Google Git
Sign in
android-kvm / linux / 6cd90e5ea72f35fa40f971c419e16142cd8272bf / . / fs / f2fs / data.c
blob: 6457e5bca9c9e77442e88dcb5b797d76128f93bb [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/sched/mm.h>
#include <linux/mpage.h>
#include <linux/writeback.h>
#include <linux/pagevec.h>
#include <linux/blkdev.h>
#include <linux/bio.h>
#include <linux/blk-crypto.h>
#include <linux/swap.h>
#include <linux/prefetch.h>
#include <linux/uio.h>
#include <linux/sched/signal.h>
#include <linux/fiemap.h>
#include <linux/iomap.h>
#include "f2fs.h"
#include "node.h"
#include "segment.h"
#include "iostat.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)
{
return bioset_init(&f2fs_bioset, F2FS_BIO_POOL_SIZE,
0, BIOSET_NEED_BVECS);
}
void f2fs_destroy_bioset(void)
{
bioset_exit(&f2fs_bioset);
}
bool f2fs_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))
return true;
if ((S_ISREG(inode->i_mode) && IS_NOQUOTA(inode)) ||
page_private_gcing(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 {
#ifdef CONFIG_FS_ENCRYPTION
STEP_DECRYPT = BIT(0),
#else
STEP_DECRYPT = 0, /* compile out the decryption-related code */
#endif
#ifdef CONFIG_F2FS_FS_COMPRESSION
STEP_DECOMPRESS = BIT(1),
#else
STEP_DECOMPRESS = 0, /* compile out the decompression-related code */
#endif
#ifdef CONFIG_FS_VERITY
STEP_VERITY = BIT(2),
#else
STEP_VERITY = 0, /* compile out the verity-related code */
#endif
};
struct bio_post_read_ctx {
struct bio *bio;
struct f2fs_sb_info *sbi;
struct work_struct work;
unsigned int enabled_steps;
/*
* decompression_attempted keeps track of whether
* f2fs_end_read_compressed_page() has been called on the pages in the
* bio that belong to a compressed cluster yet.
*/
bool decompression_attempted;
block_t fs_blkaddr;
};
/*
* Update and unlock a bio's pages, and free the bio.
*
* This marks pages up-to-date only if there was no error in the bio (I/O error,
* decryption error, or verity error), as indicated by bio->bi_status.
*
* "Compressed pages" (pagecache pages backed by a compressed cluster on-disk)
* aren't marked up-to-date here, as decompression is done on a per-compression-
* cluster basis rather than a per-bio basis. Instead, we only must do two
* things for each compressed page here: call f2fs_end_read_compressed_page()
* with failed=true if an error occurred before it would have normally gotten
* called (i.e., I/O error or decryption error, but *not* verity error), and
* release the bio's reference to the decompress_io_ctx of the page's cluster.
*/
static void f2fs_finish_read_bio(struct bio *bio, bool in_task)
{
struct bio_vec *bv;
struct bvec_iter_all iter_all;
struct bio_post_read_ctx *ctx = bio->bi_private;
bio_for_each_segment_all(bv, bio, iter_all) {
struct page *page = bv->bv_page;
if (f2fs_is_compressed_page(page)) {
if (ctx && !ctx->decompression_attempted)
f2fs_end_read_compressed_page(page, true, 0,
in_task);
f2fs_put_page_dic(page, in_task);
continue;
}
if (bio->bi_status)
ClearPageUptodate(page);
else
SetPageUptodate(page);
dec_page_count(F2FS_P_SB(page), __read_io_type(page));
unlock_page(page);
}
if (ctx)
mempool_free(ctx, bio_post_read_ctx_pool);
bio_put(bio);
}
static void f2fs_verify_bio(struct work_struct *work)
{
struct bio_post_read_ctx *ctx =
container_of(work, struct bio_post_read_ctx, work);
struct bio *bio = ctx->bio;
bool may_have_compressed_pages = (ctx->enabled_steps & STEP_DECOMPRESS);
/*
* fsverity_verify_bio() may call readahead() again, and while verity
* will be disabled for this, decryption and/or decompression 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;
/*
* Verify the bio's pages with fs-verity. Exclude compressed pages,
* as those were handled separately by f2fs_end_read_compressed_page().
*/
if (may_have_compressed_pages) {
struct bio_vec *bv;
struct bvec_iter_all iter_all;
bio_for_each_segment_all(bv, bio, iter_all) {
struct page *page = bv->bv_page;
if (!f2fs_is_compressed_page(page) &&
!fsverity_verify_page(page)) {
bio->bi_status = BLK_STS_IOERR;
break;
}
}
} else {
fsverity_verify_bio(bio);
}
f2fs_finish_read_bio(bio, true);
}
/*
* If the bio's data needs to be verified with fs-verity, then enqueue the
* verity work for the bio. Otherwise finish the bio now.
*
* Note that to avoid deadlocks, the verity work can't be done on the
* decryption/decompression workqueue. This is because verifying the data pages
* can involve reading verity metadata pages from the file, and these verity
* metadata pages may be encrypted and/or compressed.
*/
static void f2fs_verify_and_finish_bio(struct bio *bio, bool in_task)
{
struct bio_post_read_ctx *ctx = bio->bi_private;
if (ctx && (ctx->enabled_steps & STEP_VERITY)) {
INIT_WORK(&ctx->work, f2fs_verify_bio);
fsverity_enqueue_verify_work(&ctx->work);
} else {
f2fs_finish_read_bio(bio, in_task);
}
}
/*
* Handle STEP_DECOMPRESS by decompressing any compressed clusters whose last
* remaining page was read by @ctx->bio.
*
* Note that a bio may span clusters (even a mix of compressed and uncompressed
* clusters) or be for just part of a cluster. STEP_DECOMPRESS just indicates
* that the bio includes at least one compressed page. The actual decompression
* is done on a per-cluster basis, not a per-bio basis.
*/
static void f2fs_handle_step_decompress(struct bio_post_read_ctx *ctx,
bool in_task)
{
struct bio_vec *bv;
struct bvec_iter_all iter_all;
bool all_compressed = true;
block_t blkaddr = ctx->fs_blkaddr;
bio_for_each_segment_all(bv, ctx->bio, iter_all) {
struct page *page = bv->bv_page;
if (f2fs_is_compressed_page(page))
f2fs_end_read_compressed_page(page, false, blkaddr,
in_task);
else
all_compressed = false;
blkaddr++;
}
ctx->decompression_attempted = true;
/*
* Optimization: if all the bio's pages are compressed, then scheduling
* the per-bio verity work is unnecessary, as verity will be fully
* handled at the compression cluster level.
