ||
inode->i_ino == F2FS_NODE_INO(sbi) ||
S_ISDIR(inode->i_mode) ||
is_cold_data(page))
return true;
return false;
}
static void f2fs_read_end_io(struct bio *bio)
{
struct bio_vec *bvec;
int i;
#ifdef CONFIG_F2FS_FAULT_INJECTION
if (time_to_inject(F2FS_P_SB(bio->bi_io_vec->bv_page), FAULT_IO)) {
f2fs_show_injection_info(FAULT_IO);
bio->bi_status = BLK_STS_IOERR;
}
#endif
if (f2fs_bio_encrypted(bio)) {
if (bio->bi_status) {
fscrypt_release_ctx(bio->bi_private);
} else {
fscrypt_decrypt_bio_pages(bio->bi_private, bio);
return;
}
}
bio_for_each_segment_all(bvec, bio, i) {
struct page *page = bvec->bv_page;
if (!bio->bi_status) {
if (!PageUptodate(page))
SetPageUptodate(page);
} else {
ClearPageUptodate(page);
SetPageError(page);
}
unlock_page(page);
}
bio_put(bio);
}
static void f2fs_write_end_io(struct bio *bio)
{
struct f2fs_sb_info *sbi = bio->bi_private;
struct bio_vec *bvec;
int i;
bio_for_each_segment_all(bvec, bio, i) {
struct page *page = bvec->bv_page;
enum count_type type = WB_DATA_TYPE(page);
if (IS_DUMMY_WRITTEN_PAGE(page)) {
set_page_private(page, (unsigned long)NULL);
ClearPagePrivate(page);
unlock_page(page);
mempool_free(page, sbi->write_io_dummy);
if (unlikely(bio->bi_status))
f2fs_stop_checkpoint(sbi, true);
continue;
}
fscrypt_pullback_bio_page(&page, true);
if (unlikely(bio->bi_status)) {
mapping_set_error(page->mapping, -EIO);
f2fs_stop_checkpoint(sbi, true);
}
dec_page_count(sbi, type);
clear_cold_data(page);
end_page_writeback(page);
}
if (!get_pages(sbi, F2FS_WB_CP_DATA) &&
wq_has_sleeper(&sbi->cp_wait))
wake_up(&sbi->cp_wait);
bio_put(bio);
}
/*
* Return true, if pre_bio's bdev is same as its target device.
*/
struct block_device *f2fs_target_device(struct f2fs_sb_info *sbi,
block_t blk_addr, struct bio *bio)
{
struct block_device *bdev = sbi->sb->s_bdev;
int i;
for (i = 0; i < sbi->s_ndevs; i++) {
if (FDEV(i).start_blk <= blk_addr &&
FDEV(i).end_blk >= blk_addr) {
blk_addr -= FDEV(i).start_blk;
bdev = FDEV(i).bdev;
break;
}
}
if (bio) {
bio_set_dev(bio, bdev);
bio->bi_iter.bi_sector = SECTOR_FROM_BLOCK(blk_addr);
}
return bdev;
}
int f2fs_target_device_index(struct f2fs_sb_info *sbi, block_t blkaddr)
{
int i;
for (i = 0; i < sbi->s_ndevs; i++)
if (FDEV(i).start_blk <= blkaddr && FDEV(i).end_blk >= blkaddr)
return i;
return 0;
}
static bool __same_bdev(struct f2fs_sb_info *sbi,
block_t blk_addr, struct bio *bio)
{
struct block_device *b = f2fs_target_device(sbi, blk_addr, NULL);
return bio->bi_disk == b->bd_disk && bio->bi_partno == b->bd_partno;
}
/*
* Low-level block read/write IO operations.
*/
static struct bio *__bio_alloc(struct f2fs_sb_info *sbi, block_t blk_addr,
int npages, bool is_read)
{
struct bio *bio;
bio = f2fs_bio_alloc(sbi, npages, true);
f2fs_target_device(sbi, blk_addr, bio);
bio->bi_end_io = is_read ? f2fs_read_end_io : f2fs_write_end_io;
bio->bi_private = is_read ? NULL : sbi;
return bio;
}
static inline void __submit_bio(struct f2fs_sb_info *sbi,
struct bio *bio, enum page_type type)
{
if (!is_read_io(bio_op(bio))) {
unsigned int start;
if (f2fs_sb_mounted_blkzoned(sbi->sb) &&
current->plug && (type == DATA || type == NODE))
blk_finish_plug(current->plug);
if (type != DATA && type != NODE)
goto submit_io;
start = bio->bi_iter.bi_size >> F2FS_BLKSIZE_BITS;
start %= F2FS_IO_SIZE(sbi);
if (start == 0)
goto submit_io;
/* fill dummy pages */
for (; start < F2FS_IO_SIZE(sbi); start++) {
struct page *page =
mempool_alloc(sbi->write_io_dummy,
GFP_NOIO | __GFP_ZERO | __GFP_NOFAIL);
f2fs_bug_on(sbi, !page);
SetPagePrivate(page);
set_page_private(page, (unsigned long)DUMMY_WRITTEN_PAGE);
lock_page(page);
if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE)
f2fs_bug_on(sbi, 1);
}
/*
* In the NODE case, we lose next block address chain. So, we
* need to do checkpoint in f2fs_sync_file.
*/
if (type == NODE)
set_sbi_flag(sbi, SBI_NEED_CP);
}
submit_io:
if (is_read_io(bio_op(bio)))
trace_f2fs_submit_read_bio(sbi->sb, type, bio);
else
trace_f2fs_submit_write_bio(sbi->sb, type, bio);
submit_bio(bio);
}
static void __submit_merged_bio(struct f2fs_bio_info *io)
{
struct f2fs_io_info *fio = &io->fio;
if (!io->bio)
return;
bio_set_op_attrs(io->bio, fio->op, fio->op_flags);
if (is_read_io(fio->op))
trace_f2fs_prepare_read_bio(io->sbi->sb, fio->type, io->bio);
else
trace_f2fs_prepare_write_bio(io->sbi->sb, fio->type, io->bio);
__submit_bio(io->sbi, io->bio, fio->type);
io->bio = NULL;
}
static bool __has_merged_page(struct f2fs_bio_info *io,
struct inode *inode, nid_t ino, pgoff_t idx)
{
struct bio_vec *bvec;
struct page *target;
int i;
if (!io->bio)
return false;
if (!inode && !ino)
return true;
bio_for_each_segment_all(bvec, io->bio, i) {
if (bvec->bv_page->mapping)
target = bvec->bv_page;
else
target = fscrypt_control_page(bvec->bv_page);
if (idx != target->index)
continue;
if (inode && inode == target->mapping->host)
return true;
if (ino && ino == ino_of_node(target))
return true;
}
return false;
}
static bool has_merged_page(struct f2fs_sb_info *sbi, struct inode *inode,
nid_t ino, pgoff_t idx, enum page_type type)
{
enum page_type btype = PAGE_TYPE_OF_BIO(type);
enum temp_type temp;
struct f2fs_bio_info *io;
bool ret = false;
for (temp = HOT; temp < NR_TEMP_TYPE; temp++) {
io = sbi->write_io[btype] + temp;
down_read(&io->io_rwsem);
ret = __has_merged_page(io, inode, ino, idx);
up_read(&io->io_rwsem);
/* TODO: use HOT temp only for meta pages now. */
if (ret || btype == META)
break;
}
return ret;
}
static void __f2fs_submit_merged_write(struct f2fs_sb_info *sbi,
enum page_type type, enum temp_type temp)
{
enum page_type btype = PAGE_TYPE_OF_BIO(type);
struct f2fs_bio_info *io = sbi->write_io[btype] + temp;
down_write(&io->io_rwsem);
/* change META to META_FLUSH in the checkpoint procedure */
if (type >= META_FLUSH) {
io->fio.type = META_FLUSH;
io->fio.op = REQ_OP_WRITE;
io->fio.op_flags = REQ_META | REQ_PRIO | REQ_SYNC;
if (!test_opt(sbi, NOBARRIER))
io->fio.op_flags |= REQ_PREFLUSH | REQ_FUA;
}
__submit_merged_bio(io);
up_write(&io->io_rwsem);
}
static void __submit_merged_write_cond(struct f2fs_sb_info *sbi,
struct inode *inode, nid_t ino, pgoff_t idx,
enum page_type type, bool force)
{
enum temp_type temp;
if (!force && !has_merged_page(sbi, inode, ino, idx, type))
return;
for (temp = HOT; temp < NR_TEMP_TYPE; temp++) {
__f2fs_submit_merged_write(sbi, type, temp);
/* TODO: use HOT temp only for meta pages now. */
if (type >= META)
break;
}
}
void f2fs_submit_merged_write(struct f2fs_sb_info *sbi, enum page_type type)
{
__submit_merged_write_cond(sbi, NULL, 0, 0, type, true);
}
void f2fs_submit_merged_write_cond(struct f2fs_sb_info *sbi,
struct inode *inode, nid_t ino, pgoff_t idx,
enum page_type type)
{
__submit_merged_write_cond(sbi, inode, ino, idx, type, false);
}
void f2fs_flush_merged_writes(struct f2fs_sb_info *sbi)
{
f2fs_submit_merged_write(sbi, DATA);
f2fs_submit_merged_write(sbi, NODE);
f2fs_submit_merged_write(sbi, META);
}
/*
* Fill the locked page with data located in the block address.
