summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorDave Chinner <dchinner@redhat.com>2013-08-12 20:49:45 +1000
committerBen Myers <bpm@sgi.com>2013-08-12 16:53:39 -0500
commitc24b5dfadc4a4f7a13af373067871479c74455e6 (patch)
treeb723f9218cf1d6d7e73ea4241869ad1905798c36
parent836a94ad59bf6c1bcea0fdbe945540926fa3ca8b (diff)
xfs: kill xfs_vnodeops.[ch]
Now we have xfs_inode.c for holding kernel-only XFS inode operations, move all the inode operations from xfs_vnodeops.c to this new file as it holds another set of kernel-only inode operations. The name of this file traces back to the days of Irix and it's vnodes which we don't have anymore. Essentially this move consolidates the inode locking functions and a bunch of XFS inode operations into the one file. Eventually the high level functions will be merged into the VFS interface functions in xfs_iops.c. This leaves only internal preallocation, EOF block manipulation and hole punching functions in vnodeops.c. Move these to xfs_bmap_util.c where we are already consolidating various in-kernel physical extent manipulation and querying functions. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Mark Tinguely <tinguely@sgi.com> Signed-off-by: Ben Myers <bpm@sgi.com>
-rw-r--r--fs/xfs/Makefile1
-rw-r--r--fs/xfs/xfs_acl.c1
-rw-r--r--fs/xfs/xfs_aops.c1
-rw-r--r--fs/xfs/xfs_attr.c1
-rw-r--r--fs/xfs/xfs_attr.h8
-rw-r--r--fs/xfs/xfs_bmap.c1
-rw-r--r--fs/xfs/xfs_bmap_util.c861
-rw-r--r--fs/xfs/xfs_bmap_util.h11
-rw-r--r--fs/xfs/xfs_dfrag.c1
-rw-r--r--fs/xfs/xfs_dir2.c1
-rw-r--r--fs/xfs/xfs_dir2.h6
-rw-r--r--fs/xfs/xfs_dir2_priv.h6
-rw-r--r--fs/xfs/xfs_export.c1
-rw-r--r--fs/xfs/xfs_file.c3
-rw-r--r--fs/xfs/xfs_icache.c2
-rw-r--r--fs/xfs/xfs_inode.c1004
-rw-r--r--fs/xfs/xfs_inode.h23
-rw-r--r--fs/xfs/xfs_inode_buf.h1
-rw-r--r--fs/xfs/xfs_inode_fork.c1
-rw-r--r--fs/xfs/xfs_ioctl.c36
-rw-r--r--fs/xfs/xfs_ioctl.h6
-rw-r--r--fs/xfs/xfs_ioctl32.c1
-rw-r--r--fs/xfs/xfs_iops.c2
-rw-r--r--fs/xfs/xfs_iops.h13
-rw-r--r--fs/xfs/xfs_rename.c1
-rw-r--r--fs/xfs/xfs_super.c1
-rw-r--r--fs/xfs/xfs_vnodeops.c1872
-rw-r--r--fs/xfs/xfs_vnodeops.h55
-rw-r--r--fs/xfs/xfs_xattr.c1
29 files changed, 1931 insertions, 1991 deletions
diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index dcd21b95cd98..8691dba546cd 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -55,7 +55,6 @@ xfs-y += xfs_aops.o \
xfs_symlink.o \
xfs_trans.o \
xfs_utils.o \
- xfs_vnodeops.o \
xfs_xattr.o \
kmem.o \
uuid.o
diff --git a/fs/xfs/xfs_acl.c b/fs/xfs/xfs_acl.c
index 150c670e15fa..0c4368aac449 100644
--- a/fs/xfs/xfs_acl.c
+++ b/fs/xfs/xfs_acl.c
@@ -22,7 +22,6 @@
#include "xfs_attr.h"
#include "xfs_bmap_btree.h"
#include "xfs_inode.h"
-#include "xfs_vnodeops.h"
#include "xfs_sb.h"
#include "xfs_mount.h"
#include "xfs_trace.h"
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 709347d6f468..a82c83707324 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -28,7 +28,6 @@
#include "xfs_alloc.h"
#include "xfs_error.h"
#include "xfs_iomap.h"
-#include "xfs_vnodeops.h"
#include "xfs_trace.h"
#include "xfs_bmap.h"
#include "xfs_bmap_util.h"
diff --git a/fs/xfs/xfs_attr.c b/fs/xfs/xfs_attr.c
index 91acc38f664b..046cf3d7f52f 100644
--- a/fs/xfs/xfs_attr.c
+++ b/fs/xfs/xfs_attr.c
@@ -40,7 +40,6 @@
#include "xfs_error.h"
#include "xfs_quota.h"
#include "xfs_trans_space.h"
-#include "xfs_vnodeops.h"
#include "xfs_trace.h"
/*
diff --git a/fs/xfs/xfs_attr.h b/fs/xfs/xfs_attr.h
index cb604b53e2f6..dd4824589470 100644
--- a/fs/xfs/xfs_attr.h
+++ b/fs/xfs/xfs_attr.h
@@ -142,5 +142,13 @@ typedef struct xfs_attr_list_context {
int xfs_attr_inactive(struct xfs_inode *dp);
int xfs_attr_list_int(struct xfs_attr_list_context *);
int xfs_inode_hasattr(struct xfs_inode *ip);
+int xfs_attr_get(struct xfs_inode *ip, const unsigned char *name,
+ unsigned char *value, int *valuelenp, int flags);
+int xfs_attr_set(struct xfs_inode *dp, const unsigned char *name,
+ unsigned char *value, int valuelen, int flags);
+int xfs_attr_remove(struct xfs_inode *dp, const unsigned char *name, int flags);
+int xfs_attr_list(struct xfs_inode *dp, char *buffer, int bufsize,
+ int flags, struct attrlist_cursor_kern *cursor);
+
#endif /* __XFS_ATTR_H__ */
diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c
index a9331a6b36fb..51e07e7a0092 100644
--- a/fs/xfs/xfs_bmap.c
+++ b/fs/xfs/xfs_bmap.c
@@ -48,7 +48,6 @@
#include "xfs_trans_space.h"
#include "xfs_buf_item.h"
#include "xfs_filestream.h"
-#include "xfs_vnodeops.h"
#include "xfs_trace.h"
#include "xfs_symlink.h"
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 8e48ddf1c11c..f557022bd0e7 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -1,5 +1,6 @@
/*
* Copyright (c) 2000-2006 Silicon Graphics, Inc.
+ * Copyright (c) 2012 Red Hat, Inc.
* All Rights Reserved.
*
* This program is free software; you can redistribute it and/or
@@ -41,6 +42,7 @@
#include "xfs_quota.h"
#include "xfs_trans_space.h"
#include "xfs_trace.h"
+#include "xfs_icache.h"
/* Kernel only BMAP related definitions and functions */
@@ -832,3 +834,862 @@ next_block:
return error;
}
+
+/*
+ * Test whether it is appropriate to check an inode for and free post EOF
+ * blocks. The 'force' parameter determines whether we should also consider
+ * regular files that are marked preallocated or append-only.
+ */
+bool
+xfs_can_free_eofblocks(struct xfs_inode *ip, bool force)
+{
+ /* prealloc/delalloc exists only on regular files */
+ if (!S_ISREG(ip->i_d.di_mode))
+ return false;
+
+ /*
+ * Zero sized files with no cached pages and delalloc blocks will not
+ * have speculative prealloc/delalloc blocks to remove.
+ */
+ if (VFS_I(ip)->i_size == 0 &&
+ VN_CACHED(VFS_I(ip)) == 0 &&
+ ip->i_delayed_blks == 0)
+ return false;
+
+ /* If we haven't read in the extent list, then don't do it now. */
+ if (!(ip->i_df.if_flags & XFS_IFEXTENTS))
+ return false;
+
+ /*
+ * Do not free real preallocated or append-only files unless the file
+ * has delalloc blocks and we are forced to remove them.
+ */
+ if (ip->i_d.di_flags & (XFS_DIFLAG_PREALLOC | XFS_DIFLAG_APPEND))
+ if (!force || ip->i_delayed_blks == 0)
+ return false;
+
+ return true;
+}
+
+/*
+ * 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.
+ */
+int
+xfs_free_eofblocks(
+ xfs_mount_t *mp,
+ xfs_inode_t *ip,
+ bool need_iolock)
+{
+ xfs_trans_t *tp;
+ int error;
+ xfs_fileoff_t end_fsb;
+ xfs_fileoff_t last_fsb;
+ xfs_filblks_t map_len;
+ int nimaps;
+ xfs_bmbt_irec_t imap;
+
+ /*
+ * Figure out if there are any blocks beyond the end
+ * of the file. If not, then there is nothing to do.
+ */
+ end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)XFS_ISIZE(ip));
+ last_fsb = XFS_B_TO_FSB(mp, mp->m_super->s_maxbytes);
+ if (last_fsb <= end_fsb)
+ return 0;
+ map_len = last_fsb - end_fsb;
+
+ nimaps = 1;
+ xfs_ilock(ip, XFS_ILOCK_SHARED);
+ error = xfs_bmapi_read(ip, end_fsb, map_len, &imap, &nimaps, 0);
+ xfs_iunlock(ip, XFS_ILOCK_SHARED);
+
+ if (!error && (nimaps != 0) &&
+ (imap.br_startblock != HOLESTARTBLOCK ||
+ ip->i_delayed_blks)) {
+ /*
+ * Attach the dquots to the inode up front.
+ */
+ error = xfs_qm_dqattach(ip, 0);
+ if (error)
+ return error;
+
+ /*
+ * There are blocks after the end of file.
+ * Free them up now by truncating the file to
+ * its current size.
+ */
+ tp = xfs_trans_alloc(mp, XFS_TRANS_INACTIVE);
+
+ if (need_iolock) {
+ if (!xfs_ilock_nowait(ip, XFS_IOLOCK_EXCL)) {
+ xfs_trans_cancel(tp, 0);
+ return EAGAIN;
+ }
+ }
+
+ error = xfs_trans_reserve(tp, 0,
+ XFS_ITRUNCATE_LOG_RES(mp),
+ 0, XFS_TRANS_PERM_LOG_RES,
+ XFS_ITRUNCATE_LOG_COUNT);
+ if (error) {
+ ASSERT(XFS_FORCED_SHUTDOWN(mp));
+ xfs_trans_cancel(tp, 0);
+ if (need_iolock)
+ xfs_iunlock(ip, XFS_IOLOCK_EXCL);
+ return error;
+ }
+
+ xfs_ilock(ip, XFS_ILOCK_EXCL);
+ xfs_trans_ijoin(tp, ip, 0);
+
+ /*
+ * Do not update the on-disk file size. If we update the
+ * on-disk file size and then the system crashes before the
+ * contents of the file are flushed to disk then the files
+ * may be full of holes (ie NULL files bug).
+ */
+ error = xfs_itruncate_extents(&tp, ip, XFS_DATA_FORK,
+ XFS_ISIZE(ip));
+ if (error) {
+ /*
+ * If we get an error at this point we simply don't
+ * bother truncating the file.
+ */
+ xfs_trans_cancel(tp,
+ (XFS_TRANS_RELEASE_LOG_RES |
+ XFS_TRANS_ABORT));
+ } else {
+ error = xfs_trans_commit(tp,
+ XFS_TRANS_RELEASE_LOG_RES);
+ if (!error)
+ xfs_inode_clear_eofblocks_tag(ip);
+ }
+
+ xfs_iunlock(ip, XFS_ILOCK_EXCL);
+ if (need_iolock)
+ xfs_iunlock(ip, XFS_IOLOCK_EXCL);
+ }
+ return error;
+}
+
+/*
+ * xfs_alloc_file_space()
+ * This routine allocates disk space for the given file.
+ *
+ * If alloc_type == 0, this request is for an ALLOCSP type
+ * request which will change the file size. In this case, no
+ * DMAPI event will be generated by the call. A TRUNCATE event
+ * will be generated later by xfs_setattr.
+ *
+ * If alloc_type != 0, this request is for a RESVSP type
+ * request, and a DMAPI DM_EVENT_WRITE will be generated if the
+ * lower block boundary byte address is less than the file's
+ * length.
+ *
+ * RETURNS:
+ * 0 on success
+ * errno on error
+ *
+ */
+STATIC int
+xfs_alloc_file_space(
+ xfs_inode_t *ip,
+ xfs_off_t offset,
+ xfs_off_t len,
+ int alloc_type,
+ int attr_flags)
+{
+ xfs_mount_t *mp = ip->i_mount;
+ xfs_off_t count;
+ xfs_filblks_t allocated_fsb;
+ xfs_filblks_t allocatesize_fsb;
+ xfs_extlen_t extsz, temp;
+ xfs_fileoff_t startoffset_fsb;
+ xfs_fsblock_t firstfsb;
+ int nimaps;
+ int quota_flag;
+ int rt;
+ xfs_trans_t *tp;
+ xfs_bmbt_irec_t imaps[1], *imapp;
+ xfs_bmap_free_t free_list;
+ uint qblocks, resblks, resrtextents;
+ int committed;
+ int error;
+
+ trace_xfs_alloc_file_space(ip);
+
+ if (XFS_FORCED_SHUTDOWN(mp))
+ return XFS_ERROR(EIO);
+
+ error = xfs_qm_dqattach(ip, 0);
+ if (error)
+ return error;
+
+ if (len <= 0)
+ return XFS_ERROR(EINVAL);
+
+ rt = XFS_IS_REALTIME_INODE(ip);
+ extsz = xfs_get_extsz_hint(ip);
+
+ count = len;
+ imapp = &imaps[0];
+ nimaps = 1;
+ startoffset_fsb = XFS_B_TO_FSBT(mp, offset);
+ allocatesize_fsb = XFS_B_TO_FSB(mp, count);
+
+ /*
+ * Allocate file space until done or until there is an error
+ */
+ while (allocatesize_fsb && !error) {
+ xfs_fileoff_t s, e;
+
+ /*
+ * Determine space reservations for data/realtime.
