Google Git
Sign in
android-kvm / linux / 6cd90e5ea72f35fa40f971c419e16142cd8272bf / . / fs / f2fs / file.c
blob: 168f085070046e81fc48d298afdf8e2ca4ae1a39 [file] [log] [blame]
// SPDX-License-Identifier: GPL-2.0
/*
* fs/f2fs/file.c
*
* Copyright (c) 2012 Samsung Electronics Co., Ltd.
* http://www.samsung.com/
*/
#include <linux/fs.h>
#include <linux/f2fs_fs.h>
#include <linux/stat.h>
#include <linux/buffer_head.h>
#include <linux/writeback.h>
#include <linux/blkdev.h>
#include <linux/falloc.h>
#include <linux/types.h>
#include <linux/compat.h>
#include <linux/uaccess.h>
#include <linux/mount.h>
#include <linux/pagevec.h>
#include <linux/uio.h>
#include <linux/uuid.h>
#include <linux/file.h>
#include <linux/nls.h>
#include <linux/sched/signal.h>
#include <linux/fileattr.h>
#include <linux/fadvise.h>
#include <linux/iomap.h>
#include "f2fs.h"
#include "node.h"
#include "segment.h"
#include "xattr.h"
#include "acl.h"
#include "gc.h"
#include "iostat.h"
#include <trace/events/f2fs.h>
#include <uapi/linux/f2fs.h>
static vm_fault_t f2fs_filemap_fault(struct vm_fault *vmf)
{
struct inode *inode = file_inode(vmf->vma->vm_file);
vm_flags_t flags = vmf->vma->vm_flags;
vm_fault_t ret;
ret = filemap_fault(vmf);
if (ret & VM_FAULT_LOCKED)
f2fs_update_iostat(F2FS_I_SB(inode), inode,
APP_MAPPED_READ_IO, F2FS_BLKSIZE);
trace_f2fs_filemap_fault(inode, vmf->pgoff, flags, ret);
return ret;
}
static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf)
{
struct page *page = vmf->page;
struct inode *inode = file_inode(vmf->vma->vm_file);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct dnode_of_data dn;
bool need_alloc = !f2fs_is_pinned_file(inode);
int err = 0;
vm_fault_t ret;
if (unlikely(IS_IMMUTABLE(inode)))
return VM_FAULT_SIGBUS;
if (is_inode_flag_set(inode, FI_COMPRESS_RELEASED)) {
err = -EIO;
goto out;
}
if (unlikely(f2fs_cp_error(sbi))) {
err = -EIO;
goto out;
}
if (!f2fs_is_checkpoint_ready(sbi)) {
err = -ENOSPC;
goto out;
}
err = f2fs_convert_inline_inode(inode);
if (err)
goto out;
#ifdef CONFIG_F2FS_FS_COMPRESSION
if (f2fs_compressed_file(inode)) {
int ret = f2fs_is_compressed_cluster(inode, page->index);
if (ret < 0) {
err = ret;
goto out;
} else if (ret) {
need_alloc = false;
}
}
#endif
/* should do out of any locked page */
if (need_alloc)
f2fs_balance_fs(sbi, true);
sb_start_pagefault(inode->i_sb);
f2fs_bug_on(sbi, f2fs_has_inline_data(inode));
file_update_time(vmf->vma->vm_file);
filemap_invalidate_lock_shared(inode->i_mapping);
lock_page(page);
if (unlikely(page->mapping != inode->i_mapping ||
page_offset(page) > i_size_read(inode) ||
!PageUptodate(page))) {
unlock_page(page);
err = -EFAULT;
goto out_sem;
}
set_new_dnode(&dn, inode, NULL, NULL, 0);
if (need_alloc) {
/* block allocation */
err = f2fs_get_block_locked(&dn, page->index);
} else {
err = f2fs_get_dnode_of_data(&dn, page->index, LOOKUP_NODE);
f2fs_put_dnode(&dn);
if (f2fs_is_pinned_file(inode) &&
!__is_valid_data_blkaddr(dn.data_blkaddr))
err = -EIO;
}
if (err) {
unlock_page(page);
goto out_sem;
}
f2fs_wait_on_page_writeback(page, DATA, false, true);
/* wait for GCed page writeback via META_MAPPING */
f2fs_wait_on_block_writeback(inode, dn.data_blkaddr);
/*
* check to see if the page is mapped already (no holes)
*/
if (PageMappedToDisk(page))
goto out_sem;
/* page is wholly or partially inside EOF */
if (((loff_t)(page->index + 1) << PAGE_SHIFT) >
i_size_read(inode)) {
loff_t offset;
offset = i_size_read(inode) & ~PAGE_MASK;
zero_user_segment(page, offset, PAGE_SIZE);
}
set_page_dirty(page);
f2fs_update_iostat(sbi, inode, APP_MAPPED_IO, F2FS_BLKSIZE);
f2fs_update_time(sbi, REQ_TIME);
out_sem:
filemap_invalidate_unlock_shared(inode->i_mapping);
sb_end_pagefault(inode->i_sb);
out:
ret = vmf_fs_error(err);
trace_f2fs_vm_page_mkwrite(inode, page->index, vmf->vma->vm_flags, ret);
return ret;
}
static const struct vm_operations_struct f2fs_file_vm_ops = {
.fault = f2fs_filemap_fault,
.map_pages = filemap_map_pages,
.page_mkwrite = f2fs_vm_page_mkwrite,
};
static int get_parent_ino(struct inode *inode, nid_t *pino)
{
struct dentry *dentry;
/*
* Make sure to get the non-deleted alias. The alias associated with
* the open file descriptor being fsync()'ed may be deleted already.
*/
dentry = d_find_alias(inode);
if (!dentry)
return 0;
*pino = d_parent_ino(dentry);
dput(dentry);
return 1;
}
static inline enum cp_reason_type need_do_checkpoint(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
enum cp_reason_type cp_reason = CP_NO_NEEDED;
if (!S_ISREG(inode->i_mode))
cp_reason = CP_NON_REGULAR;
else if (f2fs_compressed_file(inode))
cp_reason = CP_COMPRESSED;
else if (inode->i_nlink != 1)
cp_reason = CP_HARDLINK;
else if (is_sbi_flag_set(sbi, SBI_NEED_CP))
cp_reason = CP_SB_NEED_CP;
else if (file_wrong_pino(inode))
cp_reason = CP_WRONG_PINO;
else if (!f2fs_space_for_roll_forward(sbi))
cp_reason = CP_NO_SPC_ROLL;
else if (!f2fs_is_checkpointed_node(sbi, F2FS_I(inode)->i_pino))
cp_reason = CP_NODE_NEED_CP;
else if (test_opt(sbi, FASTBOOT))
cp_reason = CP_FASTBOOT_MODE;
else if (F2FS_OPTION(sbi).active_logs == 2)
cp_reason = CP_SPEC_LOG_NUM;
else if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_STRICT &&
f2fs_need_dentry_mark(sbi, inode->i_ino) &&
f2fs_exist_written_data(sbi, F2FS_I(inode)->i_pino,
TRANS_DIR_INO))
cp_reason = CP_RECOVER_DIR;
return cp_reason;
}
static bool need_inode_page_update(struct f2fs_sb_info *sbi, nid_t ino)
{
struct page *i = find_get_page(NODE_MAPPING(sbi), ino);
bool ret = false;
/* But we need to avoid that there are some inode updates */
if ((i && PageDirty(i)) || f2fs_need_inode_block_update(sbi, ino))
ret = true;
f2fs_put_page(i, 0);
return ret;
}
static void try_to_fix_pino(struct inode *inode)
{
struct f2fs_inode_info *fi = F2FS_I(inode);
nid_t pino;
f2fs_down_write(&fi->i_sem);
if (file_wrong_pino(inode) && inode->i_nlink == 1 &&
get_parent_ino(inode, &pino)) {
f2fs_i_pino_write(inode, pino);
file_got_pino(inode);
}
f2fs_up_write(&fi->i_sem);
}
static int f2fs_do_sync_file(struct file *file, loff_t start, loff_t end,
int datasync, bool atomic)
{
struct inode *inode = file->f_mapping->host;
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
nid_t ino = inode->i_ino;
int ret = 0;
enum cp_reason_type cp_reason = 0;
struct writeback_control wbc = {
.sync_mode = WB_SYNC_ALL,
.nr_to_write = LONG_MAX,
.for_reclaim = 0,
};
unsigned int seq_id = 0;
if (unlikely(f2fs_readonly(inode->i_sb)))
return 0;
trace_f2fs_sync_file_enter(inode);
if (S_ISDIR(inode->i_mode))
goto go_write;
/* if fdatasync is triggered, let's do in-place-update */
if (datasync || get_dirty_pages(inode) <= SM_I(sbi)->min_fsync_blocks)
set_inode_flag(inode, FI_NEED_IPU);
ret = file_write_and_wait_range(file, start, end);
clear_inode_flag(inode, FI_NEED_IPU);
if (ret || is_sbi_flag_set(sbi, SBI_CP_DISABLED)) {
trace_f2fs_sync_file_exit(inode, cp_reason, datasync, ret);
return ret;
}
/* if the inode is dirty, let's recover all the time */
if (!f2fs_skip_inode_update(inode, datasync)) {
f2fs_write_inode(inode, NULL);
goto go_write;
}
/*
* if there is no written data, don't waste time to write recovery info.
*/
if (!is_inode_flag_set(inode, FI_APPEND_WRITE) &&
!f2fs_exist_written_data(sbi, ino, APPEND_INO)) {
/* it may call write_inode just prior to fsync */
if (need_inode_page_update(sbi, ino))
goto go_write;
if (is_inode_flag_set(inode, FI_UPDATE_WRITE) ||
f2fs_exist_written_data(sbi, ino, UPDATE_INO))
goto flush_out;
goto out;
} else {
/*
* for OPU case, during fsync(), node can be persisted before
* data when lower device doesn't support write barrier, result
* in data corruption after SPO.
* So for strict fsync mode, force to use atomic write semantics
* to keep write order in between data/node and last node to
* avoid potential data corruption.
*/
if (F2FS_OPTION(sbi).fsync_mode ==
FSYNC_MODE_STRICT && !atomic)
atomic = true;
}
go_write:
/*
* Both of fdatasync() and fsync() are able to be recovered from
* sudden-power-off.
*/
f2fs_down_read(&F2FS_I(inode)->i_sem);
cp_reason = need_do_checkpoint(inode);
f2fs_up_read(&F2FS_I(inode)->i_sem);
if (cp_reason) {
/* all the dirty node pages should be flushed for POR */
ret = f2fs_sync_fs(inode->i_sb, 1);
/*
* We've secured consistency through sync_fs. Following pino
* will be used only for fsynced inodes after checkpoint.
