linux-stable/fs/iomap.c
Linus Torvalds 1ac5cd4978 block: don't use un-ordered __set_current_state(TASK_UNINTERRUPTIBLE)
This mostly reverts commit 849a370016 ("block: avoid ordered task
state change for polled IO").  It was wrongly claiming that the ordering
wasn't necessary.  The memory barrier _is_ necessary.

If something is truly polling and not going to sleep, it's the whole
state setting that is unnecessary, not the memory barrier.  Whenever you
set your state to a sleeping state, you absolutely need the memory
barrier.

Note that sometimes the memory barrier can be elsewhere.  For example,
the ordering might be provided by an external lock, or by setting the
process state to sleeping before adding yourself to the wait queue list
that is used for waking up (where the wait queue lock itself will
guarantee that any wakeup will correctly see the sleeping state).

But none of those cases were true here.

NOTE! Some of the polling paths may indeed be able to drop the state
setting entirely, at which point the memory barrier also goes away.

(Also note that this doesn't revert the TASK_RUNNING cases: there is no
race between a wakeup and setting the process state to TASK_RUNNING,
since the end result doesn't depend on ordering).

Cc: Jens Axboe <axboe@kernel.dk>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-01-02 10:46:03 -08:00

2149 lines
53 KiB
C

/*
* Copyright (C) 2010 Red Hat, Inc.
* Copyright (c) 2016-2018 Christoph Hellwig.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms and conditions of the GNU General Public License,
* version 2, as published by the Free Software Foundation.
*
* This program is distributed in the hope it will be useful, but WITHOUT
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
* more details.
*/
#include <linux/module.h>
#include <linux/compiler.h>
#include <linux/fs.h>
#include <linux/iomap.h>
#include <linux/uaccess.h>
#include <linux/gfp.h>
#include <linux/migrate.h>
#include <linux/mm.h>
#include <linux/mm_inline.h>
#include <linux/swap.h>
#include <linux/pagemap.h>
#include <linux/pagevec.h>
#include <linux/file.h>
#include <linux/uio.h>
#include <linux/backing-dev.h>
#include <linux/buffer_head.h>
#include <linux/task_io_accounting_ops.h>
#include <linux/dax.h>
#include <linux/sched/signal.h>
#include "internal.h"
/*
* Execute a iomap write on a segment of the mapping that spans a
* contiguous range of pages that have identical block mapping state.
*
* This avoids the need to map pages individually, do individual allocations
* for each page and most importantly avoid the need for filesystem specific
* locking per page. Instead, all the operations are amortised over the entire
* range of pages. It is assumed that the filesystems will lock whatever
* resources they require in the iomap_begin call, and release them in the
* iomap_end call.
*/
loff_t
iomap_apply(struct inode *inode, loff_t pos, loff_t length, unsigned flags,
const struct iomap_ops *ops, void *data, iomap_actor_t actor)
{
struct iomap iomap = { 0 };
loff_t written = 0, ret;
/*
* Need to map a range from start position for length bytes. This can
* span multiple pages - it is only guaranteed to return a range of a
* single type of pages (e.g. all into a hole, all mapped or all
* unwritten). Failure at this point has nothing to undo.
*
* If allocation is required for this range, reserve the space now so
* that the allocation is guaranteed to succeed later on. Once we copy
* the data into the page cache pages, then we cannot fail otherwise we
* expose transient stale data. If the reserve fails, we can safely
* back out at this point as there is nothing to undo.
*/
ret = ops->iomap_begin(inode, pos, length, flags, &iomap);
if (ret)
return ret;
if (WARN_ON(iomap.offset > pos))
return -EIO;
if (WARN_ON(iomap.length == 0))
return -EIO;
/*
* Cut down the length to the one actually provided by the filesystem,
* as it might not be able to give us the whole size that we requested.
*/
if (iomap.offset + iomap.length < pos + length)
length = iomap.offset + iomap.length - pos;
/*
* Now that we have guaranteed that the space allocation will succeed.
* we can do the copy-in page by page without having to worry about
* failures exposing transient data.
*/
written = actor(inode, pos, length, data, &iomap);
/*
* Now the data has been copied, commit the range we've copied. This
* should not fail unless the filesystem has had a fatal error.
*/
if (ops->iomap_end) {
ret = ops->iomap_end(inode, pos, length,
written > 0 ? written : 0,
flags, &iomap);
}
return written ? written : ret;
}
static sector_t
iomap_sector(struct iomap *iomap, loff_t pos)
{
return (iomap->addr + pos - iomap->offset) >> SECTOR_SHIFT;
}
static struct iomap_page *
iomap_page_create(struct inode *inode, struct page *page)
{
struct iomap_page *iop = to_iomap_page(page);
if (iop || i_blocksize(inode) == PAGE_SIZE)
return iop;
iop = kmalloc(sizeof(*iop), GFP_NOFS | __GFP_NOFAIL);
atomic_set(&iop->read_count, 0);
atomic_set(&iop->write_count, 0);
bitmap_zero(iop->uptodate, PAGE_SIZE / SECTOR_SIZE);
set_page_private(page, (unsigned long)iop);
SetPagePrivate(page);
return iop;
}
static void
iomap_page_release(struct page *page)
{
struct iomap_page *iop = to_iomap_page(page);
if (!iop)
return;
WARN_ON_ONCE(atomic_read(&iop->read_count));
WARN_ON_ONCE(atomic_read(&iop->write_count));
ClearPagePrivate(page);
set_page_private(page, 0);
kfree(iop);
}
/*
* Calculate the range inside the page that we actually need to read.
*/
static void
iomap_adjust_read_range(struct inode *inode, struct iomap_page *iop,
loff_t *pos, loff_t length, unsigned *offp, unsigned *lenp)
{
loff_t orig_pos = *pos;
loff_t isize = i_size_read(inode);
unsigned block_bits = inode->i_blkbits;
unsigned block_size = (1 << block_bits);
unsigned poff = offset_in_page(*pos);
unsigned plen = min_t(loff_t, PAGE_SIZE - poff, length);
unsigned first = poff >> block_bits;
unsigned last = (poff + plen - 1) >> block_bits;
/*
* If the block size is smaller than the page size we need to check the
* per-block uptodate status and adjust the offset and length if needed
* to avoid reading in already uptodate ranges.
*/
if (iop) {
unsigned int i;
/* move forward for each leading block marked uptodate */
for (i = first; i <= last; i++) {
if (!test_bit(i, iop->uptodate))
break;
*pos += block_size;
poff += block_size;
plen -= block_size;
first++;
}
/* truncate len if we find any trailing uptodate block(s) */
for ( ; i <= last; i++) {
if (test_bit(i, iop->uptodate)) {
plen -= (last - i + 1) * block_size;
last = i - 1;
break;
}
}
}
/*
* If the extent spans the block that contains the i_size we need to
* handle both halves separately so that we properly zero data in the
* page cache for blocks that are entirely outside of i_size.