+ */
+ if (unlikely(extsz)) {
+ s = startoffset_fsb;
+ do_div(s, extsz);
+ s *= extsz;
+ e = startoffset_fsb + allocatesize_fsb;
+ if ((temp = do_mod(startoffset_fsb, extsz)))
+ e += temp;
+ if ((temp = do_mod(e, extsz)))
+ e += extsz - temp;
+ } else {
+ s = 0;
+ e = allocatesize_fsb;
+ }
+
+ /*
+ * The transaction reservation is limited to a 32-bit block
+ * count, hence we need to limit the number of blocks we are
+ * trying to reserve to avoid an overflow. We can't allocate
+ * more than @nimaps extents, and an extent is limited on disk
+ * to MAXEXTLEN (21 bits), so use that to enforce the limit.
+ */
+ resblks = min_t(xfs_fileoff_t, (e - s), (MAXEXTLEN * nimaps));
+ if (unlikely(rt)) {
+ resrtextents = qblocks = resblks;
+ resrtextents /= mp->m_sb.sb_rextsize;
+ resblks = XFS_DIOSTRAT_SPACE_RES(mp, 0);
+ quota_flag = XFS_QMOPT_RES_RTBLKS;
+ } else {
+ resrtextents = 0;
+ resblks = qblocks = XFS_DIOSTRAT_SPACE_RES(mp, resblks);
+ quota_flag = XFS_QMOPT_RES_REGBLKS;
+ }
+
+ /*
+ * Allocate and setup the transaction.
+ */
+ tp = xfs_trans_alloc(mp, XFS_TRANS_DIOSTRAT);
+ error = xfs_trans_reserve(tp, resblks,
+ XFS_WRITE_LOG_RES(mp), resrtextents,
+ XFS_TRANS_PERM_LOG_RES,
+ XFS_WRITE_LOG_COUNT);
+ /*
+ * Check for running out of space
+ */
+ if (error) {
+ /*
+ * Free the transaction structure.
+ */
+ ASSERT(error == ENOSPC || XFS_FORCED_SHUTDOWN(mp));
+ xfs_trans_cancel(tp, 0);
+ break;
+ }
+ xfs_ilock(ip, XFS_ILOCK_EXCL);
+ error = xfs_trans_reserve_quota_nblks(tp, ip, qblocks,
+ 0, quota_flag);
+ if (error)
+ goto error1;
+
+ xfs_trans_ijoin(tp, ip, 0);
+
+ xfs_bmap_init(&free_list, &firstfsb);
+ error = xfs_bmapi_write(tp, ip, startoffset_fsb,
+ allocatesize_fsb, alloc_type, &firstfsb,
+ 0, imapp, &nimaps, &free_list);
+ if (error) {
+ goto error0;
+ }
+
+ /*
+ * Complete the transaction
+ */
+ error = xfs_bmap_finish(&tp, &free_list, &committed);
+ if (error) {
+ goto error0;
+ }
+
+ error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
+ xfs_iunlock(ip, XFS_ILOCK_EXCL);
+ if (error) {
+ break;
+ }
+
+ allocated_fsb = imapp->br_blockcount;
+
+ if (nimaps == 0) {
+ error = XFS_ERROR(ENOSPC);
+ break;
+ }
+
+ startoffset_fsb += allocated_fsb;
+ allocatesize_fsb -= allocated_fsb;
+ }
+
+ return error;
+
+error0: /* Cancel bmap, unlock inode, unreserve quota blocks, cancel trans */
+ xfs_bmap_cancel(&free_list);
+ xfs_trans_unreserve_quota_nblks(tp, ip, (long)qblocks, 0, quota_flag);
+
+error1: /* Just cancel transaction */
+ xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT);
+ xfs_iunlock(ip, XFS_ILOCK_EXCL);
+ return error;
+}
+
+/*
+ * Zero file bytes between startoff and endoff inclusive.
+ * The iolock is held exclusive and no blocks are buffered.
+ *
+ * This function is used by xfs_free_file_space() to zero
+ * partial blocks when the range to free is not block aligned.
+ * When unreserving space with boundaries that are not block
+ * aligned we round up the start and round down the end
+ * boundaries and then use this function to zero the parts of
+ * the blocks that got dropped during the rounding.
+ */
+STATIC int
+xfs_zero_remaining_bytes(
+ xfs_inode_t *ip,
+ xfs_off_t startoff,
+ xfs_off_t endoff)
+{
+ xfs_bmbt_irec_t imap;
+ xfs_fileoff_t offset_fsb;
+ xfs_off_t lastoffset;
+ xfs_off_t offset;
+ xfs_buf_t *bp;
+ xfs_mount_t *mp = ip->i_mount;
+ int nimap;
+ int error = 0;
+
+ /*
+ * Avoid doing I/O beyond eof - it's not necessary
+ * since nothing can read beyond eof. The space will
+ * be zeroed when the file is extended anyway.
+ */
+ if (startoff >= XFS_ISIZE(ip))
+ return 0;
+
+ if (endoff > XFS_ISIZE(ip))
+ endoff = XFS_ISIZE(ip);
+
+ bp = xfs_buf_get_uncached(XFS_IS_REALTIME_INODE(ip) ?
+ mp->m_rtdev_targp : mp->m_ddev_targp,
+ BTOBB(mp->m_sb.sb_blocksize), 0);
+ if (!bp)
+ return XFS_ERROR(ENOMEM);
+
+ xfs_buf_unlock(bp);
+
+ for (offset = startoff; offset <= endoff; offset = lastoffset + 1) {
+ offset_fsb = XFS_B_TO_FSBT(mp, offset);
+ nimap = 1;
+ error = xfs_bmapi_read(ip, offset_fsb, 1, &imap, &nimap, 0);
+ if (error || nimap < 1)
+ break;
+ ASSERT(imap.br_blockcount >= 1);
+ ASSERT(imap.br_startoff == offset_fsb);
+ lastoffset = XFS_FSB_TO_B(mp, imap.br_startoff + 1) - 1;
+ if (lastoffset > endoff)
+ lastoffset = endoff;
+ if (imap.br_startblock == HOLESTARTBLOCK)
+ continue;
+ ASSERT(imap.br_startblock != DELAYSTARTBLOCK);
+ if (imap.br_state == XFS_EXT_UNWRITTEN)
+ continue;
+ XFS_BUF_UNDONE(bp);
+ XFS_BUF_UNWRITE(bp);
+ XFS_BUF_READ(bp);
+ XFS_BUF_SET_ADDR(bp, xfs_fsb_to_db(ip, imap.br_startblock));
+ xfsbdstrat(mp, bp);
+ error = xfs_buf_iowait(bp);
+ if (error) {
+ xfs_buf_ioerror_alert(bp,
+ "xfs_zero_remaining_bytes(read)");
+ break;
+ }
+ memset(bp->b_addr +
+ (offset - XFS_FSB_TO_B(mp, imap.br_startoff)),
+ 0, lastoffset - offset + 1);
+ XFS_BUF_UNDONE(bp);
+ XFS_BUF_UNREAD(bp);
+ XFS_BUF_WRITE(bp);
+ xfsbdstrat(mp, bp);
+ error = xfs_buf_iowait(bp);
+ if (error) {
+ xfs_buf_ioerror_alert(bp,
+ "xfs_zero_remaining_bytes(write)");
+ break;
+ }
+ }
+ xfs_buf_free(bp);
+ return error;
+}
+
+/*
+ * xfs_free_file_space()
+ * This routine frees disk space for the given file.
+ *
+ * This routine is only called by xfs_change_file_space
+ * for an UNRESVSP type call.
+ *
+ * RETURNS:
+ * 0 on success
+ * errno on error
+ *
+ */
+STATIC int
+xfs_free_file_space(
+ xfs_inode_t *ip,
+ xfs_off_t offset,
+ xfs_off_t len,
+ int attr_flags)
+{
+ int committed;
+ int done;
+ xfs_fileoff_t endoffset_fsb;
+ int error;
+ xfs_fsblock_t firstfsb;
+ xfs_bmap_free_t free_list;
+ xfs_bmbt_irec_t imap;
+ xfs_off_t ioffset;
+ xfs_extlen_t mod=0;
+ xfs_mount_t *mp;
+ int nimap;
+ uint resblks;
+ xfs_off_t rounding;
+ int rt;
+ xfs_fileoff_t startoffset_fsb;
+ xfs_trans_t *tp;
+ int need_iolock = 1;
+
+ mp = ip->i_mount;
+
+ trace_xfs_free_file_space(ip);
+
+ error = xfs_qm_dqattach(ip, 0);
+ if (error)
+ return error;
+
+ error = 0;
+ if (len <= 0) /* if nothing being freed */
+ return error;
+ rt = XFS_IS_REALTIME_INODE(ip);
+ startoffset_fsb = XFS_B_TO_FSB(mp, offset);
+ endoffset_fsb = XFS_B_TO_FSBT(mp, offset + len);
+
+ if (attr_flags & XFS_ATTR_NOLOCK)
+ need_iolock = 0;
+ if (need_iolock) {
+ xfs_ilock(ip, XFS_IOLOCK_EXCL);
+ /* wait for the completion of any pending DIOs */
+ inode_dio_wait(VFS_I(ip));
+ }
+
+ rounding = max_t(xfs_off_t, 1 << mp->m_sb.sb_blocklog, PAGE_CACHE_SIZE);
+ ioffset = offset & ~(rounding - 1);
+ error = -filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
+ ioffset, -1);
+ if (error)
+ goto out_unlock_iolock;
+ truncate_pagecache_range(VFS_I(ip), ioffset, -1);
+
+ /*
+ * Need to zero the stuff we're not freeing, on disk.
+ * If it's a realtime file & can't use unwritten extents then we
+ * actually need to zero the extent edges. Otherwise xfs_bunmapi
+ * will take care of it for us.
+ */
+ if (rt && !xfs_sb_version_hasextflgbit(&mp->m_sb)) {
+ nimap = 1;
+ error = xfs_bmapi_read(ip, startoffset_fsb, 1,
+ &imap, &nimap, 0);
+ if (error)
+ goto out_unlock_iolock;
+ ASSERT(nimap == 0 || nimap == 1);
+ 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);
+ if (mod)
+ startoffset_fsb += mp->m_sb.sb_rextsize - mod;
+ }
+ nimap = 1;
+ error = xfs_bmapi_read(ip, endoffset_fsb - 1, 1,
+ &imap, &nimap, 0);
+ if (error)
+ goto out_unlock_iolock;
+ ASSERT(nimap == 0 || nimap == 1);
+ if (nimap && imap.br_startblock != HOLESTARTBLOCK) {
+ ASSERT(imap.br_startblock != DELAYSTARTBLOCK);
+ mod++;
+ if (mod && (mod != mp->m_sb.sb_rextsize))
+ endoffset_fsb -= mod;
+ }
+ }
+ if ((done = (endoffset_fsb <= startoffset_fsb)))
+ /*
+ * One contiguous piece to clear
+ */
+ error = xfs_zero_remaining_bytes(ip, offset, offset + len - 1);
+ else {
+ /*
+ * Some full blocks, possibly two pieces to clear
+ */
+ if (offset < XFS_FSB_TO_B(mp, startoffset_fsb))
+ error = xfs_zero_remaining_bytes(ip, offset,
+ XFS_FSB_TO_B(mp, startoffset_fsb) - 1);
+ if (!error &&
+ XFS_FSB_TO_B(mp, endoffset_fsb) < offset + len)
+ error = xfs_zero_remaining_bytes(ip,
+ XFS_FSB_TO_B(mp, endoffset_fsb),
+ offset + len - 1);
+ }
+
+ /*
+ * free file space until done or until there is an error
+ */
+ resblks = XFS_DIOSTRAT_SPACE_RES(mp, 0);
+ while (!error && !done) {
+
+ /*
+ * allocate and setup the transaction. Allow this
+ * transaction to dip into the reserve blocks to ensure
+ * the freeing of the space succeeds at ENOSPC.
+ */
+ tp = xfs_trans_alloc(mp, XFS_TRANS_DIOSTRAT);
+ tp->t_flags |= XFS_TRANS_RESERVE;
+ error = xfs_trans_reserve(tp,
+ resblks,
+ XFS_WRITE_LOG_RES(mp),
+ 0,
+ XFS_TRANS_PERM_LOG_RES,
+ XFS_WRITE_LOG_COUNT);
+
+ /*
+ * check for running out of space
+ */
+ if (error) {
+ /*
+ * Free the transaction structure.
+ */
+ ASSERT(error == ENOSPC || XFS_FORCED_SHUTDOWN(mp));
+ xfs_trans_cancel(tp, 0);
+ break;
+ }
+ xfs_ilock(ip, XFS_ILOCK_EXCL);
+ error = xfs_trans_reserve_quota(tp, mp,
+ ip->i_udquot, ip->i_gdquot, ip->i_pdquot,
+ resblks, 0, XFS_QMOPT_RES_REGBLKS);
+ if (error)
+ goto error1;
+
+ xfs_trans_ijoin(tp, ip, 0);
+
+ /*
+ * issue the bunmapi() call to free the blocks
+ */
+ xfs_bmap_init(&free_list, &firstfsb);
+ error = xfs_bunmapi(tp, ip, startoffset_fsb,
+ endoffset_fsb - startoffset_fsb,
+ 0, 2, &firstfsb, &free_list, &done);
+ if (error) {
+ goto error0;
+ }
+
+ /*
+ * complete the transaction
+ */
+ error = xfs_bmap_finish(&tp, &free_list, &committed);
+ if (error) {
+ goto error0;
+ }
+
+ error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
+ xfs_iunlock(ip, XFS_ILOCK_EXCL);
+ }
+
+ out_unlock_iolock:
+ if (need_iolock)
+ xfs_iunlock(ip, XFS_IOLOCK_EXCL);
+ return error;
+
+ error0:
+ xfs_bmap_cancel(&free_list);
+ error1:
+ xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT);
+ xfs_iunlock(ip, need_iolock ? (XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL) :
+ XFS_ILOCK_EXCL);
+ return error;
+}
+
+
+STATIC int
+xfs_zero_file_space(
+ struct xfs_inode *ip,
+ xfs_off_t offset,
+ xfs_off_t len,
+ int attr_flags)
+{
+ struct xfs_mount *mp = ip->i_mount;
+ uint granularity;
+ xfs_off_t start_boundary;
+ xfs_off_t end_boundary;
+ int error;
+
+ granularity = max_t(uint, 1 << mp->m_sb.sb_blocklog, PAGE_CACHE_SIZE);
+
+ /*
+ * Round the range of extents we are going to convert inwards. If the
+ * offset is aligned, then it doesn't get changed so we zero from the
+ * start of the block offset points to.
