/*
* This tests whether the IO in question is block-aligned or not.
* Ext4 utilizes unwritten extents when hole-filling during direct IO, and they
* are converted to written only after the IO is complete. Until they are
* mapped, these blocks appear as holes, so dio_zero_block() will assume that
* it needs to zero out portions of the start and/or end block. If 2 AIO
* threads are at work on the same unwritten block, they must be synchronized
* or one thread will zero the other's data, causing corruption.
*/
static int
ext4_unaligned_aio(struct inode *inode, struct iov_iter *iter, loff_t pos)
{
struct super_block *sb = inode->i_sb;
int blockmask = sb->s_blocksize - 1;
size_t count = iov_iter_count(iter);
loff_t final_size = pos + count;
if (pos >= i_size_read(inode))
return 0;
if ((pos & blockmask) || (final_size & blockmask))
return 1;
return 0;
}
static ssize_t
v9fs_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
struct p9_fid *fid = iocb->ki_filp->private_data;
int ret, err = 0;
p9_debug(P9_DEBUG_VFS, "count %zu offset %lld\n",
iov_iter_count(to), iocb->ki_pos);
ret = p9_client_read(fid, iocb->ki_pos, to, &err);
if (!ret)
return err;
iocb->ki_pos += ret;
return ret;
}
/**
* process_vm_rw_single_vec - read/write pages from task specified
* @addr: start memory address of target process
* @len: size of area to copy to/from
* @iter: where to copy to/from locally
* @process_pages: struct pages area that can store at least
* nr_pages_to_copy struct page pointers
* @mm: mm for task
* @task: task to read/write from
* @vm_write: 0 means copy from, 1 means copy to
* Returns 0 on success or on failure error code
*/
static int process_vm_rw_single_vec(unsigned long addr,
unsigned long len,
struct iov_iter *iter,
struct page **process_pages,
struct mm_struct *mm,
struct task_struct *task,
int vm_write)
{
unsigned long pa = addr & PAGE_MASK;
unsigned long start_offset = addr - pa;
unsigned long nr_pages;
ssize_t rc = 0;
unsigned long max_pages_per_loop = PVM_MAX_KMALLOC_PAGES
/ sizeof(struct pages *);
/* Work out address and page range required */
if (len == 0)
return 0;
nr_pages = (addr + len - 1) / PAGE_SIZE - addr / PAGE_SIZE + 1;
while (!rc && nr_pages && iov_iter_count(iter)) {
int pages = min(nr_pages, max_pages_per_loop);
size_t bytes;
/* Get the pages we're interested in */
pages = get_user_pages_unlocked(task, mm, pa, pages,
vm_write, 0, process_pages);
if (pages <= 0)
return -EFAULT;
bytes = pages * PAGE_SIZE - start_offset;
if (bytes > len)
bytes = len;
rc = process_vm_rw_pages(process_pages,
start_offset, bytes, iter,
vm_write);
len -= bytes;
start_offset = 0;
nr_pages -= pages;
pa += pages * PAGE_SIZE;
while (pages)
put_page(process_pages[--pages]);
}
return rc;
}
static ssize_t udf_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
ssize_t retval;
struct file *file = iocb->ki_filp;
struct inode *inode = file_inode(file);
struct udf_inode_info *iinfo = UDF_I(inode);
int err;
mutex_lock(&inode->i_mutex);
retval = generic_write_checks(iocb, from);
if (retval <= 0)
goto out;
down_write(&iinfo->i_data_sem);
if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) {
loff_t end = iocb->ki_pos + iov_iter_count(from);
if (inode->i_sb->s_blocksize <
(udf_file_entry_alloc_offset(inode) + end)) {
err = udf_expand_file_adinicb(inode);
if (err) {
mutex_unlock(&inode->i_mutex);
udf_debug("udf_expand_adinicb: err=%d\n", err);
return err;
}
} else {
iinfo->i_lenAlloc = max(end, inode->i_size);
up_write(&iinfo->i_data_sem);
}
} else
up_write(&iinfo->i_data_sem);
retval = __generic_file_write_iter(iocb, from);
out:
mutex_unlock(&inode->i_mutex);
if (retval > 0) {
mark_inode_dirty(inode);
err = generic_write_sync(file, iocb->ki_pos - retval, retval);
if (err < 0)
retval = err;
}
return retval;
}
STATIC ssize_t
xfs_file_write_iter(
struct kiocb *iocb,
struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
struct xfs_inode *ip = XFS_I(inode);
ssize_t ret;
size_t ocount = iov_iter_count(from);
XFS_STATS_INC(ip->i_mount, xs_write_calls);
if (ocount == 0)
return 0;
if (XFS_FORCED_SHUTDOWN(ip->i_mount))
return -EIO;
if (IS_DAX(inode))
ret = xfs_file_dax_write(iocb, from);
else if (iocb->ki_flags & IOCB_DIRECT) {
/*
* Allow a directio write to fall back to a buffered
* write *only* in the case that we're doing a reflink
* CoW. In all other directio scenarios we do not
* allow an operation to fall back to buffered mode.