*/
if (orig_pos <= isize && orig_pos + length > isize) {
unsigned end = offset_in_page(isize - 1) >> block_bits;
if (first <= end && last > end)
plen -= (last - end) * block_size;
}
*offp = poff;
*lenp = plen;
}
static void
iomap_set_range_uptodate(struct page *page, unsigned off, unsigned len)
{
struct iomap_page *iop = to_iomap_page(page);
struct inode *inode = page->mapping->host;
unsigned first = off >> inode->i_blkbits;
unsigned last = (off + len - 1) >> inode->i_blkbits;
unsigned int i;
bool uptodate = true;
if (iop) {
for (i = 0; i < PAGE_SIZE / i_blocksize(inode); i++) {
if (i >= first && i <= last)
set_bit(i, iop->uptodate);
else if (!test_bit(i, iop->uptodate))
uptodate = false;
}
}
if (uptodate && !PageError(page))
SetPageUptodate(page);
}
static void
iomap_read_finish(struct iomap_page *iop, struct page *page)
{
if (!iop || atomic_dec_and_test(&iop->read_count))
unlock_page(page);
}
static void
iomap_read_page_end_io(struct bio_vec *bvec, int error)
{
struct page *page = bvec->bv_page;
struct iomap_page *iop = to_iomap_page(page);
if (unlikely(error)) {
ClearPageUptodate(page);
SetPageError(page);
} else {
iomap_set_range_uptodate(page, bvec->bv_offset, bvec->bv_len);
}
iomap_read_finish(iop, page);
}
static void
iomap_read_inline_data(struct inode *inode, struct page *page,
struct iomap *iomap)
{
size_t size = i_size_read(inode);
void *addr;
if (PageUptodate(page))
return;
BUG_ON(page->index);
BUG_ON(size > PAGE_SIZE - offset_in_page(iomap->inline_data));
addr = kmap_atomic(page);
memcpy(addr, iomap->inline_data, size);
memset(addr + size, 0, PAGE_SIZE - size);
kunmap_atomic(addr);
SetPageUptodate(page);
}
static void
iomap_read_end_io(struct bio *bio)
{
int error = blk_status_to_errno(bio->bi_status);
struct bio_vec *bvec;
int i;
bio_for_each_segment_all(bvec, bio, i)
iomap_read_page_end_io(bvec, error);
bio_put(bio);
}
struct iomap_readpage_ctx {
struct page *cur_page;
bool cur_page_in_bio;
bool is_readahead;
struct bio *bio;
struct list_head *pages;
};
static loff_t
iomap_readpage_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
struct iomap *iomap)
{
struct iomap_readpage_ctx *ctx = data;
struct page *page = ctx->cur_page;
struct iomap_page *iop = iomap_page_create(inode, page);
bool is_contig = false;
loff_t orig_pos = pos;
unsigned poff, plen;
sector_t sector;
if (iomap->type == IOMAP_INLINE) {
WARN_ON_ONCE(pos);
iomap_read_inline_data(inode, page, iomap);
return PAGE_SIZE;
}
/* zero post-eof blocks as the page may be mapped */
iomap_adjust_read_range(inode, iop, &pos, length, &poff, &plen);
if (plen == 0)
goto done;
if (iomap->type != IOMAP_MAPPED || pos >= i_size_read(inode)) {
zero_user(page, poff, plen);
iomap_set_range_uptodate(page, poff, plen);
goto done;
}
ctx->cur_page_in_bio = true;
/*
* Try to merge into a previous segment if we can.
*/
sector = iomap_sector(iomap, pos);
if (ctx->bio && bio_end_sector(ctx->bio) == sector) {
if (__bio_try_merge_page(ctx->bio, page, plen, poff))
goto done;
is_contig = true;
}
/*
* If we start a new segment we need to increase the read count, and we
* need to do so before submitting any previous full bio to make sure
* that we don't prematurely unlock the page.
*/
if (iop)
atomic_inc(&iop->read_count);
if (!ctx->bio || !is_contig || bio_full(ctx->bio)) {
gfp_t gfp = mapping_gfp_constraint(page->mapping, GFP_KERNEL);
int nr_vecs = (length + PAGE_SIZE - 1) >> PAGE_SHIFT;
if (ctx->bio)
submit_bio(ctx->bio);
if (ctx->is_readahead) /* same as readahead_gfp_mask */
gfp |= __GFP_NORETRY | __GFP_NOWARN;
ctx->bio = bio_alloc(gfp, min(BIO_MAX_PAGES, nr_vecs));
ctx->bio->bi_opf = REQ_OP_READ;
if (ctx->is_readahead)
ctx->bio->bi_opf |= REQ_RAHEAD;
ctx->bio->bi_iter.bi_sector = sector;
bio_set_dev(ctx->bio, iomap->bdev);
ctx->bio->bi_end_io = iomap_read_end_io;
}
__bio_add_page(ctx->bio, page, plen, poff);
done:
/*
* Move the caller beyond our range so that it keeps making progress.
* For that we have to include any leading non-uptodate ranges, but
* we can skip trailing ones as they will be handled in the next
* iteration.
*/
return pos - orig_pos + plen;
}
int
iomap_readpage(struct page *page, const struct iomap_ops *ops)
{
struct iomap_readpage_ctx ctx = { .cur_page = page };
struct inode *inode = page->mapping->host;
unsigned poff;
loff_t ret;
for (poff = 0; poff < PAGE_SIZE; poff += ret) {
ret = iomap_apply(inode, page_offset(page) + poff,
PAGE_SIZE - poff, 0, ops, &ctx,
iomap_readpage_actor);
if (ret <= 0) {
WARN_ON_ONCE(ret == 0);
SetPageError(page);
break;
}
}
if (ctx.bio) {
submit_bio(ctx.bio);
WARN_ON_ONCE(!ctx.cur_page_in_bio);
} else {
WARN_ON_ONCE(ctx.cur_page_in_bio);
unlock_page(page);
}
/*
* Just like mpage_readpages and block_read_full_page we always
* return 0 and just mark the page as PageError on errors. This
* should be cleaned up all through the stack eventually.
*/
return 0;
}
EXPORT_SYMBOL_GPL(iomap_readpage);
static struct page *
iomap_next_page(struct inode *inode, struct list_head *pages, loff_t pos,
loff_t length, loff_t *done)
{
while (!list_empty(pages)) {
struct page *page = lru_to_page(pages);
if (page_offset(page) >= (u64)pos + length)
break;
list_del(&page->lru);
if (!add_to_page_cache_lru(page, inode->i_mapping, page->index,
GFP_NOFS))
return page;
/*
* If we already have a page in the page cache at index we are
* done. Upper layers don't care if it is uptodate after the
* readpages call itself as every page gets checked again once
* actually needed.
*/
*done += PAGE_SIZE;
put_page(page);
}
return NULL;
}
static loff_t
iomap_readpages_actor(struct inode *inode, loff_t pos, loff_t length,
void *data, struct iomap *iomap)
{
struct iomap_readpage_ctx *ctx = data;
loff_t done, ret;
for (done = 0; done < length; done += ret) {
if (ctx->cur_page && offset_in_page(pos + done) == 0) {
if (!ctx->cur_page_in_bio)
unlock_page(ctx->cur_page);
put_page(ctx->cur_page);
ctx->cur_page = NULL;
}
if (!ctx->cur_page) {
ctx->cur_page = iomap_next_page(inode, ctx->pages,
pos, length, &done);
if (!ctx->cur_page)
break;
ctx->cur_page_in_bio = false;
}
ret = iomap_readpage_actor(inode, pos + done, length - done,
ctx, iomap);
}
return done;
}
int
iomap_readpages(struct address_space *mapping, struct list_head *pages,
unsigned nr_pages, const struct iomap_ops *ops)
{
struct iomap_readpage_ctx ctx = {
.pages = pages,
.is_readahead = true,
};
loff_t pos = page_offset(list_entry(pages->prev, struct page, lru));
loff_t last = page_offset(list_entry(pages->next, struct page, lru));
loff_t length = last - pos + PAGE_SIZE, ret = 0;
while (length > 0) {
ret = iomap_apply(mapping->host, pos, length, 0, ops,
&ctx, iomap_readpages_actor);
if (ret <= 0) {
WARN_ON_ONCE(ret == 0);
goto done;
}
pos += ret;
length -= ret;
}
ret = 0;
done:
if (ctx.bio)
submit_bio(ctx.bio);
if (ctx.cur_page) {
if (!ctx.cur_page_in_bio)
unlock_page(ctx.cur_page);
put_page(ctx.cur_page);
}
/*
* Check that we didn't lose a page due to the arcance calling
* conventions..
*/
WARN_ON_ONCE(!ret && !list_empty(ctx.pages));
return ret;
}
EXPORT_SYMBOL_GPL(iomap_readpages);
/*
* iomap_is_partially_uptodate checks whether blocks within a page are
* uptodate or not.
*
* Returns true if all blocks which correspond to a file portion
* we want to read within the page are uptodate.