* A caller needs to unlock the page on failure.
*/
int f2fs_submit_page_bio(struct f2fs_io_info *fio)
{
struct bio *bio;
struct page *page = fio->encrypted_page ?
fio->encrypted_page : fio->page;
trace_f2fs_submit_page_bio(page, fio);
f2fs_trace_ios(fio, 0);
/* Allocate a new bio */
bio = __bio_alloc(fio->sbi, fio->new_blkaddr, 1, is_read_io(fio->op));
if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) {
bio_put(bio);
return -EFAULT;
}
bio_set_op_attrs(bio, fio->op, fio->op_flags);
__submit_bio(fio->sbi, bio, fio->type);
if (!is_read_io(fio->op))
inc_page_count(fio->sbi, WB_DATA_TYPE(fio->page));
return 0;
}
int f2fs_submit_page_write(struct f2fs_io_info *fio)
{
struct f2fs_sb_info *sbi = fio->sbi;
enum page_type btype = PAGE_TYPE_OF_BIO(fio->type);
struct f2fs_bio_info *io = sbi->write_io[btype] + fio->temp;
struct page *bio_page;
int err = 0;
f2fs_bug_on(sbi, is_read_io(fio->op));
down_write(&io->io_rwsem);
next:
if (fio->in_list) {
spin_lock(&io->io_lock);
if (list_empty(&io->io_list)) {
spin_unlock(&io->io_lock);
goto out_fail;
}
fio = list_first_entry(&io->io_list,
struct f2fs_io_info, list);
list_del(&fio->list);
spin_unlock(&io->io_lock);
}
if (fio->old_blkaddr != NEW_ADDR)
verify_block_addr(sbi, fio->old_blkaddr);
verify_block_addr(sbi, fio->new_blkaddr);
bio_page = fio->encrypted_page ? fio->encrypted_page : fio->page;
/* set submitted = true as a return value */
fio->submitted = true;
inc_page_count(sbi, WB_DATA_TYPE(bio_page));
if (io->bio && (io->last_block_in_bio != fio->new_blkaddr - 1 ||
(io->fio.op != fio->op || io->fio.op_flags != fio->op_flags) ||
!__same_bdev(sbi, fio->new_blkaddr, io->bio)))
__submit_merged_bio(io);
alloc_new:
if (io->bio == NULL) {
if ((fio->type == DATA || fio->type == NODE) &&
fio->new_blkaddr & F2FS_IO_SIZE_MASK(sbi)) {
err = -EAGAIN;
dec_page_count(sbi, WB_DATA_TYPE(bio_page));
goto out_fail;
}
io->bio = __bio_alloc(sbi, fio->new_blkaddr,
BIO_MAX_PAGES, false);
io->fio = *fio;
}
if (bio_add_page(io->bio, bio_page, PAGE_SIZE, 0) < PAGE_SIZE) {
__submit_merged_bio(io);
goto alloc_new;
}
io->last_block_in_bio = fio->new_blkaddr;
f2fs_trace_ios(fio, 0);
trace_f2fs_submit_page_write(fio->page, fio);
if (fio->in_list)
goto next;
out_fail:
up_write(&io->io_rwsem);
return err;
}
static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr,
unsigned nr_pages)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct fscrypt_ctx *ctx = NULL;
struct bio *bio;
if (f2fs_encrypted_file(inode)) {
ctx = fscrypt_get_ctx(inode, GFP_NOFS);
if (IS_ERR(ctx))
return ERR_CAST(ctx);
/* wait the page to be moved by cleaning */
f2fs_wait_on_block_writeback(sbi, blkaddr);
}
bio = f2fs_bio_alloc(sbi, min_t(int, nr_pages, BIO_MAX_PAGES), false);
if (!bio) {
if (ctx)
fscrypt_release_ctx(ctx);
return ERR_PTR(-ENOMEM);
}
f2fs_target_device(sbi, blkaddr, bio);
bio->bi_end_io = f2fs_read_end_io;
bio->bi_private = ctx;
bio_set_op_attrs(bio, REQ_OP_READ, 0);
return bio;
}
/* This can handle encryption stuffs */
static int f2fs_submit_page_read(struct inode *inode, struct page *page,
block_t blkaddr)
{
struct bio *bio = f2fs_grab_read_bio(inode, blkaddr, 1);
if (IS_ERR(bio))
return PTR_ERR(bio);
if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) {
bio_put(bio);
return -EFAULT;
}
__submit_bio(F2FS_I_SB(inode), bio, DATA);
return 0;
}
static void __set_data_blkaddr(struct dnode_of_data *dn)
{
struct f2fs_node *rn = F2FS_NODE(dn->node_page);
__le32 *addr_array;
int base = 0;
if (IS_INODE(dn->node_page) && f2fs_has_extra_attr(dn->inode))
base = get_extra_isize(dn->inode);
/* Get physical address of data block */
addr_array = blkaddr_in_node(rn);
addr_array[base + dn->ofs_in_node] = cpu_to_le32(dn->data_blkaddr);
}
/*
* Lock ordering for the change of data block address:
* ->data_page
* ->node_page
* update block addresses in the node page
*/
void set_data_blkaddr(struct dnode_of_data *dn)
{
f2fs_wait_on_page_writeback(dn->node_page, NODE, true);
__set_data_blkaddr(dn);
if (set_page_dirty(dn->node_page))
dn->node_changed = true;
}
void f2fs_update_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr)
{
dn->data_blkaddr = blkaddr;
set_data_blkaddr(dn);
f2fs_update_extent_cache(dn);
}
/* dn->ofs_in_node will be returned with up-to-date last block pointer */
int reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
int err;
if (!count)
return 0;
if (unlikely(is_inode_flag_set(dn->inode, FI_NO_ALLOC)))
return -EPERM;
if (unlikely((err = inc_valid_block_count(sbi, dn->inode, &count))))
return err;
trace_f2fs_reserve_new_blocks(dn->inode, dn->nid,
dn->ofs_in_node, count);
f2fs_wait_on_page_writeback(dn->node_page, NODE, true);
for (; count > 0; dn->ofs_in_node++) {
block_t blkaddr = datablock_addr(dn->inode,
dn->node_page, dn->ofs_in_node);
if (blkaddr == NULL_ADDR) {
dn->data_blkaddr = NEW_ADDR;
__set_data_blkaddr(dn);
count--;
}
}
if (set_page_dirty(dn->node_page))
dn->node_changed = true;
return 0;
}
/* Should keep dn->ofs_in_node unchanged */
int reserve_new_block(struct dnode_of_data *dn)
{
unsigned int ofs_in_node = dn->ofs_in_node;
int ret;
ret = reserve_new_blocks(dn, 1);
dn->ofs_in_node = ofs_in_node;
return ret;
}
int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index)
{
bool need_put = dn->inode_page ? false : true;
int err;
err = get_dnode_of_data(dn, index, ALLOC_NODE);
if (err)
return err;
if (dn->data_blkaddr == NULL_ADDR)
err = reserve_new_block(dn);
if (err || need_put)
f2fs_put_dnode(dn);
return err;
}
int f2fs_get_block(struct dnode_of_data *dn, pgoff_t index)
{
struct extent_info ei = {0,0,0};
struct inode *inode = dn->inode;
if (f2fs_lookup_extent_cache(inode, index, &ei)) {
dn->data_blkaddr = ei.blk + index - ei.fofs;
return 0;
}
return f2fs_reserve_block(dn, index);
}
struct page *get_read_data_page(struct inode *inode, pgoff_t index,
int op_flags, bool for_write)
{
struct address_space *mapping = inode->i_mapping;
struct dnode_of_data dn;
struct page *page;
struct extent_info ei = {0,0,0};
int err;
page = f2fs_grab_cache_page(mapping, index, for_write);
if (!page)
return ERR_PTR(-ENOMEM);
if (f2fs_lookup_extent_cache(inode, index, &ei)) {
dn.data_blkaddr = ei.blk + index - ei.fofs;
goto got_it;
}
set_new_dnode(&dn, inode, NULL, NULL, 0);
err = get_dnode_of_data(&dn, index, LOOKUP_NODE);
if (err)
goto put_err;
f2fs_put_dnode(&dn);
if (unlikely(dn.data_blkaddr == NULL_ADDR)) {
err = -ENOENT;
goto put_err;
}
got_it:
if (PageUptodate(page)) {
unlock_page(page);
return page;
}
/*
* A new dentry page is allocated but not able to be written, since its
* new inode page couldn't be allocated due to -ENOSPC.
