sector_t sector = iomap->blkno +
(((pos & ~(PAGE_SIZE - 1)) - iomap->offset) >> 9);
- return __dax_zero_page_range(iomap->bdev, sector, offset, bytes);
+ return __dax_zero_page_range(iomap->bdev, iomap->dax_dev, sector,
+ offset, bytes);
}
static loff_t
flags |= IOMAP_WRITE;
}
- if (mapping->nrpages) {
- ret = filemap_write_and_wait_range(mapping, start, end);
- if (ret)
- goto out_free_dio;
+ ret = filemap_write_and_wait_range(mapping, start, end);
+ if (ret)
+ goto out_free_dio;
- ret = invalidate_inode_pages2_range(mapping,
- start >> PAGE_SHIFT, end >> PAGE_SHIFT);
- WARN_ON_ONCE(ret);
- ret = 0;
- }
+ ret = invalidate_inode_pages2_range(mapping,
+ start >> PAGE_SHIFT, end >> PAGE_SHIFT);
+ WARN_ON_ONCE(ret);
+ ret = 0;
inode_dio_begin(inode);
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);
* one is a pretty crazy thing to do, so we don't support it 100%. If
* this invalidation fails, tough, the write still worked...
*/
- if (iov_iter_rw(iter) == WRITE && mapping->nrpages) {
+ if (iov_iter_rw(iter) == WRITE) {
int err = invalidate_inode_pages2_range(mapping,
start >> PAGE_SHIFT, end >> PAGE_SHIFT);
WARN_ON_ONCE(err);
struct xfs_btree_split_args *args = container_of(work,
struct xfs_btree_split_args, work);
unsigned long pflags;
- unsigned long new_pflags = PF_FSTRANS;
+ unsigned long new_pflags = PF_MEMALLOC_NOFS;
/*
* we are in a transaction context here, but may also be doing work
fn, priv);
}
+ /* Query a btree for all records. */
+ int
+ xfs_btree_query_all(
+ struct xfs_btree_cur *cur,
+ xfs_btree_query_range_fn fn,
+ void *priv)
+ {
+ union xfs_btree_irec low_rec;
+ union xfs_btree_irec high_rec;
+
+ memset(&low_rec, 0, sizeof(low_rec));
+ memset(&high_rec, 0xFF, sizeof(high_rec));
+ return xfs_btree_query_range(cur, &low_rec, &high_rec, fn, priv);
+ }
+
/*
* Calculate the number of blocks needed to store a given number of records
* in a short-format (per-AG metadata) btree.
bsize = bh->b_size;
do {
+ if (off > end)
+ break;
next = bh->b_this_page;
if (off < bvec->bv_offset)
goto next_bh;
- if (off > end)
- break;
bh->b_end_io(bh, !error);
next_bh:
off += bsize;
* We hand off the transaction to the completion thread now, so
* clear the flag here.
*/
- current_restore_flags_nested(&tp->t_pflags, PF_FSTRANS);
+ current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
return 0;
}
* thus we need to mark ourselves as being in a transaction manually.
* Similarly for freeze protection.
*/
- current_set_flags_nested(&tp->t_pflags, PF_FSTRANS);
+ current_set_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
__sb_writers_acquired(VFS_I(ip)->i_sb, SB_FREEZE_FS);
/* we abort the update if there was an IO error */
* Given that we do not allow direct reclaim to call us, we should
* never be called while in a filesystem transaction.
*/
- if (WARN_ON_ONCE(current->flags & PF_FSTRANS))
+ if (WARN_ON_ONCE(current->flags & PF_MEMALLOC_NOFS))
goto redirty;
/*
if (nimaps) {
trace_xfs_get_blocks_found(ip, offset, size,
- ISUNWRITTEN(&imap) ? XFS_IO_UNWRITTEN
- : XFS_IO_OVERWRITE, &imap);
+ imap.br_state == XFS_EXT_UNWRITTEN ?
+ XFS_IO_UNWRITTEN : XFS_IO_OVERWRITE, &imap);
xfs_iunlock(ip, lockmode);
} else {
trace_xfs_get_blocks_notfound(ip, offset, size);
* For unwritten extents do not report a disk address in the buffered
* read case (treat as if we're reading into a hole).