*/
int
iomap_is_partially_uptodate(struct page *page, unsigned long from,
unsigned long count)
{
struct iomap_page *iop = to_iomap_page(page);
struct inode *inode = page->mapping->host;
unsigned len, first, last;
unsigned i;
/* Limit range to one page */
len = min_t(unsigned, PAGE_SIZE - from, count);
/* First and last blocks in range within page */
first = from >> inode->i_blkbits;
last = (from + len - 1) >> inode->i_blkbits;
if (iop) {
for (i = first; i <= last; i++)
if (!test_bit(i, iop->uptodate))
return 0;
return 1;
}
return 0;
}
EXPORT_SYMBOL_GPL(iomap_is_partially_uptodate);
int
iomap_releasepage(struct page *page, gfp_t gfp_mask)
{
/*
* mm accommodates an old ext3 case where clean pages might not have had
* the dirty bit cleared. Thus, it can send actual dirty pages to
* ->releasepage() via shrink_active_list(), skip those here.
*/
if (PageDirty(page) || PageWriteback(page))
return 0;
iomap_page_release(page);
return 1;
}
EXPORT_SYMBOL_GPL(iomap_releasepage);
void
iomap_invalidatepage(struct page *page, unsigned int offset, unsigned int len)
{
/*
* If we are invalidating the entire page, clear the dirty state from it
* and release it to avoid unnecessary buildup of the LRU.
*/
if (offset == 0 && len == PAGE_SIZE) {
WARN_ON_ONCE(PageWriteback(page));
cancel_dirty_page(page);
iomap_page_release(page);
}
}
EXPORT_SYMBOL_GPL(iomap_invalidatepage);
#ifdef CONFIG_MIGRATION
int
iomap_migrate_page(struct address_space *mapping, struct page *newpage,
struct page *page, enum migrate_mode mode)
{
int ret;
ret = migrate_page_move_mapping(mapping, newpage, page, mode, 0);
if (ret != MIGRATEPAGE_SUCCESS)
return ret;
if (page_has_private(page)) {
ClearPagePrivate(page);
set_page_private(newpage, page_private(page));
set_page_private(page, 0);
SetPagePrivate(newpage);
}
if (mode != MIGRATE_SYNC_NO_COPY)
migrate_page_copy(newpage, page);
else
migrate_page_states(newpage, page);
return MIGRATEPAGE_SUCCESS;
}
EXPORT_SYMBOL_GPL(iomap_migrate_page);
#endif /* CONFIG_MIGRATION */
static void
iomap_write_failed(struct inode *inode, loff_t pos, unsigned len)
{
loff_t i_size = i_size_read(inode);
/*
* Only truncate newly allocated pages beyoned EOF, even if the
* write started inside the existing inode size.
*/
if (pos + len > i_size)
truncate_pagecache_range(inode, max(pos, i_size), pos + len);
}
static int
iomap_read_page_sync(struct inode *inode, loff_t block_start, struct page *page,
unsigned poff, unsigned plen, unsigned from, unsigned to,
struct iomap *iomap)
{
struct bio_vec bvec;
struct bio bio;
if (iomap->type != IOMAP_MAPPED || block_start >= i_size_read(inode)) {
zero_user_segments(page, poff, from, to, poff + plen);
iomap_set_range_uptodate(page, poff, plen);
return 0;
}
bio_init(&bio, &bvec, 1);
bio.bi_opf = REQ_OP_READ;
bio.bi_iter.bi_sector = iomap_sector(iomap, block_start);
bio_set_dev(&bio, iomap->bdev);
__bio_add_page(&bio, page, plen, poff);
return submit_bio_wait(&bio);
}
static int
__iomap_write_begin(struct inode *inode, loff_t pos, unsigned len,
struct page *page, struct iomap *iomap)
{
struct iomap_page *iop = iomap_page_create(inode, page);
loff_t block_size = i_blocksize(inode);
loff_t block_start = pos & ~(block_size - 1);
loff_t block_end = (pos + len + block_size - 1) & ~(block_size - 1);
unsigned from = offset_in_page(pos), to = from + len, poff, plen;
int status = 0;
if (PageUptodate(page))
return 0;
do {
iomap_adjust_read_range(inode, iop, &block_start,
block_end - block_start, &poff, &plen);
if (plen == 0)
break;
if ((from > poff && from < poff + plen) ||
(to > poff && to < poff + plen)) {
status = iomap_read_page_sync(inode, block_start, page,
poff, plen, from, to, iomap);
if (status)
break;
}
} while ((block_start += plen) < block_end);
return status;
}
static int
iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags,
struct page **pagep, struct iomap *iomap)
{
pgoff_t index = pos >> PAGE_SHIFT;
struct page *page;
int status = 0;
BUG_ON(pos + len > iomap->offset + iomap->length);
if (fatal_signal_pending(current))
return -EINTR;
page = grab_cache_page_write_begin(inode->i_mapping, index, flags);
if (!page)
return -ENOMEM;
if (iomap->type == IOMAP_INLINE)
iomap_read_inline_data(inode, page, iomap);
else if (iomap->flags & IOMAP_F_BUFFER_HEAD)
status = __block_write_begin_int(page, pos, len, NULL, iomap);
else
status = __iomap_write_begin(inode, pos, len, page, iomap);
if (unlikely(status)) {
unlock_page(page);
put_page(page);
page = NULL;
iomap_write_failed(inode, pos, len);
}
*pagep = page;
return status;
}
int
iomap_set_page_dirty(struct page *page)
{
struct address_space *mapping = page_mapping(page);
int newly_dirty;
if (unlikely(!mapping))
return !TestSetPageDirty(page);
/*
* Lock out page->mem_cgroup migration to keep PageDirty
* synchronized with per-memcg dirty page counters.
*/
lock_page_memcg(page);
newly_dirty = !TestSetPageDirty(page);
if (newly_dirty)
__set_page_dirty(page, mapping, 0);
unlock_page_memcg(page);
if (newly_dirty)
__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
return newly_dirty;
}
EXPORT_SYMBOL_GPL(iomap_set_page_dirty);
static int
__iomap_write_end(struct inode *inode, loff_t pos, unsigned len,
unsigned copied, struct page *page, struct iomap *iomap)
{
flush_dcache_page(page);
/*
* The blocks that were entirely written will now be uptodate, so we
* don't have to worry about a readpage reading them and overwriting a
* partial write. However if we have encountered a short write and only
* partially written into a block, it will not be marked uptodate, so a
* readpage might come in and destroy our partial write.
*
* Do the simplest thing, and just treat any short write to a non
* uptodate page as a zero-length write, and force the caller to redo
* the whole thing.
*/
if (unlikely(copied < len && !PageUptodate(page))) {
copied = 0;
} else {
iomap_set_range_uptodate(page, offset_in_page(pos), len);
iomap_set_page_dirty(page);
}
return __generic_write_end(inode, pos, copied, page);
}
static int
iomap_write_end_inline(struct inode *inode, struct page *page,
struct iomap *iomap, loff_t pos, unsigned copied)
{
void *addr;
WARN_ON_ONCE(!PageUptodate(page));
BUG_ON(pos + copied > PAGE_SIZE - offset_in_page(iomap->inline_data));
addr = kmap_atomic(page);
memcpy(iomap->inline_data + pos, addr + pos, copied);
kunmap_atomic(addr);
mark_inode_dirty(inode);
__generic_write_end(inode, pos, copied, page);
return copied;
}
static int
iomap_write_end(struct inode *inode, loff_t pos, unsigned len,
unsigned copied, struct page *page, struct iomap *iomap)
{
int ret;
if (iomap->type == IOMAP_INLINE) {
ret = iomap_write_end_inline(inode, page, iomap, pos, copied);
} else if (iomap->flags & IOMAP_F_BUFFER_HEAD) {
ret = generic_write_end(NULL, inode->i_mapping, pos, len,
copied, page, NULL);
} else {
ret = __iomap_write_end(inode, pos, len, copied, page, iomap);
}
if (iomap->page_done)
iomap->page_done(inode, pos, copied, page, iomap);
if (ret < len)
iomap_write_failed(inode, pos, len);
return ret;
}
static loff_t
iomap_write_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
struct iomap *iomap)
{
struct iov_iter *i = data;
long status = 0;
ssize_t written = 0;
unsigned int flags = AOP_FLAG_NOFS;
do {
struct page *page;
unsigned long offset; /* Offset into pagecache page */
unsigned long bytes; /* Bytes to write to page */
size_t copied; /* Bytes copied from user */
offset = offset_in_page(pos);
bytes = min_t(unsigned long, PAGE_SIZE - offset,
iov_iter_count(i));
again:
if (bytes > length)
bytes = length;
/*
* Bring in the user page that we will copy from _first_.
