blob: b27b7210791165d579d2d84c236fd574ff8e0e37 [file] [log] [blame]
// SPDX-License-Identifier: GPL-2.0
/*
* fs/f2fs/data.c
*
* Copyright (c) 2012 Samsung Electronics Co., Ltd.
* http://www.samsung.com/
*/
#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/swap.h>
#include <linux/prefetch.h>
#include <linux/uio.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>
#define NUM_PREALLOC_POST_READ_CTXS 128
static struct kmem_cache *bio_post_read_ctx_cache;
static struct kmem_cache *bio_entry_slab;
static mempool_t *bio_post_read_ctx_pool;
static struct bio_set f2fs_bioset;
#define F2FS_BIO_POOL_SIZE NR_CURSEG_TYPE
int __init f2fs_init_bioset(void)
{
if (bioset_init(&f2fs_bioset, F2FS_BIO_POOL_SIZE,
0, BIOSET_NEED_BVECS))
return -ENOMEM;
return 0;
}
void f2fs_destroy_bioset(void)
{
bioset_exit(&f2fs_bioset);
}
static inline struct bio *__f2fs_bio_alloc(gfp_t gfp_mask,
unsigned int nr_iovecs)
{
return bio_alloc_bioset(gfp_mask, nr_iovecs, &f2fs_bioset);
}
struct bio *f2fs_bio_alloc(struct f2fs_sb_info *sbi, int npages, bool no_fail)
{
struct bio *bio;
if (no_fail) {
/* No failure on bio allocation */
bio = __f2fs_bio_alloc(GFP_NOIO, npages);
if (!bio)
bio = __f2fs_bio_alloc(GFP_NOIO | __GFP_NOFAIL, npages);
return bio;
}
if (time_to_inject(sbi, FAULT_ALLOC_BIO)) {
f2fs_show_injection_info(sbi, FAULT_ALLOC_BIO);
return NULL;
}
return __f2fs_bio_alloc(GFP_KERNEL, npages);
}
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;
if (f2fs_is_compressed_page(page))
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) ||
(S_ISREG(inode->i_mode) &&
(f2fs_is_atomic_file(inode) || IS_NOQUOTA(inode))) ||
is_cold_data(page))
return true;
return false;
}
static enum count_type __read_io_type(struct page *page)
{
struct address_space *mapping = page_file_mapping(page);
if (mapping) {
struct inode *inode = mapping->host;
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
if (inode->i_ino == F2FS_META_INO(sbi))
return F2FS_RD_META;
if (inode->i_ino == F2FS_NODE_INO(sbi))
return F2FS_RD_NODE;
}
return F2FS_RD_DATA;
}
/* postprocessing steps for read bios */
enum bio_post_read_step {
STEP_DECRYPT,
STEP_DECOMPRESS,
STEP_VERITY,
};
struct bio_post_read_ctx {
struct bio *bio;
struct f2fs_sb_info *sbi;
struct work_struct work;
unsigned int enabled_steps;
};
static void __read_end_io(struct bio *bio, bool compr, bool verity)
{
struct page *page;
struct bio_vec *bv;
struct bvec_iter_all iter_all;
bio_for_each_segment_all(bv, bio, iter_all) {
page = bv->bv_page;
#ifdef CONFIG_F2FS_FS_COMPRESSION
if (compr && f2fs_is_compressed_page(page)) {
f2fs_decompress_pages(bio, page, verity);
continue;
}
#endif
/* PG_error was set if any post_read step failed */
if (bio->bi_status || PageError(page)) {
ClearPageUptodate(page);
/* will re-read again later */
ClearPageError(page);
} else {
SetPageUptodate(page);
}
dec_page_count(F2FS_P_SB(page), __read_io_type(page));
unlock_page(page);
}
}
static void f2fs_release_read_bio(struct bio *bio);
static void __f2fs_read_end_io(struct bio *bio, bool compr, bool verity)
{
if (!compr)
__read_end_io(bio, false, verity);
f2fs_release_read_bio(bio);
}
static void f2fs_decompress_bio(struct bio *bio, bool verity)
{
__read_end_io(bio, true, verity);
}
static void bio_post_read_processing(struct bio_post_read_ctx *ctx);
static void f2fs_decrypt_work(struct bio_post_read_ctx *ctx)
{
fscrypt_decrypt_bio(ctx->bio);
}
static void f2fs_decompress_work(struct bio_post_read_ctx *ctx)
{
f2fs_decompress_bio(ctx->bio, ctx->enabled_steps & (1 << STEP_VERITY));
}
#ifdef CONFIG_F2FS_FS_COMPRESSION
static void f2fs_verify_pages(struct page **rpages, unsigned int cluster_size)
{
f2fs_decompress_end_io(rpages, cluster_size, false, true);
}
static void f2fs_verify_bio(struct bio *bio)
{
struct page *page = bio_first_page_all(bio);
struct decompress_io_ctx *dic =
(struct decompress_io_ctx *)page_private(page);
f2fs_verify_pages(dic->rpages, dic->cluster_size);
f2fs_free_dic(dic);
}
#endif
static void f2fs_verity_work(struct work_struct *work)
{
struct bio_post_read_ctx *ctx =
container_of(work, struct bio_post_read_ctx, work);
struct bio *bio = ctx->bio;
#ifdef CONFIG_F2FS_FS_COMPRESSION
unsigned int enabled_steps = ctx->enabled_steps;
#endif
/*
* fsverity_verify_bio() may call readpages() again, and while verity
* will be disabled for this, decryption may still be needed, resulting
* in another bio_post_read_ctx being allocated. So to prevent
* deadlocks we need to release the current ctx to the mempool first.
* This assumes that verity is the last post-read step.
*/
mempool_free(ctx, bio_post_read_ctx_pool);
bio->bi_private = NULL;
#ifdef CONFIG_F2FS_FS_COMPRESSION
/* previous step is decompression */
if (enabled_steps & (1 << STEP_DECOMPRESS)) {
f2fs_verify_bio(bio);
f2fs_release_read_bio(bio);
return;
}
#endif
fsverity_verify_bio(bio);
__f2fs_read_end_io(bio, false, false);
}
static void f2fs_post_read_work(struct work_struct *work)
{
struct bio_post_read_ctx *ctx =
container_of(work, struct bio_post_read_ctx, work);
if (ctx->enabled_steps & (1 << STEP_DECRYPT))
f2fs_decrypt_work(ctx);
if (ctx->enabled_steps & (1 << STEP_DECOMPRESS))
f2fs_decompress_work(ctx);
if (ctx->enabled_steps & (1 << STEP_VERITY)) {
INIT_WORK(&ctx->work, f2fs_verity_work);
fsverity_enqueue_verify_work(&ctx->work);
return;
}
__f2fs_read_end_io(ctx->bio,
ctx->enabled_steps & (1 << STEP_DECOMPRESS), false);
}
static void f2fs_enqueue_post_read_work(struct f2fs_sb_info *sbi,
struct work_struct *work)
{
queue_work(sbi->post_read_wq, work);
}
static void bio_post_read_processing(struct bio_post_read_ctx *ctx)
{
/*
* We use different work queues for decryption and for verity because
* verity may require reading metadata pages that need decryption, and
* we shouldn't recurse to the same workqueue.