* In such the case, its blkaddr can be remained as NEW_ADDR.
* see, f2fs_add_link -> get_new_data_page -> init_inode_metadata.
*/
if (dn.data_blkaddr == NEW_ADDR) {
zero_user_segment(page, 0, PAGE_SIZE);
if (!PageUptodate(page))
SetPageUptodate(page);
unlock_page(page);
return page;
}
err = f2fs_submit_page_read(inode, page, dn.data_blkaddr);
if (err)
goto put_err;
return page;
put_err:
f2fs_put_page(page, 1);
return ERR_PTR(err);
}
struct page *find_data_page(struct inode *inode, pgoff_t index)
{
struct address_space *mapping = inode->i_mapping;
struct page *page;
page = find_get_page(mapping, index);
if (page && PageUptodate(page))
return page;
f2fs_put_page(page, 0);
page = get_read_data_page(inode, index, 0, false);
if (IS_ERR(page))
return page;
if (PageUptodate(page))
return page;
wait_on_page_locked(page);
if (unlikely(!PageUptodate(page))) {
f2fs_put_page(page, 0);
return ERR_PTR(-EIO);
}
return page;
}
/*
* If it tries to access a hole, return an error.
* Because, the callers, functions in dir.c and GC, should be able to know
* whether this page exists or not.
*/
struct page *get_lock_data_page(struct inode *inode, pgoff_t index,
bool for_write)
{
struct address_space *mapping = inode->i_mapping;
struct page *page;
repeat:
page = get_read_data_page(inode, index, 0, for_write);
if (IS_ERR(page))
return page;
/* wait for read completion */
lock_page(page);
if (unlikely(page->mapping != mapping)) {
f2fs_put_page(page, 1);
goto repeat;
}
if (unlikely(!PageUptodate(page))) {
f2fs_put_page(page, 1);
return ERR_PTR(-EIO);
}
return page;
}
/*
* Caller ensures that this data page is never allocated.
* A new zero-filled data page is allocated in the page cache.
*
* Also, caller should grab and release a rwsem by calling f2fs_lock_op() and
* f2fs_unlock_op().
* Note that, ipage is set only by make_empty_dir, and if any error occur,
* ipage should be released by this function.
*/
struct page *get_new_data_page(struct inode *inode,
struct page *ipage, pgoff_t index, bool new_i_size)
{
struct address_space *mapping = inode->i_mapping;
struct page *page;
struct dnode_of_data dn;
int err;
page = f2fs_grab_cache_page(mapping, index, true);
if (!page) {
/*
* before exiting, we should make sure ipage will be released
* if any error occur.
*/
f2fs_put_page(ipage, 1);
return ERR_PTR(-ENOMEM);
}
set_new_dnode(&dn, inode, ipage, NULL, 0);
err = f2fs_reserve_block(&dn, index);
if (err) {
f2fs_put_page(page, 1);
return ERR_PTR(err);
}
if (!ipage)
f2fs_put_dnode(&dn);
if (PageUptodate(page))
goto got_it;
if (dn.data_blkaddr == NEW_ADDR) {
zero_user_segment(page, 0, PAGE_SIZE);
if (!PageUptodate(page))
SetPageUptodate(page);
} else {
f2fs_put_page(page, 1);
/* if ipage exists, blkaddr should be NEW_ADDR */
f2fs_bug_on(F2FS_I_SB(inode), ipage);
page = get_lock_data_page(inode, index, true);
if (IS_ERR(page))
return page;
}
got_it:
if (new_i_size && i_size_read(inode) <
((loff_t)(index + 1) << PAGE_SHIFT))
f2fs_i_size_write(inode, ((loff_t)(index + 1) << PAGE_SHIFT));
return page;
}
static int __allocate_data_block(struct dnode_of_data *dn)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
struct f2fs_summary sum;
struct node_info ni;
pgoff_t fofs;
blkcnt_t count = 1;
int err;
if (unlikely(is_inode_flag_set(dn->inode, FI_NO_ALLOC)))
return -EPERM;
dn->data_blkaddr = datablock_addr(dn->inode,
dn->node_page, dn->ofs_in_node);
if (dn->data_blkaddr == NEW_ADDR)
goto alloc;
if (unlikely((err = inc_valid_block_count(sbi, dn->inode, &count))))
return err;
alloc:
get_node_info(sbi, dn->nid, &ni);
set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version);
allocate_data_block(sbi, NULL, dn->data_blkaddr, &dn->data_blkaddr,
&sum, CURSEG_WARM_DATA, NULL, false);
set_data_blkaddr(dn);
/* update i_size */
fofs = start_bidx_of_node(ofs_of_node(dn->node_page), dn->inode) +
dn->ofs_in_node;
if (i_size_read(dn->inode) < ((loff_t)(fofs + 1) << PAGE_SHIFT))
f2fs_i_size_write(dn->inode,
((loff_t)(fofs + 1) << PAGE_SHIFT));
return 0;
}
static inline bool __force_buffered_io(struct inode *inode, int rw)
{
return (f2fs_encrypted_file(inode) ||
(rw == WRITE && test_opt(F2FS_I_SB(inode), LFS)) ||
F2FS_I_SB(inode)->s_ndevs);
}
int f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from)
{
struct inode *inode = file_inode(iocb->ki_filp);
struct f2fs_map_blocks map;
int err = 0;
/* convert inline data for Direct I/O*/
if (iocb->ki_flags & IOCB_DIRECT) {
err = f2fs_convert_inline_inode(inode);
if (err)
return err;
}
if (is_inode_flag_set(inode, FI_NO_PREALLOC))
return 0;
map.m_lblk = F2FS_BLK_ALIGN(iocb->ki_pos);
map.m_len = F2FS_BYTES_TO_BLK(iocb->ki_pos + iov_iter_count(from));
if (map.m_len > map.m_lblk)
map.m_len -= map.m_lblk;
else
map.m_len = 0;
map.m_next_pgofs = NULL;
if (iocb->ki_flags & IOCB_DIRECT)
return f2fs_map_blocks(inode, &map, 1,
__force_buffered_io(inode, WRITE) ?
F2FS_GET_BLOCK_PRE_AIO :
F2FS_GET_BLOCK_PRE_DIO);
if (iocb->ki_pos + iov_iter_count(from) > MAX_INLINE_DATA(inode)) {
err = f2fs_convert_inline_inode(inode);
if (err)
return err;
}
if (!f2fs_has_inline_data(inode))
return f2fs_map_blocks(inode, &map, 1, F2FS_GET_BLOCK_PRE_AIO);
return err;
}
static inline void __do_map_lock(struct f2fs_sb_info *sbi, int flag, bool lock)
{
if (flag == F2FS_GET_BLOCK_PRE_AIO) {
if (lock)
down_read(&sbi->node_change);
else
up_read(&sbi->node_change);
} else {
if (lock)
f2fs_lock_op(sbi);
else
f2fs_unlock_op(sbi);
}
}
/*
* f2fs_map_blocks() now supported readahead/bmap/rw direct_IO with
* f2fs_map_blocks structure.