* Otherwise there's a nasty deadlock on copying from the
* same page as we're writing to, without it being marked
* up-to-date.
*
* Not only is this an optimisation, but it is also required
* to check that the address is actually valid, when atomic
* usercopies are used, below.
*/
if (unlikely(iov_iter_fault_in_readable(i, bytes))) {
status = -EFAULT;
break;
}
status = iomap_write_begin(inode, pos, bytes, flags, &page,
iomap);
if (unlikely(status))
break;
if (mapping_writably_mapped(inode->i_mapping))
flush_dcache_page(page);
copied = iov_iter_copy_from_user_atomic(page, i, offset, bytes);
flush_dcache_page(page);
status = iomap_write_end(inode, pos, bytes, copied, page,
iomap);
if (unlikely(status < 0))
break;
copied = status;
cond_resched();
iov_iter_advance(i, copied);
if (unlikely(copied == 0)) {
/*
* If we were unable to copy any data at all, we must
* fall back to a single segment length write.
*
* If we didn't fallback here, we could livelock
* because not all segments in the iov can be copied at
* once without a pagefault.
*/
bytes = min_t(unsigned long, PAGE_SIZE - offset,
iov_iter_single_seg_count(i));
goto again;
}
pos += copied;
written += copied;
length -= copied;
balance_dirty_pages_ratelimited(inode->i_mapping);
} while (iov_iter_count(i) && length);
return written ? written : status;
}
ssize_t
iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *iter,
const struct iomap_ops *ops)
{
struct inode *inode = iocb->ki_filp->f_mapping->host;
loff_t pos = iocb->ki_pos, ret = 0, written = 0;
while (iov_iter_count(iter)) {
ret = iomap_apply(inode, pos, iov_iter_count(iter),
IOMAP_WRITE, ops, iter, iomap_write_actor);
if (ret <= 0)
break;
pos += ret;
written += ret;
}
return written ? written : ret;
}
EXPORT_SYMBOL_GPL(iomap_file_buffered_write);
static struct page *
__iomap_read_page(struct inode *inode, loff_t offset)
{
struct address_space *mapping = inode->i_mapping;
struct page *page;
page = read_mapping_page(mapping, offset >> PAGE_SHIFT, NULL);
if (IS_ERR(page))
return page;
if (!PageUptodate(page)) {
put_page(page);
return ERR_PTR(-EIO);
}
return page;
}
static loff_t
iomap_dirty_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
struct iomap *iomap)
{
long status = 0;
ssize_t written = 0;
do {
struct page *page, *rpage;
unsigned long offset; /* Offset into pagecache page */
unsigned long bytes; /* Bytes to write to page */
offset = offset_in_page(pos);
bytes = min_t(loff_t, PAGE_SIZE - offset, length);
rpage = __iomap_read_page(inode, pos);
if (IS_ERR(rpage))
return PTR_ERR(rpage);
status = iomap_write_begin(inode, pos, bytes,
AOP_FLAG_NOFS, &page, iomap);
put_page(rpage);
if (unlikely(status))
return status;
WARN_ON_ONCE(!PageUptodate(page));
status = iomap_write_end(inode, pos, bytes, bytes, page, iomap);
if (unlikely(status <= 0)) {
if (WARN_ON_ONCE(status == 0))
return -EIO;
return status;
}
cond_resched();
pos += status;
written += status;
length -= status;
balance_dirty_pages_ratelimited(inode->i_mapping);
} while (length);
return written;
}
int
iomap_file_dirty(struct inode *inode, loff_t pos, loff_t len,
const struct iomap_ops *ops)
{
loff_t ret;
while (len) {
ret = iomap_apply(inode, pos, len, IOMAP_WRITE, ops, NULL,
iomap_dirty_actor);
if (ret <= 0)
return ret;
pos += ret;
len -= ret;
}
return 0;
}
EXPORT_SYMBOL_GPL(iomap_file_dirty);
static int iomap_zero(struct inode *inode, loff_t pos, unsigned offset,
unsigned bytes, struct iomap *iomap)
{
struct page *page;
int status;
status = iomap_write_begin(inode, pos, bytes, AOP_FLAG_NOFS, &page,
iomap);
if (status)
return status;
zero_user(page, offset, bytes);
mark_page_accessed(page);
return iomap_write_end(inode, pos, bytes, bytes, page, iomap);
}
static int iomap_dax_zero(loff_t pos, unsigned offset, unsigned bytes,
struct iomap *iomap)
{
return __dax_zero_page_range(iomap->bdev, iomap->dax_dev,
iomap_sector(iomap, pos & PAGE_MASK), offset, bytes);
}
static loff_t
iomap_zero_range_actor(struct inode *inode, loff_t pos, loff_t count,
void *data, struct iomap *iomap)
{
bool *did_zero = data;
loff_t written = 0;
int status;
/* already zeroed? we're done. */
if (iomap->type == IOMAP_HOLE || iomap->type == IOMAP_UNWRITTEN)
return count;
do {
unsigned offset, bytes;
offset = offset_in_page(pos);
bytes = min_t(loff_t, PAGE_SIZE - offset, count);
if (IS_DAX(inode))
status = iomap_dax_zero(pos, offset, bytes, iomap);
else
status = iomap_zero(inode, pos, offset, bytes, iomap);
if (status < 0)
return status;
pos += bytes;
count -= bytes;
written += bytes;
if (did_zero)
*did_zero = true;
} while (count > 0);
return written;
}
int
iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero,
const struct iomap_ops *ops)
{
loff_t ret;
while (len > 0) {
ret = iomap_apply(inode, pos, len, IOMAP_ZERO,
ops, did_zero, iomap_zero_range_actor);
if (ret <= 0)
return ret;
pos += ret;
len -= ret;
}
return 0;
}
EXPORT_SYMBOL_GPL(iomap_zero_range);
int
iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero,
const struct iomap_ops *ops)
{
unsigned int blocksize = i_blocksize(inode);
unsigned int off = pos & (blocksize - 1);
/* Block boundary? Nothing to do */
if (!off)
return 0;
return iomap_zero_range(inode, pos, blocksize - off, did_zero, ops);
}
EXPORT_SYMBOL_GPL(iomap_truncate_page);
static loff_t
iomap_page_mkwrite_actor(struct inode *inode, loff_t pos, loff_t length,
void *data, struct iomap *iomap)
{
struct page *page = data;
int ret;
if (iomap->flags & IOMAP_F_BUFFER_HEAD) {
ret = __block_write_begin_int(page, pos, length, NULL, iomap);
if (ret)
return ret;
block_commit_write(page, 0, length);
} else {
WARN_ON_ONCE(!PageUptodate(page));
iomap_page_create(inode, page);
set_page_dirty(page);
}
return length;
}
vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops)
{
struct page *page = vmf->page;
struct inode *inode = file_inode(vmf->vma->vm_file);
unsigned long length;
loff_t offset, size;
ssize_t ret;
lock_page(page);
size = i_size_read(inode);
if ((page->mapping != inode->i_mapping) ||
(page_offset(page) > size)) {
/* We overload EFAULT to mean page got truncated */
ret = -EFAULT;
goto out_unlock;
}