*/
if (ctx->enabled_steps & (1 << STEP_DECRYPT) ||
ctx->enabled_steps & (1 << STEP_DECOMPRESS)) {
INIT_WORK(&ctx->work, f2fs_post_read_work);
f2fs_enqueue_post_read_work(ctx->sbi, &ctx->work);
return;
}
if (ctx->enabled_steps & (1 << STEP_VERITY)) {
INIT_WORK(&ctx->work, f2fs_verity_work);
fsverity_enqueue_verify_work(&ctx->work);
return;
}
__f2fs_read_end_io(ctx->bio, false, false);
}
static bool f2fs_bio_post_read_required(struct bio *bio)
{
return bio->bi_private;
}
static void f2fs_read_end_io(struct bio *bio)
{
struct f2fs_sb_info *sbi = F2FS_P_SB(bio_first_page_all(bio));
if (time_to_inject(sbi, FAULT_READ_IO)) {
f2fs_show_injection_info(sbi, FAULT_READ_IO);
bio->bi_status = BLK_STS_IOERR;
}
if (f2fs_bio_post_read_required(bio)) {
struct bio_post_read_ctx *ctx = bio->bi_private;
bio_post_read_processing(ctx);
return;
}
__f2fs_read_end_io(bio, false, false);
}
static void f2fs_write_end_io(struct bio *bio)
{
struct f2fs_sb_info *sbi = bio->bi_private;
struct bio_vec *bvec;
struct bvec_iter_all iter_all;
if (time_to_inject(sbi, FAULT_WRITE_IO)) {
f2fs_show_injection_info(sbi, FAULT_WRITE_IO);
bio->bi_status = BLK_STS_IOERR;
}
bio_for_each_segment_all(bvec, bio, iter_all) {
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_finalize_bounce_page(&page);
#ifdef CONFIG_F2FS_FS_COMPRESSION
if (f2fs_is_compressed_page(page)) {
f2fs_compress_write_end_io(bio, page);
continue;
}
#endif
if (unlikely(bio->bi_status)) {
mapping_set_error(page->mapping, -EIO);
if (type == F2FS_WB_CP_DATA)
f2fs_stop_checkpoint(sbi, true);
}
f2fs_bug_on(sbi, page->mapping == NODE_MAPPING(sbi) &&
page->index != nid_of_node(page));
dec_page_count(sbi, type);
if (f2fs_in_warm_node_list(sbi, page))
f2fs_del_fsync_node_entry(sbi, page);
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;
if (f2fs_is_multi_device(sbi)) {
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;
if (!f2fs_is_multi_device(sbi))
return 0;
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_io_info *fio, int npages)
{
struct f2fs_sb_info *sbi = fio->sbi;
struct bio *bio;
bio = f2fs_bio_alloc(sbi, npages, true);
f2fs_target_device(sbi, fio->new_blkaddr, bio);
if (is_read_io(fio->op)) {
bio->bi_end_io = f2fs_read_end_io;
bio->bi_private = NULL;
} else {
bio->bi_end_io = f2fs_write_end_io;
bio->bi_private = sbi;
bio->bi_write_hint = f2fs_io_type_to_rw_hint(sbi,
fio->type, fio->temp);
}
if (fio->io_wbc)
wbc_init_bio(fio->io_wbc, bio);
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 (type != DATA && type != NODE)
goto submit_io;
if (test_opt(sbi, LFS) && current->plug)
blk_finish_plug(current->plug);
if (F2FS_IO_ALIGNED(sbi))
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_NOFAIL);
f2fs_bug_on(sbi, !page);
zero_user_segment(page, 0, PAGE_SIZE);
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);
}
void f2fs_submit_bio(struct f2fs_sb_info *sbi,
struct bio *bio, enum page_type type)
{
__submit_bio(sbi, bio, type);
}
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 bio *bio, struct inode *inode,
struct page *page, nid_t ino)
{
struct bio_vec *bvec;
struct bvec_iter_all iter_all;
if (!bio)
return false;
if (!inode && !page && !ino)
return true;
bio_for_each_segment_all(bvec, bio, iter_all) {
struct page *target = bvec->bv_page;
if (fscrypt_is_bounce_page(target)) {
target = fscrypt_pagecache_page(target);
if (IS_ERR(target))
continue;
}
if (f2fs_is_compressed_page(target)) {
target = f2fs_compress_control_page(target);
if (IS_ERR(target))
continue;
}
if (inode && inode == target->mapping->host)
return true;
if (page && page == target)
return true;
if (ino && ino == ino_of_node(target))
return true;
}
return false;
}
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, struct page *page,
nid_t ino, enum page_type type, bool force)
{
enum temp_type temp;
bool ret = true;
for (temp = HOT; temp < NR_TEMP_TYPE; temp++) {
if (!force) {
enum page_type btype = PAGE_TYPE_OF_BIO(type);
struct f2fs_bio_info *io = sbi->write_io[btype] + temp;
down_read(&io->io_rwsem);
ret = __has_merged_page(io->bio, inode, page, ino);
up_read(&io->io_rwsem);
}
if (ret)
__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, NULL, 0, type, true);
}
void f2fs_submit_merged_write_cond(struct f2fs_sb_info *sbi,
struct inode *inode, struct page *page,
nid_t ino, enum page_type type)
{
__submit_merged_write_cond(sbi, inode, page, ino, 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;
if (!f2fs_is_valid_blkaddr(fio->sbi, fio->new_blkaddr,
fio->is_por ? META_POR : (__is_meta_io(fio) ?
META_GENERIC : DATA_GENERIC_ENHANCE)))
return -EFSCORRUPTED;
trace_f2fs_submit_page_bio(page, fio);
f2fs_trace_ios(fio, 0);
/* Allocate a new bio */
bio = __bio_alloc(fio, 1);
if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) {
bio_put(bio);
return -EFAULT;
}
if (fio->io_wbc && !is_read_io(fio->op))
wbc_account_cgroup_owner(fio->io_wbc, page, PAGE_SIZE);
bio_set_op_attrs(bio, fio->op, fio->op_flags);
inc_page_count(fio->sbi, is_read_io(fio->op) ?