+ */
+ start_boundary = round_up(offset, granularity);
+ end_boundary = round_down(offset + len, granularity);
+
+ ASSERT(start_boundary >= offset);
+ ASSERT(end_boundary <= offset + len);
+
+ if (!(attr_flags & XFS_ATTR_NOLOCK))
+ xfs_ilock(ip, XFS_IOLOCK_EXCL);
+
+ if (start_boundary < end_boundary - 1) {
+ /* punch out the page cache over the conversion range */
+ truncate_pagecache_range(VFS_I(ip), start_boundary,
+ end_boundary - 1);
+ /* convert the blocks */
+ error = xfs_alloc_file_space(ip, start_boundary,
+ end_boundary - start_boundary - 1,
+ XFS_BMAPI_PREALLOC | XFS_BMAPI_CONVERT,
+ attr_flags);
+ if (error)
+ goto out_unlock;
+
+ /* We've handled the interior of the range, now for the edges */
+ if (start_boundary != offset)
+ error = xfs_iozero(ip, offset, start_boundary - offset);
+ if (error)
+ goto out_unlock;
+
+ if (end_boundary != offset + len)
+ error = xfs_iozero(ip, end_boundary,
+ offset + len - end_boundary);
+
+ } else {
+ /*
+ * It's either a sub-granularity range or the range spanned lies
+ * partially across two adjacent blocks.
+ */
+ error = xfs_iozero(ip, offset, len);
+ }
+
+out_unlock:
+ if (!(attr_flags & XFS_ATTR_NOLOCK))
+ xfs_iunlock(ip, XFS_IOLOCK_EXCL);
+ return error;
+
+}
+
+/*
+ * xfs_change_file_space()
+ * This routine allocates or frees disk space for the given file.
+ * The user specified parameters are checked for alignment and size
+ * limitations.
+ *
+ * RETURNS:
+ * 0 on success
+ * errno on error
+ *
+ */
+int
+xfs_change_file_space(
+ xfs_inode_t *ip,
+ int cmd,
+ xfs_flock64_t *bf,
+ xfs_off_t offset,
+ int attr_flags)
+{
+ xfs_mount_t *mp = ip->i_mount;
+ int clrprealloc;
+ int error;
+ xfs_fsize_t fsize;
+ int setprealloc;
+ xfs_off_t startoffset;
+ xfs_trans_t *tp;
+ struct iattr iattr;
+
+ if (!S_ISREG(ip->i_d.di_mode))
+ return XFS_ERROR(EINVAL);
+
+ switch (bf->l_whence) {
+ case 0: /*SEEK_SET*/
+ break;
+ case 1: /*SEEK_CUR*/
+ bf->l_start += offset;
+ break;
+ case 2: /*SEEK_END*/
+ bf->l_start += XFS_ISIZE(ip);
+ break;
+ default:
+ return XFS_ERROR(EINVAL);
+ }
+
+ /*
+ * length of <= 0 for resv/unresv/zero is invalid. length for
+ * alloc/free is ignored completely and we have no idea what userspace
+ * might have set it to, so set it to zero to allow range
+ * checks to pass.
+ */
+ switch (cmd) {
+ case XFS_IOC_ZERO_RANGE:
+ case XFS_IOC_RESVSP:
+ case XFS_IOC_RESVSP64:
+ case XFS_IOC_UNRESVSP:
+ case XFS_IOC_UNRESVSP64:
+ if (bf->l_len <= 0)
+ return XFS_ERROR(EINVAL);
+ break;
+ default:
+ bf->l_len = 0;
+ break;
+ }
+
+ if (bf->l_start < 0 ||
+ bf->l_start > mp->m_super->s_maxbytes ||
+ bf->l_start + bf->l_len < 0 ||
+ bf->l_start + bf->l_len >= mp->m_super->s_maxbytes)
+ return XFS_ERROR(EINVAL);
+
+ bf->l_whence = 0;
+
+ startoffset = bf->l_start;
+ fsize = XFS_ISIZE(ip);
+
+ setprealloc = clrprealloc = 0;
+ switch (cmd) {
+ case XFS_IOC_ZERO_RANGE:
+ error = xfs_zero_file_space(ip, startoffset, bf->l_len,
+ attr_flags);
+ if (error)
+ return error;
+ setprealloc = 1;
+ break;
+
+ case XFS_IOC_RESVSP:
+ case XFS_IOC_RESVSP64:
+ error = xfs_alloc_file_space(ip, startoffset, bf->l_len,
+ XFS_BMAPI_PREALLOC, attr_flags);
+ if (error)
+ return error;
+ setprealloc = 1;
+ break;
+
+ case XFS_IOC_UNRESVSP:
+ case XFS_IOC_UNRESVSP64:
+ if ((error = xfs_free_file_space(ip, startoffset, bf->l_len,
+ attr_flags)))
+ return error;
+ break;
+
+ case XFS_IOC_ALLOCSP:
+ case XFS_IOC_ALLOCSP64:
+ case XFS_IOC_FREESP:
+ case XFS_IOC_FREESP64:
+ /*
+ * These operations actually do IO when extending the file, but
+ * the allocation is done seperately to the zeroing that is
+ * done. This set of operations need to be serialised against
+ * other IO operations, such as truncate and buffered IO. We
+ * need to take the IOLOCK here to serialise the allocation and
+ * zeroing IO to prevent other IOLOCK holders (e.g. getbmap,
+ * truncate, direct IO) from racing against the transient
+ * allocated but not written state we can have here.
+ */
+ xfs_ilock(ip, XFS_IOLOCK_EXCL);
+ if (startoffset > fsize) {
+ error = xfs_alloc_file_space(ip, fsize,
+ startoffset - fsize, 0,
+ attr_flags | XFS_ATTR_NOLOCK);
+ if (error) {
+ xfs_iunlock(ip, XFS_IOLOCK_EXCL);
+ break;
+ }
+ }
+
+ iattr.ia_valid = ATTR_SIZE;
+ iattr.ia_size = startoffset;
+
+ error = xfs_setattr_size(ip, &iattr,
+ attr_flags | XFS_ATTR_NOLOCK);
+ xfs_iunlock(ip, XFS_IOLOCK_EXCL);
+
+ if (error)
+ return error;
+
+ clrprealloc = 1;
+ break;
+
+ default:
+ ASSERT(0);
+ return XFS_ERROR(EINVAL);
+ }
+
+ /*
+ * update the inode timestamp, mode, and prealloc flag bits
+ */
+ tp = xfs_trans_alloc(mp, XFS_TRANS_WRITEID);
+
+ if ((error = xfs_trans_reserve(tp, 0, XFS_WRITEID_LOG_RES(mp),
+ 0, 0, 0))) {
+ /* ASSERT(0); */
+ xfs_trans_cancel(tp, 0);
+ return error;
+ }
+
+ xfs_ilock(ip, XFS_ILOCK_EXCL);
+ xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
+
+ if ((attr_flags & XFS_ATTR_DMI) == 0) {
+ ip->i_d.di_mode &= ~S_ISUID;
+
+ /*
+ * Note that we don't have to worry about mandatory
+ * file locking being disabled here because we only
+ * clear the S_ISGID bit if the Group execute bit is
+ * on, but if it was on then mandatory locking wouldn't
+ * have been enabled.
+ */
+ if (ip->i_d.di_mode & S_IXGRP)
+ ip->i_d.di_mode &= ~S_ISGID;
+
+ xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
+ }
+ if (setprealloc)
+ ip->i_d.di_flags |= XFS_DIFLAG_PREALLOC;
+ else if (clrprealloc)
+ ip->i_d.di_flags &= ~XFS_DIFLAG_PREALLOC;
+
+ xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+ if (attr_flags & XFS_ATTR_SYNC)
+ xfs_trans_set_sync(tp);
+ return xfs_trans_commit(tp, 0);
+}
diff --git a/fs/xfs/xfs_bmap_util.h b/fs/xfs/xfs_bmap_util.h
index 004fe4b28d49..a6d207769dee 100644
--- a/fs/xfs/xfs_bmap_util.h
+++ b/fs/xfs/xfs_bmap_util.h
@@ -21,6 +21,7 @@
/* Kernel only BMAP related definitions and functions */
struct xfs_bmbt_irec;
+struct xfs_bmap_free_item;
struct xfs_ifork;
struct xfs_inode;
struct xfs_mount;
@@ -91,6 +92,16 @@ int xfs_bmap_last_extent(struct xfs_trans *tp, struct xfs_inode *ip,
int whichfork, struct xfs_bmbt_irec *rec,
int *is_empty);
+/* preallocation and hole punch interface */
+int xfs_change_file_space(struct xfs_inode *ip, int cmd,
+ xfs_flock64_t *bf, xfs_off_t offset,
+ int attr_flags);
+
+/* EOF block manipulation functions */
+bool xfs_can_free_eofblocks(struct xfs_inode *ip, bool force);
+int xfs_free_eofblocks(struct xfs_mount *mp, struct xfs_inode *ip,
+ bool need_iolock);
+
xfs_daddr_t xfs_fsb_to_db(struct xfs_inode *ip, xfs_fsblock_t fsb);
#endif /* __XFS_BMAP_UTIL_H__ */
diff --git a/fs/xfs/xfs_dfrag.c b/fs/xfs/xfs_dfrag.c
index 815dace5e57a..b83d45f8cb12 100644
--- a/fs/xfs/xfs_dfrag.c
+++ b/fs/xfs/xfs_dfrag.c
@@ -35,7 +35,6 @@
#include "xfs_itable.h"
#include "xfs_dfrag.h"
#include "xfs_error.h"
-#include "xfs_vnodeops.h"
#include "xfs_trace.h"
diff --git a/fs/xfs/xfs_dir2.c b/fs/xfs/xfs_dir2.c
index c3263a56b861..841933c9e80f 100644
--- a/fs/xfs/xfs_dir2.c
+++ b/fs/xfs/xfs_dir2.c
@@ -35,7 +35,6 @@
#include "xfs_dir2.h"
#include "xfs_dir2_priv.h"
#include "xfs_error.h"
-#include "xfs_vnodeops.h"
#include "xfs_trace.h"
struct xfs_name xfs_name_dotdot = { (unsigned char *)"..", 2};
diff --git a/fs/xfs/xfs_dir2.h b/fs/xfs/xfs_dir2.h
index 7ef6b0fb951a..7fe2b8f0a9e3 100644
--- a/fs/xfs/xfs_dir2.h
+++ b/fs/xfs/xfs_dir2.h
@@ -63,12 +63,6 @@ extern int xfs_dir_canenter(struct xfs_trans *tp, struct xfs_inode *dp,
extern int xfs_dir2_sf_to_block(struct xfs_da_args *args);
/*
- * Direct call on directory open, before entering the readdir code.
- */
-extern int xfs_dir3_data_readahead(struct xfs_trans *tp, struct xfs_inode *dp,
- xfs_dablk_t bno, xfs_daddr_t mapped_bno);
-
-/*
* Interface routines used by userspace utilities
*/
extern xfs_ino_t xfs_dir2_sf_get_parent_ino(struct xfs_dir2_sf_hdr *sfp);
diff --git a/fs/xfs/xfs_dir2_priv.h b/fs/xfs/xfs_dir2_priv.h
index 807eb658107c..6d2a99c224b7 100644
--- a/fs/xfs/xfs_dir2_priv.h
+++ b/fs/xfs/xfs_dir2_priv.h
@@ -45,6 +45,8 @@ extern int xfs_dir2_leaf_to_block(struct xfs_da_args *args,
extern int __xfs_dir3_data_check(struct xfs_inode *dp, struct xfs_buf *bp);
extern int xfs_dir3_data_read(struct xfs_trans *tp, struct xfs_inode *dp,
xfs_dablk_t bno, xfs_daddr_t mapped_bno, struct xfs_buf **bpp);
+extern int xfs_dir3_data_readahead(struct xfs_trans *tp, struct xfs_inode *dp,
+ xfs_dablk_t bno, xfs_daddr_t mapped_bno);
extern struct xfs_dir2_data_free *
xfs_dir2_data_freeinsert(struct xfs_dir2_data_hdr *hdr,
@@ -124,4 +126,8 @@ extern int xfs_dir2_sf_lookup(struct xfs_da_args *args);
extern int xfs_dir2_sf_removename(struct xfs_da_args *args);
extern int xfs_dir2_sf_replace(struct xfs_da_args *args);
+/* xfs_dir2_readdir.c */
+extern int xfs_readdir(struct xfs_inode *dp, struct dir_context *ctx,
+ size_t bufsize);
+
#endif /* __XFS_DIR2_PRIV_H__ */
diff --git a/fs/xfs/xfs_export.c b/fs/xfs/xfs_export.c
index 29c880fbdb1b..066df425c14f 100644
--- a/fs/xfs/xfs_export.c
+++ b/fs/xfs/xfs_export.c
@@ -26,7 +26,6 @@
#include "xfs_dir2_format.h"
#include "xfs_dir2.h"
#include "xfs_export.h"
-#include "xfs_vnodeops.h"
#include "xfs_bmap_btree.h"
#include "xfs_inode.h"
#include "xfs_inode_item.h"
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 1ba3c7998b9a..4c749ab543d0 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -28,11 +28,12 @@
#include "xfs_inode.h"
#include "xfs_inode_item.h"
#include "xfs_bmap.h"
+#include "xfs_bmap_util.h"
#include "xfs_error.h"
-#include "xfs_vnodeops.h"
#include "xfs_da_btree.h"
#include "xfs_dir2_format.h"
#include "xfs_dir2.h"
+#include "xfs_dir2_priv.h"
#include "xfs_ioctl.h"
#include "xfs_trace.h"
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index d9a41671a4ad..2abc9450ce20 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -32,12 +32,12 @@
#include "xfs_dinode.h"
#include "xfs_error.h"
#include "xfs_filestream.h"
-#include "xfs_vnodeops.h"
#include "xfs_inode_item.h"
#include "xfs_quota.h"
#include "xfs_trace.h"
#include "xfs_fsops.h"
#include "xfs_icache.h"
+#include "xfs_bmap_util.h"
#include <linux/kthread.h>
#include <linux/freezer.h>
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 1029f5670207..73a7a1d84243 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -23,14 +23,19 @@
#include "xfs_log.h"
#include "xfs_inum.h"
#include "xfs_trans.h"
+#include "xfs_trans_space.h"
#include "xfs_trans_priv.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
#include "xfs_mount.h"
+#include "xfs_da_btree.h"
+#include "xfs_dir2_format.h"
+#include "xfs_dir2.h"
#include "xfs_bmap_btree.h"
#include "xfs_alloc_btree.h"
#include "xfs_ialloc_btree.h"
#include "xfs_attr_sf.h"
+#include "xfs_attr.h"
#include "xfs_dinode.h"
#include "xfs_inode.h"
#include "xfs_buf_item.h"
@@ -44,10 +49,10 @@
#include "xfs_utils.h"
#include "xfs_quota.h"
#include "xfs_filestream.h"
-#include "xfs_vnodeops.h"
#include "xfs_cksum.h"
#include "xfs_trace.h"
#include "xfs_icache.h"
+#include "xfs_symlink.h"
kmem_zone_t *xfs_inode_zone;
@@ -307,6 +312,188 @@ xfs_isilocked(
}
#endif
+#ifdef DEBUG
+int xfs_locked_n;
+int xfs_small_retries;
+int xfs_middle_retries;
+int xfs_lots_retries;
+int xfs_lock_delays;
+#endif
+
+/*
+ * Bump the subclass so xfs_lock_inodes() acquires each lock with
+ * a different value
+ */
+static inline int
+xfs_lock_inumorder(int lock_mode, int subclass)
+{
+ if (lock_mode & (XFS_IOLOCK_SHARED|XFS_IOLOCK_EXCL))
+ lock_mode |= (subclass + XFS_LOCK_INUMORDER) << XFS_IOLOCK_SHIFT;
+ if (lock_mode & (XFS_ILOCK_SHARED|XFS_ILOCK_EXCL))
+ lock_mode |= (subclass + XFS_LOCK_INUMORDER) << XFS_ILOCK_SHIFT;
+
+ return lock_mode;
+}
+
+/*
+ * The following routine will lock n inodes in exclusive mode.