*/
ret = xfs_file_dio_aio_write(iocb, from);
if (ret == -EREMCHG)
goto buffered;
} else {
buffered:
ret = xfs_file_buffered_aio_write(iocb, from);
}
if (ret > 0) {
XFS_STATS_ADD(ip->i_mount, xs_write_bytes, ret);
/* Handle various SYNC-type writes */
ret = generic_write_sync(iocb, ret);
}
return ret;
}
static noinline ssize_t
xfs_file_dax_write(
struct kiocb *iocb,
struct iov_iter *from)
{
struct inode *inode = iocb->ki_filp->f_mapping->host;
struct xfs_inode *ip = XFS_I(inode);
int iolock = XFS_IOLOCK_EXCL;
ssize_t ret, error = 0;
size_t count;
loff_t pos;
if (iocb->ki_flags & IOCB_NOWAIT) {
if (!xfs_ilock_nowait(ip, iolock))
return -EAGAIN;
} else {
xfs_ilock(ip, iolock);
}
ret = xfs_file_aio_write_checks(iocb, from, &iolock);
if (ret)
goto out;
pos = iocb->ki_pos;
count = iov_iter_count(from);
trace_xfs_file_dax_write(ip, count, pos);
ret = dax_iomap_rw(iocb, from, &xfs_iomap_ops);
if (ret > 0 && iocb->ki_pos > i_size_read(inode)) {
i_size_write(inode, iocb->ki_pos);
error = xfs_setfilesize(ip, pos, ret);
}
out:
xfs_iunlock(ip, iolock);
if (error)
return error;
if (ret > 0) {
XFS_STATS_ADD(ip->i_mount, xs_write_bytes, ret);
/* Handle various SYNC-type writes */
ret = generic_write_sync(iocb, ret);
}
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 hypfs_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
struct file *file = iocb->ki_filp;
char *data = file->private_data;
size_t available = strlen(data);
loff_t pos = iocb->ki_pos;
size_t count;
if (pos < 0)
return -EINVAL;
if (pos >= available || !iov_iter_count(to))
return 0;
count = copy_to_iter(data + pos, available - pos, to);
if (!count)
return -EFAULT;
iocb->ki_pos = pos + count;
file_accessed(file);
return count;
}
static ssize_t
zpl_iter_write(struct kiocb *kiocb, struct iov_iter *from)
{
size_t count;
ssize_t ret;
uio_seg_t seg = UIO_USERSPACE;
#ifndef HAVE_GENERIC_WRITE_CHECKS_KIOCB
struct file *file = kiocb->ki_filp;
struct address_space *mapping = file->f_mapping;
struct inode *ip = mapping->host;
int isblk = S_ISBLK(ip->i_mode);
count = iov_iter_count(from);
ret = generic_write_checks(file, &kiocb->ki_pos, &count, isblk);
if (ret)
return (ret);
#else
/*
* XXX - ideally this check should be in the same lock region with
* write operations, so that there's no TOCTTOU race when doing
* append and someone else grow the file.