*/
try_to_fix_pino(inode);
clear_inode_flag(inode, FI_APPEND_WRITE);
clear_inode_flag(inode, FI_UPDATE_WRITE);
goto out;
}
sync_nodes:
atomic_inc(&sbi->wb_sync_req[NODE]);
ret = f2fs_fsync_node_pages(sbi, inode, &wbc, atomic, &seq_id);
atomic_dec(&sbi->wb_sync_req[NODE]);
if (ret)
goto out;
/* if cp_error was enabled, we should avoid infinite loop */
if (unlikely(f2fs_cp_error(sbi))) {
ret = -EIO;
goto out;
}
if (f2fs_need_inode_block_update(sbi, ino)) {
f2fs_mark_inode_dirty_sync(inode, true);
f2fs_write_inode(inode, NULL);
goto sync_nodes;
}
/*
* If it's atomic_write, it's just fine to keep write ordering. So
* here we don't need to wait for node write completion, since we use
* node chain which serializes node blocks. If one of node writes are
* reordered, we can see simply broken chain, resulting in stopping
* roll-forward recovery. It means we'll recover all or none node blocks
* given fsync mark.
*/
if (!atomic) {
ret = f2fs_wait_on_node_pages_writeback(sbi, seq_id);
if (ret)
goto out;
}
/* once recovery info is written, don't need to tack this */
f2fs_remove_ino_entry(sbi, ino, APPEND_INO);
clear_inode_flag(inode, FI_APPEND_WRITE);
flush_out:
if ((!atomic && F2FS_OPTION(sbi).fsync_mode != FSYNC_MODE_NOBARRIER) ||
(atomic && !test_opt(sbi, NOBARRIER) && f2fs_sb_has_blkzoned(sbi)))
ret = f2fs_issue_flush(sbi, inode->i_ino);
if (!ret) {
f2fs_remove_ino_entry(sbi, ino, UPDATE_INO);
clear_inode_flag(inode, FI_UPDATE_WRITE);
f2fs_remove_ino_entry(sbi, ino, FLUSH_INO);
}
f2fs_update_time(sbi, REQ_TIME);
out:
trace_f2fs_sync_file_exit(inode, cp_reason, datasync, ret);
return ret;
}
int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
{
if (unlikely(f2fs_cp_error(F2FS_I_SB(file_inode(file)))))
return -EIO;
return f2fs_do_sync_file(file, start, end, datasync, false);
}
static bool __found_offset(struct address_space *mapping,
struct dnode_of_data *dn, pgoff_t index, int whence)
{
block_t blkaddr = f2fs_data_blkaddr(dn);
struct inode *inode = mapping->host;
bool compressed_cluster = false;
if (f2fs_compressed_file(inode)) {
block_t first_blkaddr = data_blkaddr(dn->inode, dn->node_page,
ALIGN_DOWN(dn->ofs_in_node, F2FS_I(inode)->i_cluster_size));
compressed_cluster = first_blkaddr == COMPRESS_ADDR;
}
switch (whence) {
case SEEK_DATA:
if (__is_valid_data_blkaddr(blkaddr))
return true;
if (blkaddr == NEW_ADDR &&
xa_get_mark(&mapping->i_pages, index, PAGECACHE_TAG_DIRTY))
return true;
if (compressed_cluster)
return true;
break;
case SEEK_HOLE:
if (compressed_cluster)
return false;
if (blkaddr == NULL_ADDR)
return true;
break;
}
return false;
}
static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence)
{
struct inode *inode = file->f_mapping->host;
loff_t maxbytes = inode->i_sb->s_maxbytes;
struct dnode_of_data dn;
pgoff_t pgofs, end_offset;
loff_t data_ofs = offset;
loff_t isize;
int err = 0;
inode_lock_shared(inode);
isize = i_size_read(inode);
if (offset >= isize)
goto fail;
/* handle inline data case */
if (f2fs_has_inline_data(inode)) {
if (whence == SEEK_HOLE) {
data_ofs = isize;
goto found;
} else if (whence == SEEK_DATA) {
data_ofs = offset;
goto found;
}
}
pgofs = (pgoff_t)(offset >> PAGE_SHIFT);
for (; data_ofs < isize; data_ofs = (loff_t)pgofs << PAGE_SHIFT) {
set_new_dnode(&dn, inode, NULL, NULL, 0);
err = f2fs_get_dnode_of_data(&dn, pgofs, LOOKUP_NODE);
if (err && err != -ENOENT) {
goto fail;
} else if (err == -ENOENT) {
/* direct node does not exists */
if (whence == SEEK_DATA) {
pgofs = f2fs_get_next_page_offset(&dn, pgofs);
continue;
} else {
goto found;
}
}
end_offset = ADDRS_PER_PAGE(dn.node_page, inode);
/* find data/hole in dnode block */
for (; dn.ofs_in_node < end_offset;
dn.ofs_in_node++, pgofs++,
data_ofs = (loff_t)pgofs << PAGE_SHIFT) {
block_t blkaddr;
blkaddr = f2fs_data_blkaddr(&dn);
if (__is_valid_data_blkaddr(blkaddr) &&
!f2fs_is_valid_blkaddr(F2FS_I_SB(inode),
blkaddr, DATA_GENERIC_ENHANCE)) {
f2fs_put_dnode(&dn);
goto fail;
}
if (__found_offset(file->f_mapping, &dn,
pgofs, whence)) {
f2fs_put_dnode(&dn);
goto found;
}
}
f2fs_put_dnode(&dn);
}
if (whence == SEEK_DATA)
goto fail;
found:
if (whence == SEEK_HOLE && data_ofs > isize)
data_ofs = isize;
inode_unlock_shared(inode);
return vfs_setpos(file, data_ofs, maxbytes);
fail:
inode_unlock_shared(inode);
return -ENXIO;
}
static loff_t f2fs_llseek(struct file *file, loff_t offset, int whence)
{
struct inode *inode = file->f_mapping->host;
loff_t maxbytes = inode->i_sb->s_maxbytes;
if (f2fs_compressed_file(inode))
maxbytes = max_file_blocks(inode) << F2FS_BLKSIZE_BITS;
switch (whence) {
case SEEK_SET:
case SEEK_CUR:
case SEEK_END:
return generic_file_llseek_size(file, offset, whence,
maxbytes, i_size_read(inode));
case SEEK_DATA:
case SEEK_HOLE:
if (offset < 0)
return -ENXIO;
return f2fs_seek_block(file, offset, whence);
}
return -EINVAL;
}
static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma)
{
struct inode *inode = file_inode(file);
if (unlikely(f2fs_cp_error(F2FS_I_SB(inode))))
return -EIO;
if (!f2fs_is_compress_backend_ready(inode))
return -EOPNOTSUPP;
file_accessed(file);
vma->vm_ops = &f2fs_file_vm_ops;
f2fs_down_read(&F2FS_I(inode)->i_sem);
set_inode_flag(inode, FI_MMAP_FILE);
f2fs_up_read(&F2FS_I(inode)->i_sem);
return 0;
}
static int finish_preallocate_blocks(struct inode *inode)
{
int ret;
inode_lock(inode);
if (is_inode_flag_set(inode, FI_OPENED_FILE)) {
inode_unlock(inode);
return 0;
}
if (!file_should_truncate(inode)) {
set_inode_flag(inode, FI_OPENED_FILE);
inode_unlock(inode);
return 0;
}
f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
filemap_invalidate_lock(inode->i_mapping);
truncate_setsize(inode, i_size_read(inode));
ret = f2fs_truncate(inode);
filemap_invalidate_unlock(inode->i_mapping);
f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
if (!ret)
set_inode_flag(inode, FI_OPENED_FILE);
inode_unlock(inode);
if (ret)
return ret;
file_dont_truncate(inode);
return 0;
}
static int f2fs_file_open(struct inode *inode, struct file *filp)
{
int err = fscrypt_file_open(inode, filp);
if (err)
return err;
if (!f2fs_is_compress_backend_ready(inode))
return -EOPNOTSUPP;
err = fsverity_file_open(inode, filp);
if (err)
return err;
filp->f_mode |= FMODE_NOWAIT;
filp->f_mode |= FMODE_CAN_ODIRECT;
err = dquot_file_open(inode, filp);
if (err)
return err;
return finish_preallocate_blocks(inode);
}
void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
int nr_free = 0, ofs = dn->ofs_in_node, len = count;
__le32 *addr;
bool compressed_cluster = false;
int cluster_index = 0, valid_blocks = 0;
int cluster_size = F2FS_I(dn->inode)->i_cluster_size;
bool released = !atomic_read(&F2FS_I(dn->inode)->i_compr_blocks);
addr = get_dnode_addr(dn->inode, dn->node_page) + ofs;
/* Assumption: truncation starts with cluster */
for (; count > 0; count--, addr++, dn->ofs_in_node++, cluster_index++) {
block_t blkaddr = le32_to_cpu(*addr);
if (f2fs_compressed_file(dn->inode) &&
!(cluster_index & (cluster_size - 1))) {
if (compressed_cluster)
f2fs_i_compr_blocks_update(dn->inode,
valid_blocks, false);
compressed_cluster = (blkaddr == COMPRESS_ADDR);
valid_blocks = 0;
}
if (blkaddr == NULL_ADDR)
continue;
f2fs_set_data_blkaddr(dn, NULL_ADDR);
if (__is_valid_data_blkaddr(blkaddr)) {
if (time_to_inject(sbi, FAULT_BLKADDR_CONSISTENCE))
continue;
if (!f2fs_is_valid_blkaddr_raw(sbi, blkaddr,
DATA_GENERIC_ENHANCE))
continue;
if (compressed_cluster)
valid_blocks++;
}
f2fs_invalidate_blocks(sbi, blkaddr);
if (!released || blkaddr != COMPRESS_ADDR)
nr_free++;
}
if (compressed_cluster)
f2fs_i_compr_blocks_update(dn->inode, valid_blocks, false);
if (nr_free) {
pgoff_t fofs;
/*
* once we invalidate valid blkaddr in range [ofs, ofs + count],
* we will invalidate all blkaddr in the whole range.