+ * We assume the caller calls us with the inodes in i_ino order.
+ *
+ * We need to detect deadlock where an inode that we lock
+ * is in the AIL and we start waiting for another inode that is locked
+ * by a thread in a long running transaction (such as truncate). This can
+ * result in deadlock since the long running trans might need to wait
+ * for the inode we just locked in order to push the tail and free space
+ * in the log.
+ */
+void
+xfs_lock_inodes(
+ xfs_inode_t **ips,
+ int inodes,
+ uint lock_mode)
+{
+ int attempts = 0, i, j, try_lock;
+ xfs_log_item_t *lp;
+
+ ASSERT(ips && (inodes >= 2)); /* we need at least two */
+
+ try_lock = 0;
+ i = 0;
+
+again:
+ for (; i < inodes; i++) {
+ ASSERT(ips[i]);
+
+ if (i && (ips[i] == ips[i-1])) /* Already locked */
+ continue;
+
+ /*
+ * If try_lock is not set yet, make sure all locked inodes
+ * are not in the AIL.
+ * If any are, set try_lock to be used later.
+ */
+
+ if (!try_lock) {
+ for (j = (i - 1); j >= 0 && !try_lock; j--) {
+ lp = (xfs_log_item_t *)ips[j]->i_itemp;
+ if (lp && (lp->li_flags & XFS_LI_IN_AIL)) {
+ try_lock++;
+ }
+ }
+ }
+
+ /*
+ * If any of the previous locks we have locked is in the AIL,
+ * we must TRY to get the second and subsequent locks. If
+ * we can't get any, we must release all we have
+ * and try again.
+ */
+
+ if (try_lock) {
+ /* try_lock must be 0 if i is 0. */
+ /*
+ * try_lock means we have an inode locked
+ * that is in the AIL.
+ */
+ ASSERT(i != 0);
+ if (!xfs_ilock_nowait(ips[i], xfs_lock_inumorder(lock_mode, i))) {
+ attempts++;
+
+ /*
+ * Unlock all previous guys and try again.
+ * xfs_iunlock will try to push the tail
+ * if the inode is in the AIL.
+ */
+
+ for(j = i - 1; j >= 0; j--) {
+
+ /*
+ * Check to see if we've already
+ * unlocked this one.
+ * Not the first one going back,
+ * and the inode ptr is the same.
+ */
+ if ((j != (i - 1)) && ips[j] ==
+ ips[j+1])
+ continue;
+
+ xfs_iunlock(ips[j], lock_mode);
+ }
+
+ if ((attempts % 5) == 0) {
+ delay(1); /* Don't just spin the CPU */
+#ifdef DEBUG
+ xfs_lock_delays++;
+#endif
+ }
+ i = 0;
+ try_lock = 0;
+ goto again;
+ }
+ } else {
+ xfs_ilock(ips[i], xfs_lock_inumorder(lock_mode, i));
+ }
+ }
+
+#ifdef DEBUG
+ if (attempts) {
+ if (attempts < 5) xfs_small_retries++;
+ else if (attempts < 100) xfs_middle_retries++;
+ else xfs_lots_retries++;
+ } else {
+ xfs_locked_n++;
+ }
+#endif
+}
+
+/*
+ * xfs_lock_two_inodes() can only be used to lock one type of lock
+ * at a time - the iolock or the ilock, but not both at once. If
+ * we lock both at once, lockdep will report false positives saying
+ * we have violated locking orders.
+ */
+void
+xfs_lock_two_inodes(
+ xfs_inode_t *ip0,
+ xfs_inode_t *ip1,
+ uint lock_mode)
+{
+ xfs_inode_t *temp;
+ int attempts = 0;
+ xfs_log_item_t *lp;
+
+ if (lock_mode & (XFS_IOLOCK_SHARED|XFS_IOLOCK_EXCL))
+ ASSERT((lock_mode & (XFS_ILOCK_SHARED|XFS_ILOCK_EXCL)) == 0);
+ ASSERT(ip0->i_ino != ip1->i_ino);
+
+ if (ip0->i_ino > ip1->i_ino) {
+ temp = ip0;
+ ip0 = ip1;
+ ip1 = temp;
+ }
+
+ again:
+ xfs_ilock(ip0, xfs_lock_inumorder(lock_mode, 0));
+
+ /*
+ * If the first lock we have locked is in the AIL, we must TRY to get
+ * the second lock. If we can't get it, we must release the first one
+ * and try again.
+ */
+ lp = (xfs_log_item_t *)ip0->i_itemp;
+ if (lp && (lp->li_flags & XFS_LI_IN_AIL)) {
+ if (!xfs_ilock_nowait(ip1, xfs_lock_inumorder(lock_mode, 1))) {
+ xfs_iunlock(ip0, lock_mode);
+ if ((++attempts % 5) == 0)
+ delay(1); /* Don't just spin the CPU */
+ goto again;
+ }
+ } else {
+ xfs_ilock(ip1, xfs_lock_inumorder(lock_mode, 1));
+ }
+}
+
+
void
__xfs_iflock(
struct xfs_inode *ip)
@@ -382,6 +569,49 @@ xfs_dic2xflags(
}
/*
+ * Lookups up an inode from "name". If ci_name is not NULL, then a CI match
+ * is allowed, otherwise it has to be an exact match. If a CI match is found,
+ * ci_name->name will point to a the actual name (caller must free) or
+ * will be set to NULL if an exact match is found.
+ */
+int
+xfs_lookup(
+ xfs_inode_t *dp,
+ struct xfs_name *name,
+ xfs_inode_t **ipp,
+ struct xfs_name *ci_name)
+{
+ xfs_ino_t inum;
+ int error;
+ uint lock_mode;
+
+ trace_xfs_lookup(dp, name);
+
+ if (XFS_FORCED_SHUTDOWN(dp->i_mount))
+ return XFS_ERROR(EIO);
+
+ lock_mode = xfs_ilock_map_shared(dp);
+ error = xfs_dir_lookup(NULL, dp, name, &inum, ci_name);
+ xfs_iunlock_map_shared(dp, lock_mode);
+
+ if (error)
+ goto out;
+
+ error = xfs_iget(dp->i_mount, NULL, inum, 0, 0, ipp);
+ if (error)
+ goto out_free_name;
+
+ return 0;
+
+out_free_name:
+ if (ci_name)
+ kmem_free(ci_name->name);
+out:
+ *ipp = NULL;
+ return error;
+}
+
+/*
* Allocate an inode on disk and return a copy of its in-core version.
* The in-core inode is locked exclusively. Set mode, nlink, and rdev
* appropriately within the inode. The uid and gid for the inode are
@@ -632,6 +862,308 @@ xfs_ialloc(
return 0;
}
+int
+xfs_create(
+ xfs_inode_t *dp,
+ struct xfs_name *name,
+ umode_t mode,
+ xfs_dev_t rdev,
+ xfs_inode_t **ipp)
+{
+ int is_dir = S_ISDIR(mode);
+ struct xfs_mount *mp = dp->i_mount;
+ struct xfs_inode *ip = NULL;
+ struct xfs_trans *tp = NULL;
+ int error;
+ xfs_bmap_free_t free_list;
+ xfs_fsblock_t first_block;
+ bool unlock_dp_on_error = false;
+ uint cancel_flags;
+ int committed;
+ prid_t prid;
+ struct xfs_dquot *udqp = NULL;
+ struct xfs_dquot *gdqp = NULL;
+ struct xfs_dquot *pdqp = NULL;
+ uint resblks;
+ uint log_res;
+ uint log_count;
+
+ trace_xfs_create(dp, name);
+
+ if (XFS_FORCED_SHUTDOWN(mp))
+ return XFS_ERROR(EIO);
+
+ if (dp->i_d.di_flags & XFS_DIFLAG_PROJINHERIT)
+ prid = xfs_get_projid(dp);
+ else
+ prid = XFS_PROJID_DEFAULT;
+
+ /*
+ * Make sure that we have allocated dquot(s) on disk.
+ */
+ error = xfs_qm_vop_dqalloc(dp, current_fsuid(), current_fsgid(), prid,
+ XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT,
+ &udqp, &gdqp, &pdqp);
+ if (error)
+ return error;
+
+ if (is_dir) {
+ rdev = 0;
+ resblks = XFS_MKDIR_SPACE_RES(mp, name->len);
+ log_res = XFS_MKDIR_LOG_RES(mp);
+ log_count = XFS_MKDIR_LOG_COUNT;
+ tp = xfs_trans_alloc(mp, XFS_TRANS_MKDIR);
+ } else {
+ resblks = XFS_CREATE_SPACE_RES(mp, name->len);
+ log_res = XFS_CREATE_LOG_RES(mp);
+ log_count = XFS_CREATE_LOG_COUNT;
+ tp = xfs_trans_alloc(mp, XFS_TRANS_CREATE);
+ }
+
+ cancel_flags = XFS_TRANS_RELEASE_LOG_RES;
+
+ /*
+ * Initially assume that the file does not exist and
+ * reserve the resources for that case. If that is not
+ * the case we'll drop the one we have and get a more
+ * appropriate transaction later.
+ */
+ error = xfs_trans_reserve(tp, resblks, log_res, 0,
+ XFS_TRANS_PERM_LOG_RES, log_count);
+ if (error == ENOSPC) {
+ /* flush outstanding delalloc blocks and retry */
+ xfs_flush_inodes(mp);
+ error = xfs_trans_reserve(tp, resblks, log_res, 0,
+ XFS_TRANS_PERM_LOG_RES, log_count);
+ }
+ if (error == ENOSPC) {
+ /* No space at all so try a "no-allocation" reservation */
+ resblks = 0;
+ error = xfs_trans_reserve(tp, 0, log_res, 0,
+ XFS_TRANS_PERM_LOG_RES, log_count);
+ }
+ if (error) {
+ cancel_flags = 0;
+ goto out_trans_cancel;
+ }
+
+ xfs_ilock(dp, XFS_ILOCK_EXCL | XFS_ILOCK_PARENT);
+ unlock_dp_on_error = true;
+
+ xfs_bmap_init(&free_list, &first_block);
+
+ /*
+ * Reserve disk quota and the inode.
+ */
+ error = xfs_trans_reserve_quota(tp, mp, udqp, gdqp,
+ pdqp, resblks, 1, 0);
+ if (error)
+ goto out_trans_cancel;
+
+ error = xfs_dir_canenter(tp, dp, name, resblks);
+ if (error)
+ goto out_trans_cancel;
+
+ /*
+ * A newly created regular or special file just has one directory
+ * entry pointing to them, but a directory also the "." entry
+ * pointing to itself.
+ */
+ error = xfs_dir_ialloc(&tp, dp, mode, is_dir ? 2 : 1, rdev,
+ prid, resblks > 0, &ip, &committed);
+ if (error) {
+ if (error == ENOSPC)
+ goto out_trans_cancel;
+ goto out_trans_abort;
+ }
+
+ /*
+ * Now we join the directory inode to the transaction. We do not do it
+ * earlier because xfs_dir_ialloc might commit the previous transaction
+ * (and release all the locks). An error from here on will result in
+ * the transaction cancel unlocking dp so don't do it explicitly in the
+ * error path.
+ */
+ xfs_trans_ijoin(tp, dp, XFS_ILOCK_EXCL);
+ unlock_dp_on_error = false;
+
+ error = xfs_dir_createname(tp, dp, name, ip->i_ino,
+ &first_block, &free_list, resblks ?
+ resblks - XFS_IALLOC_SPACE_RES(mp) : 0);
+ if (error) {
+ ASSERT(error != ENOSPC);
+ goto out_trans_abort;
+ }
+ xfs_trans_ichgtime(tp, dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
+ xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE);
+
+ if (is_dir) {
+ error = xfs_dir_init(tp, ip, dp);
+ if (error)
+ goto out_bmap_cancel;
+
+ error = xfs_bumplink(tp, dp);
+ if (error)
+ goto out_bmap_cancel;
+ }
+
+ /*
+ * If this is a synchronous mount, make sure that the
+ * create transaction goes to disk before returning to
+ * the user.
+ */
+ if (mp->m_flags & (XFS_MOUNT_WSYNC|XFS_MOUNT_DIRSYNC))
+ xfs_trans_set_sync(tp);
+
+ /*
+ * Attach the dquot(s) to the inodes and modify them incore.
+ * These ids of the inode couldn't have changed since the new
+ * inode has been locked ever since it was created.
