Contributors: 20
Author Tokens Token Proportion Commits Commit Proportion
Christoph Hellwig 1096 82.72% 25 40.98%
David Chinner 68 5.13% 10 16.39%
Ben Myers 54 4.08% 1 1.64%
Darrick J. Wong 26 1.96% 3 4.92%
Dan J Williams 18 1.36% 2 3.28%
Russell Cattelan 11 0.83% 1 1.64%
Nathan Scott 10 0.75% 3 4.92%
Eric Sandeen 7 0.53% 2 3.28%
Brian Foster 7 0.53% 2 3.28%
Mark Fasheh 6 0.45% 1 1.64%
Al Viro 6 0.45% 2 3.28%
Jie Liu 4 0.30% 1 1.64%
Ben Dooks 3 0.23% 1 1.64%
Eryu Guan 2 0.15% 1 1.64%
Kirill A. Shutemov 2 0.15% 1 1.64%
Greg Kroah-Hartman 1 0.08% 1 1.64%
Christian Brauner 1 0.08% 1 1.64%
Tiger Yang 1 0.08% 1 1.64%
Greg Banks 1 0.08% 1 1.64%
Ira Weiny 1 0.08% 1 1.64%
Total 1325 61 
123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (c) 2014 Christoph Hellwig.
 */
#include "xfs.h"
#include "xfs_shared.h"
#include "xfs_format.h"
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_mount.h"
#include "xfs_inode.h"
#include "xfs_trans.h"
#include "xfs_bmap.h"
#include "xfs_iomap.h"
#include "xfs_pnfs.h"

/*
 * Ensure that we do not have any outstanding pNFS layouts that can be used by
 * clients to directly read from or write to this inode.  This must be called
 * before every operation that can remove blocks from the extent map.
 * Additionally we call it during the write operation, where aren't concerned
 * about exposing unallocated blocks but just want to provide basic
 * synchronization between a local writer and pNFS clients.  mmap writes would
 * also benefit from this sort of synchronization, but due to the tricky locking
 * rules in the page fault path we don't bother.
 */
int
xfs_break_leased_layouts(
	struct inode		*inode,
	uint			*iolock,
	bool			*did_unlock)
{
	struct xfs_inode	*ip = XFS_I(inode);
	int			error;

	while ((error = break_layout(inode, false)) == -EWOULDBLOCK) {
		xfs_iunlock(ip, *iolock);
		*did_unlock = true;
		error = break_layout(inode, true);
		*iolock &= ~XFS_IOLOCK_SHARED;
		*iolock |= XFS_IOLOCK_EXCL;
		xfs_ilock(ip, *iolock);
	}

	return error;
}

/*
 * Get a unique ID including its location so that the client can identify
 * the exported device.
 */
int
xfs_fs_get_uuid(
	struct super_block	*sb,
	u8			*buf,
	u32			*len,
	u64			*offset)
{
	struct xfs_mount	*mp = XFS_M(sb);

	xfs_warn_experimental(mp, XFS_EXPERIMENTAL_PNFS);

	if (*len < sizeof(uuid_t))
		return -EINVAL;

	memcpy(buf, &mp->m_sb.sb_uuid, sizeof(uuid_t));
	*len = sizeof(uuid_t);
	*offset = offsetof(struct xfs_dsb, sb_uuid);
	return 0;
}

/*
 * We cannot use file based VFS helpers such as file_modified() to update
 * inode state as we modify the data/metadata in the inode here. Hence we have
 * to open code the timestamp updates and SUID/SGID stripping. We also need
 * to set the inode prealloc flag to ensure that the extents we allocate are not
 * removed if the inode is reclaimed from memory before xfs_fs_block_commit()
 * is from the client to indicate that data has been written and the file size
 * can be extended.
 */
static int
xfs_fs_map_update_inode(
	struct xfs_inode	*ip)
{
	struct xfs_trans	*tp;
	int			error;

	error = xfs_trans_alloc(ip->i_mount, &M_RES(ip->i_mount)->tr_writeid,
			0, 0, 0, &tp);
	if (error)
		return error;

	xfs_ilock(ip, XFS_ILOCK_EXCL);
	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);