/* page is wholly or partially inside EOF */
if (((page->index + 1) << PAGE_SHIFT) > size)
length = offset_in_page(size);
else
length = PAGE_SIZE;
offset = page_offset(page);
while (length > 0) {
ret = iomap_apply(inode, offset, length,
IOMAP_WRITE | IOMAP_FAULT, ops, page,
iomap_page_mkwrite_actor);
if (unlikely(ret <= 0))
goto out_unlock;
offset += ret;
length -= ret;
}
wait_for_stable_page(page);
return VM_FAULT_LOCKED;
out_unlock:
unlock_page(page);
return block_page_mkwrite_return(ret);
}
EXPORT_SYMBOL_GPL(iomap_page_mkwrite);
struct fiemap_ctx {
struct fiemap_extent_info *fi;
struct iomap prev;
};
static int iomap_to_fiemap(struct fiemap_extent_info *fi,
struct iomap *iomap, u32 flags)
{
switch (iomap->type) {
case IOMAP_HOLE:
/* skip holes */
return 0;
case IOMAP_DELALLOC:
flags |= FIEMAP_EXTENT_DELALLOC | FIEMAP_EXTENT_UNKNOWN;
break;
case IOMAP_MAPPED:
break;
case IOMAP_UNWRITTEN:
flags |= FIEMAP_EXTENT_UNWRITTEN;
break;
case IOMAP_INLINE:
flags |= FIEMAP_EXTENT_DATA_INLINE;
break;
}
if (iomap->flags & IOMAP_F_MERGED)
flags |= FIEMAP_EXTENT_MERGED;
if (iomap->flags & IOMAP_F_SHARED)
flags |= FIEMAP_EXTENT_SHARED;
return fiemap_fill_next_extent(fi, iomap->offset,
iomap->addr != IOMAP_NULL_ADDR ? iomap->addr : 0,
iomap->length, flags);
}
static loff_t
iomap_fiemap_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
struct iomap *iomap)
{
struct fiemap_ctx *ctx = data;
loff_t ret = length;
if (iomap->type == IOMAP_HOLE)
return length;
ret = iomap_to_fiemap(ctx->fi, &ctx->prev, 0);
ctx->prev = *iomap;
switch (ret) {
case 0: /* success */
return length;
case 1: /* extent array full */
return 0;
default:
return ret;
}
}
int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fi,
loff_t start, loff_t len, const struct iomap_ops *ops)
{
struct fiemap_ctx ctx;
loff_t ret;
memset(&ctx, 0, sizeof(ctx));
ctx.fi = fi;
ctx.prev.type = IOMAP_HOLE;
ret = fiemap_check_flags(fi, FIEMAP_FLAG_SYNC);
if (ret)
return ret;
if (fi->fi_flags & FIEMAP_FLAG_SYNC) {
ret = filemap_write_and_wait(inode->i_mapping);
if (ret)
return ret;
}
while (len > 0) {
ret = iomap_apply(inode, start, len, IOMAP_REPORT, ops, &ctx,
iomap_fiemap_actor);
/* inode with no (attribute) mapping will give ENOENT */
if (ret == -ENOENT)
break;
if (ret < 0)
return ret;
if (ret == 0)
break;
start += ret;
len -= ret;
}
if (ctx.prev.type != IOMAP_HOLE) {
ret = iomap_to_fiemap(fi, &ctx.prev, FIEMAP_EXTENT_LAST);
if (ret < 0)
return ret;
}
return 0;
}
EXPORT_SYMBOL_GPL(iomap_fiemap);
/*
* Seek for SEEK_DATA / SEEK_HOLE within @page, starting at @lastoff.
* Returns true if found and updates @lastoff to the offset in file.
*/
static bool
page_seek_hole_data(struct inode *inode, struct page *page, loff_t *lastoff,
int whence)
{
const struct address_space_operations *ops = inode->i_mapping->a_ops;
unsigned int bsize = i_blocksize(inode), off;
bool seek_data = whence == SEEK_DATA;
loff_t poff = page_offset(page);
if (WARN_ON_ONCE(*lastoff >= poff + PAGE_SIZE))
return false;
if (*lastoff < poff) {
/*
* Last offset smaller than the start of the page means we found
* a hole:
*/
if (whence == SEEK_HOLE)
return true;
*lastoff = poff;
}
/*
* Just check the page unless we can and should check block ranges:
*/
if (bsize == PAGE_SIZE || !ops->is_partially_uptodate)
return PageUptodate(page) == seek_data;
lock_page(page);
if (unlikely(page->mapping != inode->i_mapping))
goto out_unlock_not_found;
for (off = 0; off < PAGE_SIZE; off += bsize) {
if (offset_in_page(*lastoff) >= off + bsize)
continue;
if (ops->is_partially_uptodate(page, off, bsize) == seek_data) {
unlock_page(page);
return true;
}
*lastoff = poff + off + bsize;
}
out_unlock_not_found:
unlock_page(page);
return false;
}
/*
* Seek for SEEK_DATA / SEEK_HOLE in the page cache.
*
* Within unwritten extents, the page cache determines which parts are holes
* and which are data: uptodate buffer heads count as data; everything else
* counts as a hole.
*
* Returns the resulting offset on successs, and -ENOENT otherwise.
*/
static loff_t
page_cache_seek_hole_data(struct inode *inode, loff_t offset, loff_t length,
int whence)
{
pgoff_t index = offset >> PAGE_SHIFT;
pgoff_t end = DIV_ROUND_UP(offset + length, PAGE_SIZE);
loff_t lastoff = offset;
struct pagevec pvec;
if (length <= 0)
return -ENOENT;
pagevec_init(&pvec);
do {
unsigned nr_pages, i;
nr_pages = pagevec_lookup_range(&pvec, inode->i_mapping, &index,
end - 1);
if (nr_pages == 0)
break;
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
if (page_seek_hole_data(inode, page, &lastoff, whence))
goto check_range;
lastoff = page_offset(page) + PAGE_SIZE;
}
pagevec_release(&pvec);
} while (index < end);
/* When no page at lastoff and we are not done, we found a hole. */
if (whence != SEEK_HOLE)
goto not_found;
check_range:
if (lastoff < offset + length)
goto out;
not_found:
lastoff = -ENOENT;
out:
pagevec_release(&pvec);
return lastoff;
}
static loff_t
iomap_seek_hole_actor(struct inode *inode, loff_t offset, loff_t length,
void *data, struct iomap *iomap)
{
switch (iomap->type) {
case IOMAP_UNWRITTEN:
offset = page_cache_seek_hole_data(inode, offset, length,
SEEK_HOLE);
if (offset < 0)
return length;
/* fall through */
case IOMAP_HOLE:
*(loff_t *)data = offset;
return 0;
default:
return length;
}
}
loff_t
iomap_seek_hole(struct inode *inode, loff_t offset, const struct iomap_ops *ops)
{
loff_t size = i_size_read(inode);
loff_t length = size - offset;
loff_t ret;
/* Nothing to be found before or beyond the end of the file. */
if (offset < 0 || offset >= size)
return -ENXIO;
while (length > 0) {
ret = iomap_apply(inode, offset, length, IOMAP_REPORT, ops,
&offset, iomap_seek_hole_actor);
if (ret < 0)
return ret;
if (ret == 0)
break;
offset += ret;
length -= ret;
}
return offset;
}
EXPORT_SYMBOL_GPL(iomap_seek_hole);
static loff_t
iomap_seek_data_actor(struct inode *inode, loff_t offset, loff_t length,
void *data, struct iomap *iomap)
{
switch (iomap->type) {
case IOMAP_HOLE:
return length;
case IOMAP_UNWRITTEN:
offset = page_cache_seek_hole_data(inode, offset, length,
SEEK_DATA);
if (offset < 0)
return length;
/*FALLTHRU*/
default:
*(loff_t *)data = offset;