+ */
+ xfs_qm_vop_create_dqattach(tp, ip, udqp, gdqp, pdqp);
+
+ error = xfs_bmap_finish(&tp, &free_list, &committed);
+ if (error)
+ goto out_bmap_cancel;
+
+ error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
+ if (error)
+ goto out_release_inode;
+
+ xfs_qm_dqrele(udqp);
+ xfs_qm_dqrele(gdqp);
+ xfs_qm_dqrele(pdqp);
+
+ *ipp = ip;
+ return 0;
+
+ out_bmap_cancel:
+ xfs_bmap_cancel(&free_list);
+ out_trans_abort:
+ cancel_flags |= XFS_TRANS_ABORT;
+ out_trans_cancel:
+ xfs_trans_cancel(tp, cancel_flags);
+ out_release_inode:
+ /*
+ * Wait until after the current transaction is aborted to
+ * release the inode. This prevents recursive transactions
+ * and deadlocks from xfs_inactive.
+ */
+ if (ip)
+ IRELE(ip);
+
+ xfs_qm_dqrele(udqp);
+ xfs_qm_dqrele(gdqp);
+ xfs_qm_dqrele(pdqp);
+
+ if (unlock_dp_on_error)
+ xfs_iunlock(dp, XFS_ILOCK_EXCL);
+ return error;
+}
+
+int
+xfs_link(
+ xfs_inode_t *tdp,
+ xfs_inode_t *sip,
+ struct xfs_name *target_name)
+{
+ xfs_mount_t *mp = tdp->i_mount;
+ xfs_trans_t *tp;
+ int error;
+ xfs_bmap_free_t free_list;
+ xfs_fsblock_t first_block;
+ int cancel_flags;
+ int committed;
+ int resblks;
+
+ trace_xfs_link(tdp, target_name);
+
+ ASSERT(!S_ISDIR(sip->i_d.di_mode));
+
+ if (XFS_FORCED_SHUTDOWN(mp))
+ return XFS_ERROR(EIO);
+
+ error = xfs_qm_dqattach(sip, 0);
+ if (error)
+ goto std_return;
+
+ error = xfs_qm_dqattach(tdp, 0);
+ if (error)
+ goto std_return;
+
+ tp = xfs_trans_alloc(mp, XFS_TRANS_LINK);
+ cancel_flags = XFS_TRANS_RELEASE_LOG_RES;
+ resblks = XFS_LINK_SPACE_RES(mp, target_name->len);
+ error = xfs_trans_reserve(tp, resblks, XFS_LINK_LOG_RES(mp), 0,
+ XFS_TRANS_PERM_LOG_RES, XFS_LINK_LOG_COUNT);
+ if (error == ENOSPC) {
+ resblks = 0;
+ error = xfs_trans_reserve(tp, 0, XFS_LINK_LOG_RES(mp), 0,
+ XFS_TRANS_PERM_LOG_RES, XFS_LINK_LOG_COUNT);
+ }
+ if (error) {
+ cancel_flags = 0;
+ goto error_return;
+ }
+
+ xfs_lock_two_inodes(sip, tdp, XFS_ILOCK_EXCL);
+
+ xfs_trans_ijoin(tp, sip, XFS_ILOCK_EXCL);
+ xfs_trans_ijoin(tp, tdp, XFS_ILOCK_EXCL);
+
+ /*
+ * If we are using project inheritance, we only allow hard link
+ * creation in our tree when the project IDs are the same; else
+ * the tree quota mechanism could be circumvented.
+ */
+ if (unlikely((tdp->i_d.di_flags & XFS_DIFLAG_PROJINHERIT) &&
+ (xfs_get_projid(tdp) != xfs_get_projid(sip)))) {
+ error = XFS_ERROR(EXDEV);
+ goto error_return;
+ }
+
+ error = xfs_dir_canenter(tp, tdp, target_name, resblks);
+ if (error)
+ goto error_return;
+
+ xfs_bmap_init(&free_list, &first_block);
+
+ error = xfs_dir_createname(tp, tdp, target_name, sip->i_ino,
+ &first_block, &free_list, resblks);
+ if (error)
+ goto abort_return;
+ xfs_trans_ichgtime(tp, tdp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
+ xfs_trans_log_inode(tp, tdp, XFS_ILOG_CORE);
+
+ error = xfs_bumplink(tp, sip);
+ if (error)
+ goto abort_return;
+
+ /*
+ * If this is a synchronous mount, make sure that the
+ * link transaction goes to disk before returning to
+ * the user.
+ */
+ if (mp->m_flags & (XFS_MOUNT_WSYNC|XFS_MOUNT_DIRSYNC)) {
+ xfs_trans_set_sync(tp);
+ }
+
+ error = xfs_bmap_finish (&tp, &free_list, &committed);
+ if (error) {
+ xfs_bmap_cancel(&free_list);
+ goto abort_return;
+ }
+
+ return xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
+
+ abort_return:
+ cancel_flags |= XFS_TRANS_ABORT;
+ error_return:
+ xfs_trans_cancel(tp, cancel_flags);
+ std_return:
+ return error;
+}
+
/*
* Free up the underlying blocks past new_size. The new size must be smaller
* than the current size. This routine can be used both for the attribute and
@@ -771,6 +1303,276 @@ out_bmap_cancel:
goto out;
}
+int
+xfs_release(
+ xfs_inode_t *ip)
+{
+ xfs_mount_t *mp = ip->i_mount;
+ int error;
+
+ if (!S_ISREG(ip->i_d.di_mode) || (ip->i_d.di_mode == 0))
+ return 0;
+
+ /* If this is a read-only mount, don't do this (would generate I/O) */
+ if (mp->m_flags & XFS_MOUNT_RDONLY)
+ return 0;
+
+ if (!XFS_FORCED_SHUTDOWN(mp)) {
+ int truncated;
+
+ /*
+ * If we are using filestreams, and we have an unlinked
+ * file that we are processing the last close on, then nothing
+ * will be able to reopen and write to this file. Purge this
+ * inode from the filestreams cache so that it doesn't delay
+ * teardown of the inode.
+ */
+ if ((ip->i_d.di_nlink == 0) && xfs_inode_is_filestream(ip))
+ xfs_filestream_deassociate(ip);
+
+ /*
+ * If we previously truncated this file and removed old data
+ * in the process, we want to initiate "early" writeout on
+ * the last close. This is an attempt to combat the notorious
+ * NULL files problem which is particularly noticeable from a
+ * truncate down, buffered (re-)write (delalloc), followed by
+ * a crash. What we are effectively doing here is
+ * significantly reducing the time window where we'd otherwise
+ * be exposed to that problem.
+ */
+ truncated = xfs_iflags_test_and_clear(ip, XFS_ITRUNCATED);
+ if (truncated) {
+ xfs_iflags_clear(ip, XFS_IDIRTY_RELEASE);
+ if (VN_DIRTY(VFS_I(ip)) && ip->i_delayed_blks > 0) {
+ error = -filemap_flush(VFS_I(ip)->i_mapping);
+ if (error)
+ return error;
+ }
+ }
+ }
+
+ if (ip->i_d.di_nlink == 0)
+ return 0;
+
+ if (xfs_can_free_eofblocks(ip, false)) {
+
+ /*
+ * If we can't get the iolock just skip truncating the blocks
+ * past EOF because we could deadlock with the mmap_sem
+ * otherwise. We'll get another chance to drop them once the
+ * last reference to the inode is dropped, so we'll never leak
+ * blocks permanently.
+ *
+ * Further, check if the inode is being opened, written and
+ * closed frequently and we have delayed allocation blocks
+ * outstanding (e.g. streaming writes from the NFS server),
+ * truncating the blocks past EOF will cause fragmentation to
+ * occur.
+ *
+ * In this case don't do the truncation, either, but we have to
+ * be careful how we detect this case. Blocks beyond EOF show
+ * up as i_delayed_blks even when the inode is clean, so we
+ * need to truncate them away first before checking for a dirty
+ * release. Hence on the first dirty close we will still remove
+ * the speculative allocation, but after that we will leave it
+ * in place.
+ */
+ if (xfs_iflags_test(ip, XFS_IDIRTY_RELEASE))
+ return 0;
+
+ error = xfs_free_eofblocks(mp, ip, true);
+ if (error && error != EAGAIN)
+ return error;
+
+ /* delalloc blocks after truncation means it really is dirty */
+ if (ip->i_delayed_blks)
+ xfs_iflags_set(ip, XFS_IDIRTY_RELEASE);
+ }
+ return 0;
+}
+
+/*
+ * xfs_inactive
+ *
+ * This is called when the vnode reference count for the vnode
+ * goes to zero. If the file has been unlinked, then it must
+ * now be truncated. Also, we clear all of the read-ahead state
+ * kept for the inode here since the file is now closed.
+ */
+int
+xfs_inactive(
+ xfs_inode_t *ip)
+{
+ xfs_bmap_free_t free_list;
+ xfs_fsblock_t first_block;
+ int committed;
+ xfs_trans_t *tp;
+ xfs_mount_t *mp;
+ int error;
+ int truncate = 0;
+
+ /*
+ * If the inode is already free, then there can be nothing
+ * to clean up here.
+ */
+ if (ip->i_d.di_mode == 0 || is_bad_inode(VFS_I(ip))) {
+ ASSERT(ip->i_df.if_real_bytes == 0);
+ ASSERT(ip->i_df.if_broot_bytes == 0);
+ return VN_INACTIVE_CACHE;
+ }
+
+ mp = ip->i_mount;
+
+ error = 0;
+
+ /* If this is a read-only mount, don't do this (would generate I/O) */
+ if (mp->m_flags & XFS_MOUNT_RDONLY)
+ goto out;
+
+ if (ip->i_d.di_nlink != 0) {
+ /*
+ * force is true because we are evicting an inode from the
+ * cache. Post-eof blocks must be freed, lest we end up with
+ * broken free space accounting.
+ */
+ if (xfs_can_free_eofblocks(ip, true)) {
+ error = xfs_free_eofblocks(mp, ip, false);
+ if (error)
+ return VN_INACTIVE_CACHE;
+ }
+ goto out;
+ }
+
+ if (S_ISREG(ip->i_d.di_mode) &&
+ (ip->i_d.di_size != 0 || XFS_ISIZE(ip) != 0 ||
+ ip->i_d.di_nextents > 0 || ip->i_delayed_blks > 0))
+ truncate = 1;
+
+ error = xfs_qm_dqattach(ip, 0);
+ if (error)
+ return VN_INACTIVE_CACHE;
+
+ tp = xfs_trans_alloc(mp, XFS_TRANS_INACTIVE);
+ error = xfs_trans_reserve(tp, 0,
+ (truncate || S_ISLNK(ip->i_d.di_mode)) ?
+ XFS_ITRUNCATE_LOG_RES(mp) :
+ XFS_IFREE_LOG_RES(mp),
+ 0,
+ XFS_TRANS_PERM_LOG_RES,
+ XFS_ITRUNCATE_LOG_COUNT);
+ if (error) {
+ ASSERT(XFS_FORCED_SHUTDOWN(mp));
+ xfs_trans_cancel(tp, 0);
+ return VN_INACTIVE_CACHE;
+ }
+
+ xfs_ilock(ip, XFS_ILOCK_EXCL);
+ xfs_trans_ijoin(tp, ip, 0);
+
+ if (S_ISLNK(ip->i_d.di_mode)) {
+ error = xfs_inactive_symlink(ip, &tp);
+ if (error)
+ goto out_cancel;
+ } else if (truncate) {
+ ip->i_d.di_size = 0;
+ xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+
+ error = xfs_itruncate_extents(&tp, ip, XFS_DATA_FORK, 0);
+ if (error)
+ goto out_cancel;
+
+ ASSERT(ip->i_d.di_nextents == 0);
+ }
+
+ /*
+ * If there are attributes associated with the file then blow them away
+ * now. The code calls a routine that recursively deconstructs the
+ * attribute fork. We need to just commit the current transaction
+ * because we can't use it for xfs_attr_inactive().
+ */
+ if (ip->i_d.di_anextents > 0) {
+ ASSERT(ip->i_d.di_forkoff != 0);
+
+ error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
+ if (error)
+ goto out_unlock;
+
+ xfs_iunlock(ip, XFS_ILOCK_EXCL);
+
+ error = xfs_attr_inactive(ip);
+ if (error)
+ goto out;
+
+ tp = xfs_trans_alloc(mp, XFS_TRANS_INACTIVE);
+ error = xfs_trans_reserve(tp, 0,
+ XFS_IFREE_LOG_RES(mp),
+ 0, XFS_TRANS_PERM_LOG_RES,
+ XFS_INACTIVE_LOG_COUNT);
+ if (error) {
+ xfs_trans_cancel(tp, 0);
+ goto out;
+ }
+
+ xfs_ilock(ip, XFS_ILOCK_EXCL);
+ xfs_trans_ijoin(tp, ip, 0);
+ }
+
+ if (ip->i_afp)
+ xfs_idestroy_fork(ip, XFS_ATTR_FORK);
+
+ ASSERT(ip->i_d.di_anextents == 0);
+
+ /*
+ * Free the inode.
+ */
+ xfs_bmap_init(&free_list, &first_block);
+ error = xfs_ifree(tp, ip, &free_list);
+ if (error) {
+ /*
+ * If we fail to free the inode, shut down. The cancel
+ * might do that, we need to make sure. Otherwise the
+ * inode might be lost for a long time or forever.
+ */
+ if (!XFS_FORCED_SHUTDOWN(mp)) {
+ xfs_notice(mp, "%s: xfs_ifree returned error %d",
+ __func__, error);
+ xfs_force_shutdown(mp, SHUTDOWN_META_IO_ERROR);
+ }
+ xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES|XFS_TRANS_ABORT);
+ } else {
+ /*
+ * Credit the quota account(s). The inode is gone.
+ */
+ xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_ICOUNT, -1);
+
+ /*
+ * Just ignore errors at this point. There is nothing we can
+ * do except to try to keep going. Make sure it's not a silent
+ * error.
+ */
+ error = xfs_bmap_finish(&tp, &free_list, &committed);
+ if (error)
+ xfs_notice(mp, "%s: xfs_bmap_finish returned error %d",
+ __func__, error);
+ error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
+ if (error)
+ xfs_notice(mp, "%s: xfs_trans_commit returned error %d",
+ __func__, error);
+ }
+
+ /*
+ * Release the dquots held by inode, if any.
+ */
+ xfs_qm_dqdetach(ip);
+out_unlock:
+ xfs_iunlock(ip, XFS_ILOCK_EXCL);
+out:
+ return VN_INACTIVE_CACHE;
+out_cancel:
+ xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT);
+ goto out_unlock;
+}
+
/*
* This is called when the inode's link count goes to 0.
