void nilfs_clear_dirty_pages(struct address_space *mapping)
{
struct pagevec pvec;
unsigned int i;
pgoff_t index = 0;
pagevec_init(&pvec, 0);
while (pagevec_lookup_tag(&pvec, mapping, &index, PAGECACHE_TAG_DIRTY,
PAGEVEC_SIZE)) {
for (i = 0; i < pagevec_count(&pvec); i++) {
struct page *page = pvec.pages[i];
struct buffer_head *bh, *head;
lock_page(page);
ClearPageUptodate(page);
ClearPageMappedToDisk(page);
bh = head = page_buffers(page);
do {
lock_buffer(bh);
clear_buffer_dirty(bh);
clear_buffer_nilfs_volatile(bh);
clear_buffer_uptodate(bh);
clear_buffer_mapped(bh);
unlock_buffer(bh);
bh = bh->b_this_page;
} while (bh != head);
__nilfs_clear_page_dirty(page);
unlock_page(page);
}
pagevec_release(&pvec);
cond_resched();
}
}
static int gfs2_write_cache_jdata(struct address_space *mapping,
struct writeback_control *wbc)
{
struct backing_dev_info *bdi = mapping->backing_dev_info;
int ret = 0;
int done = 0;
struct pagevec pvec;
int nr_pages;
pgoff_t index;
pgoff_t end;
int scanned = 0;
int range_whole = 0;
if (wbc->nonblocking && bdi_write_congested(bdi)) {
wbc->encountered_congestion = 1;
return 0;
}
pagevec_init(&pvec, 0);
if (wbc->range_cyclic) {
index = mapping->writeback_index; /* Start from prev offset */
end = -1;
} else {
index = wbc->range_start >> PAGE_CACHE_SHIFT;
end = wbc->range_end >> PAGE_CACHE_SHIFT;
if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
range_whole = 1;
scanned = 1;
}
retry:
while (!done && (index <= end) &&
(nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
PAGECACHE_TAG_DIRTY,
min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1))) {
scanned = 1;
ret = gfs2_write_jdata_pagevec(mapping, wbc, &pvec, nr_pages, end);
if (ret)
done = 1;
if (ret > 0)
ret = 0;
pagevec_release(&pvec);
cond_resched();
}
if (!scanned && !done) {
/*
* We hit the last page and there is more work to be done: wrap
* back to the start of the file
*/
scanned = 1;
index = 0;
goto retry;
}
if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
mapping->writeback_index = index;
return ret;
}
int nilfs_copy_dirty_pages(struct address_space *dmap,
struct address_space *smap)
{
struct pagevec pvec;
unsigned int i;
pgoff_t index = 0;
int err = 0;
pagevec_init(&pvec, 0);
repeat:
if (!pagevec_lookup_tag(&pvec, smap, &index, PAGECACHE_TAG_DIRTY,
PAGEVEC_SIZE))
return 0;
for (i = 0; i < pagevec_count(&pvec); i++) {
struct page *page = pvec.pages[i], *dpage;
lock_page(page);
if (unlikely(!PageDirty(page)))
NILFS_PAGE_BUG(page, "inconsistent dirty state");
dpage = grab_cache_page(dmap, page->index);
if (unlikely(!dpage)) {
/* No empty page is added to the page cache */
err = -ENOMEM;
unlock_page(page);
break;
}
if (unlikely(!page_has_buffers(page)))
NILFS_PAGE_BUG(page,
"found empty page in dat page cache");
nilfs_copy_page(dpage, page, 1);
__set_page_dirty_nobuffers(dpage);
unlock_page(dpage);
page_cache_release(dpage);
unlock_page(page);
}
pagevec_release(&pvec);
cond_resched();
if (likely(!err))
goto repeat;
return err;
}
/*
* Radix-tree checker
*/
void nilfs_check_radix_tree(const char *fname, int line,
struct address_space *mapping, int tag)
{
struct pagevec pvec;
unsigned int i, n;
pgoff_t index = 0;
char *page_type;
int nr_found = 0;
if (tag == PAGECACHE_TAG_DIRTY)
page_type = "dirty";
else if (tag == PAGECACHE_TAG_WRITEBACK)
page_type = "writeback";
else
page_type = "leaking";
pagevec_init(&pvec, 0);
repeat:
if (tag < 0) {
n = pagevec_lookup(&pvec, mapping, index, PAGEVEC_SIZE);
if (n)
index = pvec.pages[n - 1]->index + 1;
} else
n = pagevec_lookup_tag(&pvec, mapping, &index, tag,
PAGEVEC_SIZE);
if (!n) {
if (nr_found)
printk(KERN_WARNING "%s: found %d %s pages\n",
fname, nr_found, page_type);
return;
}
for (i = 0; i < n; i++) {
nilfs_page_debug(fname, line, pvec.pages[i], "%s page",
page_type);
nr_found++;
}
pagevec_release(&pvec);
cond_resched();
goto repeat;
}
/**
* nilfs_clear_dirty_pages - discard dirty pages in address space
* @mapping: address space with dirty pages for discarding
* @silent: suppress [true] or print [false] warning messages
*/
void nilfs_clear_dirty_pages(struct address_space *mapping, bool silent)
{
struct pagevec pvec;
unsigned int i;
pgoff_t index = 0;
pagevec_init(&pvec);
while (pagevec_lookup_tag(&pvec, mapping, &index,
PAGECACHE_TAG_DIRTY)) {
for (i = 0; i < pagevec_count(&pvec); i++) {
struct page *page = pvec.pages[i];
lock_page(page);
nilfs_clear_dirty_page(page, silent);
unlock_page(page);
}
pagevec_release(&pvec);
cond_resched();
}
}
/**
* write_cache_pages - walk the list of dirty pages of the given address space and write all of them.