*/
fofs = f2fs_start_bidx_of_node(ofs_of_node(dn->node_page),
dn->inode) + ofs;
f2fs_update_read_extent_cache_range(dn, fofs, 0, len);
f2fs_update_age_extent_cache_range(dn, fofs, len);
dec_valid_block_count(sbi, dn->inode, nr_free);
}
dn->ofs_in_node = ofs;
f2fs_update_time(sbi, REQ_TIME);
trace_f2fs_truncate_data_blocks_range(dn->inode, dn->nid,
dn->ofs_in_node, nr_free);
}
static int truncate_partial_data_page(struct inode *inode, u64 from,
bool cache_only)
{
loff_t offset = from & (PAGE_SIZE - 1);
pgoff_t index = from >> PAGE_SHIFT;
struct address_space *mapping = inode->i_mapping;
struct page *page;
if (!offset && !cache_only)
return 0;
if (cache_only) {
page = find_lock_page(mapping, index);
if (page && PageUptodate(page))
goto truncate_out;
f2fs_put_page(page, 1);
return 0;
}
page = f2fs_get_lock_data_page(inode, index, true);
if (IS_ERR(page))
return PTR_ERR(page) == -ENOENT ? 0 : PTR_ERR(page);
truncate_out:
f2fs_wait_on_page_writeback(page, DATA, true, true);
zero_user(page, offset, PAGE_SIZE - offset);
/* An encrypted inode should have a key and truncate the last page. */
f2fs_bug_on(F2FS_I_SB(inode), cache_only && IS_ENCRYPTED(inode));
if (!cache_only)
set_page_dirty(page);
f2fs_put_page(page, 1);
return 0;
}
int f2fs_do_truncate_blocks(struct inode *inode, u64 from, bool lock)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct dnode_of_data dn;
pgoff_t free_from;
int count = 0, err = 0;
struct page *ipage;
bool truncate_page = false;
trace_f2fs_truncate_blocks_enter(inode, from);
free_from = (pgoff_t)F2FS_BLK_ALIGN(from);
if (free_from >= max_file_blocks(inode))
goto free_partial;
if (lock)
f2fs_lock_op(sbi);
ipage = f2fs_get_node_page(sbi, inode->i_ino);
if (IS_ERR(ipage)) {
err = PTR_ERR(ipage);
goto out;
}
if (f2fs_has_inline_data(inode)) {
f2fs_truncate_inline_inode(inode, ipage, from);
f2fs_put_page(ipage, 1);
truncate_page = true;
goto out;
}
set_new_dnode(&dn, inode, ipage, NULL, 0);
err = f2fs_get_dnode_of_data(&dn, free_from, LOOKUP_NODE_RA);
if (err) {
if (err == -ENOENT)
goto free_next;
goto out;
}
count = ADDRS_PER_PAGE(dn.node_page, inode);
count -= dn.ofs_in_node;
f2fs_bug_on(sbi, count < 0);
if (dn.ofs_in_node || IS_INODE(dn.node_page)) {
f2fs_truncate_data_blocks_range(&dn, count);
free_from += count;
}
f2fs_put_dnode(&dn);
free_next:
err = f2fs_truncate_inode_blocks(inode, free_from);
out:
if (lock)
f2fs_unlock_op(sbi);
free_partial:
/* lastly zero out the first data page */
if (!err)
err = truncate_partial_data_page(inode, from, truncate_page);
trace_f2fs_truncate_blocks_exit(inode, err);
return err;
}
int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock)
{
u64 free_from = from;
int err;
#ifdef CONFIG_F2FS_FS_COMPRESSION
/*
* for compressed file, only support cluster size
* aligned truncation.
*/
if (f2fs_compressed_file(inode))
free_from = round_up(from,
F2FS_I(inode)->i_cluster_size << PAGE_SHIFT);
#endif
err = f2fs_do_truncate_blocks(inode, free_from, lock);
if (err)
return err;
#ifdef CONFIG_F2FS_FS_COMPRESSION
/*
* For compressed file, after release compress blocks, don't allow write
* direct, but we should allow write direct after truncate to zero.
*/
if (f2fs_compressed_file(inode) && !free_from
&& is_inode_flag_set(inode, FI_COMPRESS_RELEASED))
clear_inode_flag(inode, FI_COMPRESS_RELEASED);
if (from != free_from) {
err = f2fs_truncate_partial_cluster(inode, from, lock);
if (err)
return err;
}
#endif
return 0;
}
int f2fs_truncate(struct inode *inode)
{
int err;
if (unlikely(f2fs_cp_error(F2FS_I_SB(inode))))
return -EIO;
if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
S_ISLNK(inode->i_mode)))
return 0;
trace_f2fs_truncate(inode);
if (time_to_inject(F2FS_I_SB(inode), FAULT_TRUNCATE))
return -EIO;
err = f2fs_dquot_initialize(inode);
if (err)
return err;
/* we should check inline_data size */
if (!f2fs_may_inline_data(inode)) {
err = f2fs_convert_inline_inode(inode);
if (err)
return err;
}
err = f2fs_truncate_blocks(inode, i_size_read(inode), true);
if (err)
return err;
inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode));
f2fs_mark_inode_dirty_sync(inode, false);
return 0;
}
static bool f2fs_force_buffered_io(struct inode *inode, int rw)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
if (!fscrypt_dio_supported(inode))
return true;
if (fsverity_active(inode))
return true;
if (f2fs_compressed_file(inode))
return true;
if (f2fs_has_inline_data(inode))
return true;
/* disallow direct IO if any of devices has unaligned blksize */
if (f2fs_is_multi_device(sbi) && !sbi->aligned_blksize)
return true;
/*
* for blkzoned device, fallback direct IO to buffered IO, so
* all IOs can be serialized by log-structured write.
*/
if (f2fs_sb_has_blkzoned(sbi) && (rw == WRITE) &&
!f2fs_is_pinned_file(inode))
return true;
if (is_sbi_flag_set(sbi, SBI_CP_DISABLED))
return true;
return false;
}
int f2fs_getattr(struct mnt_idmap *idmap, const struct path *path,
struct kstat *stat, u32 request_mask, unsigned int query_flags)
{
struct inode *inode = d_inode(path->dentry);
struct f2fs_inode_info *fi = F2FS_I(inode);
struct f2fs_inode *ri = NULL;
unsigned int flags;
if (f2fs_has_extra_attr(inode) &&
f2fs_sb_has_inode_crtime(F2FS_I_SB(inode)) &&
F2FS_FITS_IN_INODE(ri, fi->i_extra_isize, i_crtime)) {
stat->result_mask |= STATX_BTIME;
stat->btime.tv_sec = fi->i_crtime.tv_sec;
stat->btime.tv_nsec = fi->i_crtime.tv_nsec;
}
/*
* Return the DIO alignment restrictions if requested. We only return
* this information when requested, since on encrypted files it might
* take a fair bit of work to get if the file wasn't opened recently.
*
* f2fs sometimes supports DIO reads but not DIO writes. STATX_DIOALIGN
* cannot represent that, so in that case we report no DIO support.
*/
if ((request_mask & STATX_DIOALIGN) && S_ISREG(inode->i_mode)) {
unsigned int bsize = i_blocksize(inode);
stat->result_mask |= STATX_DIOALIGN;
if (!f2fs_force_buffered_io(inode, WRITE)) {
stat->dio_mem_align = bsize;
stat->dio_offset_align = bsize;
}
}
flags = fi->i_flags;
if (flags & F2FS_COMPR_FL)
stat->attributes |= STATX_ATTR_COMPRESSED;
if (flags & F2FS_APPEND_FL)
stat->attributes |= STATX_ATTR_APPEND;
if (IS_ENCRYPTED(inode))
stat->attributes |= STATX_ATTR_ENCRYPTED;
if (flags & F2FS_IMMUTABLE_FL)
stat->attributes |= STATX_ATTR_IMMUTABLE;
if (flags & F2FS_NODUMP_FL)
stat->attributes |= STATX_ATTR_NODUMP;
if (IS_VERITY(inode))
stat->attributes |= STATX_ATTR_VERITY;
stat->attributes_mask |= (STATX_ATTR_COMPRESSED |
STATX_ATTR_APPEND |
STATX_ATTR_ENCRYPTED |
STATX_ATTR_IMMUTABLE |
STATX_ATTR_NODUMP |
STATX_ATTR_VERITY);
generic_fillattr(idmap, request_mask, inode, stat);
/* we need to show initial sectors used for inline_data/dentries */
if ((S_ISREG(inode->i_mode) && f2fs_has_inline_data(inode)) ||
f2fs_has_inline_dentry(inode))
stat->blocks += (stat->size + 511) >> 9;
return 0;
}
#ifdef CONFIG_F2FS_FS_POSIX_ACL
static void __setattr_copy(struct mnt_idmap *idmap,
struct inode *inode, const struct iattr *attr)
{
unsigned int ia_valid = attr->ia_valid;
i_uid_update(idmap, attr, inode);
i_gid_update(idmap, attr, inode);
if (ia_valid & ATTR_ATIME)
inode_set_atime_to_ts(inode, attr->ia_atime);
if (ia_valid & ATTR_MTIME)
inode_set_mtime_to_ts(inode, attr->ia_mtime);
if (ia_valid & ATTR_CTIME)
inode_set_ctime_to_ts(inode, attr->ia_ctime);
if (ia_valid & ATTR_MODE) {
umode_t mode = attr->ia_mode;
if (!in_group_or_capable(idmap, inode, i_gid_into_vfsgid(idmap, inode)))
mode &= ~S_ISGID;
set_acl_inode(inode, mode);
}
}
#else
#define __setattr_copy setattr_copy
#endif
int f2fs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
struct iattr *attr)
{
struct inode *inode = d_inode(dentry);
struct f2fs_inode_info *fi = F2FS_I(inode);
int err;
if (unlikely(f2fs_cp_error(F2FS_I_SB(inode))))
return -EIO;
if (unlikely(IS_IMMUTABLE(inode)))
return -EPERM;
if (unlikely(IS_APPEND(inode) &&
(attr->ia_valid & (ATTR_MODE | ATTR_UID |
ATTR_GID | ATTR_TIMES_SET))))
return -EPERM;
if ((attr->ia_valid & ATTR_SIZE)) {
if (!f2fs_is_compress_backend_ready(inode))
return -EOPNOTSUPP;
if (is_inode_flag_set(inode, FI_COMPRESS_RELEASED) &&
!IS_ALIGNED(attr->ia_size,
F2FS_BLK_TO_BYTES(fi->i_cluster_size)))
return -EINVAL;
}
err = setattr_prepare(idmap, dentry, attr);
if (err)
return err;
err = fscrypt_prepare_setattr(dentry, attr);
if (err)
return err;
err = fsverity_prepare_setattr(dentry, attr);
if (err)
return err;
if (is_quota_modification(idmap, inode, attr)) {
err = f2fs_dquot_initialize(inode);
if (err)
return err;
}
if (i_uid_needs_update(idmap, attr, inode) ||
i_gid_needs_update(idmap, attr, inode)) {
f2fs_lock_op(F2FS_I_SB(inode));
err = dquot_transfer(idmap, inode, attr);
if (err) {
set_sbi_flag(F2FS_I_SB(inode),
SBI_QUOTA_NEED_REPAIR);
f2fs_unlock_op(F2FS_I_SB(inode));
return err;
}
/*
* update uid/gid under lock_op(), so that dquot and inode can
* be updated atomically.
*/
i_uid_update(idmap, attr, inode);
i_gid_update(idmap, attr, inode);
f2fs_mark_inode_dirty_sync(inode, true);
f2fs_unlock_op(F2FS_I_SB(inode));
}
if (attr->ia_valid & ATTR_SIZE) {
loff_t old_size = i_size_read(inode);
if (attr->ia_size > MAX_INLINE_DATA(inode)) {
/*
* should convert inline inode before i_size_write to
* keep smaller than inline_data size with inline flag.
*/
err = f2fs_convert_inline_inode(inode);
if (err)
return err;
}
f2fs_down_write(&fi->i_gc_rwsem[WRITE]);
filemap_invalidate_lock(inode->i_mapping);
truncate_setsize(inode, attr->ia_size);
if (attr->ia_size <= old_size)
err = f2fs_truncate(inode);
/*
* do not trim all blocks after i_size if target size is
* larger than i_size.