__read_io_type(page): WB_DATA_TYPE(fio->page));
__submit_bio(fio->sbi, bio, fio->type);
return 0;
}
static bool page_is_mergeable(struct f2fs_sb_info *sbi, struct bio *bio,
block_t last_blkaddr, block_t cur_blkaddr)
{
if (last_blkaddr + 1 != cur_blkaddr)
return false;
return __same_bdev(sbi, cur_blkaddr, bio);
}
static bool io_type_is_mergeable(struct f2fs_bio_info *io,
struct f2fs_io_info *fio)
{
if (io->fio.op != fio->op)
return false;
return io->fio.op_flags == fio->op_flags;
}
static bool io_is_mergeable(struct f2fs_sb_info *sbi, struct bio *bio,
struct f2fs_bio_info *io,
struct f2fs_io_info *fio,
block_t last_blkaddr,
block_t cur_blkaddr)
{
if (F2FS_IO_ALIGNED(sbi) && (fio->type == DATA || fio->type == NODE)) {
unsigned int filled_blocks =
F2FS_BYTES_TO_BLK(bio->bi_iter.bi_size);
unsigned int io_size = F2FS_IO_SIZE(sbi);
unsigned int left_vecs = bio->bi_max_vecs - bio->bi_vcnt;
/* IOs in bio is aligned and left space of vectors is not enough */
if (!(filled_blocks % io_size) && left_vecs < io_size)
return false;
}
if (!page_is_mergeable(sbi, bio, last_blkaddr, cur_blkaddr))
return false;
return io_type_is_mergeable(io, fio);
}
static void add_bio_entry(struct f2fs_sb_info *sbi, struct bio *bio,
struct page *page, enum temp_type temp)
{
struct f2fs_bio_info *io = sbi->write_io[DATA] + temp;
struct bio_entry *be;
be = f2fs_kmem_cache_alloc(bio_entry_slab, GFP_NOFS);
be->bio = bio;
bio_get(bio);
if (bio_add_page(bio, page, PAGE_SIZE, 0) != PAGE_SIZE)
f2fs_bug_on(sbi, 1);
down_write(&io->bio_list_lock);
list_add_tail(&be->list, &io->bio_list);
up_write(&io->bio_list_lock);
}
static void del_bio_entry(struct bio_entry *be)
{
list_del(&be->list);
kmem_cache_free(bio_entry_slab, be);
}
static int add_ipu_page(struct f2fs_sb_info *sbi, struct bio **bio,
struct page *page)
{
enum temp_type temp;
bool found = false;
int ret = -EAGAIN;
for (temp = HOT; temp < NR_TEMP_TYPE && !found; temp++) {
struct f2fs_bio_info *io = sbi->write_io[DATA] + temp;
struct list_head *head = &io->bio_list;
struct bio_entry *be;
down_write(&io->bio_list_lock);
list_for_each_entry(be, head, list) {
if (be->bio != *bio)
continue;
found = true;
if (bio_add_page(*bio, page, PAGE_SIZE, 0) ==
PAGE_SIZE) {
ret = 0;
break;
}
/* bio is full */
del_bio_entry(be);
__submit_bio(sbi, *bio, DATA);
break;
}
up_write(&io->bio_list_lock);
}
if (ret) {
bio_put(*bio);
*bio = NULL;
}
return ret;
}
void f2fs_submit_merged_ipu_write(struct f2fs_sb_info *sbi,
struct bio **bio, struct page *page)
{
enum temp_type temp;
bool found = false;
struct bio *target = bio ? *bio : NULL;
for (temp = HOT; temp < NR_TEMP_TYPE && !found; temp++) {
struct f2fs_bio_info *io = sbi->write_io[DATA] + temp;
struct list_head *head = &io->bio_list;
struct bio_entry *be;
if (list_empty(head))
continue;
down_read(&io->bio_list_lock);
list_for_each_entry(be, head, list) {
if (target)
found = (target == be->bio);
else
found = __has_merged_page(be->bio, NULL,
page, 0);
if (found)
break;
}
up_read(&io->bio_list_lock);
if (!found)
continue;
found = false;
down_write(&io->bio_list_lock);
list_for_each_entry(be, head, list) {
if (target)
found = (target == be->bio);
else
found = __has_merged_page(be->bio, NULL,
page, 0);
if (found) {
target = be->bio;
del_bio_entry(be);
break;
}
}
up_write(&io->bio_list_lock);
}
if (found)
__submit_bio(sbi, target, DATA);
if (bio && *bio) {
bio_put(*bio);
*bio = NULL;
}
}
int f2fs_merge_page_bio(struct f2fs_io_info *fio)
{
struct bio *bio = *fio->bio;
struct page *page = fio->encrypted_page ?