* If original data blocks are allocated, then give them to blockdev.
* Otherwise,
* a. preallocate requested block addresses
* b. do not use extent cache for better performance
* c. give the block addresses to blockdev
*/
int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
int create, int flag)
{
unsigned int maxblocks = map->m_len;
struct dnode_of_data dn;
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
int mode = create ? ALLOC_NODE : LOOKUP_NODE;
pgoff_t pgofs, end_offset, end;
int err = 0, ofs = 1;
unsigned int ofs_in_node, last_ofs_in_node;
blkcnt_t prealloc;
struct extent_info ei = {0,0,0};
block_t blkaddr;
if (!maxblocks)
return 0;
map->m_len = 0;
map->m_flags = 0;
/* it only supports block size == page size */
pgofs = (pgoff_t)map->m_lblk;
end = pgofs + maxblocks;
if (!create && f2fs_lookup_extent_cache(inode, pgofs, &ei)) {
map->m_pblk = ei.blk + pgofs - ei.fofs;
map->m_len = min((pgoff_t)maxblocks, ei.fofs + ei.len - pgofs);
map->m_flags = F2FS_MAP_MAPPED;
goto out;
}
next_dnode:
if (create)
__do_map_lock(sbi, flag, true);
/* When reading holes, we need its node page */
set_new_dnode(&dn, inode, NULL, NULL, 0);
err = get_dnode_of_data(&dn, pgofs, mode);
if (err) {
if (flag == F2FS_GET_BLOCK_BMAP)
map->m_pblk = 0;
if (err == -ENOENT) {
err = 0;
if (map->m_next_pgofs)
*map->m_next_pgofs =
get_next_page_offset(&dn, pgofs);
}
goto unlock_out;
}
prealloc = 0;
last_ofs_in_node = ofs_in_node = dn.ofs_in_node;
end_offset = ADDRS_PER_PAGE(dn.node_page, inode);
next_block:
blkaddr = datablock_addr(dn.inode, dn.node_page, dn.ofs_in_node);
if (blkaddr == NEW_ADDR || blkaddr == NULL_ADDR) {
if (create) {
if (unlikely(f2fs_cp_error(sbi))) {
err = -EIO;
goto sync_out;
}
if (flag == F2FS_GET_BLOCK_PRE_AIO) {
if (blkaddr == NULL_ADDR) {
prealloc++;
last_ofs_in_node = dn.ofs_in_node;
}
} else {
err = __allocate_data_block(&dn);
if (!err)
set_inode_flag(inode, FI_APPEND_WRITE);
}
if (err)
goto sync_out;
map->m_flags |= F2FS_MAP_NEW;
blkaddr = dn.data_blkaddr;
} else {
if (flag == F2FS_GET_BLOCK_BMAP) {
map->m_pblk = 0;
goto sync_out;
}
if (flag == F2FS_GET_BLOCK_FIEMAP &&
blkaddr == NULL_ADDR) {
if (map->m_next_pgofs)
*map->m_next_pgofs = pgofs + 1;
}
if (flag != F2FS_GET_BLOCK_FIEMAP ||
blkaddr != NEW_ADDR)
goto sync_out;
}
}
if (flag == F2FS_GET_BLOCK_PRE_AIO)
goto skip;
if (map->m_len == 0) {
/* preallocated unwritten block should be mapped for fiemap. */
if (blkaddr == NEW_ADDR)
map->m_flags |= F2FS_MAP_UNWRITTEN;
map->m_flags |= F2FS_MAP_MAPPED;
map->m_pblk = blkaddr;
map->m_len = 1;
} else if ((map->m_pblk != NEW_ADDR &&
blkaddr == (map->m_pblk + ofs)) ||
(map->m_pblk == NEW_ADDR && blkaddr == NEW_ADDR) ||
flag == F2FS_GET_BLOCK_PRE_DIO) {
ofs++;
map->m_len++;
} else {
goto sync_out;
}
skip:
dn.ofs_in_node++;
pgofs++;
/* preallocate blocks in batch for one dnode page */
if (flag == F2FS_GET_BLOCK_PRE_AIO &&
(pgofs == end || dn.ofs_in_node == end_offset)) {
dn.ofs_in_node = ofs_in_node;
err = reserve_new_blocks(&dn, prealloc);
if (err)
goto sync_out;
map->m_len += dn.ofs_in_node - ofs_in_node;
if (prealloc && dn.ofs_in_node != last_ofs_in_node + 1) {
err = -ENOSPC;
goto sync_out;
}
dn.ofs_in_node = end_offset;
}
if (pgofs >= end)
goto sync_out;
else if (dn.ofs_in_node < end_offset)
goto next_block;
f2fs_put_dnode(&dn);
if (create) {
__do_map_lock(sbi, flag, false);
f2fs_balance_fs(sbi, dn.node_changed);
}
goto next_dnode;
sync_out:
f2fs_put_dnode(&dn);
unlock_out:
if (create) {
__do_map_lock(sbi, flag, false);
f2fs_balance_fs(sbi, dn.node_changed);
}
out:
trace_f2fs_map_blocks(inode, map, err);
return err;
}
static int __get_data_block(struct inode *inode, sector_t iblock,
struct buffer_head *bh, int create, int flag,
pgoff_t *next_pgofs)
{
struct f2fs_map_blocks map;
int err;
map.m_lblk = iblock;
map.m_len = bh->b_size >> inode->i_blkbits;
map.m_next_pgofs = next_pgofs;
err = f2fs_map_blocks(inode, &map, create, flag);
if (!err) {
map_bh(bh, inode->i_sb, map.m_pblk);
bh->b_state = (bh->b_state & ~F2FS_MAP_FLAGS) | map.m_flags;
bh->b_size = (u64)map.m_len << inode->i_blkbits;
}
return err;
}
static int get_data_block(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create, int flag,
pgoff_t *next_pgofs)
{
return __get_data_block(inode, iblock, bh_result, create,
flag, next_pgofs);
}
static int get_data_block_dio(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create)
{
return __get_data_block(inode, iblock, bh_result, create,
F2FS_GET_BLOCK_DEFAULT, NULL);
}
static int get_data_block_bmap(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create)
{
/* Block number less than F2FS MAX BLOCKS */
if (unlikely(iblock >= F2FS_I_SB(inode)->max_file_blocks))
return -EFBIG;
return __get_data_block(inode, iblock, bh_result, create,
F2FS_GET_BLOCK_BMAP, NULL);
}
static inline sector_t logical_to_blk(struct inode *inode, loff_t offset)
{
return (offset >> inode->i_blkbits);
}
static inline loff_t blk_to_logical(struct inode *inode, sector_t blk)
{
return (blk << inode->i_blkbits);
}
int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
u64 start, u64 len)
{
struct buffer_head map_bh;
sector_t start_blk, last_blk;
pgoff_t next_pgofs;
u64 logical = 0, phys = 0, size = 0;
u32 flags = 0;
int ret = 0;
ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC);
if (ret)
return ret;
if (f2fs_has_inline_data(inode)) {
ret = f2fs_inline_data_fiemap(inode, fieinfo, start, len);
if (ret != -EAGAIN)
return ret;
}
inode_lock(inode);
if (logical_to_blk(inode, len) == 0)
len = blk_to_logical(inode, 1);
start_blk = logical_to_blk(inode, start);
last_blk = logical_to_blk(inode, start + len - 1);
next:
memset(&map_bh, 0, sizeof(struct buffer_head));
map_bh.b_size = len;
ret = get_data_block(inode, start_blk, &map_bh, 0,
F2FS_GET_BLOCK_FIEMAP, &next_pgofs);
if (ret)
goto out;
/* HOLE */
if (!buffer_mapped(&map_bh)) {
start_blk = next_pgofs;
if (blk_to_logical(inode, start_blk) < blk_to_logical(inode,
F2FS_I_SB(inode)->max_file_blocks))
goto prep_next;
flags |= FIEMAP_EXTENT_LAST;
}
if (size) {
if (f2fs_encrypted_inode(inode))
flags |= FIEMAP_EXTENT_DATA_ENCRYPTED;
ret = fiemap_fill_next_extent(fieinfo, logical,
phys, size, flags);
}
if (start_blk > last_blk || ret)
goto out;
logical = blk_to_logical(inode, start_blk);
phys = blk_to_logical(inode, map_bh.b_blocknr);
size = map_bh.b_size;
flags = 0;
if (buffer_unwritten(&map_bh))
flags = FIEMAP_EXTENT_UNWRITTEN;
start_blk += logical_to_blk(inode, size);
prep_next:
cond_resched();
if (fatal_signal_pending(current))
ret = -EINTR;
else
goto next;
out:
if (ret == 1)
ret = 0;
inode_unlock(inode);
return ret;
}
/*
* This function was originally taken from fs/mpage.c, and customized for f2fs.