*/
filemap_invalidate_unlock(inode->i_mapping);
f2fs_up_write(&fi->i_gc_rwsem[WRITE]);
if (err)
return err;
spin_lock(&fi->i_size_lock);
inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode));
fi->last_disk_size = i_size_read(inode);
spin_unlock(&fi->i_size_lock);
}
__setattr_copy(idmap, inode, attr);
if (attr->ia_valid & ATTR_MODE) {
err = posix_acl_chmod(idmap, dentry, f2fs_get_inode_mode(inode));
if (is_inode_flag_set(inode, FI_ACL_MODE)) {
if (!err)
inode->i_mode = fi->i_acl_mode;
clear_inode_flag(inode, FI_ACL_MODE);
}
}
/* file size may changed here */
f2fs_mark_inode_dirty_sync(inode, true);
/* inode change will produce dirty node pages flushed by checkpoint */
f2fs_balance_fs(F2FS_I_SB(inode), true);
return err;
}
const struct inode_operations f2fs_file_inode_operations = {
.getattr = f2fs_getattr,
.setattr = f2fs_setattr,
.get_inode_acl = f2fs_get_acl,
.set_acl = f2fs_set_acl,
.listxattr = f2fs_listxattr,
.fiemap = f2fs_fiemap,
.fileattr_get = f2fs_fileattr_get,
.fileattr_set = f2fs_fileattr_set,
};
static int fill_zero(struct inode *inode, pgoff_t index,
loff_t start, loff_t len)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct page *page;
if (!len)
return 0;
f2fs_balance_fs(sbi, true);
f2fs_lock_op(sbi);
page = f2fs_get_new_data_page(inode, NULL, index, false);
f2fs_unlock_op(sbi);
if (IS_ERR(page))
return PTR_ERR(page);
f2fs_wait_on_page_writeback(page, DATA, true, true);
zero_user(page, start, len);
set_page_dirty(page);
f2fs_put_page(page, 1);
return 0;
}
int f2fs_truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end)
{
int err;
while (pg_start < pg_end) {
struct dnode_of_data dn;
pgoff_t end_offset, count;
set_new_dnode(&dn, inode, NULL, NULL, 0);
err = f2fs_get_dnode_of_data(&dn, pg_start, LOOKUP_NODE);
if (err) {
if (err == -ENOENT) {
pg_start = f2fs_get_next_page_offset(&dn,
pg_start);
continue;
}
return err;
}
end_offset = ADDRS_PER_PAGE(dn.node_page, inode);
count = min(end_offset - dn.ofs_in_node, pg_end - pg_start);
f2fs_bug_on(F2FS_I_SB(inode), count == 0 || count > end_offset);
f2fs_truncate_data_blocks_range(&dn, count);
f2fs_put_dnode(&dn);
pg_start += count;
}
return 0;
}
static int f2fs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
{
pgoff_t pg_start, pg_end;
loff_t off_start, off_end;
int ret;
ret = f2fs_convert_inline_inode(inode);
if (ret)
return ret;
pg_start = ((unsigned long long) offset) >> PAGE_SHIFT;
pg_end = ((unsigned long long) offset + len) >> PAGE_SHIFT;
off_start = offset & (PAGE_SIZE - 1);
off_end = (offset + len) & (PAGE_SIZE - 1);
if (pg_start == pg_end) {
ret = fill_zero(inode, pg_start, off_start,
off_end - off_start);
if (ret)
return ret;
} else {
if (off_start) {
ret = fill_zero(inode, pg_start++, off_start,
PAGE_SIZE - off_start);
if (ret)
return ret;
}
if (off_end) {
ret = fill_zero(inode, pg_end, 0, off_end);
if (ret)
return ret;
}
if (pg_start < pg_end) {
loff_t blk_start, blk_end;
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
f2fs_balance_fs(sbi, true);
blk_start = (loff_t)pg_start << PAGE_SHIFT;
blk_end = (loff_t)pg_end << PAGE_SHIFT;
f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
filemap_invalidate_lock(inode->i_mapping);
truncate_pagecache_range(inode, blk_start, blk_end - 1);
f2fs_lock_op(sbi);
ret = f2fs_truncate_hole(inode, pg_start, pg_end);
f2fs_unlock_op(sbi);
filemap_invalidate_unlock(inode->i_mapping);
f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
}
}
return ret;
}
static int __read_out_blkaddrs(struct inode *inode, block_t *blkaddr,
int *do_replace, pgoff_t off, pgoff_t len)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct dnode_of_data dn;
int ret, done, i;
next_dnode:
set_new_dnode(&dn, inode, NULL, NULL, 0);
ret = f2fs_get_dnode_of_data(&dn, off, LOOKUP_NODE_RA);
if (ret && ret != -ENOENT) {
return ret;
} else if (ret == -ENOENT) {
if (dn.max_level == 0)
return -ENOENT;
done = min((pgoff_t)ADDRS_PER_BLOCK(inode) -
dn.ofs_in_node, len);
blkaddr += done;
do_replace += done;
goto next;
}
done = min((pgoff_t)ADDRS_PER_PAGE(dn.node_page, inode) -
dn.ofs_in_node, len);
for (i = 0; i < done; i++, blkaddr++, do_replace++, dn.ofs_in_node++) {
*blkaddr = f2fs_data_blkaddr(&dn);
if (__is_valid_data_blkaddr(*blkaddr) &&
!f2fs_is_valid_blkaddr(sbi, *blkaddr,
DATA_GENERIC_ENHANCE)) {
f2fs_put_dnode(&dn);
return -EFSCORRUPTED;
}
if (!f2fs_is_checkpointed_data(sbi, *blkaddr)) {
if (f2fs_lfs_mode(sbi)) {
f2fs_put_dnode(&dn);
return -EOPNOTSUPP;
}
/* do not invalidate this block address */
f2fs_update_data_blkaddr(&dn, NULL_ADDR);
*do_replace = 1;
}
}
f2fs_put_dnode(&dn);
next:
len -= done;
off += done;
if (len)
goto next_dnode;
return 0;
}
static int __roll_back_blkaddrs(struct inode *inode, block_t *blkaddr,
int *do_replace, pgoff_t off, int len)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct dnode_of_data dn;
int ret, i;
for (i = 0; i < len; i++, do_replace++, blkaddr++) {
if (*do_replace == 0)
continue;
set_new_dnode(&dn, inode, NULL, NULL, 0);
ret = f2fs_get_dnode_of_data(&dn, off + i, LOOKUP_NODE_RA);
if (ret) {
dec_valid_block_count(sbi, inode, 1);
f2fs_invalidate_blocks(sbi, *blkaddr);
} else {
f2fs_update_data_blkaddr(&dn, *blkaddr);
}
f2fs_put_dnode(&dn);
}
return 0;
}
static int __clone_blkaddrs(struct inode *src_inode, struct inode *dst_inode,
block_t *blkaddr, int *do_replace,
pgoff_t src, pgoff_t dst, pgoff_t len, bool full)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(src_inode);
pgoff_t i = 0;
int ret;
while (i < len) {
if (blkaddr[i] == NULL_ADDR && !full) {
i++;
continue;
}
if (do_replace[i] || blkaddr[i] == NULL_ADDR) {
struct dnode_of_data dn;
struct node_info ni;
size_t new_size;
pgoff_t ilen;
set_new_dnode(&dn, dst_inode, NULL, NULL, 0);
ret = f2fs_get_dnode_of_data(&dn, dst + i, ALLOC_NODE);
if (ret)
return ret;
ret = f2fs_get_node_info(sbi, dn.nid, &ni, false);
if (ret) {
f2fs_put_dnode(&dn);
return ret;
}
ilen = min((pgoff_t)
ADDRS_PER_PAGE(dn.node_page, dst_inode) -
dn.ofs_in_node, len - i);
do {
dn.data_blkaddr = f2fs_data_blkaddr(&dn);
f2fs_truncate_data_blocks_range(&dn, 1);
if (do_replace[i]) {
f2fs_i_blocks_write(src_inode,
1, false, false);
f2fs_i_blocks_write(dst_inode,
1, true, false);
f2fs_replace_block(sbi, &dn, dn.data_blkaddr,
blkaddr[i], ni.version, true, false);
do_replace[i] = 0;
}
dn.ofs_in_node++;
i++;
new_size = (loff_t)(dst + i) << PAGE_SHIFT;
if (dst_inode->i_size < new_size)
f2fs_i_size_write(dst_inode, new_size);
} while (--ilen && (do_replace[i] || blkaddr[i] == NULL_ADDR));
f2fs_put_dnode(&dn);
} else {
struct page *psrc, *pdst;
psrc = f2fs_get_lock_data_page(src_inode,
src + i, true);
if (IS_ERR(psrc))
return PTR_ERR(psrc);
pdst = f2fs_get_new_data_page(dst_inode, NULL, dst + i,
true);
if (IS_ERR(pdst)) {
f2fs_put_page(psrc, 1);
return PTR_ERR(pdst);
}
f2fs_wait_on_page_writeback(pdst, DATA, true, true);
memcpy_page(pdst, 0, psrc, 0, PAGE_SIZE);
set_page_dirty(pdst);
set_page_private_gcing(pdst);
f2fs_put_page(pdst, 1);
f2fs_put_page(psrc, 1);
ret = f2fs_truncate_hole(src_inode,
src + i, src + i + 1);
if (ret)
return ret;
i++;
}
}
return 0;
}
static int __exchange_data_block(struct inode *src_inode,
struct inode *dst_inode, pgoff_t src, pgoff_t dst,
pgoff_t len, bool full)
{
block_t *src_blkaddr;
int *do_replace;
pgoff_t olen;
int ret;
while (len) {
olen = min((pgoff_t)4 * ADDRS_PER_BLOCK(src_inode), len);
src_blkaddr = f2fs_kvzalloc(F2FS_I_SB(src_inode),
array_size(olen, sizeof(block_t)),
GFP_NOFS);
if (!src_blkaddr)
return -ENOMEM;
do_replace = f2fs_kvzalloc(F2FS_I_SB(src_inode),
array_size(olen, sizeof(int)),
GFP_NOFS);
if (!do_replace) {
kvfree(src_blkaddr);
return -ENOMEM;
}
ret = __read_out_blkaddrs(src_inode, src_blkaddr,
do_replace, src, olen);
if (ret)
goto roll_back;
ret = __clone_blkaddrs(src_inode, dst_inode, src_blkaddr,
do_replace, src, dst, olen, full);
if (ret)
goto roll_back;
src += olen;
dst += olen;
len -= olen;
kvfree(src_blkaddr);
kvfree(do_replace);
}
return 0;
roll_back:
__roll_back_blkaddrs(src_inode, src_blkaddr, do_replace, src, olen);
kvfree(src_blkaddr);
kvfree(do_replace);
return ret;
}
static int f2fs_do_collapse(struct inode *inode, loff_t offset, loff_t len)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
pgoff_t nrpages = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
pgoff_t start = offset >> PAGE_SHIFT;
pgoff_t end = (offset + len) >> PAGE_SHIFT;
int ret;
f2fs_balance_fs(sbi, true);
/* avoid gc operation during block exchange */
f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
filemap_invalidate_lock(inode->i_mapping);
f2fs_lock_op(sbi);
f2fs_drop_extent_tree(inode);
truncate_pagecache(inode, offset);
ret = __exchange_data_block(inode, inode, end, start, nrpages - end, true);
f2fs_unlock_op(sbi);
filemap_invalidate_unlock(inode->i_mapping);
f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
return ret;
}
static int f2fs_collapse_range(struct inode *inode, loff_t offset, loff_t len)
{
loff_t new_size;
int ret;
if (offset + len >= i_size_read(inode))
return -EINVAL;
/* collapse range should be aligned to block size of f2fs. */
if (offset & (F2FS_BLKSIZE - 1) || len & (F2FS_BLKSIZE - 1))
return -EINVAL;
ret = f2fs_convert_inline_inode(inode);
if (ret)
return ret;
/* write out all dirty pages from offset */
ret = filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX);
if (ret)
return ret;
ret = f2fs_do_collapse(inode, offset, len);
if (ret)
return ret;
/* write out all moved pages, if possible */
filemap_invalidate_lock(inode->i_mapping);
filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX);
truncate_pagecache(inode, offset);
new_size = i_size_read(inode) - len;
ret = f2fs_truncate_blocks(inode, new_size, true);
filemap_invalidate_unlock(inode->i_mapping);
if (!ret)
f2fs_i_size_write(inode, new_size);
return ret;
}
static int f2fs_do_zero_range(struct dnode_of_data *dn, pgoff_t start,
pgoff_t end)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
pgoff_t index = start;
unsigned int ofs_in_node = dn->ofs_in_node;
blkcnt_t count = 0;
int ret;
for (; index < end; index++, dn->ofs_in_node++) {
if (f2fs_data_blkaddr(dn) == NULL_ADDR)
count++;
}
dn->ofs_in_node = ofs_in_node;
ret = f2fs_reserve_new_blocks(dn, count);
if (ret)
return ret;
dn->ofs_in_node = ofs_in_node;
for (index = start; index < end; index++, dn->ofs_in_node++) {
dn->data_blkaddr = f2fs_data_blkaddr(dn);
/*
* f2fs_reserve_new_blocks will not guarantee entire block
* allocation.