*/
if (all_compressed)
ctx->enabled_steps &= ~STEP_VERITY;
}
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);
struct bio *bio = ctx->bio;
if ((ctx->enabled_steps & STEP_DECRYPT) && !fscrypt_decrypt_bio(bio)) {
f2fs_finish_read_bio(bio, true);
return;
}
if (ctx->enabled_steps & STEP_DECOMPRESS)
f2fs_handle_step_decompress(ctx, true);
f2fs_verify_and_finish_bio(bio, true);
}
static void f2fs_read_end_io(struct bio *bio)
{
struct f2fs_sb_info *sbi = F2FS_P_SB(bio_first_page_all(bio));
struct bio_post_read_ctx *ctx;
bool intask = in_task();
iostat_update_and_unbind_ctx(bio);
ctx = bio->bi_private;
if (time_to_inject(sbi, FAULT_READ_IO))
bio->bi_status = BLK_STS_IOERR;
if (bio->bi_status) {
f2fs_finish_read_bio(bio, intask);
return;
}
if (ctx) {
unsigned int enabled_steps = ctx->enabled_steps &
(STEP_DECRYPT | STEP_DECOMPRESS);
/*
* If we have only decompression step between decompression and
* decrypt, we don't need post processing for this.
*/
if (enabled_steps == STEP_DECOMPRESS &&
!f2fs_low_mem_mode(sbi)) {
f2fs_handle_step_decompress(ctx, intask);
} else if (enabled_steps) {
INIT_WORK(&ctx->work, f2fs_post_read_work);
queue_work(ctx->sbi->post_read_wq, &ctx->work);
return;
}
}
f2fs_verify_and_finish_bio(bio, intask);
}
static void f2fs_write_end_io(struct bio *bio)
{
struct f2fs_sb_info *sbi;
struct bio_vec *bvec;
struct bvec_iter_all iter_all;
iostat_update_and_unbind_ctx(bio);
sbi = bio->bi_private;
if (time_to_inject(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, false);
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,
STOP_CP_REASON_WRITE_FAIL);
}
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_page_private_gcing(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);
}
#ifdef CONFIG_BLK_DEV_ZONED
static void f2fs_zone_write_end_io(struct bio *bio)
{
struct f2fs_bio_info *io = (struct f2fs_bio_info *)bio->bi_private;
bio->bi_private = io->bi_private;
complete(&io->zone_wait);
f2fs_write_end_io(bio);
}
#endif
struct block_device *f2fs_target_device(struct f2fs_sb_info *sbi,
block_t blk_addr, sector_t *sector)
{
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 (sector)
*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 blk_opf_t f2fs_io_flags(struct f2fs_io_info *fio)
{
unsigned int temp_mask = GENMASK(NR_TEMP_TYPE - 1, 0);
unsigned int fua_flag, meta_flag, io_flag;
blk_opf_t op_flags = 0;
if (fio->op != REQ_OP_WRITE)
return 0;
if (fio->type == DATA)
io_flag = fio->sbi->data_io_flag;
else if (fio->type == NODE)
io_flag = fio->sbi->node_io_flag;
else
return 0;
fua_flag = io_flag & temp_mask;
meta_flag = (io_flag >> NR_TEMP_TYPE) & temp_mask;
/*
* data/node io flag bits per temp:
* REQ_META | REQ_FUA |
* 5 | 4 | 3 | 2 | 1 | 0 |
* Cold | Warm | Hot | Cold | Warm | Hot |
*/
if (BIT(fio->temp) & meta_flag)
op_flags |= REQ_META;
if (BIT(fio->temp) & fua_flag)
op_flags |= REQ_FUA;
return op_flags;
}
static struct bio *__bio_alloc(struct f2fs_io_info *fio, int npages)
{
struct f2fs_sb_info *sbi = fio->sbi;
struct block_device *bdev;
sector_t sector;
struct bio *bio;
bdev = f2fs_target_device(sbi, fio->new_blkaddr, &sector);
bio = bio_alloc_bioset(bdev, npages,
fio->op | fio->op_flags | f2fs_io_flags(fio),
GFP_NOIO, &f2fs_bioset);
bio->bi_iter.bi_sector = sector;
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);
}
iostat_alloc_and_bind_ctx(sbi, bio, NULL);
if (fio->io_wbc)
wbc_init_bio(fio->io_wbc, bio);
return bio;
}
static void f2fs_set_bio_crypt_ctx(struct bio *bio, const struct inode *inode,
pgoff_t first_idx,
const struct f2fs_io_info *fio,
gfp_t gfp_mask)
{
/*
* The f2fs garbage collector sets ->encrypted_page when it wants to
* read/write raw data without encryption.
*/
if (!fio || !fio->encrypted_page)
fscrypt_set_bio_crypt_ctx(bio, inode, first_idx, gfp_mask);
}
static bool f2fs_crypt_mergeable_bio(struct bio *bio, const struct inode *inode,
pgoff_t next_idx,
const struct f2fs_io_info *fio)
{
/*
* The f2fs garbage collector sets ->encrypted_page when it wants to
* read/write raw data without encryption.
*/
if (fio && fio->encrypted_page)
return !bio_has_crypt_ctx(bio);
return fscrypt_mergeable_bio(bio, inode, next_idx);
}
void f2fs_submit_read_bio(struct f2fs_sb_info *sbi, struct bio *bio,
enum page_type type)
{
WARN_ON_ONCE(!is_read_io(bio_op(bio)));
trace_f2fs_submit_read_bio(sbi->sb, type, bio);
iostat_update_submit_ctx(bio, type);
submit_bio(bio);
}
static void f2fs_submit_write_bio(struct f2fs_sb_info *sbi, struct bio *bio,
enum page_type type)
{
WARN_ON_ONCE(is_read_io(bio_op(bio)));
if (f2fs_lfs_mode(sbi) && current->plug && PAGE_TYPE_ON_MAIN(type))
blk_finish_plug(current->plug);
trace_f2fs_submit_write_bio(sbi->sb, type, bio);
iostat_update_submit_ctx(bio, type);
submit_bio(bio);
}
static void __submit_merged_bio(struct f2fs_bio_info *io)
{
struct f2fs_io_info *fio = &io->fio;
if (!io->bio)
return;
if (is_read_io(fio->op)) {
trace_f2fs_prepare_read_bio(io->sbi->sb, fio->type, io->bio);
f2fs_submit_read_bio(io->sbi, io->bio, fio->type);
} else {
trace_f2fs_prepare_write_bio(io->sbi->sb, fio->type, io->bio);
f2fs_submit_write_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;
}
int f2fs_init_write_merge_io(struct f2fs_sb_info *sbi)
{
int i;
for (i = 0; i < NR_PAGE_TYPE; i++) {
int n = (i == META) ? 1 : NR_TEMP_TYPE;
int j;
sbi->write_io[i] = f2fs_kmalloc(sbi,
array_size(n, sizeof(struct f2fs_bio_info)),
GFP_KERNEL);
if (!sbi->write_io[i])
return -ENOMEM;
for (j = HOT; j < n; j++) {
struct f2fs_bio_info *io = &sbi->write_io[i][j];
init_f2fs_rwsem(&io->io_rwsem);
io->sbi = sbi;
io->bio = NULL;
io->last_block_in_bio = 0;
spin_lock_init(&io->io_lock);
INIT_LIST_HEAD(&io->io_list);
INIT_LIST_HEAD(&io->bio_list);
init_f2fs_rwsem(&io->bio_list_lock);
#ifdef CONFIG_BLK_DEV_ZONED
init_completion(&io->zone_wait);
io->zone_pending_bio = NULL;
io->bi_private = NULL;
#endif
}
}
return 0;
}
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;
f2fs_down_write(&io->io_rwsem);
if (!io->bio)
goto unlock_out;
/* change META to META_FLUSH in the checkpoint procedure */
if (type >= META_FLUSH) {
io->fio.type = META_FLUSH;
io->bio->bi_opf |= REQ_META | REQ_PRIO | REQ_SYNC;
if (!test_opt(sbi, NOBARRIER))
io->bio->bi_opf |= REQ_PREFLUSH | REQ_FUA;
}
__submit_merged_bio(io);
unlock_out:
f2fs_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;
f2fs_down_read(&io->io_rwsem);
ret = __has_merged_page(io->bio, inode, page, ino);
f2fs_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);
/* Allocate a new bio */
bio = __bio_alloc(fio, 1);
f2fs_set_bio_crypt_ctx(bio, fio->page->mapping->host,
fio->page->index, fio, GFP_NOIO);
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, fio->page, PAGE_SIZE);
inc_page_count(fio->sbi, is_read_io(fio->op) ?