* @mapping: address space structure to write
* @wbc: subtract the number of written pages from *@wbc->nr_to_write
* @writepage: function called for each page
* @data: data passed to writepage function
*
* If a page is already under I/O, write_cache_pages() skips it, even
* if it's dirty. This is desirable behaviour for memory-cleaning writeback,
* but it is INCORRECT for data-integrity system calls such as fsync(). fsync()
* and msync() need to guarantee that all the data which was dirty at the time
* the call was made get new I/O started against them. If wbc->sync_mode is
* WB_SYNC_ALL then we were called for data integrity and we must wait for
* existing IO to complete.
*/
int write_cache_pages(struct address_space *mapping,
struct writeback_control *wbc, writepage_t writepage,
void *data)
{
struct backing_dev_info *bdi = mapping->backing_dev_info;
int ret = 0;
int done = 0;
struct pagevec pvec;
int nr_pages;
pgoff_t uninitialized_var(writeback_index);
pgoff_t index;
pgoff_t end; /* Inclusive */
pgoff_t done_index;
int cycled;
int range_whole = 0;
if (wbc->nonblocking && bdi_write_congested(bdi)) {
wbc->encountered_congestion = 1;
return 0;
}
pagevec_init(&pvec, 0);
if (wbc->range_cyclic) {
writeback_index = mapping->writeback_index; /* prev offset */
index = writeback_index;
if (index == 0)
cycled = 1;
else
cycled = 0;
end = -1;
} else {
index = wbc->range_start >> PAGE_CACHE_SHIFT;
end = wbc->range_end >> PAGE_CACHE_SHIFT;
if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
range_whole = 1;
cycled = 1; /* ignore range_cyclic tests */
}
retry:
done_index = index;
while (!done && (index <= end)) {
int i;
nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
PAGECACHE_TAG_DIRTY,
min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
if (nr_pages == 0)
break;
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
/*
* At this point, the page may be truncated or
* invalidated (changing page->mapping to NULL), or
* even swizzled back from swapper_space to tmpfs file
* mapping. However, page->index will not change
* because we have a reference on the page.
*/
if (page->index > end) {
/*
* can't be range_cyclic (1st pass) because
* end == -1 in that case.
*/
done = 1;
break;
}
done_index = page->index + 1;
lock_page(page);
/*
* Page truncated or invalidated. We can freely skip it
* then, even for data integrity operations: the page
* has disappeared concurrently, so there could be no
* real expectation of this data interity operation
* even if there is now a new, dirty page at the same
* pagecache address.
*/
if (unlikely(page->mapping != mapping)) {
continue_unlock:
unlock_page(page);
continue;
}
if (!PageDirty(page)) {
/* someone wrote it for us */
goto continue_unlock;
}
if (PageWriteback(page)) {
if (wbc->sync_mode != WB_SYNC_NONE)
wait_on_page_writeback(page);
else
goto continue_unlock;
}
BUG_ON(PageWriteback(page));
if (!clear_page_dirty_for_io(page))
goto continue_unlock;
ret = (*writepage)(page, wbc, data);
if (unlikely(ret)) {
if (ret == AOP_WRITEPAGE_ACTIVATE) {
unlock_page(page);
ret = 0;
} else {
/*
* done_index is set past this page,
* so media errors will not choke
* background writeout for the entire
* file. This has consequences for
* range_cyclic semantics (ie. it may
* not be suitable for data integrity
* writeout).
*/
done = 1;
break;
}
}
if (wbc->nr_to_write > 0) {
wbc->nr_to_write--;
if (wbc->nr_to_write == 0 &&
wbc->sync_mode == WB_SYNC_NONE) {
/*
* We stop writing back only if we are
* not doing integrity sync. In case of
* integrity sync we have to keep going
* because someone may be concurrently
* dirtying pages, and we might have
* synced a lot of newly appeared dirty
* pages, but have not synced all of the
* old dirty pages.