fio->encrypted_page : fio->page;
if (!f2fs_is_valid_blkaddr(fio->sbi, fio->new_blkaddr,
__is_meta_io(fio) ? META_GENERIC : DATA_GENERIC))
return -EFSCORRUPTED;
trace_f2fs_submit_page_bio(page, fio);
f2fs_trace_ios(fio, 0);
if (bio && !page_is_mergeable(fio->sbi, bio, *fio->last_block,
fio->new_blkaddr))
f2fs_submit_merged_ipu_write(fio->sbi, &bio, NULL);
alloc_new:
if (!bio) {
bio = __bio_alloc(fio, BIO_MAX_PAGES);
bio_set_op_attrs(bio, fio->op, fio->op_flags);
add_bio_entry(fio->sbi, bio, page, fio->temp);
} else {
if (add_ipu_page(fio->sbi, &bio, page))
goto alloc_new;
}
if (fio->io_wbc)
wbc_account_cgroup_owner(fio->io_wbc, page, PAGE_SIZE);
inc_page_count(fio->sbi, WB_DATA_TYPE(page));
*fio->last_block = fio->new_blkaddr;
*fio->bio = bio;
return 0;
}
void 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;
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;
}
fio = list_first_entry(&io->io_list,
struct f2fs_io_info, list);
list_del(&fio->list);
spin_unlock(&io->io_lock);
}
verify_fio_blkaddr(fio);
if (fio->encrypted_page)
bio_page = fio->encrypted_page;
else if (fio->compressed_page)
bio_page = fio->compressed_page;
else
bio_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_is_mergeable(sbi, io->bio, io, fio,
io->last_block_in_bio, fio->new_blkaddr))
__submit_merged_bio(io);
alloc_new:
if (io->bio == NULL) {
if (F2FS_IO_ALIGNED(sbi) &&
(fio->type == DATA || fio->type == NODE) &&
fio->new_blkaddr & F2FS_IO_SIZE_MASK(sbi)) {
dec_page_count(sbi, WB_DATA_TYPE(bio_page));
fio->retry = true;
goto skip;
}
io->bio = __bio_alloc(fio, BIO_MAX_PAGES);
io->fio = *fio;
}
if (bio_add_page(io->bio, bio_page, PAGE_SIZE, 0) < PAGE_SIZE) {
__submit_merged_bio(io);
goto alloc_new;
}
if (fio->io_wbc)
wbc_account_cgroup_owner(fio->io_wbc, bio_page, PAGE_SIZE);
io->last_block_in_bio = fio->new_blkaddr;
f2fs_trace_ios(fio, 0);
trace_f2fs_submit_page_write(fio->page, fio);
skip:
if (fio->in_list)
goto next;
out:
if (is_sbi_flag_set(sbi, SBI_IS_SHUTDOWN) ||
!f2fs_is_checkpoint_ready(sbi))
__submit_merged_bio(io);
up_write(&io->io_rwsem);
}
static inline bool f2fs_need_verity(const struct inode *inode, pgoff_t idx)
{
return fsverity_active(inode) &&
idx < DIV_ROUND_UP(inode->i_size, PAGE_SIZE);
}
static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr,
unsigned nr_pages, unsigned op_flag,
pgoff_t first_idx)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct bio *bio;
struct bio_post_read_ctx *ctx;
unsigned int post_read_steps = 0;
bio = f2fs_bio_alloc(sbi, min_t(int, nr_pages, BIO_MAX_PAGES), false);
if (!bio)
return ERR_PTR(-ENOMEM);
f2fs_target_device(sbi, blkaddr, bio);
bio->bi_end_io = f2fs_read_end_io;
bio_set_op_attrs(bio, REQ_OP_READ, op_flag);
if (f2fs_encrypted_file(inode))
post_read_steps |= 1 << STEP_DECRYPT;
if (f2fs_compressed_file(inode))
post_read_steps |= 1 << STEP_DECOMPRESS;
if (f2fs_need_verity(inode, first_idx))
post_read_steps |= 1 << STEP_VERITY;
if (post_read_steps) {
/* Due to the mempool, this never fails. */
ctx = mempool_alloc(bio_post_read_ctx_pool, GFP_NOFS);
ctx->bio = bio;
ctx->sbi = sbi;
ctx->enabled_steps = post_read_steps;
bio->bi_private = ctx;
}
return bio;
}
static void f2fs_release_read_bio(struct bio *bio)
{
if (bio->bi_private)
mempool_free(bio->bi_private, bio_post_read_ctx_pool);
bio_put(bio);
}
/* This can handle encryption stuffs */
static int f2fs_submit_page_read(struct inode *inode, struct page *page,
block_t blkaddr)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct bio *bio;
bio = f2fs_grab_read_bio(inode, blkaddr, 1, 0, page->index);
if (IS_ERR(bio))
return PTR_ERR(bio);
/* wait for GCed page writeback via META_MAPPING */
f2fs_wait_on_block_writeback(inode, blkaddr);
if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) {
bio_put(bio);
return -EFAULT;
}
ClearPageError(page);
inc_page_count(sbi, F2FS_RD_DATA);
__submit_bio(sbi, 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 f2fs_set_data_blkaddr(struct dnode_of_data *dn)
{
f2fs_wait_on_page_writeback(dn->node_page, NODE, true, 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;
f2fs_set_data_blkaddr(dn);
f2fs_update_extent_cache(dn);
}
/* dn->ofs_in_node will be returned with up-to-date last block pointer */
int f2fs_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, 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 f2fs_reserve_new_block(struct dnode_of_data *dn)
{
unsigned int ofs_in_node = dn->ofs_in_node;
int ret;
ret = f2fs_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 = f2fs_get_dnode_of_data(dn, index, ALLOC_NODE);
if (err)
return err;
if (dn->data_blkaddr == NULL_ADDR)
err = f2fs_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 *f2fs_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;
if (!f2fs_is_valid_blkaddr(F2FS_I_SB(inode), dn.data_blkaddr,
DATA_GENERIC_ENHANCE_READ)) {
err = -EFSCORRUPTED;
goto put_err;
}
goto got_it;
}
set_new_dnode(&dn, inode, NULL, NULL, 0);
err = f2fs_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;
}
if (dn.data_blkaddr != NEW_ADDR &&
!f2fs_is_valid_blkaddr(F2FS_I_SB(inode),
dn.data_blkaddr,
DATA_GENERIC_ENHANCE)) {
err = -EFSCORRUPTED;
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 -> f2fs_get_new_data_page ->
* f2fs_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 *f2fs_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 = f2fs_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 *f2fs_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 = f2fs_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 *f2fs_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 = f2fs_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, int seg_type)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
struct f2fs_summary sum;
struct node_info ni;
block_t old_blkaddr;
blkcnt_t count = 1;
int err;
if (unlikely(is_inode_flag_set(dn->inode, FI_NO_ALLOC)))
return -EPERM;
err = f2fs_get_node_info(sbi, dn->nid, &ni);
if (err)
return err;
dn->data_blkaddr = datablock_addr(dn->inode,
dn->node_page, dn->ofs_in_node);
if (dn->data_blkaddr != NULL_ADDR)
goto alloc;
if (unlikely((err = inc_valid_block_count(sbi, dn->inode, &count))))
return err;
alloc:
set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version);
old_blkaddr = dn->data_blkaddr;
f2fs_allocate_data_block(sbi, NULL, old_blkaddr, &dn->data_blkaddr,
&sum, seg_type, NULL, false);
if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO)
invalidate_mapping_pages(META_MAPPING(sbi),
old_blkaddr, old_blkaddr);
f2fs_update_data_blkaddr(dn, dn->data_blkaddr);
/*
* i_size will be updated by direct_IO. Otherwise, we'll get stale
* data from unwritten block via dio_read.
*/
return 0;
}
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 flag;
int err = 0;
bool direct_io = iocb->ki_flags & IOCB_DIRECT;
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;
map.m_next_extent = NULL;
map.m_seg_type = NO_CHECK_TYPE;
map.m_may_create = true;
if (direct_io) {
map.m_seg_type = f2fs_rw_hint_to_seg_type(iocb->ki_hint);
flag = f2fs_force_buffered_io(inode, iocb, from) ?