* Major change was from block_size == page_size in f2fs by default.
*/
static int f2fs_mpage_readpages(struct address_space *mapping,
struct list_head *pages, struct page *page,
unsigned nr_pages)
{
struct bio *bio = NULL;
unsigned page_idx;
sector_t last_block_in_bio = 0;
struct inode *inode = mapping->host;
const unsigned blkbits = inode->i_blkbits;
const unsigned blocksize = 1 << blkbits;
sector_t block_in_file;
sector_t last_block;
sector_t last_block_in_file;
sector_t block_nr;
struct f2fs_map_blocks map;
map.m_pblk = 0;
map.m_lblk = 0;
map.m_len = 0;
map.m_flags = 0;
map.m_next_pgofs = NULL;
for (page_idx = 0; nr_pages; page_idx++, nr_pages--) {
if (pages) {
page = list_last_entry(pages, struct page, lru);
prefetchw(&page->flags);
list_del(&page->lru);
if (add_to_page_cache_lru(page, mapping,
page->index,
readahead_gfp_mask(mapping)))
goto next_page;
}
block_in_file = (sector_t)page->index;
last_block = block_in_file + nr_pages;
last_block_in_file = (i_size_read(inode) + blocksize - 1) >>
blkbits;
if (last_block > last_block_in_file)
last_block = last_block_in_file;
/*
* Map blocks using the previous result first.
*/
if ((map.m_flags & F2FS_MAP_MAPPED) &&
block_in_file > map.m_lblk &&
block_in_file < (map.m_lblk + map.m_len))
goto got_it;
/*
* Then do more f2fs_map_blocks() calls until we are
* done with this page.
*/
map.m_flags = 0;
if (block_in_file < last_block) {
map.m_lblk = block_in_file;
map.m_len = last_block - block_in_file;
if (f2fs_map_blocks(inode, &map, 0,
F2FS_GET_BLOCK_DEFAULT))
goto set_error_page;
}
got_it:
if ((map.m_flags & F2FS_MAP_MAPPED)) {
block_nr = map.m_pblk + block_in_file - map.m_lblk;
SetPageMappedToDisk(page);
if (!PageUptodate(page) && !cleancache_get_page(page)) {
SetPageUptodate(page);
goto confused;
}
} else {
zero_user_segment(page, 0, PAGE_SIZE);
if (!PageUptodate(page))
SetPageUptodate(page);
unlock_page(page);
goto next_page;
}
/*
* This page will go to BIO. Do we need to send this
* BIO off first?
*/
if (bio && (last_block_in_bio != block_nr - 1 ||
!__same_bdev(F2FS_I_SB(inode), block_nr, bio))) {
submit_and_realloc:
__submit_bio(F2FS_I_SB(inode), bio, DATA);
bio = NULL;
}
if (bio == NULL) {
bio = f2fs_grab_read_bio(inode, block_nr, nr_pages);
if (IS_ERR(bio)) {
bio = NULL;
goto set_error_page;
}
}
if (bio_add_page(bio, page, blocksize, 0) < blocksize)
goto submit_and_realloc;
last_block_in_bio = block_nr;
goto next_page;
set_error_page:
SetPageError(page);
zero_user_segment(page, 0, PAGE_SIZE);
unlock_page(page);
goto next_page;
confused:
if (bio) {
__submit_bio(F2FS_I_SB(inode), bio, DATA);
bio = NULL;
}
unlock_page(page);
next_page:
if (pages)
put_page(page);
}
BUG_ON(pages && !list_empty(pages));
if (bio)
__submit_bio(F2FS_I_SB(inode), bio, DATA);
return 0;
}
static int f2fs_read_data_page(struct file *file, struct page *page)
{
struct inode *inode = page->mapping->host;
int ret = -EAGAIN;
trace_f2fs_readpage(page, DATA);
/* If the file has inline data, try to read it directly */
if (f2fs_has_inline_data(inode))
ret = f2fs_read_inline_data(inode, page);
if (ret == -EAGAIN)
ret = f2fs_mpage_readpages(page->mapping, NULL, page, 1);
return ret;
}
static int f2fs_read_data_pages(struct file *file,
struct address_space *mapping,
struct list_head *pages, unsigned nr_pages)
{
struct inode *inode = mapping->host;
struct page *page = list_last_entry(pages, struct page, lru);
trace_f2fs_readpages(inode, page, nr_pages);
/* If the file has inline data, skip readpages */
if (f2fs_has_inline_data(inode))
return 0;
return f2fs_mpage_readpages(mapping, pages, NULL, nr_pages);
}
static int encrypt_one_page(struct f2fs_io_info *fio)
{
struct inode *inode = fio->page->mapping->host;
gfp_t gfp_flags = GFP_NOFS;
if (!f2fs_encrypted_file(inode))
return 0;
/* wait for GCed encrypted page writeback */
f2fs_wait_on_block_writeback(fio->sbi, fio->old_blkaddr);
retry_encrypt:
fio->encrypted_page = fscrypt_encrypt_page(inode, fio->page,
PAGE_SIZE, 0, fio->page->index, gfp_flags);
if (!IS_ERR(fio->encrypted_page))
return 0;
/* flush pending IOs and wait for a while in the ENOMEM case */
if (PTR_ERR(fio->encrypted_page) == -ENOMEM) {
f2fs_flush_merged_writes(fio->sbi);
congestion_wait(BLK_RW_ASYNC, HZ/50);
gfp_flags |= __GFP_NOFAIL;
goto retry_encrypt;
}
return PTR_ERR(fio->encrypted_page);
}
static inline bool need_inplace_update(struct f2fs_io_info *fio)
{
struct inode *inode = fio->page->mapping->host;
if (S_ISDIR(inode->i_mode) || f2fs_is_atomic_file(inode))
return false;
if (is_cold_data(fio->page))
return false;
if (IS_ATOMIC_WRITTEN_PAGE(fio->page))
return false;
return need_inplace_update_policy(inode, fio);
}
static inline bool valid_ipu_blkaddr(struct f2fs_io_info *fio)
{
if (fio->old_blkaddr == NEW_ADDR)
return false;
if (fio->old_blkaddr == NULL_ADDR)
return false;
return true;
}
int do_write_data_page(struct f2fs_io_info *fio)
{
struct page *page = fio->page;
struct inode *inode = page->mapping->host;
struct dnode_of_data dn;
struct extent_info ei = {0,0,0};
bool ipu_force = false;
int err = 0;
set_new_dnode(&dn, inode, NULL, NULL, 0);
if (need_inplace_update(fio) &&
f2fs_lookup_extent_cache(inode, page->index, &ei)) {
fio->old_blkaddr = ei.blk + page->index - ei.fofs;
if (valid_ipu_blkaddr(fio)) {
ipu_force = true;
fio->need_lock = LOCK_DONE;
goto got_it;
}
}
/* Deadlock due to between page->lock and f2fs_lock_op */
if (fio->need_lock == LOCK_REQ && !f2fs_trylock_op(fio->sbi))
return -EAGAIN;
err = get_dnode_of_data(&dn, page->index, LOOKUP_NODE);
if (err)
goto out;
fio->old_blkaddr = dn.data_blkaddr;
/* This page is already truncated */
if (fio->old_blkaddr == NULL_ADDR) {
ClearPageUptodate(page);
goto out_writepage;
}
got_it:
/*
* If current allocation needs SSR,
* it had better in-place writes for updated data.