*/
done = 1;
break;
}
}
if (wbc->nonblocking && bdi_write_congested(bdi)) {
wbc->encountered_congestion = 1;
done = 1;
break;
}
}
pagevec_release(&pvec);
cond_resched();
}
if (!cycled && !done) {
/*
* range_cyclic:
* We hit the last page and there is more work to be done: wrap
* back to the start of the file
*/
cycled = 1;
index = 0;
end = writeback_index - 1;
goto retry;
}
if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
mapping->writeback_index = done_index;
return ret;
}
static int gfs2_write_cache_jdata(struct address_space *mapping,
struct writeback_control *wbc)
{
int ret = 0;
int done = 0;
struct pagevec pvec;
int nr_pages;
pgoff_t uninitialized_var(writeback_index);
pgoff_t index;
pgoff_t end;
pgoff_t done_index;
int cycled;
int range_whole = 0;
int tag;
pagevec_init(&pvec, 0);
if (wbc->range_cyclic) {
writeback_index = mapping->writeback_index; /* prev offset */
index = writeback_index;
if (index == 0)
cycled = 1;
else
cycled = 0;
end = -1;
} else {
index = wbc->range_start >> PAGE_CACHE_SHIFT;
end = wbc->range_end >> PAGE_CACHE_SHIFT;
if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
range_whole = 1;
cycled = 1; /* ignore range_cyclic tests */
}
if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
tag = PAGECACHE_TAG_TOWRITE;
else
tag = PAGECACHE_TAG_DIRTY;
retry:
if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
tag_pages_for_writeback(mapping, index, end);
done_index = index;
while (!done && (index <= end)) {
nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag,
min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
if (nr_pages == 0)
break;
ret = gfs2_write_jdata_pagevec(mapping, wbc, &pvec, nr_pages, end, &done_index);
if (ret)
done = 1;
if (ret > 0)
ret = 0;
pagevec_release(&pvec);
cond_resched();
}
if (!cycled && !done) {
/*
* range_cyclic:
* We hit the last page and there is more work to be done: wrap
* back to the start of the file
*/
cycled = 1;
index = 0;
end = writeback_index - 1;
goto retry;
}
if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
mapping->writeback_index = done_index;
return ret;
}
static int f2fs_write_data_page(struct page *page,
struct writeback_control *wbc)
{
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_CACHE_SHIFT;
unsigned offset = 0;
bool need_balance_fs = false;
int err = 0;
struct f2fs_io_info fio = {
.sbi = sbi,
.type = DATA,
.rw = (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : WRITE,
.page = page,
.encrypted_page = NULL,
};
trace_f2fs_writepage(page, DATA);
if (page->index < end_index)
goto write;
/*
* If the offset is out-of-range of file size,
* this page does not have to be written to disk.
*/
offset = i_size & (PAGE_CACHE_SIZE - 1);
if ((page->index >= end_index + 1) || !offset)
goto out;
zero_user_segment(page, offset, PAGE_CACHE_SIZE);
write:
if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
goto redirty_out;
if (f2fs_is_drop_cache(inode))
goto out;
if (f2fs_is_volatile_file(inode) && !wbc->for_reclaim &&
available_free_memory(sbi, BASE_CHECK))
goto redirty_out;
/* Dentry blocks are controlled by checkpoint */
if (S_ISDIR(inode->i_mode)) {
if (unlikely(f2fs_cp_error(sbi)))
goto redirty_out;
err = do_write_data_page(&fio);
goto done;
}
/* we should bypass data pages to proceed the kworkder jobs */
if (unlikely(f2fs_cp_error(sbi))) {
SetPageError(page);
goto out;
}
if (!wbc->for_reclaim)
need_balance_fs = true;
else if (has_not_enough_free_secs(sbi, 0))
goto redirty_out;
err = -EAGAIN;
f2fs_lock_op(sbi);
if (f2fs_has_inline_data(inode))
err = f2fs_write_inline_data(inode, page);
if (err == -EAGAIN)
err = do_write_data_page(&fio);
f2fs_unlock_op(sbi);
done:
if (err && err != -ENOENT)
goto redirty_out;
clear_cold_data(page);
out:
inode_dec_dirty_pages(inode);
if (err)
ClearPageUptodate(page);
unlock_page(page);
if (need_balance_fs)
f2fs_balance_fs(sbi);
if (wbc->for_reclaim)
f2fs_submit_merged_bio(sbi, DATA, WRITE);
return 0;
redirty_out:
redirty_page_for_writepage(wbc, page);
return AOP_WRITEPAGE_ACTIVATE;
}
static int __f2fs_writepage(struct page *page, struct writeback_control *wbc,
void *data)
{
struct address_space *mapping = data;
int ret = mapping->a_ops->writepage(page, wbc);
mapping_set_error(mapping, ret);
return ret;
}
/*
* This function was copied from write_cche_pages from mm/page-writeback.c.
* The major change is making write step of cold data page separately from
* warm/hot data page.