return 0;
}
}
loff_t
iomap_seek_data(struct inode *inode, loff_t offset, const struct iomap_ops *ops)
{
loff_t size = i_size_read(inode);
loff_t length = size - offset;
loff_t ret;
/* Nothing to be found before or beyond the end of the file. */
if (offset < 0 || offset >= size)
return -ENXIO;
while (length > 0) {
ret = iomap_apply(inode, offset, length, IOMAP_REPORT, ops,
&offset, iomap_seek_data_actor);
if (ret < 0)
return ret;
if (ret == 0)
break;
offset += ret;
length -= ret;
}
if (length <= 0)
return -ENXIO;
return offset;
}
EXPORT_SYMBOL_GPL(iomap_seek_data);
/*
* Private flags for iomap_dio, must not overlap with the public ones in
* iomap.h:
*/
#define IOMAP_DIO_WRITE_FUA (1 << 28)
#define IOMAP_DIO_NEED_SYNC (1 << 29)
#define IOMAP_DIO_WRITE (1 << 30)
#define IOMAP_DIO_DIRTY (1 << 31)
struct iomap_dio {
struct kiocb *iocb;
iomap_dio_end_io_t *end_io;
loff_t i_size;
loff_t size;
atomic_t ref;
unsigned flags;
int error;
bool wait_for_completion;
union {
/* used during submission and for synchronous completion: */
struct {
struct iov_iter *iter;
struct task_struct *waiter;
struct request_queue *last_queue;
blk_qc_t cookie;
} submit;
/* used for aio completion: */
struct {
struct work_struct work;
} aio;
};
};
static ssize_t iomap_dio_complete(struct iomap_dio *dio)
{
struct kiocb *iocb = dio->iocb;
struct inode *inode = file_inode(iocb->ki_filp);
loff_t offset = iocb->ki_pos;
ssize_t ret;
if (dio->end_io) {
ret = dio->end_io(iocb,
dio->error ? dio->error : dio->size,
dio->flags);
} else {
ret = dio->error;
}
if (likely(!ret)) {
ret = dio->size;
/* check for short read */
if (offset + ret > dio->i_size &&
!(dio->flags & IOMAP_DIO_WRITE))
ret = dio->i_size - offset;
iocb->ki_pos += ret;
}
/*
* Try again to invalidate clean pages which might have been cached by
* non-direct readahead, or faulted in by get_user_pages() if the source
* of the write was an mmap'ed region of the file we're writing. Either
* one is a pretty crazy thing to do, so we don't support it 100%. If
* this invalidation fails, tough, the write still worked...
*
* And this page cache invalidation has to be after dio->end_io(), as
* some filesystems convert unwritten extents to real allocations in
* end_io() when necessary, otherwise a racing buffer read would cache
* zeros from unwritten extents.
*/
if (!dio->error &&
(dio->flags & IOMAP_DIO_WRITE) && inode->i_mapping->nrpages) {
int err;
err = invalidate_inode_pages2_range(inode->i_mapping,
offset >> PAGE_SHIFT,
(offset + dio->size - 1) >> PAGE_SHIFT);
if (err)
dio_warn_stale_pagecache(iocb->ki_filp);
}
/*
* If this is a DSYNC write, make sure we push it to stable storage now
* that we've written data.
*/
if (ret > 0 && (dio->flags & IOMAP_DIO_NEED_SYNC))
ret = generic_write_sync(iocb, ret);
inode_dio_end(file_inode(iocb->ki_filp));
kfree(dio);
return ret;
}
static void iomap_dio_complete_work(struct work_struct *work)
{
struct iomap_dio *dio = container_of(work, struct iomap_dio, aio.work);
struct kiocb *iocb = dio->iocb;
iocb->ki_complete(iocb, iomap_dio_complete(dio), 0);
}
/*
* Set an error in the dio if none is set yet. We have to use cmpxchg
* as the submission context and the completion context(s) can race to
* update the error.
*/
static inline void iomap_dio_set_error(struct iomap_dio *dio, int ret)
{
cmpxchg(&dio->error, 0, ret);
}
static void iomap_dio_bio_end_io(struct bio *bio)
{
struct iomap_dio *dio = bio->bi_private;
bool should_dirty = (dio->flags & IOMAP_DIO_DIRTY);
if (bio->bi_status)
iomap_dio_set_error(dio, blk_status_to_errno(bio->bi_status));
if (atomic_dec_and_test(&dio->ref)) {
if (dio->wait_for_completion) {
struct task_struct *waiter = dio->submit.waiter;
WRITE_ONCE(dio->submit.waiter, NULL);
blk_wake_io_task(waiter);
} else if (dio->flags & IOMAP_DIO_WRITE) {
struct inode *inode = file_inode(dio->iocb->ki_filp);
INIT_WORK(&dio->aio.work, iomap_dio_complete_work);
queue_work(inode->i_sb->s_dio_done_wq, &dio->aio.work);
} else {
iomap_dio_complete_work(&dio->aio.work);
}
}
if (should_dirty) {
bio_check_pages_dirty(bio);
} else {
struct bio_vec *bvec;
int i;
bio_for_each_segment_all(bvec, bio, i)
put_page(bvec->bv_page);
bio_put(bio);
}
}
static blk_qc_t
iomap_dio_zero(struct iomap_dio *dio, struct iomap *iomap, loff_t pos,
unsigned len)
{
struct page *page = ZERO_PAGE(0);
int flags = REQ_SYNC | REQ_IDLE;
struct bio *bio;
bio = bio_alloc(GFP_KERNEL, 1);
bio_set_dev(bio, iomap->bdev);
bio->bi_iter.bi_sector = iomap_sector(iomap, pos);
bio->bi_private = dio;
bio->bi_end_io = iomap_dio_bio_end_io;
if (dio->iocb->ki_flags & IOCB_HIPRI)
flags |= REQ_HIPRI;
get_page(page);
__bio_add_page(bio, page, len, 0);
bio_set_op_attrs(bio, REQ_OP_WRITE, flags);
atomic_inc(&dio->ref);
return submit_bio(bio);
}
static loff_t
iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length,
struct iomap_dio *dio, struct iomap *iomap)
{
unsigned int blkbits = blksize_bits(bdev_logical_block_size(iomap->bdev));
unsigned int fs_block_size = i_blocksize(inode), pad;
unsigned int align = iov_iter_alignment(dio->submit.iter);
struct iov_iter iter;
struct bio *bio;
bool need_zeroout = false;
bool use_fua = false;
int nr_pages, ret = 0;
size_t copied = 0;
if ((pos | length | align) & ((1 << blkbits) - 1))
return -EINVAL;
if (iomap->type == IOMAP_UNWRITTEN) {
dio->flags |= IOMAP_DIO_UNWRITTEN;
need_zeroout = true;
}
if (iomap->flags & IOMAP_F_SHARED)
dio->flags |= IOMAP_DIO_COW;
if (iomap->flags & IOMAP_F_NEW) {
need_zeroout = true;
} else if (iomap->type == IOMAP_MAPPED) {
/*
* Use a FUA write if we need datasync semantics, this is a pure
* data IO that doesn't require any metadata updates (including
* after IO completion such as unwritten extent conversion) and
* the underlying device supports FUA. This allows us to avoid
* cache flushes on IO completion.
*/
if (!(iomap->flags & (IOMAP_F_SHARED|IOMAP_F_DIRTY)) &&
(dio->flags & IOMAP_DIO_WRITE_FUA) &&
blk_queue_fua(bdev_get_queue(iomap->bdev)))
use_fua = true;
}
/*
* Operate on a partial iter trimmed to the extent we were called for.
* We'll update the iter in the dio once we're done with this extent.