*/
ret = generic_write_checks(kiocb, from);
if (ret <= 0)
return (ret);
count = ret;
#endif
if (from->type & ITER_KVEC)
seg = UIO_SYSSPACE;
if (from->type & ITER_BVEC)
seg = UIO_BVEC;
ret = zpl_iter_write_common(kiocb, from->iov, from->nr_segs,
count, seg, from->iov_offset);
if (ret > 0)
iov_iter_advance(from, ret);
return (ret);
}
ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos)
{
struct kiocb kiocb;
ssize_t ret;
if (!file->f_op->write_iter)
return -EINVAL;
init_sync_kiocb(&kiocb, file);
kiocb.ki_pos = *ppos;
kiocb.ki_nbytes = iov_iter_count(iter);
iter->type |= WRITE;
ret = file->f_op->write_iter(&kiocb, iter);
if (ret == -EIOCBQUEUED)
ret = wait_on_sync_kiocb(&kiocb);
if (ret > 0)
*ppos = kiocb.ki_pos;
return ret;
}
ssize_t
nfs_file_read(struct kiocb *iocb, struct iov_iter *to)
{
struct inode *inode = file_inode(iocb->ki_filp);
ssize_t result;
if (iocb->ki_flags & IOCB_DIRECT)
return nfs_file_direct_read(iocb, to, iocb->ki_pos);
dprintk("NFS: read(%pD2, %zu@%lu)\n",
iocb->ki_filp,
iov_iter_count(to), (unsigned long) iocb->ki_pos);
result = nfs_revalidate_mapping_protected(inode, iocb->ki_filp->f_mapping);
if (!result) {
result = generic_file_read_iter(iocb, to);
if (result > 0)
nfs_add_stats(inode, NFSIOS_NORMALREADBYTES, result);
}
return result;
}
STATIC ssize_t
xfs_file_buffered_aio_read(
struct kiocb *iocb,
struct iov_iter *to)
{
struct xfs_inode *ip = XFS_I(file_inode(iocb->ki_filp));
ssize_t ret;
trace_xfs_file_buffered_read(ip, iov_iter_count(to), iocb->ki_pos);
if (iocb->ki_flags & IOCB_NOWAIT) {
if (!xfs_ilock_nowait(ip, XFS_IOLOCK_SHARED))
return -EAGAIN;
} else {
xfs_ilock(ip, XFS_IOLOCK_SHARED);
}
ret = generic_file_read_iter(iocb, to);
xfs_iunlock(ip, XFS_IOLOCK_SHARED);
return ret;
}
static noinline ssize_t
xfs_file_dax_read(
struct kiocb *iocb,
struct iov_iter *to)
{
struct xfs_inode *ip = XFS_I(iocb->ki_filp->f_mapping->host);
size_t count = iov_iter_count(to);
ssize_t ret = 0;
trace_xfs_file_dax_read(ip, count, iocb->ki_pos);
if (!count)
return 0; /* skip atime */
xfs_rw_ilock(ip, XFS_IOLOCK_SHARED);
ret = iomap_dax_rw(iocb, to, &xfs_iomap_ops);
xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
file_accessed(iocb->ki_filp);
return ret;
}
/*
* Read data from a specified offset in a file (referenced by inode).
* Data may be placed either in a user or kernel buffer.
*/
ssize_t orangefs_inode_read(struct inode *inode,
struct iov_iter *iter,
loff_t *offset,
loff_t readahead_size)
{
struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
size_t count = iov_iter_count(iter);
size_t bufmap_size;
ssize_t ret = -EINVAL;
g_orangefs_stats.reads++;
bufmap_size = orangefs_bufmap_size_query();
if (count > bufmap_size) {
gossip_debug(GOSSIP_FILE_DEBUG,
"%s: count is too large (%zd/%zd)!\n",
__func__, count, bufmap_size);
return -EINVAL;
}
gossip_debug(GOSSIP_FILE_DEBUG,
"%s(%pU) %zd@%llu\n",
__func__,
&orangefs_inode->refn.khandle,
count,
llu(*offset));
ret = wait_for_direct_io(ORANGEFS_IO_READ, inode, offset, iter,
count, readahead_size);
if (ret > 0)
*offset += ret;
gossip_debug(GOSSIP_FILE_DEBUG,
"%s(%pU): Value(%zd) returned.\n",
__func__,
&orangefs_inode->refn.khandle,
ret);
return ret;
}
/**
* process_vm_rw - check iovecs before calling core routine
* @pid: PID of process to read/write from/to
* @lvec: iovec array specifying where to copy to/from locally
* @liovcnt: size of lvec array
* @rvec: iovec array specifying where to copy to/from in the other process
* @riovcnt: size of rvec array
* @flags: currently unused
* @vm_write: 0 if reading from other process, 1 if writing to other process
* Returns the number of bytes read/written or error code. May
* return less bytes than expected if an error occurs during the copying
* process.