*/
static int f2fs_write_cache_pages(struct address_space *mapping,
struct writeback_control *wbc, writepage_t writepage,
void *data)
{
int ret = 0;
int done = 0;
struct pagevec pvec;
int nr_pages;
pgoff_t uninitialized_var(writeback_index);
pgoff_t index;
pgoff_t end; /* Inclusive */
pgoff_t done_index;
int cycled;
int range_whole = 0;
int tag;
int step = 0;
pagevec_init(&pvec, 0);
next:
if (wbc->range_cyclic) {
writeback_index = mapping->writeback_index; /* prev offset */
index = writeback_index;
if (index == 0)
cycled = 1;
else
cycled = 0;
end = -1;
} else {
index = wbc->range_start >> PAGE_CACHE_SHIFT;
end = wbc->range_end >> PAGE_CACHE_SHIFT;
if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
range_whole = 1;
cycled = 1; /* ignore range_cyclic tests */
}
if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
tag = PAGECACHE_TAG_TOWRITE;
else
tag = PAGECACHE_TAG_DIRTY;
retry:
if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
tag_pages_for_writeback(mapping, index, end);
done_index = index;
while (!done && (index <= end)) {
int i;
nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag,
min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1);
if (nr_pages == 0)
break;
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
if (page->index > end) {
done = 1;
break;
}
done_index = page->index;
lock_page(page);
if (unlikely(page->mapping != mapping)) {
continue_unlock:
unlock_page(page);
continue;
}
if (!PageDirty(page)) {
/* someone wrote it for us */
goto continue_unlock;
}
if (step == is_cold_data(page))
goto continue_unlock;
if (PageWriteback(page)) {
if (wbc->sync_mode != WB_SYNC_NONE)
f2fs_wait_on_page_writeback(page, DATA);
else
goto continue_unlock;
}
BUG_ON(PageWriteback(page));
if (!clear_page_dirty_for_io(page))
goto continue_unlock;
ret = (*writepage)(page, wbc, data);
if (unlikely(ret)) {
if (ret == AOP_WRITEPAGE_ACTIVATE) {
unlock_page(page);
ret = 0;
} else {
done_index = page->index + 1;
done = 1;
break;
}
}
if (--wbc->nr_to_write <= 0 &&
wbc->sync_mode == WB_SYNC_NONE) {
done = 1;
break;
}
}
pagevec_release(&pvec);
cond_resched();
}
if (step < 1) {
step++;
goto next;
}
if (!cycled && !done) {
cycled = 1;
index = 0;
end = writeback_index - 1;
goto retry;
}
if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
mapping->writeback_index = done_index;
return ret;
}
int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
{
struct inode *inode = file->f_mapping->host;
struct f2fs_inode_info *fi = F2FS_I(inode);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
nid_t ino = inode->i_ino;
int ret = 0;
bool need_cp = false;
struct writeback_control wbc = {
.sync_mode = WB_SYNC_ALL,
.nr_to_write = LONG_MAX,
.for_reclaim = 0,
};
if (unlikely(f2fs_readonly(inode->i_sb)))
return 0;
trace_f2fs_sync_file_enter(inode);
/* if fdatasync is triggered, let's do in-place-update */
if (get_dirty_pages(inode) <= SM_I(sbi)->min_fsync_blocks)
set_inode_flag(fi, FI_NEED_IPU);
ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
clear_inode_flag(fi, FI_NEED_IPU);
if (ret) {
trace_f2fs_sync_file_exit(inode, need_cp, datasync, ret);
return ret;
}
/* if the inode is dirty, let's recover all the time */
if (!datasync && is_inode_flag_set(fi, FI_DIRTY_INODE)) {
update_inode_page(inode);
goto go_write;
}
/*
* if there is no written data, don't waste time to write recovery info.
*/
if (!is_inode_flag_set(fi, FI_APPEND_WRITE) &&
!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(fi, FI_UPDATE_WRITE) ||
exist_written_data(sbi, ino, UPDATE_INO))
goto flush_out;
goto out;
}
go_write:
/* guarantee free sections for fsync */
f2fs_balance_fs(sbi);
/*
* Both of fdatasync() and fsync() are able to be recovered from
* sudden-power-off.