*/
iter = *dio->submit.iter;
iov_iter_truncate(&iter, length);
nr_pages = iov_iter_npages(&iter, BIO_MAX_PAGES);
if (nr_pages <= 0)
return nr_pages;
if (need_zeroout) {
/* zero out from the start of the block to the write offset */
pad = pos & (fs_block_size - 1);
if (pad)
iomap_dio_zero(dio, iomap, pos - pad, pad);
}
do {
size_t n;
if (dio->error) {
iov_iter_revert(dio->submit.iter, copied);
return 0;
}
bio = bio_alloc(GFP_KERNEL, nr_pages);
bio_set_dev(bio, iomap->bdev);
bio->bi_iter.bi_sector = iomap_sector(iomap, pos);
bio->bi_write_hint = dio->iocb->ki_hint;
bio->bi_ioprio = dio->iocb->ki_ioprio;
bio->bi_private = dio;
bio->bi_end_io = iomap_dio_bio_end_io;
ret = bio_iov_iter_get_pages(bio, &iter);
if (unlikely(ret)) {
/*
* We have to stop part way through an IO. We must fall
* through to the sub-block tail zeroing here, otherwise
* this short IO may expose stale data in the tail of
* the block we haven't written data to.
*/
bio_put(bio);
goto zero_tail;
}
n = bio->bi_iter.bi_size;
if (dio->flags & IOMAP_DIO_WRITE) {
bio->bi_opf = REQ_OP_WRITE | REQ_SYNC | REQ_IDLE;
if (use_fua)
bio->bi_opf |= REQ_FUA;
else
dio->flags &= ~IOMAP_DIO_WRITE_FUA;
task_io_account_write(n);
} else {
bio->bi_opf = REQ_OP_READ;
if (dio->flags & IOMAP_DIO_DIRTY)
bio_set_pages_dirty(bio);
}
if (dio->iocb->ki_flags & IOCB_HIPRI)
bio->bi_opf |= REQ_HIPRI;
iov_iter_advance(dio->submit.iter, n);
dio->size += n;
pos += n;
copied += n;
nr_pages = iov_iter_npages(&iter, BIO_MAX_PAGES);
atomic_inc(&dio->ref);
dio->submit.last_queue = bdev_get_queue(iomap->bdev);
dio->submit.cookie = submit_bio(bio);
} while (nr_pages);
/*
* We need to zeroout the tail of a sub-block write if the extent type
* requires zeroing or the write extends beyond EOF. If we don't zero
* the block tail in the latter case, we can expose stale data via mmap
* reads of the EOF block.
*/
zero_tail:
if (need_zeroout ||
((dio->flags & IOMAP_DIO_WRITE) && pos >= i_size_read(inode))) {
/* zero out from the end of the write to the end of the block */
pad = pos & (fs_block_size - 1);
if (pad)
iomap_dio_zero(dio, iomap, pos, fs_block_size - pad);
}
return copied ? copied : ret;
}
static loff_t
iomap_dio_hole_actor(loff_t length, struct iomap_dio *dio)
{
length = iov_iter_zero(length, dio->submit.iter);
dio->size += length;
return length;
}
static loff_t
iomap_dio_inline_actor(struct inode *inode, loff_t pos, loff_t length,
struct iomap_dio *dio, struct iomap *iomap)
{
struct iov_iter *iter = dio->submit.iter;
size_t copied;
BUG_ON(pos + length > PAGE_SIZE - offset_in_page(iomap->inline_data));
if (dio->flags & IOMAP_DIO_WRITE) {
loff_t size = inode->i_size;
if (pos > size)
memset(iomap->inline_data + size, 0, pos - size);
copied = copy_from_iter(iomap->inline_data + pos, length, iter);
if (copied) {
if (pos + copied > size)
i_size_write(inode, pos + copied);
mark_inode_dirty(inode);
}
} else {
copied = copy_to_iter(iomap->inline_data + pos, length, iter);
}
dio->size += copied;
return copied;
}
static loff_t
iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
void *data, struct iomap *iomap)
{
struct iomap_dio *dio = data;
switch (iomap->type) {
case IOMAP_HOLE:
if (WARN_ON_ONCE(dio->flags & IOMAP_DIO_WRITE))
return -EIO;
return iomap_dio_hole_actor(length, dio);
case IOMAP_UNWRITTEN:
if (!(dio->flags & IOMAP_DIO_WRITE))
return iomap_dio_hole_actor(length, dio);
return iomap_dio_bio_actor(inode, pos, length, dio, iomap);
case IOMAP_MAPPED:
return iomap_dio_bio_actor(inode, pos, length, dio, iomap);
case IOMAP_INLINE:
return iomap_dio_inline_actor(inode, pos, length, dio, iomap);
default:
WARN_ON_ONCE(1);
return -EIO;
}
}
/*
* iomap_dio_rw() always completes O_[D]SYNC writes regardless of whether the IO
* is being issued as AIO or not. This allows us to optimise pure data writes
* to use REQ_FUA rather than requiring generic_write_sync() to issue a
* REQ_FLUSH post write. This is slightly tricky because a single request here
* can be mapped into multiple disjoint IOs and only a subset of the IOs issued
* may be pure data writes. In that case, we still need to do a full data sync
* completion.
*/
ssize_t
iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
const struct iomap_ops *ops, iomap_dio_end_io_t end_io)
{
struct address_space *mapping = iocb->ki_filp->f_mapping;
struct inode *inode = file_inode(iocb->ki_filp);
size_t count = iov_iter_count(iter);
loff_t pos = iocb->ki_pos, start = pos;
loff_t end = iocb->ki_pos + count - 1, ret = 0;
unsigned int flags = IOMAP_DIRECT;
struct blk_plug plug;
struct iomap_dio *dio;
lockdep_assert_held(&inode->i_rwsem);
if (!count)
return 0;
dio = kmalloc(sizeof(*dio), GFP_KERNEL);
if (!dio)
return -ENOMEM;
dio->iocb = iocb;
atomic_set(&dio->ref, 1);
dio->size = 0;
dio->i_size = i_size_read(inode);
dio->end_io = end_io;
dio->error = 0;
dio->flags = 0;
dio->wait_for_completion = is_sync_kiocb(iocb);
dio->submit.iter = iter;
dio->submit.waiter = current;
dio->submit.cookie = BLK_QC_T_NONE;
dio->submit.last_queue = NULL;
if (iov_iter_rw(iter) == READ) {
if (pos >= dio->i_size)
goto out_free_dio;
if (iter_is_iovec(iter) && iov_iter_rw(iter) == READ)
dio->flags |= IOMAP_DIO_DIRTY;
} else {
flags |= IOMAP_WRITE;
dio->flags |= IOMAP_DIO_WRITE;
/* for data sync or sync, we need sync completion processing */
if (iocb->ki_flags & IOCB_DSYNC)
dio->flags |= IOMAP_DIO_NEED_SYNC;
/*
* For datasync only writes, we optimistically try using FUA for
* this IO. Any non-FUA write that occurs will clear this flag,
* hence we know before completion whether a cache flush is
* necessary.
*/
if ((iocb->ki_flags & (IOCB_DSYNC | IOCB_SYNC)) == IOCB_DSYNC)
dio->flags |= IOMAP_DIO_WRITE_FUA;
}
if (iocb->ki_flags & IOCB_NOWAIT) {
if (filemap_range_has_page(mapping, start, end)) {
ret = -EAGAIN;
goto out_free_dio;
}
flags |= IOMAP_NOWAIT;
}
ret = filemap_write_and_wait_range(mapping, start, end);
if (ret)
goto out_free_dio;
/*
* Try to invalidate cache pages for the range we're direct
* writing. If this invalidation fails, tough, the write will
* still work, but racing two incompatible write paths is a
* pretty crazy thing to do, so we don't support it 100%.