*/
static ssize_t process_vm_rw(pid_t pid,
const struct iovec __user *lvec,
unsigned long liovcnt,
const struct iovec __user *rvec,
unsigned long riovcnt,
unsigned long flags, int vm_write)
{
struct iovec iovstack_l[UIO_FASTIOV];
struct iovec iovstack_r[UIO_FASTIOV];
struct iovec *iov_l = iovstack_l;
struct iovec *iov_r = iovstack_r;
struct iov_iter iter;
ssize_t rc;
int dir = vm_write ? WRITE : READ;
if (flags != 0)
return -EINVAL;
/* Check iovecs */
rc = import_iovec(dir, lvec, liovcnt, UIO_FASTIOV, &iov_l, &iter);
if (rc < 0)
return rc;
if (!iov_iter_count(&iter))
goto free_iovecs;
rc = rw_copy_check_uvector(CHECK_IOVEC_ONLY, rvec, riovcnt, UIO_FASTIOV,
iovstack_r, &iov_r);
if (rc <= 0)
goto free_iovecs;
rc = process_vm_rw_core(pid, &iter, iov_r, riovcnt, flags, vm_write);
free_iovecs:
if (iov_r != iovstack_r)
kfree(iov_r);
kfree(iov_l);
return rc;
}
STATIC ssize_t
xfs_file_dio_aio_read(
struct kiocb *iocb,
struct iov_iter *to)
{
struct xfs_inode *ip = XFS_I(file_inode(iocb->ki_filp));
size_t count = iov_iter_count(to);
ssize_t ret;
trace_xfs_file_direct_read(ip, count, iocb->ki_pos);
if (!count)
return 0; /* skip atime */
file_accessed(iocb->ki_filp);
xfs_ilock(ip, XFS_IOLOCK_SHARED);
ret = iomap_dio_rw(iocb, to, &xfs_iomap_ops, NULL);
xfs_iunlock(ip, XFS_IOLOCK_SHARED);
return ret;
}
int rds_message_inc_copy_to_user(struct rds_incoming *inc, struct iov_iter *to)
{
struct rds_message *rm;
struct scatterlist *sg;
unsigned long to_copy;
unsigned long vec_off;
int copied;
int ret;
u32 len;
rm = container_of(inc, struct rds_message, m_inc);
len = be32_to_cpu(rm->m_inc.i_hdr.h_len);
sg = rm->data.op_sg;
vec_off = 0;
copied = 0;
while (iov_iter_count(to) && copied < len) {
to_copy = min_t(unsigned long, iov_iter_count(to),
sg->length - vec_off);
to_copy = min_t(unsigned long, to_copy, len - copied);
rds_stats_add(s_copy_to_user, to_copy);
ret = copy_page_to_iter(sg_page(sg), sg->offset + vec_off,
to_copy, to);
if (ret != to_copy)
return -EFAULT;
vec_off += to_copy;
copied += to_copy;
if (vec_off == sg->length) {
vec_off = 0;
sg++;
}
}
return copied;
}
/**
* v9fs_file_write - write to a file
* @filp: file pointer to write
* @data: data buffer to write data from
* @count: size of buffer
* @offset: offset at which to write data
*
*/
static ssize_t
v9fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
ssize_t retval = 0;
loff_t origin = iocb->ki_pos;
size_t count = iov_iter_count(from);
int err = 0;
retval = generic_write_checks(file, &origin, &count, 0);
if (retval)
return retval;
iov_iter_truncate(from, count);
if (!count)
return 0;
retval = p9_client_write(file->private_data, origin, from, &err);
if (retval > 0) {
struct inode *inode = file_inode(file);
loff_t i_size;
unsigned long pg_start, pg_end;
pg_start = origin >> PAGE_CACHE_SHIFT;
pg_end = (origin + retval - 1) >> PAGE_CACHE_SHIFT;
if (inode->i_mapping && inode->i_mapping->nrpages)
invalidate_inode_pages2_range(inode->i_mapping,
pg_start, pg_end);
origin += retval;
i_size = i_size_read(inode);
iocb->ki_pos = origin;
if (origin > i_size) {
inode_add_bytes(inode, origin - i_size);
i_size_write(inode, origin);
}
return retval;
}
return err;
}
static ssize_t ovl_write_iter(struct kiocb *iocb, struct iov_iter *iter)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file_inode(file);
struct fd real;
const struct cred *old_cred;
ssize_t ret;
if (!iov_iter_count(iter))
return 0;
inode_lock(inode);
/* Update mode */
ovl_copyattr(ovl_inode_real(inode), inode);
ret = file_remove_privs(file);
if (ret)
goto out_unlock;
ret = ovl_real_fdget(file, &real);
if (ret)
goto out_unlock;
old_cred = ovl_override_creds(file_inode(file)->i_sb);
file_start_write(real.file);
ret = vfs_iter_write(real.file, iter, &iocb->ki_pos,
ovl_iocb_to_rwf(iocb));
file_end_write(real.file);
revert_creds(old_cred);
/* Update size */
ovl_copyattr(ovl_inode_real(inode), inode);
fdput(real);
out_unlock:
inode_unlock(inode);
return ret;
}
static ssize_t hypfs_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
int rc;
struct super_block *sb = file_inode(iocb->ki_filp)->i_sb;
struct hypfs_sb_info *fs_info = sb->s_fs_info;
size_t count = iov_iter_count(from);
/*
* Currently we only allow one update per second for two reasons:
* 1. diag 204 is VERY expensive
* 2. If several processes do updates in parallel and then read the
* hypfs data, the likelihood of collisions is reduced, if we restrict
* the minimum update interval. A collision occurs, if during the
* data gathering of one process another process triggers an update
* If the first process wants to ensure consistent data, it has
* to restart data collection in this case.