*/
if (ipu_force || (valid_ipu_blkaddr(fio) && need_inplace_update(fio))) {
err = encrypt_one_page(fio);
if (err)
goto out_writepage;
set_page_writeback(page);
f2fs_put_dnode(&dn);
if (fio->need_lock == LOCK_REQ)
f2fs_unlock_op(fio->sbi);
err = rewrite_data_page(fio);
trace_f2fs_do_write_data_page(fio->page, IPU);
set_inode_flag(inode, FI_UPDATE_WRITE);
return err;
}
if (fio->need_lock == LOCK_RETRY) {
if (!f2fs_trylock_op(fio->sbi)) {
err = -EAGAIN;
goto out_writepage;
}
fio->need_lock = LOCK_REQ;
}
err = encrypt_one_page(fio);
if (err)
goto out_writepage;
set_page_writeback(page);
/* LFS mode write path */
write_data_page(&dn, fio);
trace_f2fs_do_write_data_page(page, OPU);
set_inode_flag(inode, FI_APPEND_WRITE);
if (page->index == 0)
set_inode_flag(inode, FI_FIRST_BLOCK_WRITTEN);
out_writepage:
f2fs_put_dnode(&dn);
out:
if (fio->need_lock == LOCK_REQ)
f2fs_unlock_op(fio->sbi);
return err;
}
static int __write_data_page(struct page *page, bool *submitted,
struct writeback_control *wbc,
enum iostat_type io_type)
{
struct inode *inode = page->mapping->host;
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
loff_t i_size = i_size_read(inode);
const pgoff_t end_index = ((unsigned long long) i_size)
>> PAGE_SHIFT;
loff_t psize = (page->index + 1) << PAGE_SHIFT;
unsigned offset = 0;
bool need_balance_fs = false;
int err = 0;
struct f2fs_io_info fio = {
.sbi = sbi,
.ino = inode->i_ino,
.type = DATA,
.op = REQ_OP_WRITE,
.op_flags = wbc_to_write_flags(wbc),
.old_blkaddr = NULL_ADDR,
.page = page,
.encrypted_page = NULL,
.submitted = false,
.need_lock = LOCK_RETRY,
.io_type = io_type,
};
trace_f2fs_writepage(page, DATA);
if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
goto redirty_out;
if (page->index < end_index)
goto write;
/*
* If the offset is out-of-range of file size,
* this page does not have to be written to disk.
*/
offset = i_size & (PAGE_SIZE - 1);
if ((page->index >= end_index + 1) || !offset)
goto out;
zero_user_segment(page, offset, PAGE_SIZE);
write:
if (f2fs_is_drop_cache(inode))
goto out;
/* we should not write 0'th page having journal header */
if (f2fs_is_volatile_file(inode) && (!page->index ||
(!wbc->for_reclaim &&
available_free_memory(sbi, BASE_CHECK))))
goto redirty_out;
/* we should bypass data pages to proceed the kworkder jobs */
if (unlikely(f2fs_cp_error(sbi))) {
mapping_set_error(page->mapping, -EIO);
goto out;
}
/* Dentry blocks are controlled by checkpoint */
if (S_ISDIR(inode->i_mode)) {
fio.need_lock = LOCK_DONE;
err = do_write_data_page(&fio);
goto done;
}
if (!wbc->for_reclaim)
need_balance_fs = true;
else if (has_not_enough_free_secs(sbi, 0, 0))
goto redirty_out;
else
set_inode_flag(inode, FI_HOT_DATA);
err = -EAGAIN;
if (f2fs_has_inline_data(inode)) {
err = f2fs_write_inline_data(inode, page);
if (!err)
goto out;
}
if (err == -EAGAIN) {
err = do_write_data_page(&fio);
if (err == -EAGAIN) {
fio.need_lock = LOCK_REQ;
err = do_write_data_page(&fio);
}
}
down_write(&F2FS_I(inode)->i_sem);
if (F2FS_I(inode)->last_disk_size < psize)
F2FS_I(inode)->last_disk_size = psize;
up_write(&F2FS_I(inode)->i_sem);
done:
if (err && err != -ENOENT)
goto redirty_out;
out:
inode_dec_dirty_pages(inode);
if (err)
ClearPageUptodate(page);
if (wbc->for_reclaim) {
f2fs_submit_merged_write_cond(sbi, inode, 0, page->index, DATA);
clear_inode_flag(inode, FI_HOT_DATA);
remove_dirty_inode(inode);
submitted = NULL;
}
unlock_page(page);
if (!S_ISDIR(inode->i_mode))
f2fs_balance_fs(sbi, need_balance_fs);
if (unlikely(f2fs_cp_error(sbi))) {
f2fs_submit_merged_write(sbi, DATA);
submitted = NULL;
}
if (submitted)
*submitted = fio.submitted;
return 0;
redirty_out:
redirty_page_for_writepage(wbc, page);
if (!err)
return AOP_WRITEPAGE_ACTIVATE;
unlock_page(page);
return err;
}
static int f2fs_write_data_page(struct page *page,
struct writeback_control *wbc)
{
return __write_data_page(page, NULL, wbc, FS_DATA_IO);
}
/*
* This function was copied from write_cche_pages from mm/page-writeback.c.
* The major change is making write step of cold data page separately from
* warm/hot data page.
*/
static int f2fs_write_cache_pages(struct address_space *mapping,
struct writeback_control *wbc,
enum iostat_type io_type)
{
int ret = 0;
int done = 0;
struct pagevec pvec;
int nr_pages;
pgoff_t uninitialized_var(writeback_index);
pgoff_t index;
pgoff_t end; /* Inclusive */
pgoff_t done_index;
pgoff_t last_idx = ULONG_MAX;
int cycled;
int range_whole = 0;
int tag;
pagevec_init(&pvec);
if (get_dirty_pages(mapping->host) <=
SM_I(F2FS_M_SB(mapping))->min_hot_blocks)
set_inode_flag(mapping->host, FI_HOT_DATA);
else
clear_inode_flag(mapping->host, FI_HOT_DATA);
if (wbc->range_cyclic) {
writeback_index = mapping->writeback_index; /* prev offset */
index = writeback_index;
if (index == 0)
cycled = 1;
else
cycled = 0;
end = -1;
} else {
index = wbc->range_start >> PAGE_SHIFT;
end = wbc->range_end >> PAGE_SHIFT;
if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
range_whole = 1;
cycled = 1; /* ignore range_cyclic tests */
}
if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
tag = PAGECACHE_TAG_TOWRITE;
else
tag = PAGECACHE_TAG_DIRTY;
retry:
if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
tag_pages_for_writeback(mapping, index, end);
done_index = index;
while (!done && (index <= end)) {
int i;
nr_pages = pagevec_lookup_range_tag(&pvec, mapping, &index, end,
tag);
if (nr_pages == 0)
break;
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
bool submitted = false;
done_index = page->index;
retry_write:
lock_page(page);
if (unlikely(page->mapping != mapping)) {
continue_unlock:
unlock_page(page);
continue;
}
if (!PageDirty(page)) {
/* someone wrote it for us */
goto continue_unlock;
}
if (PageWriteback(page)) {
if (wbc->sync_mode != WB_SYNC_NONE)
f2fs_wait_on_page_writeback(page,
DATA, true);
else
goto continue_unlock;
}
BUG_ON(PageWriteback(page));
if (!clear_page_dirty_for_io(page))
goto continue_unlock;
ret = __write_data_page(page, &submitted, wbc, io_type);
if (unlikely(ret)) {
/*
* keep nr_to_write, since vfs uses this to
* get # of written pages.