*/
ret = invalidate_inode_pages2_range(mapping,
start >> PAGE_SHIFT, end >> PAGE_SHIFT);
if (ret)
dio_warn_stale_pagecache(iocb->ki_filp);
ret = 0;
if (iov_iter_rw(iter) == WRITE && !dio->wait_for_completion &&
!inode->i_sb->s_dio_done_wq) {
ret = sb_init_dio_done_wq(inode->i_sb);
if (ret < 0)
goto out_free_dio;
}
inode_dio_begin(inode);
blk_start_plug(&plug);
do {
ret = iomap_apply(inode, pos, count, flags, ops, dio,
iomap_dio_actor);
if (ret <= 0) {
/* magic error code to fall back to buffered I/O */
if (ret == -ENOTBLK) {
dio->wait_for_completion = true;
ret = 0;
}
break;
}
pos += ret;
if (iov_iter_rw(iter) == READ && pos >= dio->i_size)
break;
} while ((count = iov_iter_count(iter)) > 0);
blk_finish_plug(&plug);
if (ret < 0)
iomap_dio_set_error(dio, ret);
/*
* If all the writes we issued were FUA, we don't need to flush the
* cache on IO completion. Clear the sync flag for this case.
*/
if (dio->flags & IOMAP_DIO_WRITE_FUA)
dio->flags &= ~IOMAP_DIO_NEED_SYNC;
if (!atomic_dec_and_test(&dio->ref)) {
if (!dio->wait_for_completion)
return -EIOCBQUEUED;
for (;;) {
set_current_state(TASK_UNINTERRUPTIBLE);
if (!READ_ONCE(dio->submit.waiter))
break;
if (!(iocb->ki_flags & IOCB_HIPRI) ||
!dio->submit.last_queue ||
!blk_poll(dio->submit.last_queue,
dio->submit.cookie, true))
io_schedule();
}
__set_current_state(TASK_RUNNING);
}
ret = iomap_dio_complete(dio);
return ret;
out_free_dio:
kfree(dio);
return ret;
}
EXPORT_SYMBOL_GPL(iomap_dio_rw);
/* Swapfile activation */
#ifdef CONFIG_SWAP
struct iomap_swapfile_info {
struct iomap iomap; /* accumulated iomap */
struct swap_info_struct *sis;
uint64_t lowest_ppage; /* lowest physical addr seen (pages) */
uint64_t highest_ppage; /* highest physical addr seen (pages) */
unsigned long nr_pages; /* number of pages collected */
int nr_extents; /* extent count */
};
/*
* Collect physical extents for this swap file. Physical extents reported to
* the swap code must be trimmed to align to a page boundary. The logical
* offset within the file is irrelevant since the swapfile code maps logical
* page numbers of the swap device to the physical page-aligned extents.
*/
static int iomap_swapfile_add_extent(struct iomap_swapfile_info *isi)
{
struct iomap *iomap = &isi->iomap;
unsigned long nr_pages;
uint64_t first_ppage;
uint64_t first_ppage_reported;
uint64_t next_ppage;
int error;
/*
* Round the start up and the end down so that the physical
* extent aligns to a page boundary.
*/
first_ppage = ALIGN(iomap->addr, PAGE_SIZE) >> PAGE_SHIFT;
next_ppage = ALIGN_DOWN(iomap->addr + iomap->length, PAGE_SIZE) >>
PAGE_SHIFT;
/* Skip too-short physical extents. */
if (first_ppage >= next_ppage)
return 0;
nr_pages = next_ppage - first_ppage;
/*
* Calculate how much swap space we're adding; the first page contains
* the swap header and doesn't count. The mm still wants that first
* page fed to add_swap_extent, however.
*/
first_ppage_reported = first_ppage;
if (iomap->offset == 0)
first_ppage_reported++;
if (isi->lowest_ppage > first_ppage_reported)
isi->lowest_ppage = first_ppage_reported;
if (isi->highest_ppage < (next_ppage - 1))
isi->highest_ppage = next_ppage - 1;
/* Add extent, set up for the next call. */
error = add_swap_extent(isi->sis, isi->nr_pages, nr_pages, first_ppage);
if (error < 0)
return error;
isi->nr_extents += error;
isi->nr_pages += nr_pages;
return 0;
}
/*
* Accumulate iomaps for this swap file. We have to accumulate iomaps because
* swap only cares about contiguous page-aligned physical extents and makes no
* distinction between written and unwritten extents.
*/
static loff_t iomap_swapfile_activate_actor(struct inode *inode, loff_t pos,
loff_t count, void *data, struct iomap *iomap)
{
struct iomap_swapfile_info *isi = data;
int error;
switch (iomap->type) {
case IOMAP_MAPPED:
case IOMAP_UNWRITTEN:
/* Only real or unwritten extents. */
break;
case IOMAP_INLINE:
/* No inline data. */
pr_err("swapon: file is inline\n");
return -EINVAL;
default:
pr_err("swapon: file has unallocated extents\n");
return -EINVAL;
}
/* No uncommitted metadata or shared blocks. */
if (iomap->flags & IOMAP_F_DIRTY) {
pr_err("swapon: file is not committed\n");
return -EINVAL;
}
if (iomap->flags & IOMAP_F_SHARED) {
pr_err("swapon: file has shared extents\n");
return -EINVAL;
}
/* Only one bdev per swap file. */
if (iomap->bdev != isi->sis->bdev) {
pr_err("swapon: file is on multiple devices\n");
return -EINVAL;
}
if (isi->iomap.length == 0) {
/* No accumulated extent, so just store it. */
memcpy(&isi->iomap, iomap, sizeof(isi->iomap));
} else if (isi->iomap.addr + isi->iomap.length == iomap->addr) {
/* Append this to the accumulated extent. */
isi->iomap.length += iomap->length;
} else {
/* Otherwise, add the retained iomap and store this one. */
error = iomap_swapfile_add_extent(isi);
if (error)
return error;
memcpy(&isi->iomap, iomap, sizeof(isi->iomap));
}
return count;
}
/*
* Iterate a swap file's iomaps to construct physical extents that can be
* passed to the swapfile subsystem.
*/
int iomap_swapfile_activate(struct swap_info_struct *sis,
struct file *swap_file, sector_t *pagespan,
const struct iomap_ops *ops)
{
struct iomap_swapfile_info isi = {
.sis = sis,
.lowest_ppage = (sector_t)-1ULL,
};
struct address_space *mapping = swap_file->f_mapping;
struct inode *inode = mapping->host;
loff_t pos = 0;
loff_t len = ALIGN_DOWN(i_size_read(inode), PAGE_SIZE);
loff_t ret;
/*
* Persist all file mapping metadata so that we won't have any
* IOMAP_F_DIRTY iomaps.
*/
ret = vfs_fsync(swap_file, 1);
if (ret)
return ret;
while (len > 0) {
ret = iomap_apply(inode, pos, len, IOMAP_REPORT,
ops, &isi, iomap_swapfile_activate_actor);
if (ret <= 0)
return ret;
pos += ret;
len -= ret;
}
if (isi.iomap.length) {
ret = iomap_swapfile_add_extent(&isi);
if (ret)
return ret;
}
*pagespan = 1 + isi.highest_ppage - isi.lowest_ppage;
sis->max = isi.nr_pages;
sis->pages = isi.nr_pages - 1;
sis->highest_bit = isi.nr_pages - 1;
return isi.nr_extents;
}
EXPORT_SYMBOL_GPL(iomap_swapfile_activate);
#endif /* CONFIG_SWAP */
static loff_t
iomap_bmap_actor(struct inode *inode, loff_t pos, loff_t length,
void *data, struct iomap *iomap)
{
sector_t *bno = data, addr;
if (iomap->type == IOMAP_MAPPED) {
addr = (pos - iomap->offset + iomap->addr) >> inode->i_blkbits;
if (addr > INT_MAX)
WARN(1, "would truncate bmap result\n");
else
*bno = addr;
}
return 0;
}
/* legacy ->bmap interface. 0 is the error return (!) */
sector_t
iomap_bmap(struct address_space *mapping, sector_t bno,
const struct iomap_ops *ops)
{
struct inode *inode = mapping->host;
loff_t pos = bno << inode->i_blkbits;
unsigned blocksize = i_blocksize(inode);
if (filemap_write_and_wait(mapping))
return 0;
bno = 0;
iomap_apply(inode, pos, blocksize, 0, ops, &bno, iomap_bmap_actor);
return bno;
}
EXPORT_SYMBOL_GPL(iomap_bmap);