__read_io_type(page) : WB_DATA_TYPE(fio->page, false));
if (is_read_io(bio_op(bio)))
f2fs_submit_read_bio(fio->sbi, bio, fio->type);
else
f2fs_submit_write_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 (unlikely(sbi->max_io_bytes &&
bio->bi_iter.bi_size >= sbi->max_io_bytes))
return false;
if (last_blkaddr + 1 != cur_blkaddr)
return false;
return bio->bi_bdev == f2fs_target_device(sbi, cur_blkaddr, NULL);
}
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 (!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, true, NULL);
be->bio = bio;
bio_get(bio);
if (bio_add_page(bio, page, PAGE_SIZE, 0) != PAGE_SIZE)
f2fs_bug_on(sbi, 1);
f2fs_down_write(&io->bio_list_lock);
list_add_tail(&be->list, &io->bio_list);
f2fs_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_io_info *fio, struct bio **bio,
struct page *page)
{
struct f2fs_sb_info *sbi = fio->sbi;
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;
f2fs_down_write(&io->bio_list_lock);
list_for_each_entry(be, head, list) {
if (be->bio != *bio)
continue;
found = true;
f2fs_bug_on(sbi, !page_is_mergeable(sbi, *bio,
*fio->last_block,
fio->new_blkaddr));
if (f2fs_crypt_mergeable_bio(*bio,
fio->page->mapping->host,
fio->page->index, fio) &&
bio_add_page(*bio, page, PAGE_SIZE, 0) ==
PAGE_SIZE) {
ret = 0;
break;
}
/* page can't be merged into bio; submit the bio */
del_bio_entry(be);
f2fs_submit_write_bio(sbi, *bio, DATA);
break;
}
f2fs_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;
f2fs_bug_on(sbi, !target && !page);
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;
f2fs_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;
}
f2fs_up_read(&io->bio_list_lock);
if (!found)
continue;
found = false;
f2fs_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;
}
}
f2fs_up_write(&io->bio_list_lock);
}
if (found)
f2fs_submit_write_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);
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_VECS);
f2fs_set_bio_crypt_ctx(bio, fio->page->mapping->host,
fio->page->index, fio, GFP_NOIO);
add_bio_entry(fio->sbi, bio, page, fio->temp);
} else {
if (add_ipu_page(fio, &bio, page))
goto alloc_new;
}
if (fio->io_wbc)
wbc_account_cgroup_owner(fio->io_wbc, fio->page, PAGE_SIZE);
inc_page_count(fio->sbi, WB_DATA_TYPE(page, false));
*fio->last_block = fio->new_blkaddr;
*fio->bio = bio;
return 0;
}
#ifdef CONFIG_BLK_DEV_ZONED
static bool is_end_zone_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr)
{
struct block_device *bdev = sbi->sb->s_bdev;
int devi = 0;
if (f2fs_is_multi_device(sbi)) {
devi = f2fs_target_device_index(sbi, blkaddr);
if (blkaddr < FDEV(devi).start_blk ||
blkaddr > FDEV(devi).end_blk) {
f2fs_err(sbi, "Invalid block %x", blkaddr);
return false;
}
blkaddr -= FDEV(devi).start_blk;
bdev = FDEV(devi).bdev;
}
return bdev_is_zoned(bdev) &&
f2fs_blkz_is_seq(sbi, devi, blkaddr) &&
(blkaddr % sbi->blocks_per_blkz == sbi->blocks_per_blkz - 1);
}
#endif
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;
enum count_type type;
f2fs_bug_on(sbi, is_read_io(fio->op));
f2fs_down_write(&io->io_rwsem);
next:
#ifdef CONFIG_BLK_DEV_ZONED
if (f2fs_sb_has_blkzoned(sbi) && btype < META && io->zone_pending_bio) {
wait_for_completion_io(&io->zone_wait);
bio_put(io->zone_pending_bio);
io->zone_pending_bio = NULL;
io->bi_private = NULL;
}
#endif
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 = 1;
type = WB_DATA_TYPE(bio_page, fio->compressed_page);
inc_page_count(sbi, type);
if (io->bio &&
(!io_is_mergeable(sbi, io->bio, io, fio, io->last_block_in_bio,
fio->new_blkaddr) ||
!f2fs_crypt_mergeable_bio(io->bio, fio->page->mapping->host,
bio_page->index, fio)))
__submit_merged_bio(io);
alloc_new:
if (io->bio == NULL) {
io->bio = __bio_alloc(fio, BIO_MAX_VECS);
f2fs_set_bio_crypt_ctx(io->bio, fio->page->mapping->host,
bio_page->index, fio, GFP_NOIO);
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, fio->page, PAGE_SIZE);
io->last_block_in_bio = fio->new_blkaddr;
trace_f2fs_submit_page_write(fio->page, fio);
#ifdef CONFIG_BLK_DEV_ZONED
if (f2fs_sb_has_blkzoned(sbi) && btype < META &&
is_end_zone_blkaddr(sbi, fio->new_blkaddr)) {
bio_get(io->bio);
reinit_completion(&io->zone_wait);
io->bi_private = io->bio->bi_private;
io->bio->bi_private = io;
io->bio->bi_end_io = f2fs_zone_write_end_io;
io->zone_pending_bio = io->bio;
__submit_merged_bio(io);
}
#endif
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);
f2fs_up_write(&io->io_rwsem);
}
static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr,
unsigned nr_pages, blk_opf_t op_flag,
pgoff_t first_idx, bool for_write)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct bio *bio;
struct bio_post_read_ctx *ctx = NULL;
unsigned int post_read_steps = 0;
sector_t sector;
struct block_device *bdev = f2fs_target_device(sbi, blkaddr, &sector);
bio = bio_alloc_bioset(bdev, bio_max_segs(nr_pages),
REQ_OP_READ | op_flag,
for_write ? GFP_NOIO : GFP_KERNEL, &f2fs_bioset);
if (!bio)
return ERR_PTR(-ENOMEM);
bio->bi_iter.bi_sector = sector;
f2fs_set_bio_crypt_ctx(bio, inode, first_idx, NULL, GFP_NOFS);
bio->bi_end_io = f2fs_read_end_io;
if (fscrypt_inode_uses_fs_layer_crypto(inode))
post_read_steps |= STEP_DECRYPT;
if (f2fs_need_verity(inode, first_idx))
post_read_steps |= STEP_VERITY;
/*
* STEP_DECOMPRESS is handled specially, since a compressed file might
* contain both compressed and uncompressed clusters. We'll allocate a
* bio_post_read_ctx if the file is compressed, but the caller is
* responsible for enabling STEP_DECOMPRESS if it's actually needed.