*/
down_read(&fi->i_sem);
need_cp = need_do_checkpoint(inode);
up_read(&fi->i_sem);
if (need_cp) {
/* 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(fi, FI_APPEND_WRITE);
clear_inode_flag(fi, FI_UPDATE_WRITE);
goto out;
}
sync_nodes:
sync_node_pages(sbi, ino, &wbc);
/* if cp_error was enabled, we should avoid infinite loop */
if (unlikely(f2fs_cp_error(sbi)))
goto out;
if (need_inode_block_update(sbi, ino)) {
mark_inode_dirty_sync(inode);
f2fs_write_inode(inode, NULL);
goto sync_nodes;
}
ret = wait_on_node_pages_writeback(sbi, ino);
if (ret)
goto out;
/* once recovery info is written, don't need to tack this */
remove_dirty_inode(sbi, ino, APPEND_INO);
clear_inode_flag(fi, FI_APPEND_WRITE);
flush_out:
remove_dirty_inode(sbi, ino, UPDATE_INO);
clear_inode_flag(fi, FI_UPDATE_WRITE);
ret = f2fs_issue_flush(sbi);
out:
trace_f2fs_sync_file_exit(inode, need_cp, datasync, ret);
f2fs_trace_ios(NULL, 1);
return ret;
}
static pgoff_t __get_first_dirty_index(struct address_space *mapping,
pgoff_t pgofs, int whence)
{
struct pagevec pvec;
int nr_pages;
if (whence != SEEK_DATA)
return 0;
/* find first dirty page index */
pagevec_init(&pvec, 0);
nr_pages = pagevec_lookup_tag(&pvec, mapping, &pgofs,
PAGECACHE_TAG_DIRTY, 1);
pgofs = nr_pages ? pvec.pages[0]->index : LONG_MAX;
pagevec_release(&pvec);
return pgofs;
}
static bool __found_offset(block_t blkaddr, pgoff_t dirty, pgoff_t pgofs,
int whence)
{
switch (whence) {
case SEEK_DATA:
if ((blkaddr == NEW_ADDR && dirty == pgofs) ||
(blkaddr != NEW_ADDR && blkaddr != NULL_ADDR))
return true;
break;
case SEEK_HOLE:
if (blkaddr == NULL_ADDR)
return true;
break;
}
return false;
}
static inline int unsigned_offsets(struct file *file)
{
return file->f_mode & FMODE_UNSIGNED_OFFSET;
}
static loff_t vfs_setpos(struct file *file, loff_t offset, loff_t maxsize)
{
if (offset < 0 && !unsigned_offsets(file))
return -EINVAL;
if (offset > maxsize)
return -EINVAL;
if (offset != file->f_pos) {
file->f_pos = offset;
file->f_version = 0;
}
return offset;
}
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, dirty;
loff_t data_ofs = offset;
loff_t isize;
int err = 0;
mutex_lock(&inode->i_mutex);
isize = i_size_read(inode);
if (offset >= isize)
goto fail;
/* handle inline data case */
if (f2fs_has_inline_data(inode) || f2fs_has_inline_dentry(inode)) {
if (whence == SEEK_HOLE)
data_ofs = isize;
goto found;
}
pgofs = (pgoff_t)(offset >> PAGE_CACHE_SHIFT);
dirty = __get_first_dirty_index(inode->i_mapping, pgofs, whence);
for (; data_ofs < isize; data_ofs = pgofs << PAGE_CACHE_SHIFT) {
set_new_dnode(&dn, inode, NULL, NULL, 0);
err = get_dnode_of_data(&dn, pgofs, LOOKUP_NODE_RA);
if (err && err != -ENOENT) {
goto fail;
} else if (err == -ENOENT) {
/* direct node does not exists */
if (whence == SEEK_DATA) {
pgofs = PGOFS_OF_NEXT_DNODE(pgofs,
F2FS_I(inode));
continue;
} else {
goto found;
}
}
end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(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_CACHE_SHIFT) {
block_t blkaddr;
blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node);
if (__found_offset(blkaddr, dirty, 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;
mutex_unlock(&inode->i_mutex);
return vfs_setpos(file, data_ofs, maxbytes);
fail:
mutex_unlock(&inode->i_mutex);
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;
switch (whence) {
case SEEK_SET:
case SEEK_CUR:
case SEEK_END:
return generic_file_llseek_size(file, offset, whence,
maxbytes);
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 (f2fs_encrypted_inode(inode)) {
int err = f2fs_get_encryption_info(inode);
if (err)
return 0;
}
/* we don't need to use inline_data strictly */
if (f2fs_has_inline_data(inode)) {
int err = f2fs_convert_inline_inode(inode);
if (err)
return err;
}
file_accessed(file);
vma->vm_ops = &f2fs_file_vm_ops;
return 0;
}
static int f2fs_file_open(struct inode *inode, struct file *filp)
{
int ret = generic_file_open(inode, filp);
if (!ret && f2fs_encrypted_inode(inode)) {
ret = f2fs_get_encryption_info(inode);
if (ret)
ret = -EACCES;
}
return ret;
}
/**ltl
功能:遍历给定地址空间的"脏"页面，写这些页面
参数:
返回值:
说明:
*/
int write_cache_pages(struct address_space *mapping,
struct writeback_control *wbc, writepage_t writepage,
void *data)
{
int ret = 0;
int done = 0;
struct pagevec pvec;
int nr_pages;
pgoff_t uninitialized_var(writeback_index);
pgoff_t index;/*要冲刷页面的索引*/
pgoff_t end; /* Inclusive *//*冲刷最后一个页面的索引，-1表示要循环冲刷*/
pgoff_t done_index;
int cycled;/*主要用在回绕需要分成两段进行冲刷的情况下，为1表示前一段冲刷已经完成。*/
int range_whole = 0;
int tag;
pagevec_init(&pvec, 0);
if (wbc->range_cyclic)
{//是否要循环进行冲刷
writeback_index = mapping->writeback_index; /* prev offset */
index = writeback_index;
if (index == 0)
cycled = 1;
else
cycled = 0;
end = -1;
}
else
{
index = wbc->range_start >> PAGE_CACHE_SHIFT;
end = wbc->range_end >> PAGE_CACHE_SHIFT;
if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
range_whole = 1;
cycled = 1; /* ignore range_cyclic tests */
}
if (wbc->sync_mode == WB_SYNC_ALL)
tag = PAGECACHE_TAG_TOWRITE;
else
tag = PAGECACHE_TAG_DIRTY;
retry:
if (wbc->sync_mode == WB_SYNC_ALL)
tag_pages_for_writeback(mapping, index, end);
done_index = index;
while (!done && (index <= end))
{
int i;
/*在地址空间中查找设备了PAGECACHE_TAG_DIRTY标志的页面，将结果保存在pagevec中*/
nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag,
min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
if (nr_pages == 0)
break;
//对找到的页面进行处理。
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
/*
* At this point, the page may be truncated or
* invalidated (changing page->mapping to NULL), or
* even swizzled back from swapper_space to tmpfs file
* mapping. However, page->index will not change
* because we have a reference on the page.