F2FS_GET_BLOCK_PRE_AIO :
F2FS_GET_BLOCK_PRE_DIO;
goto map_blocks;
}
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 err;
flag = F2FS_GET_BLOCK_PRE_AIO;
map_blocks:
err = f2fs_map_blocks(inode, &map, 1, flag);
if (map.m_len > 0 && err == -ENOSPC) {
if (!direct_io)
set_inode_flag(inode, FI_NO_PREALLOC);
err = 0;
}
return err;
}
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 = map->m_may_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;
unsigned int start_pgofs;
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)) {
if (test_opt(sbi, LFS) && flag == F2FS_GET_BLOCK_DIO &&
map->m_may_create)
goto next_dnode;
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;
if (map->m_next_extent)
*map->m_next_extent = pgofs + map->m_len;
/* for hardware encryption, but to avoid potential issue in future */
if (flag == F2FS_GET_BLOCK_DIO)
f2fs_wait_on_block_writeback_range(inode,
map->m_pblk, map->m_len);
goto out;
}
next_dnode:
if (map->m_may_create)
__do_map_lock(sbi, flag, true);
/* When reading holes, we need its node page */
set_new_dnode(&dn, inode, NULL, NULL, 0);
err = f2fs_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 =
f2fs_get_next_page_offset(&dn, pgofs);
if (map->m_next_extent)
*map->m_next_extent =
f2fs_get_next_page_offset(&dn, pgofs);
}
goto unlock_out;
}
start_pgofs = pgofs;
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 (__is_valid_data_blkaddr(blkaddr) &&
!f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC_ENHANCE)) {
err = -EFSCORRUPTED;
goto sync_out;
}
if (__is_valid_data_blkaddr(blkaddr)) {
/* use out-place-update for driect IO under LFS mode */
if (test_opt(sbi, LFS) && flag == F2FS_GET_BLOCK_DIO &&
map->m_may_create) {
err = __allocate_data_block(&dn, map->m_seg_type);
if (err)
goto sync_out;
blkaddr = dn.data_blkaddr;
set_inode_flag(inode, FI_APPEND_WRITE);
}
} else {
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 {
WARN_ON(flag != F2FS_GET_BLOCK_PRE_DIO &&
flag != F2FS_GET_BLOCK_DIO);
err = __allocate_data_block(&dn,
map->m_seg_type);
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_PRECACHE)
goto sync_out;
if (flag == F2FS_GET_BLOCK_FIEMAP &&
blkaddr == NULL_ADDR) {
if (map->m_next_pgofs)
*map->m_next_pgofs = pgofs + 1;
goto sync_out;
}
if (flag != F2FS_GET_BLOCK_FIEMAP) {
/* for defragment case */
if (map->m_next_pgofs)
*map->m_next_pgofs = pgofs + 1;
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 = f2fs_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;
if (flag == F2FS_GET_BLOCK_PRECACHE) {
if (map->m_flags & F2FS_MAP_MAPPED) {
unsigned int ofs = start_pgofs - map->m_lblk;
f2fs_update_extent_cache_range(&dn,
start_pgofs, map->m_pblk + ofs,
map->m_len - ofs);
}
}
f2fs_put_dnode(&dn);
if (map->m_may_create) {
__do_map_lock(sbi, flag, false);
f2fs_balance_fs(sbi, dn.node_changed);
}
goto next_dnode;
sync_out:
/* for hardware encryption, but to avoid potential issue in future */
if (flag == F2FS_GET_BLOCK_DIO && map->m_flags & F2FS_MAP_MAPPED)
f2fs_wait_on_block_writeback_range(inode,
map->m_pblk, map->m_len);
if (flag == F2FS_GET_BLOCK_PRECACHE) {
if (map->m_flags & F2FS_MAP_MAPPED) {
unsigned int ofs = start_pgofs - map->m_lblk;
f2fs_update_extent_cache_range(&dn,
start_pgofs, map->m_pblk + ofs,
map->m_len - ofs);
}
if (map->m_next_extent)
*map->m_next_extent = pgofs + 1;
}
f2fs_put_dnode(&dn);
unlock_out:
if (map->m_may_create) {
__do_map_lock(sbi, flag, false);
f2fs_balance_fs(sbi, dn.node_changed);
}
out:
trace_f2fs_map_blocks(inode, map, err);
return err;
}
bool f2fs_overwrite_io(struct inode *inode, loff_t pos, size_t len)
{
struct f2fs_map_blocks map;
block_t last_lblk;
int err;
if (pos + len > i_size_read(inode))
return false;
map.m_lblk = F2FS_BYTES_TO_BLK(pos);
map.m_next_pgofs = NULL;
map.m_next_extent = NULL;
map.m_seg_type = NO_CHECK_TYPE;
map.m_may_create = false;
last_lblk = F2FS_BLK_ALIGN(pos + len);
while (map.m_lblk < last_lblk) {
map.m_len = last_lblk - map.m_lblk;
err = f2fs_map_blocks(inode, &map, 0, F2FS_GET_BLOCK_DEFAULT);
if (err || map.m_len == 0)
return false;
map.m_lblk += map.m_len;
}
return true;
}
static int __get_data_block(struct inode *inode, sector_t iblock,
struct buffer_head *bh, int create, int flag,
pgoff_t *next_pgofs, int seg_type, bool may_write)
{
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;
map.m_next_extent = NULL;
map.m_seg_type = seg_type;
map.m_may_create = may_write;
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,
NO_CHECK_TYPE, create);
}
static int get_data_block_dio_write(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_DIO, NULL,
f2fs_rw_hint_to_seg_type(inode->i_write_hint),
IS_SWAPFILE(inode) ? false : true);
}
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_DIO, NULL,
f2fs_rw_hint_to_seg_type(inode->i_write_hint),
false);
}
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,
NO_CHECK_TYPE, create);
}
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);
}
static int f2fs_xattr_fiemap(struct inode *inode,
struct fiemap_extent_info *fieinfo)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct page *page;
struct node_info ni;
__u64 phys = 0, len;
__u32 flags;
nid_t xnid = F2FS_I(inode)->i_xattr_nid;
int err = 0;
if (f2fs_has_inline_xattr(inode)) {
int offset;
page = f2fs_grab_cache_page(NODE_MAPPING(sbi),
inode->i_ino, false);
if (!page)
return -ENOMEM;
err = f2fs_get_node_info(sbi, inode->i_ino, &ni);
if (err) {
f2fs_put_page(page, 1);
return err;
}
phys = (__u64)blk_to_logical(inode, ni.blk_addr);
offset = offsetof(struct f2fs_inode, i_addr) +
sizeof(__le32) * (DEF_ADDRS_PER_INODE -
get_inline_xattr_addrs(inode));
phys += offset;
len = inline_xattr_size(inode);
f2fs_put_page(page, 1);
flags = FIEMAP_EXTENT_DATA_INLINE | FIEMAP_EXTENT_NOT_ALIGNED;
if (!xnid)
flags |= FIEMAP_EXTENT_LAST;
err = fiemap_fill_next_extent(fieinfo, 0, phys, len, flags);
if (err || err == 1)
return err;
}
if (xnid) {
page = f2fs_grab_cache_page(NODE_MAPPING(sbi), xnid, false);
if (!page)
return -ENOMEM;
err = f2fs_get_node_info(sbi, xnid, &ni);
if (err) {
f2fs_put_page(page, 1);
return err;
}
phys = (__u64)blk_to_logical(inode, ni.blk_addr);
len = inode->i_sb->s_blocksize;