*/
mutex_lock(&fs_info->lock);
if (fs_info->last_update == get_seconds()) {
rc = -EBUSY;
goto out;
}
hypfs_delete_tree(sb->s_root);
if (MACHINE_IS_VM)
rc = hypfs_vm_create_files(sb->s_root);
else
rc = hypfs_diag_create_files(sb->s_root);
if (rc) {
pr_err("Updating the hypfs tree failed\n");
hypfs_delete_tree(sb->s_root);
goto out;
}
hypfs_update_update(sb);
rc = count;
iov_iter_advance(from, count);
out:
mutex_unlock(&fs_info->lock);
return rc;
}
STATIC ssize_t
xfs_file_write_iter(
struct kiocb *iocb,
struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
struct xfs_inode *ip = XFS_I(inode);
ssize_t ret;
size_t ocount = iov_iter_count(from);
XFS_STATS_INC(xs_write_calls);
if (ocount == 0)
return 0;
if (XFS_FORCED_SHUTDOWN(ip->i_mount))
return -EIO;
if (unlikely(file->f_flags & O_DIRECT))
ret = xfs_file_dio_aio_write(iocb, from);
else
ret = xfs_file_buffered_aio_write(iocb, from);
if (ret > 0) {
ssize_t err;
XFS_STATS_ADD(xs_write_bytes, ret);
/* Handle various SYNC-type writes */
err = generic_write_sync(file, iocb->ki_pos - ret, ret);
if (err < 0)
ret = err;
}
return ret;
}
static ssize_t jfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
{
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, 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 = iocb->ki_pos + count;
if (end > isize)
jfs_write_failed(mapping, end);
}
return ret;
}
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;
}
/* Do it by hand, with file-ops */
static ssize_t do_loop_readv_writev(struct file *filp, struct iov_iter *iter,
loff_t *ppos, io_fn_t fn)
{
ssize_t ret = 0;
while (iov_iter_count(iter)) {
struct iovec iovec = iov_iter_iovec(iter);
ssize_t nr;
nr = fn(filp, iovec.iov_base, iovec.iov_len, ppos);
if (nr < 0) {
if (!ret)
ret = nr;
break;
}
ret += nr;
if (nr != iovec.iov_len)
break;
iov_iter_advance(iter, nr);
}
return ret;
}
STATIC ssize_t
xfs_file_read_iter(
struct kiocb *iocb,
struct iov_iter *to)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
size_t size = iov_iter_count(to);
ssize_t ret = 0;
int ioflags = 0;
xfs_fsize_t n;
loff_t pos = iocb->ki_pos;
XFS_STATS_INC(xs_read_calls);
if (unlikely(file->f_flags & O_DIRECT))
ioflags |= XFS_IO_ISDIRECT;
if (file->f_mode & FMODE_NOCMTIME)
ioflags |= XFS_IO_INVIS;
if (unlikely(ioflags & XFS_IO_ISDIRECT)) {
xfs_buftarg_t *target =
XFS_IS_REALTIME_INODE(ip) ?
mp->m_rtdev_targp : mp->m_ddev_targp;
/* DIO must be aligned to device logical sector size */
if ((pos | size) & target->bt_logical_sectormask) {
if (pos == i_size_read(inode))
return 0;
return -EINVAL;
}
}
n = mp->m_super->s_maxbytes - pos;
if (n <= 0 || size == 0)
return 0;
if (n < size)
size = n;
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
/*
* Locking is a bit tricky here. If we take an exclusive lock
* for direct IO, we effectively serialise all new concurrent
* read IO to this file and block it behind IO that is currently in
* progress because IO in progress holds the IO lock shared. We only
* need to hold the lock exclusive to blow away the page cache, so
* only take lock exclusively if the page cache needs invalidation.
* This allows the normal direct IO case of no page cache pages to
* proceeed concurrently without serialisation.