*/
if (ret == AOP_WRITEPAGE_ACTIVATE) {
unlock_page(page);
ret = 0;
continue;
} else if (ret == -EAGAIN) {
ret = 0;
if (wbc->sync_mode == WB_SYNC_ALL) {
cond_resched();
congestion_wait(BLK_RW_ASYNC,
HZ/50);
goto retry_write;
}
continue;
}
done_index = page->index + 1;
done = 1;
break;
} else if (submitted) {
last_idx = page->index;
}
/* give a priority to WB_SYNC threads */
if ((atomic_read(&F2FS_M_SB(mapping)->wb_sync_req) ||
--wbc->nr_to_write <= 0) &&
wbc->sync_mode == WB_SYNC_NONE) {
done = 1;
break;
}
}
pagevec_release(&pvec);
cond_resched();
}
if (!cycled && !done) {
cycled = 1;
index = 0;
end = writeback_index - 1;
goto retry;
}
if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
mapping->writeback_index = done_index;
if (last_idx != ULONG_MAX)
f2fs_submit_merged_write_cond(F2FS_M_SB(mapping), mapping->host,
0, last_idx, DATA);
return ret;
}
int __f2fs_write_data_pages(struct address_space *mapping,
struct writeback_control *wbc,
enum iostat_type io_type)
{
struct inode *inode = mapping->host;
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct blk_plug plug;
int ret;
/* deal with chardevs and other special file */
if (!mapping->a_ops->writepage)
return 0;
/* skip writing if there is no dirty page in this inode */
if (!get_dirty_pages(inode) && wbc->sync_mode == WB_SYNC_NONE)
return 0;
/* during POR, we don't need to trigger writepage at all. */
if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
goto skip_write;
if (S_ISDIR(inode->i_mode) && wbc->sync_mode == WB_SYNC_NONE &&
get_dirty_pages(inode) < nr_pages_to_skip(sbi, DATA) &&
available_free_memory(sbi, DIRTY_DENTS))
goto skip_write;
/* skip writing during file defragment */
if (is_inode_flag_set(inode, FI_DO_DEFRAG))
goto skip_write;
trace_f2fs_writepages(mapping->host, wbc, DATA);
/* to avoid spliting IOs due to mixed WB_SYNC_ALL and WB_SYNC_NONE */
if (wbc->sync_mode == WB_SYNC_ALL)
atomic_inc(&sbi->wb_sync_req);
else if (atomic_read(&sbi->wb_sync_req))
goto skip_write;
blk_start_plug(&plug);
ret = f2fs_write_cache_pages(mapping, wbc, io_type);
blk_finish_plug(&plug);
if (wbc->sync_mode == WB_SYNC_ALL)
atomic_dec(&sbi->wb_sync_req);
/*
* if some pages were truncated, we cannot guarantee its mapping->host
* to detect pending bios.
*/
remove_dirty_inode(inode);
return ret;
skip_write:
wbc->pages_skipped += get_dirty_pages(inode);
trace_f2fs_writepages(mapping->host, wbc, DATA);
return 0;
}
static int f2fs_write_data_pages(struct address_space *mapping,
struct writeback_control *wbc)
{
struct inode *inode = mapping->host;
return __f2fs_write_data_pages(mapping, wbc,
F2FS_I(inode)->cp_task == current ?
FS_CP_DATA_IO : FS_DATA_IO);
}
static void f2fs_write_failed(struct address_space *mapping, loff_t to)
{
struct inode *inode = mapping->host;
loff_t i_size = i_size_read(inode);
if (to > i_size) {
down_write(&F2FS_I(inode)->i_mmap_sem);
truncate_pagecache(inode, i_size);
truncate_blocks(inode, i_size, true);
up_write(&F2FS_I(inode)->i_mmap_sem);
}
}
static int prepare_write_begin(struct f2fs_sb_info *sbi,
struct page *page, loff_t pos, unsigned len,
block_t *blk_addr, bool *node_changed)
{
struct inode *inode = page->mapping->host;
pgoff_t index = page->index;
struct dnode_of_data dn;
struct page *ipage;
bool locked = false;
struct extent_info ei = {0,0,0};
int err = 0;
/*
* we already allocated all the blocks, so we don't need to get
* the block addresses when there is no need to fill the page.
*/
if (!f2fs_has_inline_data(inode) && len == PAGE_SIZE &&
!is_inode_flag_set(inode, FI_NO_PREALLOC))
return 0;
if (f2fs_has_inline_data(inode) ||
(pos & PAGE_MASK) >= i_size_read(inode)) {
__do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, true);
locked = true;
}
restart:
/* check inline_data */
ipage = get_node_page(sbi, inode->i_ino);
if (IS_ERR(ipage)) {
err = PTR_ERR(ipage);
goto unlock_out;
}
set_new_dnode(&dn, inode, ipage, ipage, 0);
if (f2fs_has_inline_data(inode)) {
if (pos + len <= MAX_INLINE_DATA(inode)) {
read_inline_data(page, ipage);
set_inode_flag(inode, FI_DATA_EXIST);
if (inode->i_nlink)
set_inline_node(ipage);
} else {
err = f2fs_convert_inline_page(&dn, page);
if (err)
goto out;
if (dn.data_blkaddr == NULL_ADDR)
err = f2fs_get_block(&dn, index);
}
} else if (locked) {
err = f2fs_get_block(&dn, index);
} else {
if (f2fs_lookup_extent_cache(inode, index, &ei)) {
dn.data_blkaddr = ei.blk + index - ei.fofs;
} else {
/* hole case */
err = get_dnode_of_data(&dn, index, LOOKUP_NODE);
if (err || dn.data_blkaddr == NULL_ADDR) {
f2fs_put_dnode(&dn);
__do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO,
true);
locked = true;
goto restart;
}
}
}
/* convert_inline_page can make node_changed */
*blk_addr = dn.data_blkaddr;
*node_changed = dn.node_changed;
out:
f2fs_put_dnode(&dn);
unlock_out:
if (locked)
__do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, false);
return err;
}
static int f2fs_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
struct page **pagep, void **fsdata)
{
struct inode *inode = mapping->host;
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct page *page = NULL;
pgoff_t index = ((unsigned long long) pos) >> PAGE_SHIFT;
bool need_balance = false;
block_t blkaddr = NULL_ADDR;
int err = 0;
trace_f2fs_write_begin(inode, pos, len, flags);
if (f2fs_is_atomic_file(inode) &&
!available_free_memory(sbi, INMEM_PAGES)) {
err = -ENOMEM;
goto fail;
}
/*
* We should check this at this moment to avoid deadlock on inode page
* and #0 page. The locking rule for inline_data conversion should be:
* lock_page(page #0) -> lock_page(inode_page)
*/
if (index != 0) {
err = f2fs_convert_inline_inode(inode);
if (err)
goto fail;
}
repeat:
/*
* Do not use grab_cache_page_write_begin() to avoid deadlock due to
* wait_for_stable_page. Will wait that below with our IO control.
*/
page = f2fs_pagecache_get_page(mapping, index,
FGP_LOCK | FGP_WRITE | FGP_CREAT, GFP_NOFS);
if (!page) {
err = -ENOMEM;
goto fail;
}
*pagep = page;
err = prepare_write_begin(sbi, page, pos, len,
&blkaddr, &need_balance);
if (err)
goto fail;
if (need_balance && has_not_enough_free_secs(sbi, 0, 0)) {
unlock_page(page);
f2fs_balance_fs(sbi, true);
lock_page(page);
if (page->mapping != mapping) {
/* The page got truncated from under us */
f2fs_put_page(page, 1);
goto repeat;
}
}
f2fs_wait_on_page_writeback(page, DATA, false);
/* wait for GCed encrypted page writeback */
if (f2fs_encrypted_file(inode))
f2fs_wait_on_block_writeback(sbi, blkaddr);
if (len == PAGE_SIZE || PageUptodate(page))
return 0;
if (!(pos & (PAGE_SIZE - 1)) && (pos + len) >= i_size_read(inode)) {
zero_user_segment(page, len, PAGE_SIZE);
return 0;
}
if (blkaddr == NEW_ADDR) {
zero_user_segment(page, 0, PAGE_SIZE);
SetPageUptodate(page);
} else {
err = f2fs_submit_page_read(inode, page, blkaddr);
if (err)
goto fail;
lock_page(page);
if (unlikely(page->mapping != mapping)) {
f2fs_put_page(page, 1);
goto repeat;
}
if (unlikely(!PageUptodate(page))) {
err = -EIO;
goto fail;
}
}
return 0;
fail:
f2fs_put_page(page, 1);
f2fs_write_failed(mapping, pos + len);
if (f2fs_is_atomic_file(inode))
drop_inmem_pages_all(sbi);
return err;
}
static int f2fs_write_end(struct file *file,
struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
struct page *page, void *fsdata)
{
struct inode *inode = page->mapping->host;
trace_f2fs_write_end(inode, pos, len, copied);
/*
* This should be come from len == PAGE_SIZE, and we expect copied
* should be PAGE_SIZE. Otherwise, we treat it with zero copied and
* let generic_perform_write() try to copy data again through copied=0.