*/
if (page->index > end) {
/*
* can't be range_cyclic (1st pass) because
* end == -1 in that case.
*/
done = 1;
break;
}
done_index = page->index + 1;
//页面加锁
lock_page(page);
/*
* Page truncated or invalidated. We can freely skip it
* then, even for data integrity operations: the page
* has disappeared concurrently, so there could be no
* real expectation of this data interity operation
* even if there is now a new, dirty page at the same
* pagecache address.
*/
/*由于在加锁过程中可能其它进程对页面做过改动，因此要做以下判断*/
if (unlikely(page->mapping != mapping)) {//页面无效
continue_unlock:
unlock_page(page);
continue;
}
if (!PageDirty(page)) {//页面回写完成，I_DIRTY标志已经清除。
/* someone wrote it for us */
goto continue_unlock;
}
if (PageWriteback(page)) {//页面正在回写中，那要根据sync_mode采取策略
if (wbc->sync_mode != WB_SYNC_NONE)
wait_on_page_writeback(page);//要等待正在回写完成后才继续
else
goto continue_unlock;
}
BUG_ON(PageWriteback(page));
if (!clear_page_dirty_for_io(page))
goto continue_unlock;
trace_wbc_writepage(wbc, mapping->backing_dev_info);
//开始回写"脏"页面
ret = (*writepage)(page, wbc, data);
if (unlikely(ret)) {
if (ret == AOP_WRITEPAGE_ACTIVATE) {
unlock_page(page);
ret = 0;
} else {
/*
* done_index is set past this page,
* so media errors will not choke
* background writeout for the entire
* file. This has consequences for
* range_cyclic semantics (ie. it may
* not be suitable for data integrity
* writeout).
*/
done = 1;
break;
}
}
/*
* We stop writing back only if we are not doing
* integrity sync. In case of integrity sync we have to
* keep going until we have written all the pages
* we tagged for writeback prior to entering this loop.
*/
/*页面写成功后，递减计数器*/
if (--wbc->nr_to_write <= 0 &&
wbc->sync_mode == WB_SYNC_NONE) {
done = 1;
break;
}
}
pagevec_release(&pvec);
cond_resched();
}
if (!cycled && !done) {
/*
* range_cyclic:
* We hit the last page and there is more work to be done: wrap
* back to the start of the file
*/
cycled = 1;
index = 0;
end = writeback_index - 1;
goto retry;
}
if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
mapping->writeback_index = done_index;
return ret;
}
/**
* write_cache_pages - walk the list of dirty pages of the given address space and write all of them.
* @mapping: address space structure to write
* @wbc: subtract the number of written pages from *@wbc->nr_to_write
* @writepage: function called for each page
* @data: data passed to writepage function
*
* If a page is already under I/O, write_cache_pages() skips it, even
* if it's dirty. This is desirable behaviour for memory-cleaning writeback,
* but it is INCORRECT for data-integrity system calls such as fsync(). fsync()
* and msync() need to guarantee that all the data which was dirty at the time
* the call was made get new I/O started against them. If wbc->sync_mode is
* WB_SYNC_ALL then we were called for data integrity and we must wait for
* existing IO to complete.