f2fs_put_page(page, 1);
flags = FIEMAP_EXTENT_LAST;
}
if (phys)
err = fiemap_fill_next_extent(fieinfo, 0, phys, len, flags);
return (err < 0 ? err : 0);
}
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;
if (fieinfo->fi_flags & FIEMAP_FLAG_CACHE) {
ret = f2fs_precache_extents(inode);
if (ret)
return ret;
}
ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC | FIEMAP_FLAG_XATTR);
if (ret)
return ret;
inode_lock(inode);
if (fieinfo->fi_flags & FIEMAP_FLAG_XATTR) {
ret = f2fs_xattr_fiemap(inode, fieinfo);
goto out;
}
if (f2fs_has_inline_data(inode) || f2fs_has_inline_dentry(inode)) {
ret = f2fs_inline_data_fiemap(inode, fieinfo, start, len);
if (ret != -EAGAIN)
goto out;
}
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 (IS_ENCRYPTED(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;
}
static inline loff_t f2fs_readpage_limit(struct inode *inode)
{
if (IS_ENABLED(CONFIG_FS_VERITY) &&
(IS_VERITY(inode) || f2fs_verity_in_progress(inode)))
return inode->i_sb->s_maxbytes;
return i_size_read(inode);
}
static int f2fs_read_single_page(struct inode *inode, struct page *page,
unsigned nr_pages,
struct f2fs_map_blocks *map,
struct bio **bio_ret,
sector_t *last_block_in_bio,
bool is_readahead)
{
struct bio *bio = *bio_ret;
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;
int ret = 0;
block_in_file = (sector_t)page_index(page);
last_block = block_in_file + nr_pages;
last_block_in_file = (f2fs_readpage_limit(inode) + blocksize - 1) >>
blkbits;
if (last_block > last_block_in_file)
last_block = last_block_in_file;
/* just zeroing out page which is beyond EOF */
if (block_in_file >= last_block)
goto zero_out;
/*
* 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_lblk = block_in_file;
map->m_len = last_block - block_in_file;
ret = f2fs_map_blocks(inode, map, 0, F2FS_GET_BLOCK_DEFAULT);
if (ret)
goto out;
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) && (!PageSwapCache(page) &&
!cleancache_get_page(page))) {
SetPageUptodate(page);
goto confused;
}
if (!f2fs_is_valid_blkaddr(F2FS_I_SB(inode), block_nr,
DATA_GENERIC_ENHANCE_READ)) {
ret = -EFSCORRUPTED;
goto out;
}
} else {
zero_out:
zero_user_segment(page, 0, PAGE_SIZE);
if (f2fs_need_verity(inode, page->index) &&
!fsverity_verify_page(page)) {
ret = -EIO;
goto out;
}
if (!PageUptodate(page))
SetPageUptodate(page);
unlock_page(page);
goto out;
}
/*
* This page will go to BIO. Do we need to send this
* BIO off first?
*/
if (bio && !page_is_mergeable(F2FS_I_SB(inode), bio,
*last_block_in_bio, block_nr)) {
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,
is_readahead ? REQ_RAHEAD : 0, page->index);
if (IS_ERR(bio)) {
ret = PTR_ERR(bio);
bio = NULL;
goto out;
}
}
/*
* If the page is under writeback, we need to wait for
* its completion to see the correct decrypted data.
*/
f2fs_wait_on_block_writeback(inode, block_nr);
if (bio_add_page(bio, page, blocksize, 0) < blocksize)
goto submit_and_realloc;
inc_page_count(F2FS_I_SB(inode), F2FS_RD_DATA);
ClearPageError(page);
*last_block_in_bio = block_nr;
goto out;
confused:
if (bio) {
__submit_bio(F2FS_I_SB(inode), bio, DATA);
bio = NULL;
}
unlock_page(page);
out:
*bio_ret = bio;
return ret;
}
#ifdef CONFIG_F2FS_FS_COMPRESSION
int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret,
unsigned nr_pages, sector_t *last_block_in_bio,
bool is_readahead)
{
struct dnode_of_data dn;
struct inode *inode = cc->inode;
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct bio *bio = *bio_ret;
unsigned int start_idx = cc->cluster_idx << cc->log_cluster_size;
sector_t last_block_in_file;
const unsigned blkbits = inode->i_blkbits;
const unsigned blocksize = 1 << blkbits;
struct decompress_io_ctx *dic = NULL;
int i;
int ret = 0;
f2fs_bug_on(sbi, f2fs_cluster_is_empty(cc));
last_block_in_file = (i_size_read(inode) + blocksize - 1) >> blkbits;
/* get rid of pages beyond EOF */
for (i = 0; i < cc->cluster_size; i++) {
struct page *page = cc->rpages[i];
if (!page)
continue;
if ((sector_t)page->index >= last_block_in_file) {
zero_user_segment(page, 0, PAGE_SIZE);
if (!PageUptodate(page))
SetPageUptodate(page);
} else if (!PageUptodate(page)) {
continue;
}
unlock_page(page);
cc->rpages[i] = NULL;
cc->nr_rpages--;
}
/* we are done since all pages are beyond EOF */
if (f2fs_cluster_is_empty(cc))
goto out;
set_new_dnode(&dn, inode, NULL, NULL, 0);
ret = f2fs_get_dnode_of_data(&dn, start_idx, LOOKUP_NODE);
if (ret)
goto out;
/* cluster was overwritten as normal cluster */
if (dn.data_blkaddr != COMPRESS_ADDR)
goto out;
for (i = 1; i < cc->cluster_size; i++) {
block_t blkaddr;
blkaddr = datablock_addr(dn.inode, dn.node_page,
dn.ofs_in_node + i);
if (!__is_valid_data_blkaddr(blkaddr))
break;
if (!f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC)) {
ret = -EFAULT;
goto out_put_dnode;
}
cc->nr_cpages++;
}
/* nothing to decompress */
if (cc->nr_cpages == 0) {
ret = 0;
goto out_put_dnode;
}
dic = f2fs_alloc_dic(cc);
if (IS_ERR(dic)) {
ret = PTR_ERR(dic);
goto out_put_dnode;
}
for (i = 0; i < dic->nr_cpages; i++) {
struct page *page = dic->cpages[i];
block_t blkaddr;
blkaddr = datablock_addr(dn.inode, dn.node_page,
dn.ofs_in_node + i + 1);
if (bio && !page_is_mergeable(sbi, bio,
*last_block_in_bio, blkaddr)) {
submit_and_realloc:
__submit_bio(sbi, bio, DATA);
bio = NULL;
}
if (!bio) {
bio = f2fs_grab_read_bio(inode, blkaddr, nr_pages,
is_readahead ? REQ_RAHEAD : 0,
page->index);
if (IS_ERR(bio)) {
ret = PTR_ERR(bio);
bio = NULL;
dic->failed = true;
if (refcount_sub_and_test(dic->nr_cpages - i,
&dic->ref))
f2fs_decompress_end_io(dic->rpages,
cc->cluster_size, true,
false);
f2fs_free_dic(dic);
f2fs_put_dnode(&dn);
*bio_ret = bio;
return ret;
}
}
f2fs_wait_on_block_writeback(inode, blkaddr);
if (bio_add_page(bio, page, blocksize, 0) < blocksize)
goto submit_and_realloc;
inc_page_count(sbi, F2FS_RD_DATA);
ClearPageError(page);
*last_block_in_bio = blkaddr;
}
f2fs_put_dnode(&dn);
*bio_ret = bio;
return 0;
out_put_dnode:
f2fs_put_dnode(&dn);
out:
f2fs_decompress_end_io(cc->rpages, cc->cluster_size, true, false);
*bio_ret = bio;
return ret;
}
#endif
/*
* 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.