*/
- if (imap.br_startblock != HOLESTARTBLOCK &&
- imap.br_startblock != DELAYSTARTBLOCK &&
- !ISUNWRITTEN(&imap))
+ if (xfs_bmap_is_real_extent(&imap))
xfs_map_buffer(inode, bh_result, &imap, offset);
/*
return blkdev_issue_zeroout(xfs_find_bdev_for_inode(VFS_I(ip)),
block << (mp->m_super->s_blocksize_bits - 9),
count_fsb << (mp->m_super->s_blocksize_bits - 9),
- GFP_NOFS, true);
+ GFP_NOFS, 0);
}
int
next_map->br_blockcount = 0;
/* Only written data blocks can be shared. */
- if (!xfs_is_reflink_inode(ip) || whichfork != XFS_DATA_FORK ||
- map->br_startblock == DELAYSTARTBLOCK ||
- map->br_startblock == HOLESTARTBLOCK ||
- ISUNWRITTEN(map))
+ if (!xfs_is_reflink_inode(ip) ||
+ whichfork != XFS_DATA_FORK ||
+ !xfs_bmap_is_real_extent(map))
return 0;
agno = XFS_FSB_TO_AGNO(mp, map->br_startblock);
}
/*
- * This is called by xfs_inactive to free any blocks beyond eof
- * when the link count isn't zero and by xfs_dm_punch_hole() when
- * punching a hole to EOF.
+ * This is called to free any blocks beyond eof. The caller must hold
+ * IOLOCK_EXCL unless we are in the inode reclaim path and have the only
+ * reference to the inode.
*/
int
xfs_free_eofblocks(
struct xfs_bmbt_irec imap;
struct xfs_mount *mp = ip->i_mount;
- ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
-
/*
* Figure out if there are any blocks beyond the end
* of the file. If not, then there is nothing to do.
return error;
if (nimap && imap.br_startblock != HOLESTARTBLOCK) {
- xfs_daddr_t block;
-
ASSERT(imap.br_startblock != DELAYSTARTBLOCK);
- block = imap.br_startblock;
- mod = do_div(block, mp->m_sb.sb_rextsize);
+ mod = do_mod(imap.br_startblock, mp->m_sb.sb_rextsize);
if (mod)
*startoffset_fsb += mp->m_sb.sb_rextsize - mod;
}
bp->b_addr = NULL;
} else {
int retried = 0;
- unsigned noio_flag;
+ unsigned nofs_flag;
/*
* vm_map_ram() will allocate auxillary structures (e.g.
* pagetables) with GFP_KERNEL, yet we are likely to be under
* GFP_NOFS context here. Hence we need to tell memory reclaim
- * that we are in such a context via PF_MEMALLOC_NOIO to prevent
+ * that we are in such a context via PF_MEMALLOC_NOFS to prevent
* memory reclaim re-entering the filesystem here and
* potentially deadlocking.
*/
- noio_flag = memalloc_noio_save();
+ nofs_flag = memalloc_nofs_save();
do {
bp->b_addr = vm_map_ram(bp->b_pages, bp->b_page_count,
-1, PAGE_KERNEL);
break;
vm_unmap_aliases();
} while (retried++ <= 1);
- memalloc_noio_restore(noio_flag);
+ memalloc_nofs_restore(nofs_flag);
if (!bp->b_addr)
return -ENOMEM;
xfs_buf_unlock(
struct xfs_buf *bp)
{
+ ASSERT(xfs_buf_islocked(bp));
+
XB_CLEAR_OWNER(bp);
up(&bp->b_sema);
return NULL;
}
+ /*
+ * Cancel a delayed write list.
+ *
+ * Remove each buffer from the list, clear the delwri queue flag and drop the
+ * associated buffer reference.
+ */
+ void
+ xfs_buf_delwri_cancel(
+ struct list_head *list)
+ {
+ struct xfs_buf *bp;
+
+ while (!list_empty(list)) {
+ bp = list_first_entry(list, struct xfs_buf, b_list);
+
+ xfs_buf_lock(bp);
+ bp->b_flags &= ~_XBF_DELWRI_Q;
+ list_del_init(&bp->b_list);
+ xfs_buf_relse(bp);
+ }
+ }
+
/*
* Add a buffer to the delayed write list.