	VFS_I(ip)->i_mode &= ~S_ISUID;
	if (VFS_I(ip)->i_mode & S_IXGRP)
		VFS_I(ip)->i_mode &= ~S_ISGID;
	xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
	ip->i_diflags |= XFS_DIFLAG_PREALLOC;

	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
	return xfs_trans_commit(tp);
}

/*
 * Get a layout for the pNFS client.
 */
int
xfs_fs_map_blocks(
	struct inode		*inode,
	loff_t			offset,
	u64			length,
	struct iomap		*iomap,
	bool			write,
	u32			*device_generation)
{
	struct xfs_inode	*ip = XFS_I(inode);
	struct xfs_mount	*mp = ip->i_mount;
	struct xfs_bmbt_irec	imap;
	xfs_fileoff_t		offset_fsb, end_fsb;
	loff_t			limit;
	int			bmapi_flags = XFS_BMAPI_ENTIRE;
	int			nimaps = 1;
	uint			lock_flags;
	int			error = 0;
	u64			seq;

	if (xfs_is_shutdown(mp))
		return -EIO;

	/*
	 * We can't export inodes residing on the realtime device.  The realtime
	 * device doesn't have a UUID to identify it, so the client has no way
	 * to find it.
	 */
	if (XFS_IS_REALTIME_INODE(ip))
		return -ENXIO;

	/*
	 * The pNFS block layout spec actually supports reflink like
	 * functionality, but the Linux pNFS server doesn't implement it yet.
	 */
	if (xfs_is_reflink_inode(ip))
		return -ENXIO;

	/*
	 * Lock out any other I/O before we flush and invalidate the pagecache,
	 * and then hand out a layout to the remote system.  This is very
	 * similar to direct I/O, except that the synchronization is much more
	 * complicated.  See the comment near xfs_break_leased_layouts
	 * for a detailed explanation.
	 */
	xfs_ilock(ip, XFS_IOLOCK_EXCL);

	error = -EINVAL;
	limit = mp->m_super->s_maxbytes;
	if (!write)
		limit = max(limit, round_up(i_size_read(inode),
				     inode->i_sb->s_blocksize));
	if (offset > limit)
		goto out_unlock;
	if (offset > limit - length)
		length = limit - offset;

	error = filemap_write_and_wait(inode->i_mapping);
	if (error)
		goto out_unlock;
	error = invalidate_inode_pages2(inode->i_mapping);
	if (WARN_ON_ONCE(error))
		goto out_unlock;

	end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)offset + length);
	offset_fsb = XFS_B_TO_FSBT(mp, offset);

	lock_flags = xfs_ilock_data_map_shared(ip);
	error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb,
				&imap, &nimaps, bmapi_flags);
	seq = xfs_iomap_inode_sequence(ip, 0);

	ASSERT(!nimaps || imap.br_startblock != DELAYSTARTBLOCK);

	if (!error && write &&
	    (!nimaps || imap.br_startblock == HOLESTARTBLOCK)) {
		if (offset + length > XFS_ISIZE(ip))
			end_fsb = xfs_iomap_eof_align_last_fsb(ip, end_fsb);
		else if (nimaps && imap.br_startblock == HOLESTARTBLOCK)
			end_fsb = min(end_fsb, imap.br_startoff +
					       imap.br_blockcount);
		xfs_iunlock(ip, lock_flags);

		error = xfs_iomap_write_direct(ip, offset_fsb,
				end_fsb - offset_fsb, 0, &imap, &seq);
		if (error)
			goto out_unlock;

		/*
		 * Ensure the next transaction is committed synchronously so
		 * that the blocks allocated and handed out to the client are
		 * guaranteed to be present even after a server crash.
		 */
		error = xfs_fs_map_update_inode(ip);
		if (!error)
			error = xfs_log_force_inode(ip);
		if (error)
			goto out_unlock;