*
* Note that the aops->readpages() function is ONLY used for read-ahead. If
* this function ever deviates from doing just read-ahead, it should either
* use ->readpage() or do the necessary surgery to decouple ->readpages()
* from read-ahead.
*/
int f2fs_mpage_readpages(struct address_space *mapping,
struct list_head *pages, struct page *page,
unsigned nr_pages, bool is_readahead)
{
struct bio *bio = NULL;
sector_t last_block_in_bio = 0;
struct inode *inode = mapping->host;
struct f2fs_map_blocks map;
#ifdef CONFIG_F2FS_FS_COMPRESSION
struct compress_ctx cc = {
.inode = inode,
.log_cluster_size = F2FS_I(inode)->i_log_cluster_size,
.cluster_size = F2FS_I(inode)->i_cluster_size,
.cluster_idx = NULL_CLUSTER,
.rpages = NULL,
.cpages = NULL,
.nr_rpages = 0,
.nr_cpages = 0,
};
#endif
unsigned max_nr_pages = nr_pages;
int ret = 0;
map.m_pblk = 0;
map.m_lblk = 0;
map.m_len = 0;
map.m_flags = 0;
map.m_next_pgofs = NULL;
map.m_next_extent = NULL;
map.m_seg_type = NO_CHECK_TYPE;
map.m_may_create = false;
for (; nr_pages; 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(page),
readahead_gfp_mask(mapping)))
goto next_page;
}
#ifdef CONFIG_F2FS_FS_COMPRESSION
if (f2fs_compressed_file(inode)) {
/* there are remained comressed pages, submit them */
if (!f2fs_cluster_can_merge_page(&cc, page->index)) {
ret = f2fs_read_multi_pages(&cc, &bio,
max_nr_pages,
&last_block_in_bio,
is_readahead);
f2fs_destroy_compress_ctx(&cc);
if (ret)
goto set_error_page;
}
ret = f2fs_is_compressed_cluster(inode, page->index);
if (ret < 0)
goto set_error_page;
else if (!ret)
goto read_single_page;
ret = f2fs_init_compress_ctx(&cc);
if (ret)
goto set_error_page;
f2fs_compress_ctx_add_page(&cc, page);
goto next_page;
}
read_single_page:
#endif
ret = f2fs_read_single_page(inode, page, max_nr_pages, &map,
&bio, &last_block_in_bio, is_readahead);
if (ret) {
#ifdef CONFIG_F2FS_FS_COMPRESSION
set_error_page:
#endif
SetPageError(page);
zero_user_segment(page, 0, PAGE_SIZE);
unlock_page(page);
}
next_page:
if (pages)
put_page(page);
#ifdef CONFIG_F2FS_FS_COMPRESSION
if (f2fs_compressed_file(inode)) {
/* last page */
if (nr_pages == 1 && !f2fs_cluster_is_empty(&cc)) {
ret = f2fs_read_multi_pages(&cc, &bio,
max_nr_pages,
&last_block_in_bio,
is_readahead);
f2fs_destroy_compress_ctx(&cc);
}
}
#endif
}
BUG_ON(pages && !list_empty(pages));
if (bio)
__submit_bio(F2FS_I_SB(inode), bio, DATA);
return pages ? 0 : ret;
}
static int f2fs_read_data_page(struct file *file, struct page *page)
{
struct inode *inode = page_file_mapping(page)->host;
int ret = -EAGAIN;
trace_f2fs_readpage(page, DATA);
if (!f2fs_is_compress_backend_ready(inode)) {
unlock_page(page);
return -EOPNOTSUPP;
}
/* 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_file_mapping(page),
NULL, page, 1, false);
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 (!f2fs_is_compress_backend_ready(inode))
return 0;
/* 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, true);
}
int f2fs_encrypt_one_page(struct f2fs_io_info *fio)
{
struct inode *inode = fio->page->mapping->host;
struct page *mpage, *page;
gfp_t gfp_flags = GFP_NOFS;
if (!f2fs_encrypted_file(inode))
return 0;
page = fio->compressed_page ? fio->compressed_page : fio->page;
/* wait for GCed page writeback via META_MAPPING */
f2fs_wait_on_block_writeback(inode, fio->old_blkaddr);
retry_encrypt:
fio->encrypted_page = fscrypt_encrypt_pagecache_blocks(page,
PAGE_SIZE, 0, gfp_flags);
if (IS_ERR(fio->encrypted_page)) {
/* 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);
}
mpage = find_lock_page(META_MAPPING(fio->sbi), fio->old_blkaddr);
if (mpage) {
if (PageUptodate(mpage))
memcpy(page_address(mpage),
page_address(fio->encrypted_page), PAGE_SIZE);
f2fs_put_page(mpage, 1);
}
return 0;
}
static inline bool check_inplace_update_policy(struct inode *inode,
struct f2fs_io_info *fio)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
unsigned int policy = SM_I(sbi)->ipu_policy;
if (policy & (0x1 << F2FS_IPU_FORCE))
return true;
if (policy & (0x1 << F2FS_IPU_SSR) && f2fs_need_SSR(sbi))
return true;
if (policy & (0x1 << F2FS_IPU_UTIL) &&
utilization(sbi) > SM_I(sbi)->min_ipu_util)
return true;
if (policy & (0x1 << F2FS_IPU_SSR_UTIL) && f2fs_need_SSR(sbi) &&
utilization(sbi) > SM_I(sbi)->min_ipu_util)
return true;
/*
* IPU for rewrite async pages
*/
if (policy & (0x1 << F2FS_IPU_ASYNC) &&
fio && fio->op == REQ_OP_WRITE &&
!(fio->op_flags & REQ_SYNC) &&
!IS_ENCRYPTED(inode))
return true;
/* this is only set during fdatasync */
if (policy & (0x1 << F2FS_IPU_FSYNC) &&
is_inode_flag_set(inode, FI_NEED_IPU))
return true;
if (unlikely(fio && is_sbi_flag_set(sbi, SBI_CP_DISABLED) &&
!f2fs_is_checkpointed_data(sbi, fio->old_blkaddr)))
return true;
return false;
}
bool f2fs_should_update_inplace(struct inode *inode, struct f2fs_io_info *fio)
{
if (f2fs_is_pinned_file(inode))
return true;
/* if this is cold file, we should overwrite to avoid fragmentation */