*
*/
if (IS_DAX(VFS_I(ip))) {
bmapi_flags = XFS_BMAPI_CONVERT | XFS_BMAPI_ZERO;
- if (ISUNWRITTEN(imap)) {
+ if (imap->br_state == XFS_EXT_UNWRITTEN) {
tflags |= XFS_TRANS_RESERVE;
resblks = XFS_DIOSTRAT_SPACE_RES(mp, 0) << 1;
}
return !nimaps ||
imap->br_startblock == HOLESTARTBLOCK ||
imap->br_startblock == DELAYSTARTBLOCK ||
- (IS_DAX(inode) && ISUNWRITTEN(imap));
+ (IS_DAX(inode) && imap->br_state == XFS_EXT_UNWRITTEN);
}
static inline bool need_excl_ilock(struct xfs_inode *ip, unsigned flags)
int nimaps = 1, error = 0;
bool shared = false, trimmed = false;
unsigned lockmode;
+ struct block_device *bdev;
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
}
xfs_bmbt_to_iomap(ip, iomap, &imap);
+
+ /* optionally associate a dax device with the iomap bdev */
+ bdev = iomap->bdev;
+ if (blk_queue_dax(bdev->bd_queue))
+ iomap->dax_dev = dax_get_by_host(bdev->bd_disk->disk_name);
+ else
+ iomap->dax_dev = NULL;
+
if (shared)
iomap->flags |= IOMAP_F_SHARED;
return 0;
unsigned flags,
struct iomap *iomap)
{
+ put_dax(iomap->dax_dev);
if ((flags & IOMAP_WRITE) && iomap->type == IOMAP_DELALLOC)
return xfs_file_iomap_end_delalloc(XFS_I(inode), offset,
length, written, iomap);
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
- lockmode = xfs_ilock_data_map_shared(ip);
+ lockmode = xfs_ilock_attr_map_shared(ip);
/* if there are no attribute fork or extents, return ENOENT */
- if (XFS_IFORK_Q(ip) || !ip->i_d.di_anextents) {
+ if (!XFS_IFORK_Q(ip) || !ip->i_d.di_anextents) {
error = -ENOENT;
goto out_unlock;
}
bool rsvd = (tp->t_flags & XFS_TRANS_RESERVE) != 0;
/* Mark this thread as being in a transaction */
- current_set_flags_nested(&tp->t_pflags, PF_FSTRANS);
+ current_set_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
/*
* Attempt to reserve the needed disk blocks by decrementing
if (blocks > 0) {
error = xfs_mod_fdblocks(tp->t_mountp, -((int64_t)blocks), rsvd);
if (error != 0) {
- current_restore_flags_nested(&tp->t_pflags, PF_FSTRANS);
+ current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
return -ENOSPC;
}
tp->t_blk_res += blocks;
tp->t_blk_res = 0;
}
- current_restore_flags_nested(&tp->t_pflags, PF_FSTRANS);
+ current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
return error;
}
return 0;
}
+ /*
+ * Create an empty transaction with no reservation. This is a defensive
+ * mechanism for routines that query metadata without actually modifying
+ * them -- if the metadata being queried is somehow cross-linked (think a
+ * btree block pointer that points higher in the tree), we risk deadlock.
+ * However, blocks grabbed as part of a transaction can be re-grabbed.
+ * The verifiers will notice the corrupt block and the operation will fail
+ * back to userspace without deadlocking.
+ *
+ * Note the zero-length reservation; this transaction MUST be cancelled
+ * without any dirty data.
+ */
+ int
+ xfs_trans_alloc_empty(
+ struct xfs_mount *mp,
+ struct xfs_trans **tpp)
+ {
+ struct xfs_trans_res resv = {0};
+
+ return xfs_trans_alloc(mp, &resv, 0, 0, XFS_TRANS_NO_WRITECOUNT, tpp);
+ }
+
/*
* Record the indicated change to the given field for application
* to the file system's superblock when the transaction commits.
xfs_log_commit_cil(mp, tp, &commit_lsn, regrant);
- current_restore_flags_nested(&tp->t_pflags, PF_FSTRANS);
+ current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
xfs_trans_free(tp);
/*
if (commit_lsn == -1 && !error)
error = -EIO;
}
- current_restore_flags_nested(&tp->t_pflags, PF_FSTRANS);
+ current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
xfs_trans_free_items(tp, NULLCOMMITLSN, !!error);
xfs_trans_free(tp);
xfs_log_done(mp, tp->t_ticket, NULL, false);
/* mark this thread as no longer being in a transaction */
- current_restore_flags_nested(&tp->t_pflags, PF_FSTRANS);
+ current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
xfs_trans_free_items(tp, NULLCOMMITLSN, dirty);
xfs_trans_free(tp);
* chunk we've been working on and get a new transaction to continue.
*/
int
- __xfs_trans_roll(
+ xfs_trans_roll(
struct xfs_trans **tpp,
- struct xfs_inode *dp,
- int *committed)
+ struct xfs_inode *dp)
{
struct xfs_trans *trans;
struct xfs_trans_res tres;
int error;
- *committed = 0;
-
/*
* Ensure that the inode is always logged.
*/
if (error)
return error;
- *committed = 1;
trans = *tpp;
/*
xfs_trans_ijoin(trans, dp, 0);
return 0;
}
-
- int
- xfs_trans_roll(
- struct xfs_trans **tpp,
- struct xfs_inode *dp)
- {
- int committed;
- return __xfs_trans_roll(tpp, dp, &committed);
- }