	} else {
		xfs_iunlock(ip, lock_flags);
	}
	xfs_iunlock(ip, XFS_IOLOCK_EXCL);

	error = xfs_bmbt_to_iomap(ip, iomap, &imap, 0, 0, seq);
	*device_generation = mp->m_generation;
	return error;
out_unlock:
	xfs_iunlock(ip, XFS_IOLOCK_EXCL);
	return error;
}

/*
 * Ensure the size update falls into a valid allocated block.
 */
static int
xfs_pnfs_validate_isize(
	struct xfs_inode	*ip,
	xfs_off_t		isize)
{
	struct xfs_bmbt_irec	imap;
	int			nimaps = 1;
	int			error = 0;

	xfs_ilock(ip, XFS_ILOCK_SHARED);
	error = xfs_bmapi_read(ip, XFS_B_TO_FSBT(ip->i_mount, isize - 1), 1,
				&imap, &nimaps, 0);
	xfs_iunlock(ip, XFS_ILOCK_SHARED);
	if (error)
		return error;

	if (imap.br_startblock == HOLESTARTBLOCK ||
	    imap.br_startblock == DELAYSTARTBLOCK ||
	    imap.br_state == XFS_EXT_UNWRITTEN)
		return -EIO;
	return 0;
}

/*
 * Make sure the blocks described by maps are stable on disk.  This includes
 * converting any unwritten extents, flushing the disk cache and updating the
 * time stamps.
 *
 * Note that we rely on the caller to always send us a timestamp update so that
 * we always commit a transaction here.  If that stops being true we will have
 * to manually flush the cache here similar to what the fsync code path does
 * for datasyncs on files that have no dirty metadata.
 */
int
xfs_fs_commit_blocks(
	struct inode		*inode,
	struct iomap		*maps,
	int			nr_maps,
	struct iattr		*iattr)
{
	struct xfs_inode	*ip = XFS_I(inode);
	struct xfs_mount	*mp = ip->i_mount;
	struct xfs_trans	*tp;
	bool			update_isize = false;
	int			error, i;
	loff_t			size;

	ASSERT(iattr->ia_valid & (ATTR_ATIME|ATTR_CTIME|ATTR_MTIME));

	xfs_ilock(ip, XFS_IOLOCK_EXCL);

	size = i_size_read(inode);
	if ((iattr->ia_valid & ATTR_SIZE) && iattr->ia_size > size) {
		update_isize = true;
		size = iattr->ia_size;
	}

	for (i = 0; i < nr_maps; i++) {
		u64 start, length, end;

		start = maps[i].offset;
		if (start > size)
			continue;

		end = start + maps[i].length;
		if (end > size)
			end = size;

		length = end - start;
		if (!length)
			continue;

		/*
		 * Make sure reads through the pagecache see the new data.
		 */
		error = invalidate_inode_pages2_range(inode->i_mapping,
					start >> PAGE_SHIFT,
					(end - 1) >> PAGE_SHIFT);
		WARN_ON_ONCE(error);

		error = xfs_iomap_write_unwritten(ip, start, length, false);
		if (error)
			goto out_drop_iolock;
	}

	if (update_isize) {
		error = xfs_pnfs_validate_isize(ip, size);
		if (error)
			goto out_drop_iolock;
	}

	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ichange, 0, 0, 0, &tp);
	if (error)
		goto out_drop_iolock;

	xfs_ilock(ip, XFS_ILOCK_EXCL);
	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);

	ASSERT(!(iattr->ia_valid & (ATTR_UID | ATTR_GID)));
	setattr_copy(&nop_mnt_idmap, inode, iattr);
	if (update_isize) {
		i_size_write(inode, iattr->ia_size);
		ip->i_disk_size = iattr->ia_size;
	}

	xfs_trans_set_sync(tp);
	error = xfs_trans_commit(tp);

out_drop_iolock:
	xfs_iunlock(ip, XFS_IOLOCK_EXCL);
	return error;
}