*/
if (dn->data_blkaddr == NULL_ADDR) {
ret = -ENOSPC;
break;
}
if (dn->data_blkaddr == NEW_ADDR)
continue;
if (!f2fs_is_valid_blkaddr(sbi, dn->data_blkaddr,
DATA_GENERIC_ENHANCE)) {
ret = -EFSCORRUPTED;
break;
}
f2fs_invalidate_blocks(sbi, dn->data_blkaddr);
f2fs_set_data_blkaddr(dn, NEW_ADDR);
}
f2fs_update_read_extent_cache_range(dn, start, 0, index - start);
f2fs_update_age_extent_cache_range(dn, start, index - start);
return ret;
}
static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len,
int mode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct address_space *mapping = inode->i_mapping;
pgoff_t index, pg_start, pg_end;
loff_t new_size = i_size_read(inode);
loff_t off_start, off_end;
int ret = 0;
ret = inode_newsize_ok(inode, (len + offset));
if (ret)
return ret;
ret = f2fs_convert_inline_inode(inode);
if (ret)
return ret;
ret = filemap_write_and_wait_range(mapping, offset, offset + len - 1);
if (ret)
return ret;
pg_start = ((unsigned long long) offset) >> PAGE_SHIFT;
pg_end = ((unsigned long long) offset + len) >> PAGE_SHIFT;
off_start = offset & (PAGE_SIZE - 1);
off_end = (offset + len) & (PAGE_SIZE - 1);
if (pg_start == pg_end) {
ret = fill_zero(inode, pg_start, off_start,
off_end - off_start);
if (ret)
return ret;
new_size = max_t(loff_t, new_size, offset + len);
} else {
if (off_start) {
ret = fill_zero(inode, pg_start++, off_start,
PAGE_SIZE - off_start);
if (ret)
return ret;
new_size = max_t(loff_t, new_size,
(loff_t)pg_start << PAGE_SHIFT);
}
for (index = pg_start; index < pg_end;) {
struct dnode_of_data dn;
unsigned int end_offset;
pgoff_t end;
f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
filemap_invalidate_lock(mapping);
truncate_pagecache_range(inode,
(loff_t)index << PAGE_SHIFT,
((loff_t)pg_end << PAGE_SHIFT) - 1);
f2fs_lock_op(sbi);
set_new_dnode(&dn, inode, NULL, NULL, 0);
ret = f2fs_get_dnode_of_data(&dn, index, ALLOC_NODE);
if (ret) {
f2fs_unlock_op(sbi);
filemap_invalidate_unlock(mapping);
f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
goto out;
}
end_offset = ADDRS_PER_PAGE(dn.node_page, inode);
end = min(pg_end, end_offset - dn.ofs_in_node + index);
ret = f2fs_do_zero_range(&dn, index, end);
f2fs_put_dnode(&dn);
f2fs_unlock_op(sbi);
filemap_invalidate_unlock(mapping);
f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
f2fs_balance_fs(sbi, dn.node_changed);
if (ret)
goto out;
index = end;
new_size = max_t(loff_t, new_size,
(loff_t)index << PAGE_SHIFT);
}
if (off_end) {
ret = fill_zero(inode, pg_end, 0, off_end);
if (ret)
goto out;
new_size = max_t(loff_t, new_size, offset + len);
}
}
out:
if (new_size > i_size_read(inode)) {
if (mode & FALLOC_FL_KEEP_SIZE)
file_set_keep_isize(inode);
else
f2fs_i_size_write(inode, new_size);
}
return ret;
}
static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct address_space *mapping = inode->i_mapping;
pgoff_t nr, pg_start, pg_end, delta, idx;
loff_t new_size;
int ret = 0;
new_size = i_size_read(inode) + len;
ret = inode_newsize_ok(inode, new_size);
if (ret)
return ret;
if (offset >= i_size_read(inode))
return -EINVAL;
/* insert range should be aligned to block size of f2fs. */
if (offset & (F2FS_BLKSIZE - 1) || len & (F2FS_BLKSIZE - 1))
return -EINVAL;
ret = f2fs_convert_inline_inode(inode);
if (ret)
return ret;
f2fs_balance_fs(sbi, true);
filemap_invalidate_lock(mapping);
ret = f2fs_truncate_blocks(inode, i_size_read(inode), true);
filemap_invalidate_unlock(mapping);
if (ret)
return ret;
/* write out all dirty pages from offset */
ret = filemap_write_and_wait_range(mapping, offset, LLONG_MAX);
if (ret)
return ret;
pg_start = offset >> PAGE_SHIFT;
pg_end = (offset + len) >> PAGE_SHIFT;
delta = pg_end - pg_start;
idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
/* avoid gc operation during block exchange */
f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
filemap_invalidate_lock(mapping);
truncate_pagecache(inode, offset);
while (!ret && idx > pg_start) {
nr = idx - pg_start;
if (nr > delta)
nr = delta;
idx -= nr;
f2fs_lock_op(sbi);
f2fs_drop_extent_tree(inode);
ret = __exchange_data_block(inode, inode, idx,
idx + delta, nr, false);
f2fs_unlock_op(sbi);
}
filemap_invalidate_unlock(mapping);
f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
if (ret)
return ret;
/* write out all moved pages, if possible */
filemap_invalidate_lock(mapping);
ret = filemap_write_and_wait_range(mapping, offset, LLONG_MAX);
truncate_pagecache(inode, offset);
filemap_invalidate_unlock(mapping);
if (!ret)
f2fs_i_size_write(inode, new_size);
return ret;
}
static int f2fs_expand_inode_data(struct inode *inode, loff_t offset,
loff_t len, int mode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct f2fs_map_blocks map = { .m_next_pgofs = NULL,
.m_next_extent = NULL, .m_seg_type = NO_CHECK_TYPE,
.m_may_create = true };
struct f2fs_gc_control gc_control = { .victim_segno = NULL_SEGNO,
.init_gc_type = FG_GC,
.should_migrate_blocks = false,
.err_gc_skipped = true,
.nr_free_secs = 0 };
pgoff_t pg_start, pg_end;
loff_t new_size;
loff_t off_end;
block_t expanded = 0;
int err;
err = inode_newsize_ok(inode, (len + offset));
if (err)
return err;
err = f2fs_convert_inline_inode(inode);
if (err)
return err;
f2fs_balance_fs(sbi, true);
pg_start = ((unsigned long long)offset) >> PAGE_SHIFT;
pg_end = ((unsigned long long)offset + len) >> PAGE_SHIFT;
off_end = (offset + len) & (PAGE_SIZE - 1);
map.m_lblk = pg_start;
map.m_len = pg_end - pg_start;
if (off_end)
map.m_len++;
if (!map.m_len)
return 0;
if (f2fs_is_pinned_file(inode)) {
block_t sec_blks = CAP_BLKS_PER_SEC(sbi);
block_t sec_len = roundup(map.m_len, sec_blks);
map.m_len = sec_blks;
next_alloc:
if (has_not_enough_free_secs(sbi, 0,
GET_SEC_FROM_SEG(sbi, overprovision_segments(sbi)))) {
f2fs_down_write(&sbi->gc_lock);
stat_inc_gc_call_count(sbi, FOREGROUND);
err = f2fs_gc(sbi, &gc_control);
if (err && err != -ENODATA)
goto out_err;
}
f2fs_down_write(&sbi->pin_sem);
err = f2fs_allocate_pinning_section(sbi);
if (err) {
f2fs_up_write(&sbi->pin_sem);
goto out_err;
}
map.m_seg_type = CURSEG_COLD_DATA_PINNED;
err = f2fs_map_blocks(inode, &map, F2FS_GET_BLOCK_PRE_DIO);
file_dont_truncate(inode);
f2fs_up_write(&sbi->pin_sem);
expanded += map.m_len;
sec_len -= map.m_len;
map.m_lblk += map.m_len;
if (!err && sec_len)
goto next_alloc;
map.m_len = expanded;
} else {
err = f2fs_map_blocks(inode, &map, F2FS_GET_BLOCK_PRE_AIO);
expanded = map.m_len;
}
out_err:
if (err) {
pgoff_t last_off;
if (!expanded)
return err;
last_off = pg_start + expanded - 1;
/* update new size to the failed position */
new_size = (last_off == pg_end) ? offset + len :
(loff_t)(last_off + 1) << PAGE_SHIFT;
} else {
new_size = ((loff_t)pg_end << PAGE_SHIFT) + off_end;
}
if (new_size > i_size_read(inode)) {
if (mode & FALLOC_FL_KEEP_SIZE)
file_set_keep_isize(inode);
else
f2fs_i_size_write(inode, new_size);
}
return err;
}
static long f2fs_fallocate(struct file *file, int mode,
loff_t offset, loff_t len)
{
struct inode *inode = file_inode(file);
long ret = 0;
if (unlikely(f2fs_cp_error(F2FS_I_SB(inode))))
return -EIO;
if (!f2fs_is_checkpoint_ready(F2FS_I_SB(inode)))
return -ENOSPC;
if (!f2fs_is_compress_backend_ready(inode))
return -EOPNOTSUPP;
/* f2fs only support ->fallocate for regular file */
if (!S_ISREG(inode->i_mode))
return -EINVAL;
if (IS_ENCRYPTED(inode) &&
(mode & (FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_INSERT_RANGE)))
return -EOPNOTSUPP;
if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE |
FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE |
FALLOC_FL_INSERT_RANGE))
return -EOPNOTSUPP;
inode_lock(inode);
/*
* Pinned file should not support partial truncation since the block
* can be used by applications.
