static ssize_t jfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
loff_t offset)
{
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
struct inode *inode = file->f_mapping->host;
size_t count = iov_iter_count(iter);
ssize_t ret;
ret = blockdev_direct_IO(iocb, inode, iter, offset, jfs_get_block);
/*
* In case of error extending write may have instantiated a few
* blocks outside i_size. Trim these off again.
*/
if (unlikely(iov_iter_rw(iter) == WRITE && ret < 0)) {
loff_t isize = i_size_read(inode);
loff_t end = offset + count;
if (end > isize)
jfs_write_failed(mapping, end);
}
return ret;
}
/**
* dax_do_io - Perform I/O to a DAX file
* @iocb: The control block for this I/O
* @inode: The file which the I/O is directed at
* @iter: The addresses to do I/O from or to
* @pos: The file offset where the I/O starts
* @get_block: The filesystem method used to translate file offsets to blocks
* @end_io: A filesystem callback for I/O completion
* @flags: See below
*
* This function uses the same locking scheme as do_blockdev_direct_IO:
* If @flags has DIO_LOCKING set, we assume that the i_mutex is held by the
* caller for writes. For reads, we take and release the i_mutex ourselves.
* If DIO_LOCKING is not set, the filesystem takes care of its own locking.
* As with do_blockdev_direct_IO(), we increment i_dio_count while the I/O
* is in progress.
*/
ssize_t dax_do_io(struct kiocb *iocb, struct inode *inode,
struct iov_iter *iter, loff_t pos, get_block_t get_block,
dio_iodone_t end_io, int flags)
{
struct buffer_head bh;
ssize_t retval = -EINVAL;
loff_t end = pos + iov_iter_count(iter);
memset(&bh, 0, sizeof(bh));
bh.b_bdev = inode->i_sb->s_bdev;
if ((flags & DIO_LOCKING) && iov_iter_rw(iter) == READ) {
struct address_space *mapping = inode->i_mapping;
inode_lock(inode);
retval = filemap_write_and_wait_range(mapping, pos, end - 1);
if (retval) {
inode_unlock(inode);
goto out;
}
}
/* Protects against truncate */
if (!(flags & DIO_SKIP_DIO_COUNT))
inode_dio_begin(inode);
retval = dax_io(inode, iter, pos, end, get_block, &bh);
if ((flags & DIO_LOCKING) && iov_iter_rw(iter) == READ)
inode_unlock(inode);
if (end_io) {
int err;
err = end_io(iocb, pos, retval, bh.b_private);
if (err)
retval = err;
}
if (!(flags & DIO_SKIP_DIO_COUNT))
inode_dio_end(inode);
out:
return retval;
}
static ssize_t
nilfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
{
struct inode *inode = file_inode(iocb->ki_filp);
if (iov_iter_rw(iter) == WRITE)
return 0;
/* Needs synchronization with the cleaner */
return blockdev_direct_IO(iocb, inode, iter, nilfs_get_block);
}
static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
loff_t offset)
{
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
size_t count = iov_iter_count(iter);
int err;
/* we don't need to use inline_data strictly */
if (f2fs_has_inline_data(inode)) {
err = f2fs_convert_inline_inode(inode);
if (err)
return err;
}
if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
return 0;
err = check_direct_IO(inode, iter, offset);
if (err)
return err;
trace_f2fs_direct_IO_enter(inode, offset, count, iov_iter_rw(iter));
if (iov_iter_rw(iter) == WRITE)
__allocate_data_blocks(inode, offset, count);
err = blockdev_direct_IO(iocb, inode, iter, offset, get_data_block_dio);
if (err < 0 && iov_iter_rw(iter) == WRITE)
f2fs_write_failed(mapping, offset + count);
trace_f2fs_direct_IO_exit(inode, offset, count, iov_iter_rw(iter), err);
return err;
}
/**
* dax_do_io - Perform I/O to a DAX file
* @iocb: The control block for this I/O
* @inode: The file which the I/O is directed at
* @iter: The addresses to do I/O from or to
* @get_block: The filesystem method used to translate file offsets to blocks
* @end_io: A filesystem callback for I/O completion
* @flags: See below
*
* This function uses the same locking scheme as do_blockdev_direct_IO:
* If @flags has DIO_LOCKING set, we assume that the i_mutex is held by the
* caller for writes. For reads, we take and release the i_mutex ourselves.