*/
xfs_rw_ilock(ip, XFS_IOLOCK_SHARED);
if ((ioflags & XFS_IO_ISDIRECT) && inode->i_mapping->nrpages) {
xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
xfs_rw_ilock(ip, XFS_IOLOCK_EXCL);
if (inode->i_mapping->nrpages) {
ret = filemap_write_and_wait_range(
VFS_I(ip)->i_mapping,
pos, pos + size - 1);
if (ret) {
xfs_rw_iunlock(ip, XFS_IOLOCK_EXCL);
return ret;
}
/*
* Invalidate whole pages. This can return an error if
* we fail to invalidate a page, but this should never
* happen on XFS. Warn if it does fail.
*/
ret = invalidate_inode_pages2_range(VFS_I(ip)->i_mapping,
pos >> PAGE_CACHE_SHIFT,
(pos + size - 1) >> PAGE_CACHE_SHIFT);
WARN_ON_ONCE(ret);
ret = 0;
}
/*
* Common pre-write limit and setup checks.
*
* Called with the iolocked held either shared and exclusive according to
* @iolock, and returns with it held. Might upgrade the iolock to exclusive
* if called for a direct write beyond i_size.
*/
STATIC ssize_t
xfs_file_aio_write_checks(
struct kiocb *iocb,
struct iov_iter *from,
int *iolock)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
struct xfs_inode *ip = XFS_I(inode);
ssize_t error = 0;
size_t count = iov_iter_count(from);
bool drained_dio = false;
restart:
error = generic_write_checks(iocb, from);
if (error <= 0)
return error;
error = xfs_break_layouts(inode, iolock);
if (error)
return error;
/*
* For changing security info in file_remove_privs() we need i_rwsem
* exclusively.
*/
if (*iolock == XFS_IOLOCK_SHARED && !IS_NOSEC(inode)) {
xfs_iunlock(ip, *iolock);
*iolock = XFS_IOLOCK_EXCL;
xfs_ilock(ip, *iolock);
goto restart;
}
/*
* If the offset is beyond the size of the file, we need to zero any
* blocks that fall between the existing EOF and the start of this
* write. If zeroing is needed and we are currently holding the
* iolock shared, we need to update it to exclusive which implies
* having to redo all checks before.
*
* We need to serialise against EOF updates that occur in IO
* completions here. We want to make sure that nobody is changing the
* size while we do this check until we have placed an IO barrier (i.e.
* hold the XFS_IOLOCK_EXCL) that prevents new IO from being dispatched.
* The spinlock effectively forms a memory barrier once we have the
* XFS_IOLOCK_EXCL so we are guaranteed to see the latest EOF value
* and hence be able to correctly determine if we need to run zeroing.
*/
spin_lock(&ip->i_flags_lock);
if (iocb->ki_pos > i_size_read(inode)) {
spin_unlock(&ip->i_flags_lock);
if (!drained_dio) {
if (*iolock == XFS_IOLOCK_SHARED) {
xfs_iunlock(ip, *iolock);
*iolock = XFS_IOLOCK_EXCL;
xfs_ilock(ip, *iolock);
iov_iter_reexpand(from, count);
}
/*
* We now have an IO submission barrier in place, but
* AIO can do EOF updates during IO completion and hence
* we now need to wait for all of them to drain. Non-AIO
* DIO will have drained before we are given the
* XFS_IOLOCK_EXCL, and so for most cases this wait is a
* no-op.
*/
inode_dio_wait(inode);
drained_dio = true;
goto restart;
}
error = xfs_zero_eof(ip, iocb->ki_pos, i_size_read(inode), NULL);
if (error)
return error;
} else
spin_unlock(&ip->i_flags_lock);
/*
* Updating the timestamps will grab the ilock again from
* xfs_fs_dirty_inode, so we have to call it after dropping the
* lock above. Eventually we should look into a way to avoid
* the pointless lock roundtrip.
*/
if (likely(!(file->f_mode & FMODE_NOCMTIME))) {
error = file_update_time(file);
if (error)
return error;
}
/*
* If we're writing the file then make sure to clear the setuid and
* setgid bits if the process is not being run by root. This keeps
* people from modifying setuid and setgid binaries.
*/
if (!IS_NOSEC(inode))
return file_remove_privs(file);
return 0;
}
/*
* xfs_file_dio_aio_write - handle direct IO writes
*
* Lock the inode appropriately to prepare for and issue a direct IO write.
* By separating it from the buffered write path we remove all the tricky to
* follow locking changes and looping.
*
* If there are cached pages or we're extending the file, we need IOLOCK_EXCL
* until we're sure the bytes at the new EOF have been zeroed and/or the cached
* pages are flushed out.