*/
if ((f2fs_compressed_file(inode) || f2fs_is_pinned_file(inode)) &&
(mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_COLLAPSE_RANGE |
FALLOC_FL_ZERO_RANGE | FALLOC_FL_INSERT_RANGE))) {
ret = -EOPNOTSUPP;
goto out;
}
ret = file_modified(file);
if (ret)
goto out;
if (mode & FALLOC_FL_PUNCH_HOLE) {
if (offset >= inode->i_size)
goto out;
ret = f2fs_punch_hole(inode, offset, len);
} else if (mode & FALLOC_FL_COLLAPSE_RANGE) {
ret = f2fs_collapse_range(inode, offset, len);
} else if (mode & FALLOC_FL_ZERO_RANGE) {
ret = f2fs_zero_range(inode, offset, len, mode);
} else if (mode & FALLOC_FL_INSERT_RANGE) {
ret = f2fs_insert_range(inode, offset, len);
} else {
ret = f2fs_expand_inode_data(inode, offset, len, mode);
}
if (!ret) {
inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode));
f2fs_mark_inode_dirty_sync(inode, false);
f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
}
out:
inode_unlock(inode);
trace_f2fs_fallocate(inode, mode, offset, len, ret);
return ret;
}
static int f2fs_release_file(struct inode *inode, struct file *filp)
{
/*
* f2fs_release_file is called at every close calls. So we should
* not drop any inmemory pages by close called by other process.
*/
if (!(filp->f_mode & FMODE_WRITE) ||
atomic_read(&inode->i_writecount) != 1)
return 0;
inode_lock(inode);
f2fs_abort_atomic_write(inode, true);
inode_unlock(inode);
return 0;
}
static int f2fs_file_flush(struct file *file, fl_owner_t id)
{
struct inode *inode = file_inode(file);
/*
* If the process doing a transaction is crashed, we should do
* roll-back. Otherwise, other reader/write can see corrupted database
* until all the writers close its file. Since this should be done
* before dropping file lock, it needs to do in ->flush.
*/
if (F2FS_I(inode)->atomic_write_task == current &&
(current->flags & PF_EXITING)) {
inode_lock(inode);
f2fs_abort_atomic_write(inode, true);
inode_unlock(inode);
}
return 0;
}
static int f2fs_setflags_common(struct inode *inode, u32 iflags, u32 mask)
{
struct f2fs_inode_info *fi = F2FS_I(inode);
u32 masked_flags = fi->i_flags & mask;
/* mask can be shrunk by flags_valid selector */
iflags &= mask;
/* Is it quota file? Do not allow user to mess with it */
if (IS_NOQUOTA(inode))
return -EPERM;
if ((iflags ^ masked_flags) & F2FS_CASEFOLD_FL) {
if (!f2fs_sb_has_casefold(F2FS_I_SB(inode)))
return -EOPNOTSUPP;
if (!f2fs_empty_dir(inode))
return -ENOTEMPTY;
}
if (iflags & (F2FS_COMPR_FL | F2FS_NOCOMP_FL)) {
if (!f2fs_sb_has_compression(F2FS_I_SB(inode)))
return -EOPNOTSUPP;
if ((iflags & F2FS_COMPR_FL) && (iflags & F2FS_NOCOMP_FL))
return -EINVAL;
}
if ((iflags ^ masked_flags) & F2FS_COMPR_FL) {
if (masked_flags & F2FS_COMPR_FL) {
if (!f2fs_disable_compressed_file(inode))
return -EINVAL;
} else {
/* try to convert inline_data to support compression */
int err = f2fs_convert_inline_inode(inode);
if (err)
return err;
f2fs_down_write(&fi->i_sem);
if (!f2fs_may_compress(inode) ||
(S_ISREG(inode->i_mode) &&
F2FS_HAS_BLOCKS(inode))) {
f2fs_up_write(&fi->i_sem);
return -EINVAL;
}
err = set_compress_context(inode);
f2fs_up_write(&fi->i_sem);
if (err)
return err;
}
}
fi->i_flags = iflags | (fi->i_flags & ~mask);
f2fs_bug_on(F2FS_I_SB(inode), (fi->i_flags & F2FS_COMPR_FL) &&
(fi->i_flags & F2FS_NOCOMP_FL));
if (fi->i_flags & F2FS_PROJINHERIT_FL)
set_inode_flag(inode, FI_PROJ_INHERIT);
else
clear_inode_flag(inode, FI_PROJ_INHERIT);
inode_set_ctime_current(inode);
f2fs_set_inode_flags(inode);
f2fs_mark_inode_dirty_sync(inode, true);
return 0;
}
/* FS_IOC_[GS]ETFLAGS and FS_IOC_FS[GS]ETXATTR support */
/*
* To make a new on-disk f2fs i_flag gettable via FS_IOC_GETFLAGS, add an entry
* for it to f2fs_fsflags_map[], and add its FS_*_FL equivalent to
* F2FS_GETTABLE_FS_FL. To also make it settable via FS_IOC_SETFLAGS, also add
* its FS_*_FL equivalent to F2FS_SETTABLE_FS_FL.
*
* Translating flags to fsx_flags value used by FS_IOC_FSGETXATTR and
* FS_IOC_FSSETXATTR is done by the VFS.
*/
static const struct {
u32 iflag;
u32 fsflag;
} f2fs_fsflags_map[] = {
{ F2FS_COMPR_FL, FS_COMPR_FL },
{ F2FS_SYNC_FL, FS_SYNC_FL },
{ F2FS_IMMUTABLE_FL, FS_IMMUTABLE_FL },
{ F2FS_APPEND_FL, FS_APPEND_FL },
{ F2FS_NODUMP_FL, FS_NODUMP_FL },
{ F2FS_NOATIME_FL, FS_NOATIME_FL },
{ F2FS_NOCOMP_FL, FS_NOCOMP_FL },
{ F2FS_INDEX_FL, FS_INDEX_FL },
{ F2FS_DIRSYNC_FL, FS_DIRSYNC_FL },
{ F2FS_PROJINHERIT_FL, FS_PROJINHERIT_FL },
{ F2FS_CASEFOLD_FL, FS_CASEFOLD_FL },
};
#define F2FS_GETTABLE_FS_FL ( \
FS_COMPR_FL | \
FS_SYNC_FL | \
FS_IMMUTABLE_FL | \
FS_APPEND_FL | \
FS_NODUMP_FL | \
FS_NOATIME_FL | \
FS_NOCOMP_FL | \
FS_INDEX_FL | \
FS_DIRSYNC_FL | \
FS_PROJINHERIT_FL | \
FS_ENCRYPT_FL | \
FS_INLINE_DATA_FL | \
FS_NOCOW_FL | \
FS_VERITY_FL | \
FS_CASEFOLD_FL)
#define F2FS_SETTABLE_FS_FL ( \
FS_COMPR_FL | \
FS_SYNC_FL | \
FS_IMMUTABLE_FL | \
FS_APPEND_FL | \
FS_NODUMP_FL | \
FS_NOATIME_FL | \
FS_NOCOMP_FL | \
FS_DIRSYNC_FL | \
FS_PROJINHERIT_FL | \
FS_CASEFOLD_FL)
/* Convert f2fs on-disk i_flags to FS_IOC_{GET,SET}FLAGS flags */
static inline u32 f2fs_iflags_to_fsflags(u32 iflags)
{
u32 fsflags = 0;
int i;
for (i = 0; i < ARRAY_SIZE(f2fs_fsflags_map); i++)
if (iflags & f2fs_fsflags_map[i].iflag)
fsflags |= f2fs_fsflags_map[i].fsflag;
return fsflags;
}
/* Convert FS_IOC_{GET,SET}FLAGS flags to f2fs on-disk i_flags */
static inline u32 f2fs_fsflags_to_iflags(u32 fsflags)
{
u32 iflags = 0;
int i;
for (i = 0; i < ARRAY_SIZE(f2fs_fsflags_map); i++)
if (fsflags & f2fs_fsflags_map[i].fsflag)
iflags |= f2fs_fsflags_map[i].iflag;
return iflags;
}
static int f2fs_ioc_getversion(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
return put_user(inode->i_generation, (int __user *)arg);
}
static int f2fs_ioc_start_atomic_write(struct file *filp, bool truncate)
{
struct inode *inode = file_inode(filp);
struct mnt_idmap *idmap = file_mnt_idmap(filp);
struct f2fs_inode_info *fi = F2FS_I(inode);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct inode *pinode;
loff_t isize;
int ret;
if (!inode_owner_or_capable(idmap, inode))
return -EACCES;
if (!S_ISREG(inode->i_mode))
return -EINVAL;
if (filp->f_flags & O_DIRECT)
return -EINVAL;
ret = mnt_want_write_file(filp);
if (ret)
return ret;
inode_lock(inode);
if (!f2fs_disable_compressed_file(inode) ||
f2fs_is_pinned_file(inode)) {
ret = -EINVAL;
goto out;
}
if (f2fs_is_atomic_file(inode))
goto out;
ret = f2fs_convert_inline_inode(inode);
if (ret)
goto out;
f2fs_down_write(&fi->i_gc_rwsem[WRITE]);
/*
* Should wait end_io to count F2FS_WB_CP_DATA correctly by
* f2fs_is_atomic_file.