* If DIO_LOCKING is not set, the filesystem takes care of its own locking.
* As with do_blockdev_direct_IO(), we increment i_dio_count while the I/O
* is in progress.
*/
ssize_t dax_do_io(struct kiocb *iocb, struct inode *inode,
struct iov_iter *iter, get_block_t get_block,
dio_iodone_t end_io, int flags)
{
struct buffer_head bh;
ssize_t retval = -EINVAL;
loff_t pos = iocb->ki_pos;
loff_t end = pos + iov_iter_count(iter);
memset(&bh, 0, sizeof(bh));
bh.b_bdev = inode->i_sb->s_bdev;
if ((flags & DIO_LOCKING) && iov_iter_rw(iter) == READ)
inode_lock(inode);
/* Protects against truncate */
if (!(flags & DIO_SKIP_DIO_COUNT))
inode_dio_begin(inode);
retval = dax_io(inode, iter, pos, end, get_block, &bh);
if ((flags & DIO_LOCKING) && iov_iter_rw(iter) == READ)
inode_unlock(inode);
if (end_io) {
int err;
err = end_io(iocb, pos, retval, bh.b_private);
if (err)
retval = err;
}
if (!(flags & DIO_SKIP_DIO_COUNT))
inode_dio_end(inode);
return retval;
}
static ssize_t dax_io(struct inode *inode, struct iov_iter *iter,
loff_t start, loff_t end, get_block_t get_block,
struct buffer_head *bh)
{
loff_t pos = start, max = start, bh_max = start;
bool hole = false, need_wmb = false;
struct block_device *bdev = NULL;
int rw = iov_iter_rw(iter), rc;
long map_len = 0;
struct blk_dax_ctl dax = {
.addr = (void __pmem *) ERR_PTR(-EIO),
};
if (rw == READ)
end = min(end, i_size_read(inode));
while (pos < end) {
size_t len;
if (pos == max) {
unsigned blkbits = inode->i_blkbits;
long page = pos >> PAGE_SHIFT;
sector_t block = page << (PAGE_SHIFT - blkbits);
unsigned first = pos - (block << blkbits);
long size;
if (pos == bh_max) {
bh->b_size = PAGE_ALIGN(end - pos);
bh->b_state = 0;
rc = get_block(inode, block, bh, rw == WRITE);
if (rc)
break;
if (!buffer_size_valid(bh))
bh->b_size = 1 << blkbits;
bh_max = pos - first + bh->b_size;
bdev = bh->b_bdev;
} else {
unsigned done = bh->b_size -
(bh_max - (pos - first));
bh->b_blocknr += done >> blkbits;
bh->b_size -= done;
}
hole = rw == READ && !buffer_written(bh);
if (hole) {
size = bh->b_size - first;
} else {
dax_unmap_atomic(bdev, &dax);
dax.sector = to_sector(bh, inode);
dax.size = bh->b_size;
map_len = dax_map_atomic(bdev, &dax);
if (map_len < 0) {
rc = map_len;
break;
}
if (buffer_unwritten(bh) || buffer_new(bh)) {
dax_new_buf(dax.addr, map_len, first,
pos, end);
need_wmb = true;
}
dax.addr += first;
size = map_len - first;
}
max = min(pos + size, end);
}
if (iov_iter_rw(iter) == WRITE) {
len = copy_from_iter_pmem(dax.addr, max - pos, iter);
need_wmb = true;
} else if (!hole)
len = copy_to_iter((void __force *) dax.addr, max - pos,
iter);
else
len = iov_iter_zero(max - pos, iter);
if (!len) {
rc = -EFAULT;
break;
}
pos += len;
if (!IS_ERR(dax.addr))
dax.addr += len;
}
if (need_wmb)
wmb_pmem();
dax_unmap_atomic(bdev, &dax);
return (pos == start) ? rc : pos - start;
}
static ssize_t
ll_direct_IO(
# ifndef HAVE_IOV_ITER_RW
int rw,
# endif
struct kiocb *iocb, struct iov_iter *iter,
loff_t file_offset)
{
struct ll_cl_context *lcc;
const struct lu_env *env;
struct cl_io *io;
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
ssize_t count = iov_iter_count(iter);
ssize_t tot_bytes = 0, result = 0;
size_t size = MAX_DIO_SIZE;