* We place the on-disk inode on a list in the AGI. It
@@ -1302,6 +2104,170 @@ xfs_iunpin_wait(
__xfs_iunpin_wait(ip);
}
+int
+xfs_remove(
+ xfs_inode_t *dp,
+ struct xfs_name *name,
+ xfs_inode_t *ip)
+{
+ xfs_mount_t *mp = dp->i_mount;
+ xfs_trans_t *tp = NULL;
+ int is_dir = S_ISDIR(ip->i_d.di_mode);
+ int error = 0;
+ xfs_bmap_free_t free_list;
+ xfs_fsblock_t first_block;
+ int cancel_flags;
+ int committed;
+ int link_zero;
+ uint resblks;
+ uint log_count;
+
+ trace_xfs_remove(dp, name);
+
+ if (XFS_FORCED_SHUTDOWN(mp))
+ return XFS_ERROR(EIO);
+
+ error = xfs_qm_dqattach(dp, 0);
+ if (error)
+ goto std_return;
+
+ error = xfs_qm_dqattach(ip, 0);
+ if (error)
+ goto std_return;
+
+ if (is_dir) {
+ tp = xfs_trans_alloc(mp, XFS_TRANS_RMDIR);
+ log_count = XFS_DEFAULT_LOG_COUNT;
+ } else {
+ tp = xfs_trans_alloc(mp, XFS_TRANS_REMOVE);
+ log_count = XFS_REMOVE_LOG_COUNT;
+ }
+ cancel_flags = XFS_TRANS_RELEASE_LOG_RES;
+
+ /*
+ * We try to get the real space reservation first,
+ * allowing for directory btree deletion(s) implying
+ * possible bmap insert(s). If we can't get the space
+ * reservation then we use 0 instead, and avoid the bmap
+ * btree insert(s) in the directory code by, if the bmap
+ * insert tries to happen, instead trimming the LAST
+ * block from the directory.
+ */
+ resblks = XFS_REMOVE_SPACE_RES(mp);
+ error = xfs_trans_reserve(tp, resblks, XFS_REMOVE_LOG_RES(mp), 0,
+ XFS_TRANS_PERM_LOG_RES, log_count);
+ if (error == ENOSPC) {
+ resblks = 0;
+ error = xfs_trans_reserve(tp, 0, XFS_REMOVE_LOG_RES(mp), 0,
+ XFS_TRANS_PERM_LOG_RES, log_count);
+ }
+ if (error) {
+ ASSERT(error != ENOSPC);
+ cancel_flags = 0;
+ goto out_trans_cancel;
+ }
+
+ xfs_lock_two_inodes(dp, ip, XFS_ILOCK_EXCL);
+
+ xfs_trans_ijoin(tp, dp, XFS_ILOCK_EXCL);
+ xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
+
+ /*
+ * If we're removing a directory perform some additional validation.
+ */
+ if (is_dir) {
+ ASSERT(ip->i_d.di_nlink >= 2);
+ if (ip->i_d.di_nlink != 2) {
+ error = XFS_ERROR(ENOTEMPTY);
+ goto out_trans_cancel;
+ }
+ if (!xfs_dir_isempty(ip)) {
+ error = XFS_ERROR(ENOTEMPTY);
+ goto out_trans_cancel;
+ }
+ }
+
+ xfs_bmap_init(&free_list, &first_block);
+ error = xfs_dir_removename(tp, dp, name, ip->i_ino,
+ &first_block, &free_list, resblks);
+ if (error) {
+ ASSERT(error != ENOENT);
+ goto out_bmap_cancel;
+ }
+ xfs_trans_ichgtime(tp, dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
+
+ if (is_dir) {
+ /*
+ * Drop the link from ip's "..".
+ */
+ error = xfs_droplink(tp, dp);
+ if (error)
+ goto out_bmap_cancel;
+
+ /*
+ * Drop the "." link from ip to self.
+ */
+ error = xfs_droplink(tp, ip);
+ if (error)
+ goto out_bmap_cancel;
+ } else {
+ /*
+ * When removing a non-directory we need to log the parent
+ * inode here. For a directory this is done implicitly
+ * by the xfs_droplink call for the ".." entry.
+ */
+ xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE);
+ }
+
+ /*
+ * Drop the link from dp to ip.
+ */
+ error = xfs_droplink(tp, ip);
+ if (error)
+ goto out_bmap_cancel;
+
+ /*
+ * Determine if this is the last link while
+ * we are in the transaction.
+ */
+ link_zero = (ip->i_d.di_nlink == 0);
+
+ /*
+ * If this is a synchronous mount, make sure that the
+ * remove transaction goes to disk before returning to
+ * the user.
+ */
+ if (mp->m_flags & (XFS_MOUNT_WSYNC|XFS_MOUNT_DIRSYNC))
+ xfs_trans_set_sync(tp);
+
+ error = xfs_bmap_finish(&tp, &free_list, &committed);
+ if (error)
+ goto out_bmap_cancel;
+
+ error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
+ if (error)
+ goto std_return;
+
+ /*
+ * If we are using filestreams, kill the stream association.
+ * If the file is still open it may get a new one but that
+ * will get killed on last close in xfs_close() so we don't
+ * have to worry about that.
+ */
+ if (!is_dir && link_zero && xfs_inode_is_filestream(ip))
+ xfs_filestream_deassociate(ip);
+
+ return 0;
+
+ out_bmap_cancel:
+ xfs_bmap_cancel(&free_list);
+ cancel_flags |= XFS_TRANS_ABORT;
+ out_trans_cancel:
+ xfs_trans_cancel(tp, cancel_flags);
+ std_return:
+ return error;
+}
+
STATIC int
xfs_iflush_cluster(
xfs_inode_t *ip,
@@ -1746,39 +2712,3 @@ xfs_iflush_int(
corrupt_out:
return XFS_ERROR(EFSCORRUPTED);
}
-
-/*
- * Test whether it is appropriate to check an inode for and free post EOF
- * blocks. The 'force' parameter determines whether we should also consider
- * regular files that are marked preallocated or append-only.
- */
-bool
-xfs_can_free_eofblocks(struct xfs_inode *ip, bool force)
-{
- /* prealloc/delalloc exists only on regular files */
- if (!S_ISREG(ip->i_d.di_mode))
- return false;
-
- /*
- * Zero sized files with no cached pages and delalloc blocks will not
- * have speculative prealloc/delalloc blocks to remove.
- */
- if (VFS_I(ip)->i_size == 0 &&
- VN_CACHED(VFS_I(ip)) == 0 &&
- ip->i_delayed_blks == 0)
- return false;
-
- /* If we haven't read in the extent list, then don't do it now. */
- if (!(ip->i_df.if_flags & XFS_IFEXTENTS))
- return false;
-
- /*
- * Do not free real preallocated or append-only files unless the file
- * has delalloc blocks and we are forced to remove them.
- */
- if (ip->i_d.di_flags & (XFS_DIFLAG_PREALLOC | XFS_DIFLAG_APPEND))
- if (!force || ip->i_delayed_blks == 0)
- return false;
-
- return true;
-}
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 8f775ed722a9..2a6347038cd8 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -315,9 +315,21 @@ static inline int xfs_isiflocked(struct xfs_inode *ip)
((pip)->i_d.di_mode & S_ISGID))
-/*
- * xfs_inode.c prototypes.
- */
+int xfs_release(struct xfs_inode *ip);
+int xfs_inactive(struct xfs_inode *ip);
+int xfs_lookup(struct xfs_inode *dp, struct xfs_name *name,
+ struct xfs_inode **ipp, struct xfs_name *ci_name);
+int xfs_create(struct xfs_inode *dp, struct xfs_name *name,
+ umode_t mode, xfs_dev_t rdev, struct xfs_inode **ipp);
+int xfs_remove(struct xfs_inode *dp, struct xfs_name *name,
+ struct xfs_inode *ip);
+int xfs_link(struct xfs_inode *tdp, struct xfs_inode *sip,
+ struct xfs_name *target_name);
+int xfs_rename(struct xfs_inode *src_dp, struct xfs_name *src_name,
+ struct xfs_inode *src_ip, struct xfs_inode *target_dp,
+ struct xfs_name *target_name,
+ struct xfs_inode *target_ip);
+
void xfs_ilock(xfs_inode_t *, uint);
int xfs_ilock_nowait(xfs_inode_t *, uint);
void xfs_iunlock(xfs_inode_t *, uint);
@@ -348,6 +360,11 @@ void xfs_lock_two_inodes(xfs_inode_t *, xfs_inode_t *, uint);
xfs_extlen_t xfs_get_extsz_hint(struct xfs_inode *ip);
+/* from xfs_file.c */
+int xfs_zero_eof(struct xfs_inode *, xfs_off_t, xfs_fsize_t);
+int xfs_iozero(struct xfs_inode *, loff_t, size_t);
+
+
#define IHOLD(ip) \
do { \
ASSERT(atomic_read(&VFS_I(ip)->i_count) > 0) ; \
diff --git a/fs/xfs/xfs_inode_buf.h b/fs/xfs/xfs_inode_buf.h
index b5f1e22bf44e..aae9fc465fe0 100644
--- a/fs/xfs/xfs_inode_buf.h
+++ b/fs/xfs/xfs_inode_buf.h
@@ -40,7 +40,6 @@ int xfs_iread(struct xfs_mount *, struct xfs_trans *,
void xfs_dinode_calc_crc(struct xfs_mount *, struct xfs_dinode *);
void xfs_dinode_to_disk(struct xfs_dinode *,
struct xfs_icdinode *);
-bool xfs_can_free_eofblocks(struct xfs_inode *, bool);
#if defined(DEBUG)
void xfs_inobp_check(struct xfs_mount *, struct xfs_buf *);
diff --git a/fs/xfs/xfs_inode_fork.c b/fs/xfs/xfs_inode_fork.c
index f06570bb36bd..3f9ff99d6007 100644
--- a/fs/xfs/xfs_inode_fork.c
+++ b/fs/xfs/xfs_inode_fork.c
@@ -43,7 +43,6 @@
#include "xfs_utils.h"
#include "xfs_quota.h"
#include "xfs_filestream.h"
-#include "xfs_vnodeops.h"
#include "xfs_cksum.h"
#include "xfs_trace.h"
#include "xfs_icache.h"
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 7c275380d40a..ce636bf0d550 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -38,13 +38,13 @@
#include "xfs_utils.h"
#include "xfs_dfrag.h"
#include "xfs_fsops.h"
-#include "xfs_vnodeops.h"
#include "xfs_discard.h"
#include "xfs_quota.h"
#include "xfs_inode_item.h"
#include "xfs_export.h"
#include "xfs_trace.h"
#include "xfs_icache.h"
+#include "xfs_symlink.h"
#include <linux/capability.h>
#include <linux/dcache.h>
@@ -352,6 +352,40 @@ xfs_readlink_by_handle(
return error;
}
+int
+xfs_set_dmattrs(
+ xfs_inode_t *ip,
+ u_int evmask,
+ u_int16_t state)
+{
+ xfs_mount_t *mp = ip->i_mount;
+ xfs_trans_t *tp;
+ int error;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return XFS_ERROR(EPERM);
+
+ if (XFS_FORCED_SHUTDOWN(mp))
+ return XFS_ERROR(EIO);
+
+ tp = xfs_trans_alloc(mp, XFS_TRANS_SET_DMATTRS);
+ error = xfs_trans_reserve(tp, 0, XFS_ICHANGE_LOG_RES (mp), 0, 0, 0);
+ if (error) {
+ xfs_trans_cancel(tp, 0);
+ return error;
+ }
+ xfs_ilock(ip, XFS_ILOCK_EXCL);
+ xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
+
+ ip->i_d.di_dmevmask = evmask;
+ ip->i_d.di_dmstate = state;
+
+ xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+ error = xfs_trans_commit(tp, 0);
+
+ return error;
+}
+
STATIC int
xfs_fssetdm_by_handle(
struct file *parfilp,
diff --git a/fs/xfs/xfs_ioctl.h b/fs/xfs/xfs_ioctl.h
index d56173b34a2a..1233dee4fef0 100644
--- a/fs/xfs/xfs_ioctl.h
+++ b/fs/xfs/xfs_ioctl.h
@@ -82,4 +82,10 @@ xfs_file_compat_ioctl(
unsigned int cmd,
unsigned long arg);
+extern int
+xfs_set_dmattrs(
+ struct xfs_inode *ip,
+ u_int evmask,
+ u_int16_t state);
+
#endif
diff --git a/fs/xfs/xfs_ioctl32.c b/fs/xfs/xfs_ioctl32.c
index c0c66259cc91..55a3072e7f56 100644
--- a/fs/xfs/xfs_ioctl32.c
+++ b/fs/xfs/xfs_ioctl32.c
@@ -34,7 +34,6 @@
#include "xfs_itable.h"
#include "xfs_error.h"
#include "xfs_dfrag.h"
-#include "xfs_vnodeops.h"
#include "xfs_fsops.h"
#include "xfs_alloc.h"
#include "xfs_rtalloc.h"
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index 17b70f0ccf8a..e0cefd417bf8 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -37,10 +37,10 @@
#include "xfs_attr.h"
#include "xfs_buf_item.h"
#include "xfs_utils.h"
-#include "xfs_vnodeops.h"
#include "xfs_inode_item.h"
#include "xfs_trace.h"
#include "xfs_icache.h"
+#include "xfs_symlink.h"
#include <linux/capability.h>
#include <linux/xattr.h>
diff --git a/fs/xfs/xfs_iops.h b/fs/xfs/xfs_iops.h
index ef41c92ce66e..d81fb41205ec 100644
--- a/fs/xfs/xfs_iops.h
+++ b/fs/xfs/xfs_iops.h
@@ -27,4 +27,17 @@ extern ssize_t xfs_vn_listxattr(struct dentry *, char *data, size_t size);
extern void xfs_setup_inode(struct xfs_inode *);
+/*
+ * Internal setattr interfaces.