*
* In most cases the direct IO writes will be done holding IOLOCK_SHARED
* allowing them to be done in parallel with reads and other direct IO writes.
* However, if the IO is not aligned to filesystem blocks, the direct IO layer
* needs to do sub-block zeroing and that requires serialisation against other
* direct IOs to the same block. In this case we need to serialise the
* submission of the unaligned IOs so that we don't get racing block zeroing in
* the dio layer. To avoid the problem with aio, we also need to wait for
* outstanding IOs to complete so that unwritten extent conversion is completed
* before we try to map the overlapping block. This is currently implemented by
* hitting it with a big hammer (i.e. inode_dio_wait()).
*
* Returns with locks held indicated by @iolock and errors indicated by
* negative return values.
*/
STATIC ssize_t
xfs_file_dio_aio_write(
struct kiocb *iocb,
struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
ssize_t ret = 0;
int unaligned_io = 0;
int iolock;
size_t count = iov_iter_count(from);
struct xfs_buftarg *target = XFS_IS_REALTIME_INODE(ip) ?
mp->m_rtdev_targp : mp->m_ddev_targp;
/* DIO must be aligned to device logical sector size */
if ((iocb->ki_pos | count) & target->bt_logical_sectormask)
return -EINVAL;
/*
* Don't take the exclusive iolock here unless the I/O is unaligned to
* the file system block size. We don't need to consider the EOF
* extension case here because xfs_file_aio_write_checks() will relock
* the inode as necessary for EOF zeroing cases and fill out the new
* inode size as appropriate.
*/
if ((iocb->ki_pos & mp->m_blockmask) ||
((iocb->ki_pos + count) & mp->m_blockmask)) {
unaligned_io = 1;
/*
* We can't properly handle unaligned direct I/O to reflink
* files yet, as we can't unshare a partial block.
*/
if (xfs_is_reflink_inode(ip)) {
trace_xfs_reflink_bounce_dio_write(ip, iocb->ki_pos, count);
return -EREMCHG;
}
iolock = XFS_IOLOCK_EXCL;
} else {
iolock = XFS_IOLOCK_SHARED;
}
if (iocb->ki_flags & IOCB_NOWAIT) {
if (!xfs_ilock_nowait(ip, iolock))
return -EAGAIN;
} else {
xfs_ilock(ip, iolock);
}
ret = xfs_file_aio_write_checks(iocb, from, &iolock);
if (ret)
goto out;
count = iov_iter_count(from);
/*
* If we are doing unaligned IO, wait for all other IO to drain,
* otherwise demote the lock if we had to take the exclusive lock
* for other reasons in xfs_file_aio_write_checks.
*/
if (unaligned_io) {
/* If we are going to wait for other DIO to finish, bail */
if (iocb->ki_flags & IOCB_NOWAIT) {
if (atomic_read(&inode->i_dio_count))
return -EAGAIN;
} else {
inode_dio_wait(inode);
}
} else if (iolock == XFS_IOLOCK_EXCL) {
xfs_ilock_demote(ip, XFS_IOLOCK_EXCL);
iolock = XFS_IOLOCK_SHARED;
}
trace_xfs_file_direct_write(ip, count, iocb->ki_pos);
ret = iomap_dio_rw(iocb, from, &xfs_iomap_ops, xfs_dio_write_end_io);
out:
xfs_iunlock(ip, iolock);
/*
* No fallback to buffered IO on errors for XFS, direct IO will either
* complete fully or fail.
*/
ASSERT(ret < 0 || ret == count);
return ret;
}
/**
* process_vm_rw_core - core of reading/writing pages from task specified
* @pid: PID of process to read/write from/to
* @iter: where to copy to/from locally
* @rvec: iovec array specifying where to copy to/from in the other process
* @riovcnt: size of rvec array
* @flags: currently unused
* @vm_write: 0 if reading from other process, 1 if writing to other process
* Returns the number of bytes read/written or error code. May
* return less bytes than expected if an error occurs during the copying
* process.