/* FIXME: io smaller than PAGE_SIZE is broken on ia64 ??? */
if ((file_offset & ~PAGE_MASK) || (count & ~PAGE_MASK))
return -EINVAL;
CDEBUG(D_VFSTRACE, "VFS Op:inode="DFID"(%p), size=%zd (max %lu), "
"offset=%lld=%llx, pages %zd (max %lu)\n",
PFID(ll_inode2fid(inode)), inode, count, MAX_DIO_SIZE,
file_offset, file_offset, count >> PAGE_SHIFT,
MAX_DIO_SIZE >> PAGE_SHIFT);
/* Check that all user buffers are aligned as well */
if (iov_iter_alignment(iter) & ~PAGE_MASK)
return -EINVAL;
lcc = ll_cl_find(file);
if (lcc == NULL)
RETURN(-EIO);
env = lcc->lcc_env;
LASSERT(!IS_ERR(env));
io = lcc->lcc_io;
LASSERT(io != NULL);
/* 0. Need locking between buffered and direct access. and race with
* size changing by concurrent truncates and writes.
* 1. Need inode mutex to operate transient pages.
*/
if (iov_iter_rw(iter) == READ)
inode_lock(inode);
while (iov_iter_count(iter)) {
struct page **pages;
size_t offs;
count = min_t(size_t, iov_iter_count(iter), size);
if (iov_iter_rw(iter) == READ) {
if (file_offset >= i_size_read(inode))
break;
if (file_offset + count > i_size_read(inode))
count = i_size_read(inode) - file_offset;
}
result = iov_iter_get_pages_alloc(iter, &pages, count, &offs);
if (likely(result > 0)) {
int n = DIV_ROUND_UP(result + offs, PAGE_SIZE);
result = ll_direct_IO_seg(env, io, iov_iter_rw(iter),
inode, result, file_offset,
pages, n);
ll_free_user_pages(pages, n,
iov_iter_rw(iter) == READ);
}
if (unlikely(result <= 0)) {
/* If we can't allocate a large enough buffer
* for the request, shrink it to a smaller
* PAGE_SIZE multiple and try again.
* We should always be able to kmalloc for a
* page worth of page pointers = 4MB on i386. */
if (result == -ENOMEM &&
size > (PAGE_SIZE / sizeof(*pages)) *
PAGE_SIZE) {
size = ((((size / 2) - 1) |
~PAGE_MASK) + 1) & PAGE_MASK;
CDEBUG(D_VFSTRACE, "DIO size now %zu\n",
size);
continue;
}
GOTO(out, result);
}
iov_iter_advance(iter, result);
tot_bytes += result;
file_offset += result;
}
out:
if (iov_iter_rw(iter) == READ)
inode_unlock(inode);
if (tot_bytes > 0) {
struct vvp_io *vio = vvp_env_io(env);
/* no commit async for direct IO */
vio->u.write.vui_written += tot_bytes;
}
return tot_bytes ? : result;
}
static ssize_t dax_io(struct inode *inode, struct iov_iter *iter,
loff_t start, loff_t end, get_block_t get_block,
struct buffer_head *bh)
{
loff_t pos = start, max = start, bh_max = start;
bool hole = false, need_wmb = false;
struct block_device *bdev = NULL;
int rw = iov_iter_rw(iter), rc;
long map_len = 0;
struct blk_dax_ctl dax = {
.addr = (void __pmem *) ERR_PTR(-EIO),
};
unsigned blkbits = inode->i_blkbits;
sector_t file_blks = (i_size_read(inode) + (1 << blkbits) - 1)
>> blkbits;
if (rw == READ)
end = min(end, i_size_read(inode));
while (pos < end) {
size_t len;
if (pos == max) {
long page = pos >> PAGE_SHIFT;
sector_t block = page << (PAGE_SHIFT - blkbits);
unsigned first = pos - (block << blkbits);
long size;
if (pos == bh_max) {
bh->b_size = PAGE_ALIGN(end - pos);
bh->b_state = 0;
rc = get_block(inode, block, bh, rw == WRITE);
if (rc)
break;
if (!buffer_size_valid(bh))
bh->b_size = 1 << blkbits;
bh_max = pos - first + bh->b_size;
bdev = bh->b_bdev;
/*
* We allow uninitialized buffers for writes
* beyond EOF as those cannot race with faults