+ */
+#define XFS_ATTR_DMI 0x01 /* invocation from a DMI function */
+#define XFS_ATTR_NONBLOCK 0x02 /* return EAGAIN if op would block */
+#define XFS_ATTR_NOLOCK 0x04 /* Don't grab any conflicting locks */
+#define XFS_ATTR_NOACL 0x08 /* Don't call xfs_acl_chmod */
+#define XFS_ATTR_SYNC 0x10 /* synchronous operation required */
+
+extern int xfs_setattr_nonsize(struct xfs_inode *ip, struct iattr *vap,
+ int flags);
+extern int xfs_setattr_size(struct xfs_inode *ip, struct iattr *vap, int flags);
+
#endif /* __XFS_IOPS_H__ */
diff --git a/fs/xfs/xfs_rename.c b/fs/xfs/xfs_rename.c
index 68cb7251cb99..c15c6c581d56 100644
--- a/fs/xfs/xfs_rename.c
+++ b/fs/xfs/xfs_rename.c
@@ -36,7 +36,6 @@
#include "xfs_quota.h"
#include "xfs_utils.h"
#include "xfs_trans_space.h"
-#include "xfs_vnodeops.h"
#include "xfs_trace.h"
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index aefc0044237d..978a2845f9af 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -41,7 +41,6 @@
#include "xfs_attr.h"
#include "xfs_buf_item.h"
#include "xfs_utils.h"
-#include "xfs_vnodeops.h"
#include "xfs_log_priv.h"
#include "xfs_trans_priv.h"
#include "xfs_filestream.h"
diff --git a/fs/xfs/xfs_vnodeops.c b/fs/xfs/xfs_vnodeops.c
deleted file mode 100644
index dc81a8d86ba5..000000000000
--- a/fs/xfs/xfs_vnodeops.c
+++ /dev/null
@@ -1,1872 +0,0 @@
-/*
- * Copyright (c) 2000-2006 Silicon Graphics, Inc.
- * Copyright (c) 2012 Red Hat, Inc.
- * All Rights Reserved.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it would 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.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write the Free Software Foundation,
- * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
- */
-
-#include "xfs.h"
-#include "xfs_fs.h"
-#include "xfs_format.h"
-#include "xfs_bit.h"
-#include "xfs_log.h"
-#include "xfs_trans.h"
-#include "xfs_sb.h"
-#include "xfs_ag.h"
-#include "xfs_mount.h"
-#include "xfs_da_btree.h"
-#include "xfs_dir2_format.h"
-#include "xfs_dir2.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_ialloc_btree.h"
-#include "xfs_dinode.h"
-#include "xfs_inode.h"
-#include "xfs_inode_item.h"
-#include "xfs_itable.h"
-#include "xfs_ialloc.h"
-#include "xfs_alloc.h"
-#include "xfs_bmap.h"
-#include "xfs_bmap_util.h"
-#include "xfs_acl.h"
-#include "xfs_attr.h"
-#include "xfs_error.h"
-#include "xfs_quota.h"
-#include "xfs_utils.h"
-#include "xfs_rtalloc.h"
-#include "xfs_trans_space.h"
-#include "xfs_log_priv.h"
-#include "xfs_filestream.h"
-#include "xfs_vnodeops.h"
-#include "xfs_trace.h"
-#include "xfs_icache.h"
-#include "xfs_symlink.h"
-
-
-/*
- * 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.
- */
-int
-xfs_free_eofblocks(
- xfs_mount_t *mp,
- xfs_inode_t *ip,
- bool need_iolock)
-{
- xfs_trans_t *tp;
- int error;
- xfs_fileoff_t end_fsb;
- xfs_fileoff_t last_fsb;
- xfs_filblks_t map_len;
- int nimaps;
- xfs_bmbt_irec_t imap;
-
- /*
- * Figure out if there are any blocks beyond the end
- * of the file. If not, then there is nothing to do.
- */
- end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)XFS_ISIZE(ip));
- last_fsb = XFS_B_TO_FSB(mp, mp->m_super->s_maxbytes);
- if (last_fsb <= end_fsb)
- return 0;
- map_len = last_fsb - end_fsb;
-
- nimaps = 1;
- xfs_ilock(ip, XFS_ILOCK_SHARED);
- error = xfs_bmapi_read(ip, end_fsb, map_len, &imap, &nimaps, 0);
- xfs_iunlock(ip, XFS_ILOCK_SHARED);
-
- if (!error && (nimaps != 0) &&
- (imap.br_startblock != HOLESTARTBLOCK ||
- ip->i_delayed_blks)) {
- /*
- * Attach the dquots to the inode up front.
- */
- error = xfs_qm_dqattach(ip, 0);
- if (error)
- return error;
-
- /*
- * There are blocks after the end of file.
- * Free them up now by truncating the file to
- * its current size.
- */
- tp = xfs_trans_alloc(mp, XFS_TRANS_INACTIVE);
-
- if (need_iolock) {
- if (!xfs_ilock_nowait(ip, XFS_IOLOCK_EXCL)) {
- xfs_trans_cancel(tp, 0);
- return EAGAIN;
- }
- }
-
- error = xfs_trans_reserve(tp, 0,
- XFS_ITRUNCATE_LOG_RES(mp),
- 0, XFS_TRANS_PERM_LOG_RES,
- XFS_ITRUNCATE_LOG_COUNT);
- if (error) {
- ASSERT(XFS_FORCED_SHUTDOWN(mp));
- xfs_trans_cancel(tp, 0);
- if (need_iolock)
- xfs_iunlock(ip, XFS_IOLOCK_EXCL);
- return error;
- }
-
- xfs_ilock(ip, XFS_ILOCK_EXCL);
- xfs_trans_ijoin(tp, ip, 0);
-
- /*
- * Do not update the on-disk file size. If we update the
- * on-disk file size and then the system crashes before the
- * contents of the file are flushed to disk then the files
- * may be full of holes (ie NULL files bug).
- */
- error = xfs_itruncate_extents(&tp, ip, XFS_DATA_FORK,
- XFS_ISIZE(ip));
- if (error) {
- /*
- * If we get an error at this point we simply don't
- * bother truncating the file.
- */
- xfs_trans_cancel(tp,
- (XFS_TRANS_RELEASE_LOG_RES |
- XFS_TRANS_ABORT));
- } else {
- error = xfs_trans_commit(tp,
- XFS_TRANS_RELEASE_LOG_RES);
- if (!error)
- xfs_inode_clear_eofblocks_tag(ip);
- }
-
- xfs_iunlock(ip, XFS_ILOCK_EXCL);
- if (need_iolock)
- xfs_iunlock(ip, XFS_IOLOCK_EXCL);
- }
- return error;
-}
-
-int
-xfs_release(
- xfs_inode_t *ip)
-{
- xfs_mount_t *mp = ip->i_mount;
- int error;
-
- if (!S_ISREG(ip->i_d.di_mode) || (ip->i_d.di_mode == 0))
- return 0;
-
- /* If this is a read-only mount, don't do this (would generate I/O) */
- if (mp->m_flags & XFS_MOUNT_RDONLY)
- return 0;
-
- if (!XFS_FORCED_SHUTDOWN(mp)) {
- int truncated;
-
- /*
- * If we are using filestreams, and we have an unlinked
- * file that we are processing the last close on, then nothing
- * will be able to reopen and write to this file. Purge this
- * inode from the filestreams cache so that it doesn't delay
- * teardown of the inode.
- */
- if ((ip->i_d.di_nlink == 0) && xfs_inode_is_filestream(ip))
- xfs_filestream_deassociate(ip);
-
- /*
- * If we previously truncated this file and removed old data
- * in the process, we want to initiate "early" writeout on
- * the last close. This is an attempt to combat the notorious
- * NULL files problem which is particularly noticeable from a
- * truncate down, buffered (re-)write (delalloc), followed by
- * a crash. What we are effectively doing here is
- * significantly reducing the time window where we'd otherwise
- * be exposed to that problem.
- */
- truncated = xfs_iflags_test_and_clear(ip, XFS_ITRUNCATED);
- if (truncated) {
- xfs_iflags_clear(ip, XFS_IDIRTY_RELEASE);
- if (VN_DIRTY(VFS_I(ip)) && ip->i_delayed_blks > 0) {
- error = -filemap_flush(VFS_I(ip)->i_mapping);
- if (error)
- return error;
- }
- }
- }
-
- if (ip->i_d.di_nlink == 0)
- return 0;
-
- if (xfs_can_free_eofblocks(ip, false)) {
-
- /*
- * If we can't get the iolock just skip truncating the blocks
- * past EOF because we could deadlock with the mmap_sem
- * otherwise. We'll get another chance to drop them once the
- * last reference to the inode is dropped, so we'll never leak
- * blocks permanently.
- *
- * Further, check if the inode is being opened, written and
- * closed frequently and we have delayed allocation blocks
- * outstanding (e.g. streaming writes from the NFS server),
- * truncating the blocks past EOF will cause fragmentation to
- * occur.
- *
- * In this case don't do the truncation, either, but we have to
- * be careful how we detect this case. Blocks beyond EOF show
- * up as i_delayed_blks even when the inode is clean, so we
- * need to truncate them away first before checking for a dirty
- * release. Hence on the first dirty close we will still remove
- * the speculative allocation, but after that we will leave it
- * in place.
- */
- if (xfs_iflags_test(ip, XFS_IDIRTY_RELEASE))
- return 0;
-
- error = xfs_free_eofblocks(mp, ip, true);
- if (error && error != EAGAIN)
- return error;
-
- /* delalloc blocks after truncation means it really is dirty */
- if (ip->i_delayed_blks)
- xfs_iflags_set(ip, XFS_IDIRTY_RELEASE);
- }
- return 0;
-}
-
-/*
- * xfs_inactive
- *
- * This is called when the vnode reference count for the vnode
- * goes to zero. If the file has been unlinked, then it must
- * now be truncated. Also, we clear all of the read-ahead state
- * kept for the inode here since the file is now closed.
- */
-int
-xfs_inactive(
- xfs_inode_t *ip)
-{
- xfs_bmap_free_t free_list;
- xfs_fsblock_t first_block;
- int committed;
- xfs_trans_t *tp;
- xfs_mount_t *mp;
- int error;
- int truncate = 0;
-
- /*
- * If the inode is already free, then there can be nothing
- * to clean up here.
- */
- if (ip->i_d.di_mode == 0 || is_bad_inode(VFS_I(ip))) {
- ASSERT(ip->i_df.if_real_bytes == 0);
- ASSERT(ip->i_df.if_broot_bytes == 0);
- return VN_INACTIVE_CACHE;
- }
-
- mp = ip->i_mount;
-
- error = 0;
-
- /* If this is a read-only mount, don't do this (would generate I/O) */
- if (mp->m_flags & XFS_MOUNT_RDONLY)
- goto out;
-
- if (ip->i_d.di_nlink != 0) {
- /*
- * force is true because we are evicting an inode from the
- * cache. Post-eof blocks must be freed, lest we end up with
- * broken free space accounting.
- */
- if (xfs_can_free_eofblocks(ip, true)) {
- error = xfs_free_eofblocks(mp, ip, false);
- if (error)
- return VN_INACTIVE_CACHE;
- }
- goto out;
- }
-
- if (S_ISREG(ip->i_d.di_mode) &&
- (ip->i_d.di_size != 0 || XFS_ISIZE(ip) != 0 ||
- ip->i_d.di_nextents > 0 || ip->i_delayed_blks > 0))
- truncate = 1;
-
- error = xfs_qm_dqattach(ip, 0);
- if (error)
- return VN_INACTIVE_CACHE;
-
- tp = xfs_trans_alloc(mp, XFS_TRANS_INACTIVE);
- error = xfs_trans_reserve(tp, 0,
- (truncate || S_ISLNK(ip->i_d.di_mode)) ?
- XFS_ITRUNCATE_LOG_RES(mp) :
- XFS_IFREE_LOG_RES(mp),
- 0,
- XFS_TRANS_PERM_LOG_RES,
- XFS_ITRUNCATE_LOG_COUNT);
- if (error) {
- ASSERT(XFS_FORCED_SHUTDOWN(mp));
- xfs_trans_cancel(tp, 0);
- return VN_INACTIVE_CACHE;
- }
-
- xfs_ilock(ip, XFS_ILOCK_EXCL);
- xfs_trans_ijoin(tp, ip, 0);
-
- if (S_ISLNK(ip->i_d.di_mode)) {
- error = xfs_inactive_symlink(ip, &tp);
- if (error)
- goto out_cancel;
- } else if (truncate) {
- ip->i_d.di_size = 0;
- xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
-
- error = xfs_itruncate_extents(&tp, ip, XFS_DATA_FORK, 0);
- if (error)
- goto out_cancel;
-
- ASSERT(ip->i_d.di_nextents == 0);
- }
-
- /*
- * If there are attributes associated with the file then blow them away
- * now. The code calls a routine that recursively deconstructs the
- * attribute fork. We need to just commit the current transaction
- * because we can't use it for xfs_attr_inactive().
- */
- if (ip->i_d.di_anextents > 0) {
- ASSERT(ip->i_d.di_forkoff != 0);
-
- error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
- if (error)
- goto out_unlock;
-
- xfs_iunlock(ip, XFS_ILOCK_EXCL);
-
- error = xfs_attr_inactive(ip);
- if (error)
- goto out;
-
- tp = xfs_trans_alloc(mp, XFS_TRANS_INACTIVE);
- error = xfs_trans_reserve(tp, 0,
- XFS_IFREE_LOG_RES(mp),
- 0, XFS_TRANS_PERM_LOG_RES,
- XFS_INACTIVE_LOG_COUNT);
- if (error) {
- xfs_trans_cancel(tp, 0);
- goto out;
- }
-
- xfs_ilock(ip, XFS_ILOCK_EXCL);
- xfs_trans_ijoin(tp, ip, 0);
- }
-
- if (ip->i_afp)
- xfs_idestroy_fork(ip, XFS_ATTR_FORK);
-
- ASSERT(ip->i_d.di_anextents == 0);
-
- /*
- * Free the inode.
- */
- xfs_bmap_init(&free_list, &first_block);
- error = xfs_ifree(tp, ip, &free_list);
- if (error) {
- /*
- * If we fail to free the inode, shut down. The cancel
- * might do that, we need to make sure. Otherwise the
- * inode might be lost for a long time or forever.
- */
- if (!XFS_FORCED_SHUTDOWN(mp)) {
- xfs_notice(mp, "%s: xfs_ifree returned error %d",
- __func__, error);
- xfs_force_shutdown(mp, SHUTDOWN_META_IO_ERROR);
- }
- xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES|XFS_TRANS_ABORT);
- } else {
- /*
- * Credit the quota account(s). The inode is gone.