*/
if (get_dirty_pages(inode))
f2fs_warn(sbi, "Unexpected flush for atomic writes: ino=%lu, npages=%u",
inode->i_ino, get_dirty_pages(inode));
ret = filemap_write_and_wait_range(inode->i_mapping, 0, LLONG_MAX);
if (ret) {
f2fs_up_write(&fi->i_gc_rwsem[WRITE]);
goto out;
}
/* Check if the inode already has a COW inode */
if (fi->cow_inode == NULL) {
/* Create a COW inode for atomic write */
pinode = f2fs_iget(inode->i_sb, fi->i_pino);
if (IS_ERR(pinode)) {
f2fs_up_write(&fi->i_gc_rwsem[WRITE]);
ret = PTR_ERR(pinode);
goto out;
}
ret = f2fs_get_tmpfile(idmap, pinode, &fi->cow_inode);
iput(pinode);
if (ret) {
f2fs_up_write(&fi->i_gc_rwsem[WRITE]);
goto out;
}
set_inode_flag(fi->cow_inode, FI_COW_FILE);
clear_inode_flag(fi->cow_inode, FI_INLINE_DATA);
/* Set the COW inode's atomic_inode to the atomic inode */
F2FS_I(fi->cow_inode)->atomic_inode = inode;
} else {
/* Reuse the already created COW inode */
ret = f2fs_do_truncate_blocks(fi->cow_inode, 0, true);
if (ret) {
f2fs_up_write(&fi->i_gc_rwsem[WRITE]);
goto out;
}
}
f2fs_write_inode(inode, NULL);
stat_inc_atomic_inode(inode);
set_inode_flag(inode, FI_ATOMIC_FILE);
isize = i_size_read(inode);
fi->original_i_size = isize;
if (truncate) {
set_inode_flag(inode, FI_ATOMIC_REPLACE);
truncate_inode_pages_final(inode->i_mapping);
f2fs_i_size_write(inode, 0);
isize = 0;
}
f2fs_i_size_write(fi->cow_inode, isize);
f2fs_up_write(&fi->i_gc_rwsem[WRITE]);
f2fs_update_time(sbi, REQ_TIME);
fi->atomic_write_task = current;
stat_update_max_atomic_write(inode);
fi->atomic_write_cnt = 0;
out:
inode_unlock(inode);
mnt_drop_write_file(filp);
return ret;
}
static int f2fs_ioc_commit_atomic_write(struct file *filp)
{
struct inode *inode = file_inode(filp);
struct mnt_idmap *idmap = file_mnt_idmap(filp);
int ret;
if (!inode_owner_or_capable(idmap, inode))
return -EACCES;
ret = mnt_want_write_file(filp);
if (ret)
return ret;
f2fs_balance_fs(F2FS_I_SB(inode), true);
inode_lock(inode);
if (f2fs_is_atomic_file(inode)) {
ret = f2fs_commit_atomic_write(inode);
if (!ret)
ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 0, true);
f2fs_abort_atomic_write(inode, ret);
} else {
ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 1, false);
}
inode_unlock(inode);
mnt_drop_write_file(filp);
return ret;
}
static int f2fs_ioc_abort_atomic_write(struct file *filp)
{
struct inode *inode = file_inode(filp);
struct mnt_idmap *idmap = file_mnt_idmap(filp);
int ret;
if (!inode_owner_or_capable(idmap, inode))
return -EACCES;
ret = mnt_want_write_file(filp);
if (ret)
return ret;
inode_lock(inode);
f2fs_abort_atomic_write(inode, true);
inode_unlock(inode);
mnt_drop_write_file(filp);
f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
return ret;
}
int f2fs_do_shutdown(struct f2fs_sb_info *sbi, unsigned int flag,
bool readonly)
{
struct super_block *sb = sbi->sb;
int ret = 0;
switch (flag) {
case F2FS_GOING_DOWN_FULLSYNC:
ret = bdev_freeze(sb->s_bdev);
if (ret)
goto out;
f2fs_stop_checkpoint(sbi, false, STOP_CP_REASON_SHUTDOWN);
bdev_thaw(sb->s_bdev);
break;
case F2FS_GOING_DOWN_METASYNC:
/* do checkpoint only */
ret = f2fs_sync_fs(sb, 1);
if (ret) {
if (ret == -EIO)
ret = 0;
goto out;
}
f2fs_stop_checkpoint(sbi, false, STOP_CP_REASON_SHUTDOWN);
break;
case F2FS_GOING_DOWN_NOSYNC:
f2fs_stop_checkpoint(sbi, false, STOP_CP_REASON_SHUTDOWN);
break;
case F2FS_GOING_DOWN_METAFLUSH:
f2fs_sync_meta_pages(sbi, META, LONG_MAX, FS_META_IO);
f2fs_stop_checkpoint(sbi, false, STOP_CP_REASON_SHUTDOWN);
break;
case F2FS_GOING_DOWN_NEED_FSCK:
set_sbi_flag(sbi, SBI_NEED_FSCK);
set_sbi_flag(sbi, SBI_CP_DISABLED_QUICK);
set_sbi_flag(sbi, SBI_IS_DIRTY);
/* do checkpoint only */
ret = f2fs_sync_fs(sb, 1);
if (ret == -EIO)
ret = 0;
goto out;
default:
ret = -EINVAL;
goto out;
}
if (readonly)
goto out;
f2fs_stop_gc_thread(sbi);
f2fs_stop_discard_thread(sbi);
f2fs_drop_discard_cmd(sbi);
clear_opt(sbi, DISCARD);
f2fs_update_time(sbi, REQ_TIME);
out:
trace_f2fs_shutdown(sbi, flag, ret);
return ret;
}
static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
__u32 in;
int ret;
bool need_drop = false, readonly = false;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (get_user(in, (__u32 __user *)arg))
return -EFAULT;
if (in != F2FS_GOING_DOWN_FULLSYNC) {
ret = mnt_want_write_file(filp);
if (ret) {
if (ret != -EROFS)
return ret;
/* fallback to nosync shutdown for readonly fs */
in = F2FS_GOING_DOWN_NOSYNC;
readonly = true;
} else {
need_drop = true;
}
}
ret = f2fs_do_shutdown(sbi, in, readonly);
if (need_drop)
mnt_drop_write_file(filp);
return ret;
}
static int f2fs_ioc_fitrim(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
struct super_block *sb = inode->i_sb;
struct fstrim_range range;
int ret;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (!f2fs_hw_support_discard(F2FS_SB(sb)))
return -EOPNOTSUPP;
if (copy_from_user(&range, (struct fstrim_range __user *)arg,
sizeof(range)))
return -EFAULT;
ret = mnt_want_write_file(filp);
if (ret)
return ret;
range.minlen = max((unsigned int)range.minlen,
bdev_discard_granularity(sb->s_bdev));
ret = f2fs_trim_fs(F2FS_SB(sb), &range);
mnt_drop_write_file(filp);
if (ret < 0)
return ret;
if (copy_to_user((struct fstrim_range __user *)arg, &range,
sizeof(range)))
return -EFAULT;
f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
return 0;
}
static bool uuid_is_nonzero(__u8 u[16])
{
int i;
for (i = 0; i < 16; i++)
if (u[i])
return true;
return false;
}
static int f2fs_ioc_set_encryption_policy(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
int ret;
if (!f2fs_sb_has_encrypt(F2FS_I_SB(inode)))
return -EOPNOTSUPP;
ret = fscrypt_ioctl_set_policy(filp, (const void __user *)arg);
f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
return ret;
}
static int f2fs_ioc_get_encryption_policy(struct file *filp, unsigned long arg)
{
if (!f2fs_sb_has_encrypt(F2FS_I_SB(file_inode(filp))))
return -EOPNOTSUPP;
return fscrypt_ioctl_get_policy(filp, (void __user *)arg);
}
static int f2fs_ioc_get_encryption_pwsalt(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
u8 encrypt_pw_salt[16];
int err;
if (!f2fs_sb_has_encrypt(sbi))
return -EOPNOTSUPP;
err = mnt_want_write_file(filp);
if (err)
return err;
f2fs_down_write(&sbi->sb_lock);
if (uuid_is_nonzero(sbi->raw_super->encrypt_pw_salt))
goto got_it;
/* update superblock with uuid */
generate_random_uuid(sbi->raw_super->encrypt_pw_salt);
err = f2fs_commit_super(sbi, false);
if (err) {
/* undo new data */
memset(sbi->raw_super->encrypt_pw_salt, 0, 16);
goto out_err;
}
got_it:
memcpy(encrypt_pw_salt, sbi->raw_super->encrypt_pw_salt, 16);
out_err:
f2fs_up_write(&sbi->sb_lock);
mnt_drop_write_file(filp);
if (!err && copy_to_user((__u8 __user *)arg, encrypt_pw_salt, 16))
err = -EFAULT;
return err;
}
static int f2fs_ioc_get_encryption_policy_ex(struct file *filp,
unsigned long arg)
{
if (!f2fs_sb_has_encrypt(F2FS_I_SB(file_inode(filp))))
return -EOPNOTSUPP;
return fscrypt_ioctl_get_policy_ex(filp, (void __user *)arg);
}
static int f2fs_ioc_add_encryption_key(struct file *filp, unsigned long arg)
{
if (!f2fs_sb_has_encrypt(F2FS_I_SB(file_inode(filp))))
return -EOPNOTSUPP;
return fscrypt_ioctl_add_key(filp, (void __user *)arg);
}
static int f2fs_ioc_remove_encryption_key(struct file *filp, unsigned long arg)
{
if (!f2fs_sb_has_encrypt(F2FS_I_SB(file_inode(filp))))
return -EOPNOTSUPP;
return fscrypt_ioctl_remove_key(filp, (void __user *)arg);
}
static int f2fs_ioc_remove_encryption_key_all_users(struct file *filp,
unsigned long arg)
{
if (!f2fs_sb_has_encrypt(F2FS_I_SB(file_inode(filp))))
return -EOPNOTSUPP;
return fscrypt_ioctl_remove_key_all_users(filp, (void __user *)arg);
}
static int f2fs_ioc_get_encryption_key_status(struct file *filp,
unsigned long arg)
{
if (!f2fs_sb_has_encrypt(F2FS_I_SB(file_inode(filp))))
return -EOPNOTSUPP;
return fscrypt_ioctl_get_key_status(filp, (void __user *)arg);
}
static int f2fs_ioc_get_encryption_nonce(struct file *filp, unsigned long arg)
{
if (!f2fs_sb_has_encrypt(F2FS_I_SB(file_inode(filp))))
return -EOPNOTSUPP;
return fscrypt_ioctl_get_nonce(filp, (void __user *)arg);
}
static int f2fs_ioc_gc(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct f2fs_gc_control gc_control = { .victim_segno = NULL_SEGNO,
.no_bg_gc = false,
.should_migrate_blocks = false,
.nr_free_secs = 0 };
__u32 sync;
int ret;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (get_user(sync, (__u32 __user *)arg))
return -EFAULT;
if (f2fs_readonly(sbi->sb))
return -EROFS;
ret = mnt_want_write_file(filp);
if (ret)
return ret;
if (!sync) {
if (!f2fs_down_write_trylock(&sbi->gc_lock)) {
ret = -EBUSY;
goto out;
}
} else {
f2fs_down_write(&sbi->gc_lock);
}
gc_control.init_gc_type = sync ? FG_GC : BG_GC;
gc_control.err_gc_skipped = sync;
stat_inc_gc_call_count(sbi, FOREGROUND);
ret = f2fs_gc(sbi, &gc_control);
out:
mnt_drop_write_file(filp);
return ret;
}
static int __f2fs_ioc_gc_range(struct file *filp, struct f2fs_gc_range *range)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(file_inode(filp));
struct f2fs_gc_control gc_control = {
.init_gc_type = range->sync ? FG_GC : BG_GC,
.no_bg_gc = false,
.should_migrate_blocks = false,
.err_gc_skipped = range->sync,
.nr_free_secs = 0 };
u64 end;
int ret;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (f2fs_readonly(sbi->sb))
return -EROFS;
end = range->start + range->len;
if (end < range->start || range->start < MAIN_BLKADDR(sbi) ||
end >= MAX_BLKADDR(sbi))
return -EINVAL;
ret = mnt_want_write_file(filp);
if (ret)
return ret;
do_more:
if (!range->sync) {
if (!f2fs_down_write_trylock(&sbi->gc_lock)) {
ret = -EBUSY;
goto out;
}
} else {
f2fs_down_write(&sbi->gc_lock);
}
gc_control.victim_segno = GET_SEGNO(sbi, range->start);
stat_inc_gc_call_count(sbi, FOREGROUND);
ret = f2fs_gc(sbi, &gc_control);
if (ret) {
if (ret == -EBUSY)
ret = -EAGAIN;
goto out;
}
range->start += CAP_BLKS_PER_SEC(sbi);
if (range->start <= end)
goto do_more;
out:
mnt_drop_write_file(filp);
return ret;
}
static int f2fs_ioc_gc_range(struct file *filp, unsigned long arg)
{
struct f2fs_gc_range range;
if (copy_from_user(&range, (struct f2fs_gc_range __user *)arg,
sizeof(range)))
return -EFAULT;
return __f2fs_ioc_gc_range(filp, &range);
}
static int f2fs_ioc_write_checkpoint(struct file *filp)
{
struct inode *inode = file_inode(filp);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
int ret;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (f2fs_readonly(sbi->sb))
return -EROFS;
if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) {
f2fs_info(sbi, "Skipping Checkpoint. Checkpoints currently disabled.");
return -EINVAL;
}
ret = mnt_want_write_file(filp);
if (ret)
return ret;
ret = f2fs_sync_fs(sbi->sb, 1);
mnt_drop_write_file(filp);
return ret;
}
static int f2fs_defragment_range(struct f2fs_sb_info *sbi,
struct file *filp,
struct f2fs_defragment *range)
{
struct inode *inode = file_inode(filp);
struct f2fs_map_blocks map = { .m_next_extent = NULL,
.m_seg_type = NO_CHECK_TYPE,
.m_may_create = false };
struct extent_info ei = {};
pgoff_t pg_start, pg_end, next_pgofs;
unsigned int total = 0, sec_num;
block_t blk_end = 0;
bool fragmented = false;
int err;
f2fs_balance_fs(sbi, true);
inode_lock(inode);
pg_start = range->start >> PAGE_SHIFT;
pg_end = min_t(pgoff_t,
(range->start + range->len) >> PAGE_SHIFT,
DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE));
if (is_inode_flag_set(inode, FI_COMPRESS_RELEASED)) {
err = -EINVAL;
goto unlock_out;
}
/* if in-place-update policy is enabled, don't waste time here */
set_inode_flag(inode, FI_OPU_WRITE);
if (f2fs_should_update_inplace(inode, NULL)) {
err = -EINVAL;
goto out;
}
/* writeback all dirty pages in the range */
err = filemap_write_and_wait_range(inode->i_mapping,
pg_start << PAGE_SHIFT,
(pg_end << PAGE_SHIFT) - 1);
if (err)
goto out;
/*
* lookup mapping info in extent cache, skip defragmenting if physical
* block addresses are continuous.