*/
if (post_read_steps || f2fs_compressed_file(inode)) {
/* 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;
ctx->fs_blkaddr = blkaddr;
ctx->decompression_attempted = false;
bio->bi_private = ctx;
}
iostat_alloc_and_bind_ctx(sbi, bio, ctx);
return bio;
}
/* This can handle encryption stuffs */
static int f2fs_submit_page_read(struct inode *inode, struct page *page,
block_t blkaddr, blk_opf_t op_flags,
bool for_write)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct bio *bio;
bio = f2fs_grab_read_bio(inode, blkaddr, 1, op_flags,
page->index, for_write);
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) {
iostat_update_and_unbind_ctx(bio);
if (bio->bi_private)
mempool_free(bio->bi_private, bio_post_read_ctx_pool);
bio_put(bio);
return -EFAULT;
}
inc_page_count(sbi, F2FS_RD_DATA);
f2fs_update_iostat(sbi, NULL, FS_DATA_READ_IO, F2FS_BLKSIZE);
f2fs_submit_read_bio(sbi, bio, DATA);
return 0;
}
static void __set_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr)
{
__le32 *addr = get_dnode_addr(dn->inode, dn->node_page);
dn->data_blkaddr = blkaddr;
addr[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, block_t blkaddr)
{
f2fs_wait_on_page_writeback(dn->node_page, NODE, true, true);
__set_data_blkaddr(dn, blkaddr);
if (set_page_dirty(dn->node_page))
dn->node_changed = true;
}
void f2fs_update_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr)
{
f2fs_set_data_blkaddr(dn, blkaddr);
f2fs_update_read_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;
err = inc_valid_block_count(sbi, dn->inode, &count, true);
if (unlikely(err))
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 = f2fs_data_blkaddr(dn);
if (blkaddr == NULL_ADDR) {
__set_data_blkaddr(dn, NEW_ADDR);
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;
}
struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index,
blk_opf_t op_flags, bool for_write,
pgoff_t *next_pgofs)
{
struct address_space *mapping = inode->i_mapping;
struct dnode_of_data dn;
struct page *page;
int err;
page = f2fs_grab_cache_page(mapping, index, for_write);
if (!page)
return ERR_PTR(-ENOMEM);
if (f2fs_lookup_read_extent_cache_block(inode, index,
&dn.data_blkaddr)) {
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) {
if (err == -ENOENT && next_pgofs)
*next_pgofs = f2fs_get_next_page_offset(&dn, index);
goto put_err;
}
f2fs_put_dnode(&dn);
if (unlikely(dn.data_blkaddr == NULL_ADDR)) {
err = -ENOENT;
if (next_pgofs)
*next_pgofs = index + 1;
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,
op_flags, for_write);
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,
pgoff_t *next_pgofs)
{
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, next_pgofs);
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;
page = f2fs_get_read_data_page(inode, index, 0, for_write, NULL);
if (IS_ERR(page))
return page;
/* wait for read completion */
lock_page(page);
if (unlikely(page->mapping != mapping || !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, false);
if (err)
return err;
dn->data_blkaddr = f2fs_data_blkaddr(dn);
if (dn->data_blkaddr == NULL_ADDR) {
err = inc_valid_block_count(sbi, dn->inode, &count, true);
if (unlikely(err))
return err;
}
set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version);
old_blkaddr = dn->data_blkaddr;
err = f2fs_allocate_data_block(sbi, NULL, old_blkaddr,
&dn->data_blkaddr, &sum, seg_type, NULL);
if (err)
return err;
if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO)
f2fs_invalidate_internal_cache(sbi, old_blkaddr);
f2fs_update_data_blkaddr(dn, dn->data_blkaddr);
return 0;
}
static void f2fs_map_lock(struct f2fs_sb_info *sbi, int flag)
{
if (flag == F2FS_GET_BLOCK_PRE_AIO)
f2fs_down_read(&sbi->node_change);
else
f2fs_lock_op(sbi);
}
static void f2fs_map_unlock(struct f2fs_sb_info *sbi, int flag)
{
if (flag == F2FS_GET_BLOCK_PRE_AIO)
f2fs_up_read(&sbi->node_change);
else
f2fs_unlock_op(sbi);
}
int f2fs_get_block_locked(struct dnode_of_data *dn, pgoff_t index)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
int err = 0;
f2fs_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO);
if (!f2fs_lookup_read_extent_cache_block(dn->inode, index,
&dn->data_blkaddr))
err = f2fs_reserve_block(dn, index);
f2fs_map_unlock(sbi, F2FS_GET_BLOCK_PRE_AIO);
return err;
}
static int f2fs_map_no_dnode(struct inode *inode,
struct f2fs_map_blocks *map, struct dnode_of_data *dn,
pgoff_t pgoff)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
/*
* There is one exceptional case that read_node_page() may return
* -ENOENT due to filesystem has been shutdown or cp_error, return
* -EIO in that case.
*/
if (map->m_may_create &&
(is_sbi_flag_set(sbi, SBI_IS_SHUTDOWN) || f2fs_cp_error(sbi)))
return -EIO;
if (map->m_next_pgofs)
*map->m_next_pgofs = f2fs_get_next_page_offset(dn, pgoff);
if (map->m_next_extent)
*map->m_next_extent = f2fs_get_next_page_offset(dn, pgoff);
return 0;
}
static bool f2fs_map_blocks_cached(struct inode *inode,
struct f2fs_map_blocks *map, int flag)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
unsigned int maxblocks = map->m_len;
pgoff_t pgoff = (pgoff_t)map->m_lblk;
struct extent_info ei = {};
if (!f2fs_lookup_read_extent_cache(inode, pgoff, &ei))
return false;
map->m_pblk = ei.blk + pgoff - ei.fofs;
map->m_len = min((pgoff_t)maxblocks, ei.fofs + ei.len - pgoff);
map->m_flags = F2FS_MAP_MAPPED;
if (map->m_next_extent)
*map->m_next_extent = pgoff + 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);
if (f2fs_allow_multi_device_dio(sbi, flag)) {
int bidx = f2fs_target_device_index(sbi, map->m_pblk);
struct f2fs_dev_info *dev = &sbi->devs[bidx];
map->m_bdev = dev->bdev;
map->m_pblk -= dev->start_blk;
map->m_len = min(map->m_len, dev->end_blk + 1 - map->m_pblk);
} else {
map->m_bdev = inode->i_sb->s_bdev;
}
return true;
}
static bool map_is_mergeable(struct f2fs_sb_info *sbi,
struct f2fs_map_blocks *map,
block_t blkaddr, int flag, int bidx,
int ofs)
{
if (map->m_multidev_dio && map->m_bdev != FDEV(bidx).bdev)
return false;
if (map->m_pblk != NEW_ADDR && blkaddr == (map->m_pblk + ofs))
return true;
if (map->m_pblk == NEW_ADDR && blkaddr == NEW_ADDR)
return true;
if (flag == F2FS_GET_BLOCK_PRE_DIO)
return true;
if (flag == F2FS_GET_BLOCK_DIO &&
map->m_pblk == NULL_ADDR && blkaddr == NULL_ADDR)
return true;
return false;
}
/*
* f2fs_map_blocks() tries to find or build mapping relationship which
* maps continuous logical blocks to physical blocks, and return such
* info via f2fs_map_blocks structure.