*/
static ssize_t process_vm_rw_core(pid_t pid, struct iov_iter *iter,
const struct iovec *rvec,
unsigned long riovcnt,
unsigned long flags, int vm_write)
{
struct task_struct *task;
struct page *pp_stack[PVM_MAX_PP_ARRAY_COUNT];
struct page **process_pages = pp_stack;
struct mm_struct *mm;
unsigned long i;
ssize_t rc = 0;
unsigned long nr_pages = 0;
unsigned long nr_pages_iov;
ssize_t iov_len;
size_t total_len = iov_iter_count(iter);
return -ENOSYS; // PaX: until properly audited
/*
* Work out how many pages of struct pages we're going to need
* when eventually calling get_user_pages
*/
for (i = 0; i < riovcnt; i++) {
iov_len = rvec[i].iov_len;
if (iov_len <= 0)
continue;
nr_pages_iov = ((unsigned long)rvec[i].iov_base + iov_len) / PAGE_SIZE -
(unsigned long)rvec[i].iov_base / PAGE_SIZE + 1;
nr_pages = max(nr_pages, nr_pages_iov);
}
if (nr_pages == 0)
return 0;
if (nr_pages > PVM_MAX_PP_ARRAY_COUNT) {
/* For reliability don't try to kmalloc more than
2 pages worth */
process_pages = kmalloc(min_t(size_t, PVM_MAX_KMALLOC_PAGES,
sizeof(struct pages *)*nr_pages),
GFP_KERNEL);
if (!process_pages)
return -ENOMEM;
}
/* Get process information */
rcu_read_lock();
task = find_task_by_vpid(pid);
if (task)
get_task_struct(task);
rcu_read_unlock();
if (!task) {
rc = -ESRCH;
goto free_proc_pages;
}
if (gr_handle_ptrace(task, vm_write ? PTRACE_POKETEXT : PTRACE_ATTACH)) {
rc = -EPERM;
goto put_task_struct;
}
mm = mm_access(task, PTRACE_MODE_ATTACH);
if (!mm || IS_ERR(mm)) {
rc = IS_ERR(mm) ? PTR_ERR(mm) : -ESRCH;
/*
* Explicitly map EACCES to EPERM as EPERM is a more a
* appropriate error code for process_vw_readv/writev
*/
if (rc == -EACCES)
rc = -EPERM;
goto put_task_struct;
}
for (i = 0; i < riovcnt && iov_iter_count(iter) && !rc; i++)
rc = process_vm_rw_single_vec(
(unsigned long)rvec[i].iov_base, rvec[i].iov_len,
iter, process_pages, mm, task, vm_write);
/* copied = space before - space after */
total_len -= iov_iter_count(iter);
/* If we have managed to copy any data at all then
we return the number of bytes copied. Otherwise
we return the error code */
if (total_len)
rc = total_len;
mmput(mm);
put_task_struct:
put_task_struct(task);
free_proc_pages:
if (process_pages != pp_stack)
kfree(process_pages);
return rc;
}
STATIC ssize_t
xfs_file_buffered_aio_write(
struct kiocb *iocb,
struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
struct xfs_inode *ip = XFS_I(inode);
ssize_t ret;
int enospc = 0;
int iolock;
if (iocb->ki_flags & IOCB_NOWAIT)
return -EOPNOTSUPP;
write_retry:
iolock = XFS_IOLOCK_EXCL;
xfs_ilock(ip, iolock);
ret = xfs_file_aio_write_checks(iocb, from, &iolock);
if (ret)
goto out;
/* We can write back this queue in page reclaim */
current->backing_dev_info = inode_to_bdi(inode);
trace_xfs_file_buffered_write(ip, iov_iter_count(from), iocb->ki_pos);
ret = iomap_file_buffered_write(iocb, from, &xfs_iomap_ops);
if (likely(ret >= 0))
iocb->ki_pos += ret;
/*
* If we hit a space limit, try to free up some lingering preallocated
* space before returning an error. In the case of ENOSPC, first try to
* write back all dirty inodes to free up some of the excess reserved
* metadata space. This reduces the chances that the eofblocks scan
* waits on dirty mappings. Since xfs_flush_inodes() is serialized, this
* also behaves as a filter to prevent too many eofblocks scans from
* running at the same time.
*/
if (ret == -EDQUOT && !enospc) {
xfs_iunlock(ip, iolock);
enospc = xfs_inode_free_quota_eofblocks(ip);
if (enospc)
goto write_retry;
enospc = xfs_inode_free_quota_cowblocks(ip);
if (enospc)
goto write_retry;
iolock = 0;
} else if (ret == -ENOSPC && !enospc) {
struct xfs_eofblocks eofb = {0};
enospc = 1;
xfs_flush_inodes(ip->i_mount);
xfs_iunlock(ip, iolock);
eofb.eof_flags = XFS_EOF_FLAGS_SYNC;
xfs_icache_free_eofblocks(ip->i_mount, &eofb);
xfs_icache_free_cowblocks(ip->i_mount, &eofb);
goto write_retry;
}
current->backing_dev_info = NULL;
out:
if (iolock)
xfs_iunlock(ip, iolock);
return ret;
}