*/
if (f2fs_lookup_read_extent_cache(inode, pg_start, &ei)) {
if (ei.fofs + ei.len >= pg_end)
goto out;
}
map.m_lblk = pg_start;
map.m_next_pgofs = &next_pgofs;
/*
* lookup mapping info in dnode page cache, skip defragmenting if all
* physical block addresses are continuous even if there are hole(s)
* in logical blocks.
*/
while (map.m_lblk < pg_end) {
map.m_len = pg_end - map.m_lblk;
err = f2fs_map_blocks(inode, &map, F2FS_GET_BLOCK_DEFAULT);
if (err)
goto out;
if (!(map.m_flags & F2FS_MAP_FLAGS)) {
map.m_lblk = next_pgofs;
continue;
}
if (blk_end && blk_end != map.m_pblk)
fragmented = true;
/* record total count of block that we're going to move */
total += map.m_len;
blk_end = map.m_pblk + map.m_len;
map.m_lblk += map.m_len;
}
if (!fragmented) {
total = 0;
goto out;
}
sec_num = DIV_ROUND_UP(total, CAP_BLKS_PER_SEC(sbi));
/*
* make sure there are enough free section for LFS allocation, this can
* avoid defragment running in SSR mode when free section are allocated
* intensively
*/
if (has_not_enough_free_secs(sbi, 0, sec_num)) {
err = -EAGAIN;
goto out;
}
map.m_lblk = pg_start;
map.m_len = pg_end - pg_start;
total = 0;
while (map.m_lblk < pg_end) {
pgoff_t idx;
int cnt = 0;
do_map:
map.m_len = pg_end - map.m_lblk;
err = f2fs_map_blocks(inode, &map, F2FS_GET_BLOCK_DEFAULT);
if (err)
goto clear_out;
if (!(map.m_flags & F2FS_MAP_FLAGS)) {
map.m_lblk = next_pgofs;
goto check;
}
set_inode_flag(inode, FI_SKIP_WRITES);
idx = map.m_lblk;
while (idx < map.m_lblk + map.m_len &&
cnt < BLKS_PER_SEG(sbi)) {
struct page *page;
page = f2fs_get_lock_data_page(inode, idx, true);
if (IS_ERR(page)) {
err = PTR_ERR(page);
goto clear_out;
}
set_page_dirty(page);
set_page_private_gcing(page);
f2fs_put_page(page, 1);
idx++;
cnt++;
total++;
}
map.m_lblk = idx;
check:
if (map.m_lblk < pg_end && cnt < BLKS_PER_SEG(sbi))
goto do_map;
clear_inode_flag(inode, FI_SKIP_WRITES);
err = filemap_fdatawrite(inode->i_mapping);
if (err)
goto out;
}
clear_out:
clear_inode_flag(inode, FI_SKIP_WRITES);
out:
clear_inode_flag(inode, FI_OPU_WRITE);
unlock_out:
inode_unlock(inode);
if (!err)
range->len = (u64)total << PAGE_SHIFT;
return err;
}
static int f2fs_ioc_defragment(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct f2fs_defragment range;
int err;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (!S_ISREG(inode->i_mode) || f2fs_is_atomic_file(inode))
return -EINVAL;
if (f2fs_readonly(sbi->sb))
return -EROFS;
if (copy_from_user(&range, (struct f2fs_defragment __user *)arg,
sizeof(range)))
return -EFAULT;
/* verify alignment of offset & size */
if (range.start & (F2FS_BLKSIZE - 1) || range.len & (F2FS_BLKSIZE - 1))
return -EINVAL;
if (unlikely((range.start + range.len) >> PAGE_SHIFT >
max_file_blocks(inode)))
return -EINVAL;
err = mnt_want_write_file(filp);
if (err)
return err;
err = f2fs_defragment_range(sbi, filp, &range);
mnt_drop_write_file(filp);
if (range.len)
f2fs_update_time(sbi, REQ_TIME);
if (err < 0)
return err;
if (copy_to_user((struct f2fs_defragment __user *)arg, &range,
sizeof(range)))
return -EFAULT;
return 0;
}
static int f2fs_move_file_range(struct file *file_in, loff_t pos_in,
struct file *file_out, loff_t pos_out, size_t len)
{
struct inode *src = file_inode(file_in);
struct inode *dst = file_inode(file_out);
struct f2fs_sb_info *sbi = F2FS_I_SB(src);
size_t olen = len, dst_max_i_size = 0;
size_t dst_osize;
int ret;
if (file_in->f_path.mnt != file_out->f_path.mnt ||
src->i_sb != dst->i_sb)
return -EXDEV;
if (unlikely(f2fs_readonly(src->i_sb)))
return -EROFS;
if (!S_ISREG(src->i_mode) || !S_ISREG(dst->i_mode))
return -EINVAL;
if (IS_ENCRYPTED(src) || IS_ENCRYPTED(dst))
return -EOPNOTSUPP;
if (pos_out < 0 || pos_in < 0)
return -EINVAL;
if (src == dst) {
if (pos_in == pos_out)
return 0;
if (pos_out > pos_in && pos_out < pos_in + len)
return -EINVAL;
}
inode_lock(src);
if (src != dst) {
ret = -EBUSY;
if (!inode_trylock(dst))
goto out;
}
if (f2fs_compressed_file(src) || f2fs_compressed_file(dst) ||
f2fs_is_pinned_file(src) || f2fs_is_pinned_file(dst)) {
ret = -EOPNOTSUPP;
goto out_unlock;
}
ret = -EINVAL;
if (pos_in + len > src->i_size || pos_in + len < pos_in)
goto out_unlock;
if (len == 0)
olen = len = src->i_size - pos_in;
if (pos_in + len == src->i_size)
len = ALIGN(src->i_size, F2FS_BLKSIZE) - pos_in;
if (len == 0) {
ret = 0;
goto out_unlock;
}
dst_osize = dst->i_size;
if (pos_out + olen > dst->i_size)
dst_max_i_size = pos_out + olen;
/* verify the end result is block aligned */
if (!IS_ALIGNED(pos_in, F2FS_BLKSIZE) ||
!IS_ALIGNED(pos_in + len, F2FS_BLKSIZE) ||
!IS_ALIGNED(pos_out, F2FS_BLKSIZE))
goto out_unlock;
ret = f2fs_convert_inline_inode(src);
if (ret)
goto out_unlock;
ret = f2fs_convert_inline_inode(dst);
if (ret)
goto out_unlock;
/* write out all dirty pages from offset */
ret = filemap_write_and_wait_range(src->i_mapping,
pos_in, pos_in + len);
if (ret)
goto out_unlock;
ret = filemap_write_and_wait_range(dst->i_mapping,
pos_out, pos_out + len);
if (ret)
goto out_unlock;
f2fs_balance_fs(sbi, true);
f2fs_down_write(&F2FS_I(src)->i_gc_rwsem[WRITE]);
if (src != dst) {
ret = -EBUSY;
if (!f2fs_down_write_trylock(&F2FS_I(dst)->i_gc_rwsem[WRITE]))
goto out_src;
}
f2fs_lock_op(sbi);
ret = __exchange_data_block(src, dst, pos_in >> F2FS_BLKSIZE_BITS,
pos_out >> F2FS_BLKSIZE_BITS,
len >> F2FS_BLKSIZE_BITS, false);
if (!ret) {
if (dst_max_i_size)
f2fs_i_size_write(dst, dst_max_i_size);
else if (dst_osize != dst->i_size)
f2fs_i_size_write(dst, dst_osize);
}
f2fs_unlock_op(sbi);
if (src != dst)
f2fs_up_write(&F2FS_I(dst)->i_gc_rwsem[WRITE]);
out_src:
f2fs_up_write(&F2FS_I(src)->i_gc_rwsem[WRITE]);
if (ret)
goto out_unlock;
inode_set_mtime_to_ts(src, inode_set_ctime_current(src));
f2fs_mark_inode_dirty_sync(src, false);
if (src != dst) {
inode_set_mtime_to_ts(dst, inode_set_ctime_current(dst));
f2fs_mark_inode_dirty_sync(dst, false);
}
f2fs_update_time(sbi, REQ_TIME);
out_unlock:
if (src != dst)
inode_unlock(dst);
out:
inode_unlock(src);
return ret;
}
static int __f2fs_ioc_move_range(struct file *filp,
struct f2fs_move_range *range)
{
struct fd dst;
int err;
if (!(filp->f_mode & FMODE_READ) ||
!(filp->f_mode & FMODE_WRITE))
return -EBADF;
dst = fdget(range->dst_fd);
if (!dst.file)
return -EBADF;
if (!(dst.file->f_mode & FMODE_WRITE)) {
err = -EBADF;
goto err_out;
}
err = mnt_want_write_file(filp);
if (err)
goto err_out;
err = f2fs_move_file_range(filp, range->pos_in, dst.file,
range->pos_out, range->len);
mnt_drop_write_file(filp);
err_out:
fdput(dst);
return err;
}