*/
int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map, 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;
block_t blkaddr;
unsigned int start_pgofs;
int bidx = 0;
bool is_hole;
if (!maxblocks)
return 0;
if (!map->m_may_create && f2fs_map_blocks_cached(inode, map, flag))
goto out;
map->m_bdev = inode->i_sb->s_bdev;
map->m_multidev_dio =
f2fs_allow_multi_device_dio(F2FS_I_SB(inode), flag);
map->m_len = 0;
map->m_flags = 0;
/* it only supports block size == page size */
pgofs = (pgoff_t)map->m_lblk;
end = pgofs + maxblocks;
next_dnode:
if (map->m_may_create)
f2fs_map_lock(sbi, flag);
/* 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 = f2fs_map_no_dnode(inode, map, &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 = f2fs_data_blkaddr(&dn);
is_hole = !__is_valid_data_blkaddr(blkaddr);
if (!is_hole &&
!f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC_ENHANCE)) {
err = -EFSCORRUPTED;
goto sync_out;
}
/* use out-place-update for direct IO under LFS mode */
if (map->m_may_create && (is_hole ||
(flag == F2FS_GET_BLOCK_DIO && f2fs_lfs_mode(sbi) &&
!f2fs_is_pinned_file(inode)))) {
if (unlikely(f2fs_cp_error(sbi))) {
err = -EIO;
goto sync_out;
}
switch (flag) {
case F2FS_GET_BLOCK_PRE_AIO:
if (blkaddr == NULL_ADDR) {
prealloc++;
last_ofs_in_node = dn.ofs_in_node;
}
break;
case F2FS_GET_BLOCK_PRE_DIO:
case F2FS_GET_BLOCK_DIO:
err = __allocate_data_block(&dn, map->m_seg_type);
if (err)
goto sync_out;
if (flag == F2FS_GET_BLOCK_PRE_DIO)
file_need_truncate(inode);
set_inode_flag(inode, FI_APPEND_WRITE);
break;
default:
WARN_ON_ONCE(1);
err = -EIO;
goto sync_out;
}
blkaddr = dn.data_blkaddr;
if (is_hole)
map->m_flags |= F2FS_MAP_NEW;
} else if (is_hole) {
if (f2fs_compressed_file(inode) &&
f2fs_sanity_check_cluster(&dn)) {
err = -EFSCORRUPTED;
f2fs_handle_error(sbi,
ERROR_CORRUPTED_CLUSTER);
goto sync_out;
}
switch (flag) {
case F2FS_GET_BLOCK_PRECACHE:
goto sync_out;
case F2FS_GET_BLOCK_BMAP:
map->m_pblk = 0;
goto sync_out;
case F2FS_GET_BLOCK_FIEMAP:
if (blkaddr == NULL_ADDR) {
if (map->m_next_pgofs)
*map->m_next_pgofs = pgofs + 1;
goto sync_out;
}
break;
case F2FS_GET_BLOCK_DIO:
if (map->m_next_pgofs)
*map->m_next_pgofs = pgofs + 1;
break;
default:
/* 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_multidev_dio)
bidx = f2fs_target_device_index(sbi, blkaddr);
if (map->m_len == 0) {
/* reserved delalloc block should be mapped for fiemap. */
if (blkaddr == NEW_ADDR)
map->m_flags |= F2FS_MAP_DELALLOC;
if (flag != F2FS_GET_BLOCK_DIO || !is_hole)
map->m_flags |= F2FS_MAP_MAPPED;
map->m_pblk = blkaddr;
map->m_len = 1;
if (map->m_multidev_dio)
map->m_bdev = FDEV(bidx).bdev;
} else if (map_is_mergeable(sbi, map, blkaddr, flag, bidx, ofs)) {
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_read_extent_cache_range(&dn,
start_pgofs, map->m_pblk + ofs,
map->m_len - ofs);
}
}
f2fs_put_dnode(&dn);
if (map->m_may_create) {
f2fs_map_unlock(sbi, flag);
f2fs_balance_fs(sbi, dn.node_changed);
}
goto next_dnode;
sync_out:
if (flag == F2FS_GET_BLOCK_DIO && map->m_flags & F2FS_MAP_MAPPED) {
/*
* for hardware encryption, but to avoid potential issue
* in future
*/
f2fs_wait_on_block_writeback_range(inode,
map->m_pblk, map->m_len);
if (map->m_multidev_dio) {
block_t blk_addr = map->m_pblk;
bidx = f2fs_target_device_index(sbi, map->m_pblk);
map->m_bdev = FDEV(bidx).bdev;
map->m_pblk -= FDEV(bidx).start_blk;
if (map->m_may_create)
f2fs_update_device_state(sbi, inode->i_ino,
blk_addr, map->m_len);
f2fs_bug_on(sbi, blk_addr + map->m_len >
FDEV(bidx).end_blk + 1);
}
}
if (flag == F2FS_GET_BLOCK_PRECACHE) {
if (map->m_flags & F2FS_MAP_MAPPED) {
unsigned int ofs = start_pgofs - map->m_lblk;
f2fs_update_read_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) {
f2fs_map_unlock(sbi, flag);
f2fs_balance_fs(sbi, dn.node_changed);
}
out:
trace_f2fs_map_blocks(inode, map, flag, 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, F2FS_GET_BLOCK_DEFAULT);
if (err || map.m_len == 0)
return false;
map.m_lblk += map.m_len;
}
return true;
}
static inline u64 bytes_to_blks(struct inode *inode, u64 bytes)
{
return (bytes >> inode->i_blkbits);
}
static inline u64 blks_to_bytes(struct inode *inode, u64 blks)
{
return (blks << 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, false);
if (err) {
f2fs_put_page(page, 1);
return err;
}
phys = blks_to_bytes(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);
trace_f2fs_fiemap(inode, 0, phys, len, flags, err);
if (err)
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, false);
if (err) {
f2fs_put_page(page, 1);
return err;
}
phys = blks_to_bytes(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);
trace_f2fs_fiemap(inode, 0, phys, len, flags, err);
}
return (err < 0 ? err : 0);
}
static loff_t max_inode_blocks(struct inode *inode)
{
loff_t result = ADDRS_PER_INODE(inode);
loff_t leaf_count = ADDRS_PER_BLOCK(inode);
/* two direct node blocks */
result += (leaf_count * 2);
/* two indirect node blocks */
leaf_count *= NIDS_PER_BLOCK;
result += (leaf_count * 2);
/* one double indirect node block */
leaf_count *= NIDS_PER_BLOCK;
result += leaf_count;
return result;
}
int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
u64 start, u64 len)
{
struct f2fs_map_blocks map;
sector_t start_blk, last_blk;
pgoff_t next_pgofs;
u64 logical = 0, phys = 0, size = 0;
u32 flags = 0;
int ret = 0;
bool compr_cluster = false, compr_appended;
unsigned int cluster_size = F2FS_I(inode)->i_cluster_size;
unsigned int count_in_cluster = 0;
loff_t maxbytes;
if (fieinfo->fi_flags & FIEMAP_FLAG_CACHE) {
ret = f2fs_precache_extents(inode);
if (ret)
return ret;
}
ret = fiemap_prep(inode, fieinfo, start, &len, FIEMAP_FLAG_XATTR);
if (ret)