*/
int write_cache_pages(struct address_space *mapping,
struct writeback_control *wbc, writepage_t writepage,
void *data)
{
struct backing_dev_info *bdi = mapping->backing_dev_info;
int ret = 0;
int done = 0;
struct pagevec pvec;
int nr_pages;
pgoff_t index;
pgoff_t end; /* Inclusive */
int scanned = 0;
int range_whole = 0;
long nr_to_write = wbc->nr_to_write;
if (wbc->nonblocking && bdi_write_congested(bdi)) {
wbc->encountered_congestion = 1;
return 0;
}
pagevec_init(&pvec, 0);
if (wbc->range_cyclic) {
index = mapping->writeback_index; /* Start from prev offset */
end = -1;
} else {
index = wbc->range_start >> PAGE_CACHE_SHIFT;
end = wbc->range_end >> PAGE_CACHE_SHIFT;
if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
range_whole = 1;
scanned = 1;
}
retry:
while (!done && (index <= end) &&
(nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
PAGECACHE_TAG_DIRTY,
min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1))) {
unsigned i;
scanned = 1;
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
/*
* At this point we hold neither mapping->tree_lock nor
* lock on the page itself: the page may be truncated or
* invalidated (changing page->mapping to NULL), or even
* swizzled back from swapper_space to tmpfs file
* mapping
*/
lock_page(page);
if (unlikely(page->mapping != mapping)) {
unlock_page(page);
continue;
}
if (!wbc->range_cyclic && page->index > end) {
done = 1;
unlock_page(page);
continue;
}
if (wbc->sync_mode != WB_SYNC_NONE)
wait_on_page_writeback(page);
if (PageWriteback(page) ||
!clear_page_dirty_for_io(page)) {
unlock_page(page);
continue;
}
ret = (*writepage)(page, wbc, data);
if (unlikely(ret == AOP_WRITEPAGE_ACTIVATE)) {
unlock_page(page);
ret = 0;
}
if (ret || (--nr_to_write <= 0))
done = 1;
if (wbc->nonblocking && bdi_write_congested(bdi)) {
wbc->encountered_congestion = 1;
done = 1;
}
}
pagevec_release(&pvec);
cond_resched();
}
if (!scanned && !done) {
/*
* We hit the last page and there is more work to be done: wrap
* back to the start of the file
*/
scanned = 1;
index = 0;
goto retry;
}
if (!wbc->no_nrwrite_index_update) {
if (wbc->range_cyclic || (range_whole && nr_to_write > 0))
mapping->writeback_index = index;
wbc->nr_to_write = nr_to_write;
}
return ret;
}
/*
* Inspired by write_cache_pages from /mm/page-writeback.c
*/
static int ecryptfs_writepages(struct address_space *mapping,
struct writeback_control *wbc)
{
int ret = 0;
int done = 0;
struct pagevec pvec;
int nr_pages;
pgoff_t uninitialized_var(writeback_index);
pgoff_t index;
pgoff_t end; /* Inclusive */
pgoff_t done_index;
int cycled;
int range_whole = 0;
int tag;
struct page **pgs;
int pgidx;
/* printk("[g-ecryptfs] Info: call writepages\n"); */
pgs = kmalloc(sizeof(struct page*)*PAGEVEC_SIZE, GFP_KERNEL);
if (!pgs) {
printk("[g-ecryptfs] Error: pgs alloc failed!\n");
return -EFAULT;
}
pagevec_init(&pvec, 0);
if (wbc->range_cyclic) {
writeback_index = mapping->writeback_index; /* prev offset */
index = writeback_index;
if (index == 0)
cycled = 1;
else
cycled = 0;
end = -1;
} else {
index = wbc->range_start >> PAGE_CACHE_SHIFT;
end = wbc->range_end >> PAGE_CACHE_SHIFT;
if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
range_whole = 1;
cycled = 1; /* ignore range_cyclic tests */
}
if (wbc->sync_mode == WB_SYNC_ALL)
tag = PAGECACHE_TAG_TOWRITE;
else
tag = PAGECACHE_TAG_DIRTY;
retry:
if (wbc->sync_mode == WB_SYNC_ALL)
tag_pages_for_writeback(mapping, index, end);
done_index = index;
while (!done && (index <= end)) {
int i;
struct page *page;
nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag,
min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
if (nr_pages == 0)
break;
pgidx = 0;
for (i = 0; i < nr_pages; i++) {
page = pvec.pages[i];
/*
* At this point, the page may be truncated or
* invalidated (changing page->mapping to NULL), or
* even swizzled back from swapper_space to tmpfs file
* mapping. However, page->index will not change
* because we have a reference on the page.
*/
if (page->index > end) {
/*
* can't be range_cyclic (1st pass) because
* end == -1 in that case.
*/
done = 1;
break;
}
done_index = page->index + 1;
lock_page(page);
/*
* Page truncated or invalidated. We can freely skip it
* then, even for data integrity operations: the page
* has disappeared concurrently, so there could be no
* real expectation of this data interity operation
* even if there is now a new, dirty page at the same
* pagecache address.
*/
if (unlikely(page->mapping != mapping)) {
continue_unlock:
unlock_page(page);
continue;
}
if (!PageDirty(page)) {
/* someone wrote it for us */
goto continue_unlock;
}
if (PageWriteback(page)) {
if (wbc->sync_mode != WB_SYNC_NONE)
wait_on_page_writeback(page);
else
goto continue_unlock;
}
BUG_ON(PageWriteback(page));
if (!clear_page_dirty_for_io(page))
goto continue_unlock;
pgs[pgidx++] = page;
}
/*trace_wbc_writepage(wbc, mapping->backing_dev_info);*/
ret = ecryptfs_encrypt_pages(pgs, pgidx);
//printk("[g-ecryptfs] Info: enc %d pages in writepages\n", pgidx);
mapping_set_error(mapping, ret);
for (i = 0; i < nr_pages; i++) {
page = pvec.pages[i];
if (unlikely(ret)) {
if (ret == AOP_WRITEPAGE_ACTIVATE) {
if (PageLocked(page))
unlock_page(page);
ret = 0;
} else {
/*
* done_index is set past this page,
* so media errors will not choke
* background writeout for the entire
* file. This has consequences for
* range_cyclic semantics (ie. it may
* not be suitable for data integrity
* writeout).