if (file_is_cold(inode))
return true;
return check_inplace_update_policy(inode, fio);
}
bool f2fs_should_update_outplace(struct inode *inode, struct f2fs_io_info *fio)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
if (test_opt(sbi, LFS))
return true;
if (S_ISDIR(inode->i_mode))
return true;
if (IS_NOQUOTA(inode))
return true;
if (f2fs_is_atomic_file(inode))
return true;
if (fio) {
if (is_cold_data(fio->page))
return true;
if (IS_ATOMIC_WRITTEN_PAGE(fio->page))
return true;
if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED) &&
f2fs_is_checkpointed_data(sbi, fio->old_blkaddr)))
return true;
}
return false;
}
static inline bool need_inplace_update(struct f2fs_io_info *fio)
{
struct inode *inode = fio->page->mapping->host;
if (f2fs_should_update_outplace(inode, fio))
return false;
return f2fs_should_update_inplace(inode, fio);
}
int f2fs_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};
struct node_info ni;
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 (!f2fs_is_valid_blkaddr(fio->sbi, fio->old_blkaddr,
DATA_GENERIC_ENHANCE))
return -EFSCORRUPTED;
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 = f2fs_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);
clear_cold_data(page);
goto out_writepage;
}
got_it:
if (__is_valid_data_blkaddr(fio->old_blkaddr) &&
!f2fs_is_valid_blkaddr(fio->sbi, fio->old_blkaddr,
DATA_GENERIC_ENHANCE)) {
err = -EFSCORRUPTED;
goto out_writepage;
}
/*
* If current allocation needs SSR,
* it had better in-place writes for updated data.
*/
if (ipu_force ||
(__is_valid_data_blkaddr(fio->old_blkaddr) &&
need_inplace_update(fio))) {
err = f2fs_encrypt_one_page(fio);
if (err)
goto out_writepage;
set_page_writeback(page);
ClearPageError(page);
f2fs_put_dnode(&dn);
if (fio->need_lock == LOCK_REQ)
f2fs_unlock_op(fio->sbi);
err = f2fs_inplace_write_data(fio);
if (err) {
if (f2fs_encrypted_file(inode))
fscrypt_finalize_bounce_page(&fio->encrypted_page);
if (PageWriteback(page))
end_page_writeback(page);
} else {
set_inode_flag(inode, FI_UPDATE_WRITE);
}
trace_f2fs_do_write_data_page(fio->page, IPU);
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 = f2fs_get_node_info(fio->sbi, dn.nid, &ni);
if (err)
goto out_writepage;
fio->version = ni.version;
err = f2fs_encrypt_one_page(fio);
if (err)
goto out_writepage;
set_page_writeback(page);
ClearPageError(page);
if (fio->compr_blocks && fio->old_blkaddr == COMPRESS_ADDR)
f2fs_i_compr_blocks_update(inode, fio->compr_blocks - 1, false);
/* LFS mode write path */
f2fs_outplace_write_data(&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;
}
int f2fs_write_single_data_page(struct page *page, int *submitted,
struct bio **bio,
sector_t *last_block,
struct writeback_control *wbc,
enum iostat_type io_type,
int compr_blocks)
{
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 = (loff_t)(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,
.compr_blocks = compr_blocks,
.need_lock = LOCK_RETRY,
.io_type = io_type,
.io_wbc = wbc,
.bio = bio,
.last_block = last_block,
};
trace_f2fs_writepage(page, DATA);
/* we should bypass data pages to proceed the kworkder jobs */
if (unlikely(f2fs_cp_error(sbi))) {
mapping_set_error(page->mapping, -EIO);
/*
* don't drop any dirty dentry pages for keeping lastest
* directory structure.
*/
if (S_ISDIR(inode->i_mode))
goto redirty_out;
goto out;
}
if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
goto redirty_out;
if (page->index < end_index ||
f2fs_verity_in_progress(inode) ||
compr_blocks)
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 &&
f2fs_available_free_memory(sbi, BASE_CHECK))))
goto redirty_out;
/* Dentry blocks are controlled by checkpoint */
if (S_ISDIR(inode->i_mode)) {
fio.need_lock = LOCK_DONE;
err = f2fs_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 = f2fs_do_write_data_page(&fio);
if (err == -EAGAIN) {
fio.need_lock = LOCK_REQ;
err = f2fs_do_write_data_page(&fio);
}
}
if (err) {
file_set_keep_isize(inode);
} else {
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);
clear_cold_data(page);
}
if (wbc->for_reclaim) {
f2fs_submit_merged_write_cond(sbi, NULL, page, 0, DATA);
clear_inode_flag(inode, FI_HOT_DATA);
f2fs_remove_dirty_inode(inode);
submitted = NULL;
}
unlock_page(page);
if (!S_ISDIR(inode->i_mode) && !IS_NOQUOTA(inode) &&
!F2FS_I(inode)->cp_task)
f2fs_balance_fs(sbi, need_balance_fs);
if (unlikely(f2fs_cp_error(sbi))) {
f2fs_submit_merged_write(sbi, DATA);
f2fs_submit_merged_ipu_write(sbi, bio, NULL);
submitted = NULL;
}
if (submitted)
*submitted = fio.submitted ? 1 : 0;
return 0;
redirty_out:
redirty_page_for_writepage(wbc, page);
/*
* pageout() in MM traslates EAGAIN, so calls handle_write_error()
* -> mapping_set_error() -> set_bit(AS_EIO, ...).
* file_write_and_wait_range() will see EIO error, which is critical
* to return value of fsync() followed by atomic_write failure to user.
*/
if