return ret;
inode_lock_shared(inode);
maxbytes = max_file_blocks(inode) << F2FS_BLKSIZE_BITS;
if (start > maxbytes) {
ret = -EFBIG;
goto out;
}
if (len > maxbytes || (maxbytes - len) < start)
len = maxbytes - start;
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 (bytes_to_blks(inode, len) == 0)
len = blks_to_bytes(inode, 1);
start_blk = bytes_to_blks(inode, start);
last_blk = bytes_to_blks(inode, start + len - 1);
next:
memset(&map, 0, sizeof(map));
map.m_lblk = start_blk;
map.m_len = bytes_to_blks(inode, len);
map.m_next_pgofs = &next_pgofs;
map.m_seg_type = NO_CHECK_TYPE;
if (compr_cluster) {
map.m_lblk += 1;
map.m_len = cluster_size - count_in_cluster;
}
ret = f2fs_map_blocks(inode, &map, F2FS_GET_BLOCK_FIEMAP);
if (ret)
goto out;
/* HOLE */
if (!compr_cluster && !(map.m_flags & F2FS_MAP_FLAGS)) {
start_blk = next_pgofs;
if (blks_to_bytes(inode, start_blk) < blks_to_bytes(inode,
max_inode_blocks(inode)))
goto prep_next;
flags |= FIEMAP_EXTENT_LAST;
}
compr_appended = false;
/* In a case of compressed cluster, append this to the last extent */
if (compr_cluster && ((map.m_flags & F2FS_MAP_DELALLOC) ||
!(map.m_flags & F2FS_MAP_FLAGS))) {
compr_appended = true;
goto skip_fill;
}
if (size) {
flags |= FIEMAP_EXTENT_MERGED;
if (IS_ENCRYPTED(inode))
flags |= FIEMAP_EXTENT_DATA_ENCRYPTED;
ret = fiemap_fill_next_extent(fieinfo, logical,
phys, size, flags);
trace_f2fs_fiemap(inode, logical, phys, size, flags, ret);
if (ret)
goto out;
size = 0;
}
if (start_blk > last_blk)
goto out;
skip_fill:
if (map.m_pblk == COMPRESS_ADDR) {
compr_cluster = true;
count_in_cluster = 1;
} else if (compr_appended) {
unsigned int appended_blks = cluster_size -
count_in_cluster + 1;
size += blks_to_bytes(inode, appended_blks);
start_blk += appended_blks;
compr_cluster = false;
} else {
logical = blks_to_bytes(inode, start_blk);
phys = __is_valid_data_blkaddr(map.m_pblk) ?
blks_to_bytes(inode, map.m_pblk) : 0;
size = blks_to_bytes(inode, map.m_len);
flags = 0;
if (compr_cluster) {
flags = FIEMAP_EXTENT_ENCODED;
count_in_cluster += map.m_len;
if (count_in_cluster == cluster_size) {
compr_cluster = false;
size += blks_to_bytes(inode, 1);
}
} else if (map.m_flags & F2FS_MAP_DELALLOC) {
flags = FIEMAP_EXTENT_UNWRITTEN;
}
start_blk += bytes_to_blks(inode, size);
}
prep_next:
cond_resched();
if (fatal_signal_pending(current))
ret = -EINTR;
else
goto next;
out:
if (ret == 1)
ret = 0;
inode_unlock_shared(inode);
return ret;
}
static inline loff_t f2fs_readpage_limit(struct inode *inode)
{
if (IS_ENABLED(CONFIG_FS_VERITY) && IS_VERITY(inode))
return inode->i_sb->s_maxbytes;
return i_size_read(inode);
}
static inline blk_opf_t f2fs_ra_op_flags(struct readahead_control *rac)
{
return rac ? REQ_RAHEAD : 0;
}
static int f2fs_read_single_page(struct inode *inode, struct folio *folio,
unsigned nr_pages,
struct f2fs_map_blocks *map,
struct bio **bio_ret,
sector_t *last_block_in_bio,
struct readahead_control *rac)
{
struct bio *bio = *bio_ret;
const unsigned blocksize = blks_to_bytes(inode, 1);
sector_t block_in_file;
sector_t last_block;
sector_t last_block_in_file;
sector_t block_nr;
pgoff_t index = folio_index(folio);
int ret = 0;
block_in_file = (sector_t)index;
last_block = block_in_file + nr_pages;
last_block_in_file = bytes_to_blks(inode,
f2fs_readpage_limit(inode) + blocksize - 1);
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, 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;
folio_set_mappedtodisk(folio);
if (!f2fs_is_valid_blkaddr(F2FS_I_SB(inode), block_nr,
DATA_GENERIC_ENHANCE_READ)) {
ret = -EFSCORRUPTED;
goto out;
}
} else {
zero_out:
folio_zero_segment(folio, 0, folio_size(folio));
if (f2fs_need_verity(inode, index) &&
!fsverity_verify_folio(folio)) {
ret = -EIO;
goto out;
}
if (!folio_test_uptodate(folio))
folio_mark_uptodate(folio);
folio_unlock(folio);
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) ||
!f2fs_crypt_mergeable_bio(bio, inode, index, NULL))) {
submit_and_realloc:
f2fs_submit_read_bio(F2FS_I_SB(inode), bio, DATA);
bio = NULL;
}
if (bio == NULL) {
bio = f2fs_grab_read_bio(inode, block_nr, nr_pages,
f2fs_ra_op_flags(rac), index,
false);
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_folio(bio, folio, blocksize, 0))
goto submit_and_realloc;
inc_page_count(F2FS_I_SB(inode), F2FS_RD_DATA);
f2fs_update_iostat(F2FS_I_SB(inode), NULL, FS_DATA_READ_IO,
F2FS_BLKSIZE);
*last_block_in_bio = block_nr;
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,
struct readahead_control *rac, bool for_write)
{
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 blocksize = blks_to_bytes(inode, 1);
struct decompress_io_ctx *dic = NULL;
struct extent_info ei = {};
bool from_dnode = true;
int i;
int ret = 0;
f2fs_bug_on(sbi, f2fs_cluster_is_empty(cc));
last_block_in_file = bytes_to_blks(inode,
f2fs_readpage_limit(inode) + blocksize - 1);
/* 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);
if (for_write)
put_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;
if (f2fs_lookup_read_extent_cache(inode, start_idx, &ei))
from_dnode = false;
if (!from_dnode)
goto skip_reading_dnode;
set_new_dnode(&dn, inode, NULL, NULL, 0);
ret = f2fs_get_dnode_of_data(&dn, start_idx, LOOKUP_NODE);
if (ret)
goto out;
if (unlikely(f2fs_cp_error(sbi))) {
ret = -EIO;
goto out_put_dnode;
}
f2fs_bug_on(sbi, dn.data_blkaddr != COMPRESS_ADDR);
skip_reading_dnode:
for (i = 1; i < cc->cluster_size; i++) {
block_t blkaddr;
blkaddr = from_dnode ? data_blkaddr(dn.inode, dn.node_page,
dn.ofs_in_node + i) :
ei.blk + i - 1;
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++;
if (!from_dnode && i >= ei.c_len)
break;
}
/* 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 < cc->nr_cpages; i++) {