*/
if (!PageUptodate(page)) {
if (unlikely(copied != len))
copied = 0;
else
SetPageUptodate(page);
}
if (!copied)
goto unlock_out;
set_page_dirty(page);
if (pos + copied > i_size_read(inode))
f2fs_i_size_write(inode, pos + copied);
unlock_out:
f2fs_put_page(page, 1);
f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
return copied;
}
static int check_direct_IO(struct inode *inode, struct iov_iter *iter,
loff_t offset)
{
unsigned blocksize_mask = inode->i_sb->s_blocksize - 1;
if (offset & blocksize_mask)
return -EINVAL;
if (iov_iter_alignment(iter) & blocksize_mask)
return -EINVAL;
return 0;
}
static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
{
struct address_space *mapping = iocb->ki_filp->f_mapping;
struct inode *inode = mapping->host;
size_t count = iov_iter_count(iter);
loff_t offset = iocb->ki_pos;
int rw = iov_iter_rw(iter);
int err;
err = check_direct_IO(inode, iter, offset);
if (err)
return err;
if (__force_buffered_io(inode, rw))
return 0;
trace_f2fs_direct_IO_enter(inode, offset, count, rw);
down_read(&F2FS_I(inode)->dio_rwsem[rw]);
err = blockdev_direct_IO(iocb, inode, iter, get_data_block_dio);
up_read(&F2FS_I(inode)->dio_rwsem[rw]);
if (rw == WRITE) {
if (err > 0) {
f2fs_update_iostat(F2FS_I_SB(inode), APP_DIRECT_IO,
err);
set_inode_flag(inode, FI_UPDATE_WRITE);
} else if (err < 0) {
f2fs_write_failed(mapping, offset + count);
}
}
trace_f2fs_direct_IO_exit(inode, offset, count, rw, err);
return err;
}
void f2fs_invalidate_page(struct page *page, unsigned int offset,
unsigned int length)
{
struct inode *inode = page->mapping->host;
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
if (inode->i_ino >= F2FS_ROOT_INO(sbi) &&
(offset % PAGE_SIZE || length != PAGE_SIZE))
return;
if (PageDirty(page)) {
if (inode->i_ino == F2FS_META_INO(sbi)) {
dec_page_count(sbi, F2FS_DIRTY_META);
} else if (inode->i_ino == F2FS_NODE_INO(sbi)) {
dec_page_count(sbi, F2FS_DIRTY_NODES);
} else {
inode_dec_dirty_pages(inode);
remove_dirty_inode(inode);
}
}
/* This is atomic written page, keep Private */
if (IS_ATOMIC_WRITTEN_PAGE(page))
return drop_inmem_page(inode, page);
set_page_private(page, 0);
ClearPagePrivate(page);
}
int f2fs_release_page(struct page *page, gfp_t wait)
{
/* If this is dirty page, keep PagePrivate */
if (PageDirty(page))
return 0;
/* This is atomic written page, keep Private */
if (IS_ATOMIC_WRITTEN_PAGE(page))
return 0;
set_page_private(page, 0);
ClearPagePrivate(page);
return 1;
}
/*
* This was copied from __set_page_dirty_buffers which gives higher performance
* in very high speed storages. (e.g., pmem)
*/
void f2fs_set_page_dirty_nobuffers(struct page *page)
{
struct address_space *mapping = page->mapping;
unsigned long flags;
if (unlikely(!mapping))
return;
spin_lock(&mapping->private_lock);
lock_page_memcg(page);
SetPageDirty(page);
spin_unlock(&mapping->private_lock);
spin_lock_irqsave(&mapping->tree_lock, flags);
WARN_ON_ONCE(!PageUptodate(page));
account_page_dirtied(page, mapping);
radix_tree_tag_set(&mapping->page_tree,
page_index(page), PAGECACHE_TAG_DIRTY);
spin_unlock_irqrestore(&mapping->tree_lock, flags);
unlock_page_memcg(page);
__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
return;
}
static int f2fs_set_data_page_dirty(struct page *page)
{
struct address_space *mapping = page->mapping;
struct inode *inode = mapping->host;
trace_f2fs_set_page_dirty(page, DATA);
if (!PageUptodate(page))
SetPageUptodate(page);
if (f2fs_is_atomic_file(inode) && !f2fs_is_commit_atomic_write(inode)) {
if (!IS_ATOMIC_WRITTEN_PAGE(page)) {
register_inmem_page(inode, page);
return 1;
}
/*
* Previously, this page has been registered, we just
* return here.
*/
return 0;
}
if (!PageDirty(page)) {
f2fs_set_page_dirty_nobuffers(page);
update_dirty_page(inode, page);
return 1;
}
return 0;
}
static sector_t f2fs_bmap(struct address_space *mapping, sector_t block)
{
struct inode *inode = mapping->host;
if (f2fs_has_inline_data(inode))
return 0;
/* make sure allocating whole blocks */
if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
filemap_write_and_wait(mapping);
return generic_block_bmap(mapping, block, get_data_block_bmap);
}
#ifdef CONFIG_MIGRATION
#include <linux/migrate.h>
int f2fs_migrate_page(struct address_space *mapping,
struct page *newpage, struct page *page, enum migrate_mode mode)
{
int rc, extra_count;
struct f2fs_inode_info *fi = F2FS_I(mapping->host);
bool atomic_written = IS_ATOMIC_WRITTEN_PAGE(page);
BUG_ON(PageWriteback(page));
/* migrating an atomic written page is safe with the inmem_lock hold */
if (atomic_written) {
if (mode != MIGRATE_SYNC)
return -EBUSY;
if (!mutex_trylock(&fi->inmem_lock))
return -EAGAIN;
}
/*
* A reference is expected if PagePrivate set when move mapping,
* however F2FS breaks this for maintaining dirty page counts when
* truncating pages. So here adjusting the 'extra_count' make it work.
*/
extra_count = (atomic_written ? 1 : 0) - page_has_private(page);
rc = migrate_page_move_mapping(mapping, newpage,
page, NULL, mode, extra_count);
if (rc != MIGRATEPAGE_SUCCESS) {
if (atomic_written)
mutex_unlock(&fi->inmem_lock);
return rc;
}
if (atomic_written) {
struct inmem_pages *cur;
list_for_each_entry(cur, &fi->inmem_pages, list)
if (cur->page == page) {
cur->page = newpage;
break;
}
mutex_unlock(&fi->inmem_lock);
put_page(page);
get_page(newpage);
}
if (PagePrivate(page))
SetPagePrivate(newpage);
set_page_private(newpage, page_private(page));
if (mode != MIGRATE_SYNC_NO_COPY)
migrate_page_copy(newpage, page);
else
migrate_page_states(newpage, page);
return MIGRATEPAGE_SUCCESS;
}
#endif
const struct address_space_operations f2fs_dblock_aops = {
.readpage = f2fs_read_data_page,
.readpages = f2fs_read_data_pages,
.writepage = f2fs_write_data_page,
.writepages = f2fs_write_data_pages,
.write_begin = f2fs_write_begin,
.write_end = f2fs_write_end,
.set_page_dirty = f2fs_set_data_page_dirty,
.invalidatepage = f2fs_invalidate_page,
.releasepage = f2fs_release_page,
.direct_IO = f2fs_direct_IO,
.bmap = f2fs_bmap,
#ifdef CONFIG_MIGRATION
.migratepage = f2fs_migrate_page,
#endif
};
Reference in New Issue View Git Blame Copy Permalink