*/
done = 1;
break;
}
}
/*
* We stop writing back only if we are not doing
* integrity sync. In case of integrity sync we have to
* keep going until we have written all the pages
* we tagged for writeback prior to entering this loop.
*/
if (--wbc->nr_to_write <= 0 &&
wbc->sync_mode == WB_SYNC_NONE) {
done = 1;
break;
}
}
pagevec_release(&pvec);
cond_resched();
}
if (!cycled && !done) {
/*
* range_cyclic:
* We hit the last page and there is more work to be done: wrap
* back to the start of the file
*/
cycled = 1;
index = 0;
end = writeback_index - 1;
goto retry;
}
if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
mapping->writeback_index = done_index;
kfree(pgs);
return ret;
}
/**
* write_cache_pages - walk the list of dirty pages of the given address space and write all of them.
* @mapping: address space structure to write
* @wbc: subtract the number of written pages from *@wbc->nr_to_write
* @writepage: function called for each page
* @data: data passed to writepage function
*
* If a page is already under I/O, write_cache_pages() skips it, even
* if it's dirty. This is desirable behaviour for memory-cleaning writeback,
* but it is INCORRECT for data-integrity system calls such as fsync(). fsync()
* and msync() need to guarantee that all the data which was dirty at the time
* the call was made get new I/O started against them. If wbc->sync_mode is
* WB_SYNC_ALL then we were called for data integrity and we must wait for
* existing IO to complete.
*
* To avoid livelocks (when other process dirties new pages), we first tag
* pages which should be written back with TOWRITE tag and only then start
* writing them. For data-integrity sync we have to be careful so that we do
* not miss some pages (e.g., because some other process has cleared TOWRITE
* tag we set). The rule we follow is that TOWRITE tag can be cleared only
* by the process clearing the DIRTY tag (and submitting the page for IO).
*/
int write_cache_pages(struct address_space *mapping,
struct writeback_control *wbc, writepage_t writepage,
void *data)
{
int ret = 0;
int done = 0;
struct pagevec pvec;
int nr_pages;
pgoff_t index;
pgoff_t end; /* Inclusive */
pgoff_t done_index;
int range_whole = 0;
int tag;
pagevec_init(&pvec, 0);
if (wbc->range_cyclic) {
index = mapping->writeback_index; /* prev offset */
end = -1;
} else {
index = wbc->range_start >> PAGE_CACHE_SHIFT;
end = wbc->range_end >> PAGE_CACHE_SHIFT;
if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
range_whole = 1;
}
if (wbc->sync_mode == WB_SYNC_ALL)
tag = PAGECACHE_TAG_TOWRITE;
else
tag = PAGECACHE_TAG_DIRTY;
if (wbc->sync_mode == WB_SYNC_ALL)
tag_pages_for_writeback(mapping, index, end);
done_index = index;
while (!done && (index <= end)) {
int i;
nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag,
min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
if (nr_pages == 0) {
done_index = 0;
break;
}
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
/*
* At this point, the page may be truncated or
* invalidated (changing page->mapping to NULL), or
* even swizzled back from swapper_space to tmpfs file
* mapping. However, page->index will not change
* because we have a reference on the page.
*/
if (page->index > end) {
/*
* can't be range_cyclic (1st pass) because
* end == -1 in that case.
*/
done = 1;
break;
}
done_index = page->index + 1;
lock_page(page);
/*
* Page truncated or invalidated. We can freely skip it
* then, even for data integrity operations: the page
* has disappeared concurrently, so there could be no
* real expectation of this data interity operation
* even if there is now a new, dirty page at the same
* pagecache address.
*/
if (unlikely(page->mapping != mapping)) {
continue_unlock:
unlock_page(page);
continue;
}
if (!PageDirty(page)) {
/* someone wrote it for us */
goto continue_unlock;
}
if (PageWriteback(page)) {
if (wbc->sync_mode != WB_SYNC_NONE)
wait_on_page_writeback(page);
else
goto continue_unlock;
}
BUG_ON(PageWriteback(page));
if (!clear_page_dirty_for_io(page))
goto continue_unlock;
trace_wbc_writepage(wbc, mapping->backing_dev_info);
ret = (*writepage)(page, wbc, data);
if (unlikely(ret)) {
if (ret == AOP_WRITEPAGE_ACTIVATE) {
unlock_page(page);
ret = 0;
} else {
/*
* done_index is set past this page,
* so media errors will not choke
* background writeout for the entire
* file. This has consequences for
* range_cyclic semantics (ie. it may
* not be suitable for data integrity
* writeout).
*/
done = 1;
break;
}
}
/*
* We stop writing back only if we are not doing
* integrity sync. In case of integrity sync we have to
* keep going until we have written all the pages
* we tagged for writeback prior to entering this loop.
*/
if (--wbc->nr_to_write <= 0 &&
wbc->sync_mode == WB_SYNC_NONE) {
done = 1;
break;
}
}
pagevec_release(&pvec);
cond_resched();
}
if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
mapping->writeback_index = done_index;
return ret;
}