struct page *page = dic->cpages[i];
block_t blkaddr;
struct bio_post_read_ctx *ctx;
blkaddr = from_dnode ? data_blkaddr(dn.inode, dn.node_page,
dn.ofs_in_node + i + 1) :
ei.blk + i;
f2fs_wait_on_block_writeback(inode, blkaddr);
if (f2fs_load_compressed_page(sbi, page, blkaddr)) {
if (atomic_dec_and_test(&dic->remaining_pages)) {
f2fs_decompress_cluster(dic, true);
break;
}
continue;
}
if (bio && (!page_is_mergeable(sbi, bio,
*last_block_in_bio, blkaddr) ||
!f2fs_crypt_mergeable_bio(bio, inode, page->index, NULL))) {
submit_and_realloc:
f2fs_submit_read_bio(sbi, bio, DATA);
bio = NULL;
}
if (!bio) {
bio = f2fs_grab_read_bio(inode, blkaddr, nr_pages,
f2fs_ra_op_flags(rac),
page->index, for_write);
if (IS_ERR(bio)) {
ret = PTR_ERR(bio);
f2fs_decompress_end_io(dic, ret, true);
f2fs_put_dnode(&dn);
*bio_ret = NULL;
return ret;
}
}
if (bio_add_page(bio, page, blocksize, 0) < blocksize)
goto submit_and_realloc;
ctx = get_post_read_ctx(bio);
ctx->enabled_steps |= STEP_DECOMPRESS;
refcount_inc(&dic->refcnt);
inc_page_count(sbi, F2FS_RD_DATA);
f2fs_update_iostat(sbi, inode, FS_DATA_READ_IO, F2FS_BLKSIZE);
*last_block_in_bio = blkaddr;
}
if (from_dnode)
f2fs_put_dnode(&dn);
*bio_ret = bio;
return 0;
out_put_dnode:
if (from_dnode)
f2fs_put_dnode(&dn);
out:
for (i = 0; i < cc->cluster_size; i++) {
if (cc->rpages[i]) {
ClearPageUptodate(cc->rpages[i]);
unlock_page(cc->rpages[i]);
}
}
*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.
*/
static int f2fs_mpage_readpages(struct inode *inode,
struct readahead_control *rac, struct folio *folio)
{
struct bio *bio = NULL;
sector_t last_block_in_bio = 0;
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,
};
pgoff_t nc_cluster_idx = NULL_CLUSTER;
#endif
unsigned nr_pages = rac ? readahead_count(rac) : 1;
unsigned max_nr_pages = nr_pages;
pgoff_t index;
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 (rac) {
folio = readahead_folio(rac);
prefetchw(&folio->flags);
}
index = folio_index(folio);
#ifdef CONFIG_F2FS_FS_COMPRESSION
if (!f2fs_compressed_file(inode))
goto read_single_page;
/* there are remained compressed pages, submit them */
if (!f2fs_cluster_can_merge_page(&cc, index)) {
ret = f2fs_read_multi_pages(&cc, &bio,
max_nr_pages,
&last_block_in_bio,
rac, false);
f2fs_destroy_compress_ctx(&cc, false);
if (ret)
goto set_error_page;
}
if (cc.cluster_idx == NULL_CLUSTER) {
if (nc_cluster_idx == index >> cc.log_cluster_size)
goto read_single_page;
ret = f2fs_is_compressed_cluster(inode, index);
if (ret < 0)
goto set_error_page;
else if (!ret) {
nc_cluster_idx =
index >> cc.log_cluster_size;
goto read_single_page;
}
nc_cluster_idx = NULL_CLUSTER;
}
ret = f2fs_init_compress_ctx(&cc);
if (ret)
goto set_error_page;
f2fs_compress_ctx_add_page(&cc, &folio->page);
goto next_page;
read_single_page:
#endif
ret = f2fs_read_single_page(inode, folio, max_nr_pages, &map,
&bio, &last_block_in_bio, rac);
if (ret) {
#ifdef CONFIG_F2FS_FS_COMPRESSION
set_error_page:
#endif
folio_zero_segment(folio, 0, folio_size(folio));
folio_unlock(folio);
}
#ifdef CONFIG_F2FS_FS_COMPRESSION
next_page:
#endif
#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,
rac, false);
f2fs_destroy_compress_ctx(&cc, false);
}
}
#endif
}
if (bio)
f2fs_submit_read_bio(F2FS_I_SB(inode), bio, DATA);
return ret;
}
static int f2fs_read_data_folio(struct file *file, struct folio *folio)
{
struct inode *inode = folio_file_mapping(folio)->host;
int ret = -EAGAIN;
trace_f2fs_readpage(folio, DATA);
if (!f2fs_is_compress_backend_ready(inode)) {
folio_unlock(folio);
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, folio);
if (ret == -EAGAIN)
ret = f2fs_mpage_readpages(inode, NULL, folio);
return ret;
}
static void f2fs_readahead(struct readahead_control *rac)
{
struct inode *inode = rac->mapping->host;
trace_f2fs_readpages(inode, readahead_index(rac), readahead_count(rac));
if (!f2fs_is_compress_backend_ready(inode))
return;
/* If the file has inline data, skip readahead */
if (f2fs_has_inline_data(inode))
return;
f2fs_mpage_readpages(inode, rac, NULL);
}
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;
if (fscrypt_inode_uses_inline_crypto(inode))
return 0;
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);
memalloc_retry_wait(GFP_NOFS);
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);
if (IS_F2FS_IPU_HONOR_OPU_WRITE(sbi) &&
is_inode_flag_set(inode, FI_OPU_WRITE))
return false;
if (IS_F2FS_IPU_FORCE(sbi))
return true;
if (IS_F2FS_IPU_SSR(sbi) && f2fs_need_SSR(sbi))
return true;
if (IS_F2FS_IPU_UTIL(sbi) && utilization(sbi) > SM_I(sbi)->min_ipu_util)
return true;
if (IS_F2FS_IPU_SSR_UTIL(sbi) && f2fs_need_SSR(sbi) &&
utilization(sbi) > SM_I(sbi)->min_ipu_util)
return true;
/*
* IPU for rewrite async pages
*/
if (IS_F2FS_IPU_ASYNC(sbi) && fio && fio->op == REQ_OP_WRITE &&
!(fio->op_flags & REQ_SYNC) && !IS_ENCRYPTED(inode))
return true;
/* this is only set during fdatasync */
if (IS_F2FS_IPU_FSYNC(sbi) && 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)
{
/* swap file is migrating in aligned write mode */
if (is_inode_flag_set(inode, FI_ALIGNED_WRITE))
return false;
if (f2fs_is_pinned_file(inode))
return true;
/* if this is cold file, we should overwrite to avoid fragmentation */
if (file_is_cold(inode) && !is_inode_flag_set(inode, FI_OPU_WRITE))
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);
/* The below cases were checked when setting it. */
if (f2fs_is_pinned_file(inode))
return false;
if (fio && is_sbi_flag_set(sbi, SBI_NEED_FSCK))
return true;
if (f2fs_lfs_mode(sbi))
return true;
if (S_ISDIR(inode->i_mode))
return true;
if (IS_NOQUOTA(inode))
return true;
if (f2fs_used_in_atomic_write(inode))