*/
WARN_ON_ONCE(
(buffer_new(bh) && block < file_blks) ||
(rw == WRITE && buffer_unwritten(bh)));
} else {
unsigned done = bh->b_size -
(bh_max - (pos - first));
bh->b_blocknr += done >> blkbits;
bh->b_size -= done;
}
hole = rw == READ && !buffer_written(bh);
if (hole) {
size = bh->b_size - first;
} else {
dax_unmap_atomic(bdev, &dax);
dax.sector = to_sector(bh, inode);
dax.size = bh->b_size;
map_len = dax_map_atomic(bdev, &dax);
if (map_len < 0) {
rc = map_len;
break;
}
dax.addr += first;
size = map_len - first;
}
/*
* pos + size is one past the last offset for IO,
* so pos + size can overflow loff_t at extreme offsets.
* Cast to u64 to catch this and get the true minimum.
*/
max = min_t(u64, pos + size, end);
}
if (iov_iter_rw(iter) == WRITE) {
len = copy_from_iter_pmem(dax.addr, max - pos, iter);
need_wmb = true;
} else if (!hole)
len = copy_to_iter((void __force *) dax.addr, max - pos,
iter);
else
len = iov_iter_zero(max - pos, iter);
if (!len) {
rc = -EFAULT;
break;
}
pos += len;
if (!IS_ERR(dax.addr))
dax.addr += len;
}
if (need_wmb)
wmb_pmem();
dax_unmap_atomic(bdev, &dax);
return (pos == start) ? rc : pos - start;
}
static ssize_t gfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
loff_t offset)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
struct address_space *mapping = inode->i_mapping;
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_holder gh;
int rv;
/*
* Deferred lock, even if its a write, since we do no allocation
* on this path. All we need change is atime, and this lock mode
* ensures that other nodes have flushed their buffered read caches
* (i.e. their page cache entries for this inode). We do not,
* unfortunately have the option of only flushing a range like
* the VFS does.
*/
gfs2_holder_init(ip->i_gl, LM_ST_DEFERRED, 0, &gh);
rv = gfs2_glock_nq(&gh);
if (rv)
return rv;
rv = gfs2_ok_for_dio(ip, offset);
if (rv != 1)
goto out; /* dio not valid, fall back to buffered i/o */
/*
* Now since we are holding a deferred (CW) lock at this point, you
* might be wondering why this is ever needed. There is a case however
* where we've granted a deferred local lock against a cached exclusive
* glock. That is ok provided all granted local locks are deferred, but
* it also means that it is possible to encounter pages which are
* cached and possibly also mapped. So here we check for that and sort
* them out ahead of the dio. The glock state machine will take care of
* everything else.
*
* If in fact the cached glock state (gl->gl_state) is deferred (CW) in
* the first place, mapping->nr_pages will always be zero.
*/
if (mapping->nrpages) {
loff_t lstart = offset & (PAGE_CACHE_SIZE - 1);
loff_t len = iov_iter_count(iter);
loff_t end = PAGE_ALIGN(offset + len) - 1;
rv = 0;
if (len == 0)
goto out;
if (test_and_clear_bit(GIF_SW_PAGED, &ip->i_flags))
unmap_shared_mapping_range(ip->i_inode.i_mapping, offset, len);
rv = filemap_write_and_wait_range(mapping, lstart, end);
if (rv)
goto out;
if (iov_iter_rw(iter) == WRITE)
truncate_inode_pages_range(mapping, lstart, end);
}
rv = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter,
offset, gfs2_get_block_direct, NULL, NULL, 0);
out:
gfs2_glock_dq(&gh);
gfs2_holder_uninit(&gh);
return rv;
}