return true;
/* rewrite low ratio compress data w/ OPU mode to avoid fragmentation */
if (f2fs_compressed_file(inode) &&
F2FS_OPTION(sbi).compress_mode == COMPR_MODE_USER &&
is_inode_flag_set(inode, FI_ENABLE_COMPRESS))
return true;
/* swap file is migrating in aligned write mode */
if (is_inode_flag_set(inode, FI_ALIGNED_WRITE))
return true;
if (is_inode_flag_set(inode, FI_OPU_WRITE))
return true;
if (fio) {
if (page_private_gcing(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 node_info ni;
bool ipu_force = false;
int err = 0;
/* Use COW inode to make dnode_of_data for atomic write */
if (f2fs_is_atomic_file(inode))
set_new_dnode(&dn, F2FS_I(inode)->cow_inode, NULL, NULL, 0);
else
set_new_dnode(&dn, inode, NULL, NULL, 0);
if (need_inplace_update(fio) &&
f2fs_lookup_read_extent_cache_block(inode, page->index,
&fio->old_blkaddr)) {
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_page_private_gcing(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;
}
/* wait for GCed page writeback via META_MAPPING */
if (fio->meta_gc)
f2fs_wait_on_block_writeback(inode, fio->old_blkaddr);
/*
* 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);
f2fs_put_dnode(&dn);
if (fio->need_lock == LOCK_REQ)
f2fs_unlock_op(fio->sbi);
err = f2fs_inplace_write_data(fio);
if (err) {
if (fscrypt_inode_uses_fs_layer_crypto(inode))
fscrypt_finalize_bounce_page(&fio->encrypted_page);
end_page_writeback(page);
} else {
set_inode_flag(inode, FI_UPDATE_WRITE);
}
trace_f2fs_do_write_data_page(page_folio(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, false);
if (err)
goto out_writepage;
fio->version = ni.version;
err = f2fs_encrypt_one_page(fio);
if (err)
goto out_writepage;
set_page_writeback(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_folio(page), OPU);
set_inode_flag(inode, FI_APPEND_WRITE);
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,
bool allow_balance)
{
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;
bool quota_inode = IS_NOQUOTA(inode);
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 = 0,
.compr_blocks = compr_blocks,
.need_lock = compr_blocks ? LOCK_DONE : LOCK_RETRY,
.meta_gc = f2fs_meta_inode_gc_required(inode) ? 1 : 0,
.io_type = io_type,
.io_wbc = wbc,
.bio = bio,
.last_block = last_block,
};
trace_f2fs_writepage(page_folio(page), DATA);
/* we should bypass data pages to proceed the kworker 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) &&
!is_sbi_flag_set(sbi, SBI_IS_CLOSE))
goto redirty_out;
/* keep data pages in remount-ro mode */
if (F2FS_OPTION(sbi).errors == MOUNT_ERRORS_READONLY)
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:
/* Dentry/quota blocks are controlled by checkpoint */
if (S_ISDIR(inode->i_mode) || quota_inode) {
/*
* We need to wait for node_write to avoid block allocation during
* checkpoint. This can only happen to quota writes which can cause
* the below discard race condition.
*/
if (quota_inode)
f2fs_down_read(&sbi->node_write);
fio.need_lock = LOCK_DONE;
err = f2fs_do_write_data_page(&fio);
if (quota_inode)
f2fs_up_read(&sbi->node_write);
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) {
f2fs_bug_on(sbi, compr_blocks);
fio.need_lock = LOCK_REQ;
err = f2fs_do_write_data_page(&fio);
}
}
if (err) {
file_set_keep_isize(inode);
} else {
spin_lock(&F2FS_I(inode)->i_size_lock);
if (F2FS_I(inode)->last_disk_size < psize)
F2FS_I(inode)->last_disk_size = psize;
spin_unlock(&F2FS_I(inode)->i_size_lock);
}
done:
if (err && err != -ENOENT)
goto redirty_out;
out:
inode_dec_dirty_pages(inode);
if (err) {
ClearPageUptodate(page);
clear_page_private_gcing(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)->wb_task && allow_balance)
f2fs_balance_fs(sbi, need_balance_fs);
if (unlikely(f2fs_cp_error(sbi))) {
f2fs_submit_merged_write(sbi, DATA);
if (bio && *bio)
f2fs_submit_merged_ipu_write(sbi, bio, NULL);
submitted = NULL;
}
if (submitted)
*submitted = fio.submitted;
return 0;
redirty_out:
redirty_page_for_writepage(wbc, page);
/*
* pageout() in MM translates 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 (!err || wbc->for_reclaim)
return AOP_WRITEPAGE_ACTIVATE;
unlock_page(page);
return err;
}
static int f2fs_write_data_page(struct page *page,
struct writeback_control *wbc)
{
#ifdef CONFIG_F2FS_FS_COMPRESSION
struct inode *inode = page->mapping->host;
if (unlikely(f2fs_cp_error(F2FS_I_SB(inode))))
goto out;
if (f2fs_compressed_file(inode)) {
if (f2fs_is_compressed_cluster(inode, page->index)) {
redirty_page_for_writepage(wbc, page);
return AOP_WRITEPAGE_ACTIVATE;
}
}
out:
#endif
return f2fs_write_single_data_page(page, NULL, NULL, NULL,
wbc, FS_DATA_IO, 0, true);
}
/*
* This function was copied from write_cache_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, retry = 0;
struct page *pages_local[F2FS_ONSTACK_PAGES];
struct page **pages = pages_local;
struct folio_batch fbatch;
struct f2fs_sb_info *sbi = F2FS_M_SB(mapping);
struct bio *bio = NULL;
sector_t last_block;
#ifdef CONFIG_F2FS_FS_COMPRESSION
struct inode *inode = mapping->host;
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,
.nr_rpages = 0,
.cpages = NULL,
.valid_nr_cpages = 0,
.rbuf = NULL,
.cbuf = NULL,
.rlen = PAGE_SIZE * F2FS_I(inode)->i_cluster_size,
.private = NULL,
};
#endif
int nr_folios, p, idx;
int nr_pages;
unsigned int max_pages = F2FS_ONSTACK_PAGES;
pgoff_t index;
pgoff_t end; /* Inclusive */
pgoff_t done_index;
int range_whole = 0;
xa_mark_t tag;
int nwritten = 0;
int submitted = 0;
int i;
#ifdef CONFIG_F2FS_FS_COMPRESSION
if (f2fs_compressed_file(inode) &&
1 << cc.log_cluster_size > F2FS_ONSTACK_PAGES) {
pages = f2fs_kzalloc(sbi, sizeof(struct page *) <<
cc.log_cluster_size, GFP_NOFS | __GFP_NOFAIL);