- */
- xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_ICOUNT, -1);
-
- /*
- * Just ignore errors at this point. There is nothing we can
- * do except to try to keep going. Make sure it's not a silent
- * error.
- */
- error = xfs_bmap_finish(&tp, &free_list, &committed);
- if (error)
- xfs_notice(mp, "%s: xfs_bmap_finish returned error %d",
- __func__, error);
- error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
- if (error)
- xfs_notice(mp, "%s: xfs_trans_commit returned error %d",
- __func__, error);
- }
-
- /*
- * Release the dquots held by inode, if any.
- */
- xfs_qm_dqdetach(ip);
-out_unlock:
- xfs_iunlock(ip, XFS_ILOCK_EXCL);
-out:
- return VN_INACTIVE_CACHE;
-out_cancel:
- xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT);
- goto out_unlock;
-}
-
-/*
- * Lookups up an inode from "name". If ci_name is not NULL, then a CI match
- * is allowed, otherwise it has to be an exact match. If a CI match is found,
- * ci_name->name will point to a the actual name (caller must free) or
- * will be set to NULL if an exact match is found.
- */
-int
-xfs_lookup(
- xfs_inode_t *dp,
- struct xfs_name *name,
- xfs_inode_t **ipp,
- struct xfs_name *ci_name)
-{
- xfs_ino_t inum;
- int error;
- uint lock_mode;
-
- trace_xfs_lookup(dp, name);
-
- if (XFS_FORCED_SHUTDOWN(dp->i_mount))
- return XFS_ERROR(EIO);
-
- lock_mode = xfs_ilock_map_shared(dp);
- error = xfs_dir_lookup(NULL, dp, name, &inum, ci_name);
- xfs_iunlock_map_shared(dp, lock_mode);
-
- if (error)
- goto out;
-
- error = xfs_iget(dp->i_mount, NULL, inum, 0, 0, ipp);
- if (error)
- goto out_free_name;
-
- return 0;
-
-out_free_name:
- if (ci_name)
- kmem_free(ci_name->name);
-out:
- *ipp = NULL;
- return error;
-}
-
-int
-xfs_create(
- xfs_inode_t *dp,
- struct xfs_name *name,
- umode_t mode,
- xfs_dev_t rdev,
- xfs_inode_t **ipp)
-{
- int is_dir = S_ISDIR(mode);
- struct xfs_mount *mp = dp->i_mount;
- struct xfs_inode *ip = NULL;
- struct xfs_trans *tp = NULL;
- int error;
- xfs_bmap_free_t free_list;
- xfs_fsblock_t first_block;
- bool unlock_dp_on_error = false;
- uint cancel_flags;
- int committed;
- prid_t prid;
- struct xfs_dquot *udqp = NULL;
- struct xfs_dquot *gdqp = NULL;
- struct xfs_dquot *pdqp = NULL;
- uint resblks;
- uint log_res;
- uint log_count;
-
- trace_xfs_create(dp, name);
-
- if (XFS_FORCED_SHUTDOWN(mp))
- return XFS_ERROR(EIO);
-
- if (dp->i_d.di_flags & XFS_DIFLAG_PROJINHERIT)
- prid = xfs_get_projid(dp);
- else
- prid = XFS_PROJID_DEFAULT;
-
- /*
- * Make sure that we have allocated dquot(s) on disk.
- */
- error = xfs_qm_vop_dqalloc(dp, current_fsuid(), current_fsgid(), prid,
- XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT,
- &udqp, &gdqp, &pdqp);
- if (error)
- return error;
-
- if (is_dir) {
- rdev = 0;
- resblks = XFS_MKDIR_SPACE_RES(mp, name->len);
- log_res = XFS_MKDIR_LOG_RES(mp);
- log_count = XFS_MKDIR_LOG_COUNT;
- tp = xfs_trans_alloc(mp, XFS_TRANS_MKDIR);
- } else {
- resblks = XFS_CREATE_SPACE_RES(mp, name->len);
- log_res = XFS_CREATE_LOG_RES(mp);
- log_count = XFS_CREATE_LOG_COUNT;
- tp = xfs_trans_alloc(mp, XFS_TRANS_CREATE);
- }
-
- cancel_flags = XFS_TRANS_RELEASE_LOG_RES;
-
- /*
- * Initially assume that the file does not exist and
- * reserve the resources for that case. If that is not
- * the case we'll drop the one we have and get a more
- * appropriate transaction later.
- */
- error = xfs_trans_reserve(tp, resblks, log_res, 0,
- XFS_TRANS_PERM_LOG_RES, log_count);
- if (error == ENOSPC) {
- /* flush outstanding delalloc blocks and retry */
- xfs_flush_inodes(mp);
- error = xfs_trans_reserve(tp, resblks, log_res, 0,
- XFS_TRANS_PERM_LOG_RES, log_count);
- }
- if (error == ENOSPC) {
- /* No space at all so try a "no-allocation" reservation */
- resblks = 0;
- error = xfs_trans_reserve(tp, 0, log_res, 0,
- XFS_TRANS_PERM_LOG_RES, log_count);
- }
- if (error) {
- cancel_flags = 0;
- goto out_trans_cancel;
- }
-
- xfs_ilock(dp, XFS_ILOCK_EXCL | XFS_ILOCK_PARENT);
- unlock_dp_on_error = true;
-
- xfs_bmap_init(&free_list, &first_block);
-
- /*
- * Reserve disk quota and the inode.
- */
- error = xfs_trans_reserve_quota(tp, mp, udqp, gdqp,
- pdqp, resblks, 1, 0);
- if (error)
- goto out_trans_cancel;
-
- error = xfs_dir_canenter(tp, dp, name, resblks);
- if (error)
- goto out_trans_cancel;
-
- /*
- * A newly created regular or special file just has one directory
- * entry pointing to them, but a directory also the "." entry
- * pointing to itself.
- */
- error = xfs_dir_ialloc(&tp, dp, mode, is_dir ? 2 : 1, rdev,
- prid, resblks > 0, &ip, &committed);
- if (error) {
- if (error == ENOSPC)
- goto out_trans_cancel;
- goto out_trans_abort;
- }
-
- /*
- * Now we join the directory inode to the transaction. We do not do it
- * earlier because xfs_dir_ialloc might commit the previous transaction
- * (and release all the locks). An error from here on will result in
- * the transaction cancel unlocking dp so don't do it explicitly in the
- * error path.
- */
- xfs_trans_ijoin(tp, dp, XFS_ILOCK_EXCL);
- unlock_dp_on_error = false;
-
- error = xfs_dir_createname(tp, dp, name, ip->i_ino,
- &first_block, &free_list, resblks ?
- resblks - XFS_IALLOC_SPACE_RES(mp) : 0);
- if (error) {
- ASSERT(error != ENOSPC);
- goto out_trans_abort;
- }
- xfs_trans_ichgtime(tp, dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
- xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE);
-
- if (is_dir) {
- error = xfs_dir_init(tp, ip, dp);
- if (error)
- goto out_bmap_cancel;
-
- error = xfs_bumplink(tp, dp);
- if (error)
- goto out_bmap_cancel;
- }
-
- /*
- * If this is a synchronous mount, make sure that the
- * create transaction goes to disk before returning to
- * the user.
- */
- if (mp->m_flags & (XFS_MOUNT_WSYNC|XFS_MOUNT_DIRSYNC))
- xfs_trans_set_sync(tp);
-
- /*
- * Attach the dquot(s) to the inodes and modify them incore.
- * These ids of the inode couldn't have changed since the new
- * inode has been locked ever since it was created.
- */
- xfs_qm_vop_create_dqattach(tp, ip, udqp, gdqp, pdqp);
-
- error = xfs_bmap_finish(&tp, &free_list, &committed);
- if (error)
- goto out_bmap_cancel;
-
- error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
- if (error)
- goto out_release_inode;
-
- xfs_qm_dqrele(udqp);
- xfs_qm_dqrele(gdqp);
- xfs_qm_dqrele(pdqp);
-
- *ipp = ip;
- return 0;
-
- out_bmap_cancel:
- xfs_bmap_cancel(&free_list);
- out_trans_abort:
- cancel_flags |= XFS_TRANS_ABORT;
- out_trans_cancel:
- xfs_trans_cancel(tp, cancel_flags);
- out_release_inode:
- /*
- * Wait until after the current transaction is aborted to
- * release the inode. This prevents recursive transactions
- * and deadlocks from xfs_inactive.
- */
- if (ip)
- IRELE(ip);
-
- xfs_qm_dqrele(udqp);
- xfs_qm_dqrele(gdqp);
- xfs_qm_dqrele(pdqp);
-
- if (unlock_dp_on_error)
- xfs_iunlock(dp, XFS_ILOCK_EXCL);
- return error;
-}
-
-#ifdef DEBUG
-int xfs_locked_n;
-int xfs_small_retries;
-int xfs_middle_retries;
-int xfs_lots_retries;
-int xfs_lock_delays;
-#endif
-
-/*
- * Bump the subclass so xfs_lock_inodes() acquires each lock with
- * a different value
- */
-static inline int
-xfs_lock_inumorder(int lock_mode, int subclass)
-{
- if (lock_mode & (XFS_IOLOCK_SHARED|XFS_IOLOCK_EXCL))
- lock_mode |= (subclass + XFS_LOCK_INUMORDER) << XFS_IOLOCK_SHIFT;
- if (lock_mode & (XFS_ILOCK_SHARED|XFS_ILOCK_EXCL))
- lock_mode |= (subclass + XFS_LOCK_INUMORDER) << XFS_ILOCK_SHIFT;
-
- return lock_mode;
-}
-
-/*
- * The following routine will lock n inodes in exclusive mode.
- * We assume the caller calls us with the inodes in i_ino order.
- *
- * We need to detect deadlock where an inode that we lock
- * is in the AIL and we start waiting for another inode that is locked
- * by a thread in a long running transaction (such as truncate). This can
- * result in deadlock since the long running trans might need to wait
- * for the inode we just locked in order to push the tail and free space
- * in the log.
- */
-void
-xfs_lock_inodes(
- xfs_inode_t **ips,
- int inodes,
- uint lock_mode)
-{
- int attempts = 0, i, j, try_lock;
- xfs_log_item_t *lp;
-
- ASSERT(ips && (inodes >= 2)); /* we need at least two */
-
- try_lock = 0;
- i = 0;
-
-again:
- for (; i < inodes; i++) {
- ASSERT(ips[i]);
-
- if (i && (ips[i] == ips[i-1])) /* Already locked */
- continue;
-
- /*
- * If try_lock is not set yet, make sure all locked inodes
- * are not in the AIL.
- * If any are, set try_lock to be used later.
- */
-
- if (!try_lock) {
- for (j = (i - 1); j >= 0 && !try_lock; j--) {
- lp = (xfs_log_item_t *)ips[j]->i_itemp;
- if (lp && (lp->li_flags & XFS_LI_IN_AIL)) {
- try_lock++;
- }
- }
- }
-
- /*
- * If any of the previous locks we have locked is in the AIL,
- * we must TRY to get the second and subsequent locks. If
- * we can't get any, we must release all we have
- * and try again.
- */
-
- if (try_lock) {
- /* try_lock must be 0 if i is 0. */
- /*
- * try_lock means we have an inode locked
- * that is in the AIL.
- */
- ASSERT(i != 0);
- if (!xfs_ilock_nowait(ips[i], xfs_lock_inumorder(lock_mode, i))) {
- attempts++;
-
- /*
- * Unlock all previous guys and try again.
- * xfs_iunlock will try to push the tail
- * if the inode is in the AIL.
- */
-
- for(j = i - 1; j >= 0; j--) {
-
- /*
- * Check to see if we've already
- * unlocked this one.
- * Not the first one going back,
- * and the inode ptr is the same.
- */
- if ((j != (i - 1)) && ips[j] ==
- ips[j+1])
- continue;
-
- xfs_iunlock(ips[j], lock_mode);
- }
-
- if ((attempts % 5) == 0) {
- delay(1); /* Don't just spin the CPU */
-#ifdef DEBUG
- xfs_lock_delays++;
-#endif
- }
- i = 0;
- try_lock = 0;
- goto again;
- }
- } else {
- xfs_ilock(ips[i], xfs_lock_inumorder(lock_mode, i));
- }
- }
-
-#ifdef DEBUG
- if (attempts) {
- if (attempts < 5) xfs_small_retries++;
- else if (attempts < 100) xfs_middle_retries++;
- else xfs_lots_retries++;
- } else {
- xfs_locked_n++;
- }
-#endif
-}
-
-/*
- * xfs_lock_two_inodes() can only be used to lock one type of lock
- * at a time - the iolock or the ilock, but not both at once. If
- * we lock both at once, lockdep will report false positives saying
- * we have violated locking orders.
- */
-void
-xfs_lock_two_inodes(
- xfs_inode_t *ip0,
- xfs_inode_t *ip1,
- uint lock_mode)
-{
- xfs_inode_t *temp;
- int attempts = 0;
- xfs_log_item_t *lp;
-
- if (lock_mode & (XFS_IOLOCK_SHARED|XFS_IOLOCK_EXCL))
- ASSERT((lock_mode & (XFS_ILOCK_SHARED|XFS_ILOCK_EXCL)) == 0);
- ASSERT(ip0->i_ino != ip1->i_ino);
-
- if (ip0->i_ino > ip1->i_ino) {
- temp = ip0;
- ip0 = ip1;
- ip1 = temp;
- }
-
- again:
- xfs_ilock(ip0, xfs_lock_inumorder(lock_mode, 0));
-
- /*
- * If the first lock we have locked is in the AIL, we must TRY to get
- * the second lock. If we can't get it, we must release the first one
- * and try again.
- */
- lp = (xfs_log_item_t *)ip0->i_itemp;
- if (lp && (lp->li_flags & XFS_LI_IN_AIL)) {
- if (!xfs_ilock_nowait(ip1, xfs_lock_inumorder(lock_mode, 1))) {
- xfs_iunlock(ip0, lock_mode);
- if ((++attempts % 5) == 0)
- delay(1); /* Don't just spin the CPU */
- goto again;
- }
- } else {
- xfs_ilock(ip1, xfs_lock_inumorder(lock_mode, 1));
- }
-}
-
-int
-xfs_remove(
- xfs_inode_t *dp,
- struct xfs_name *name,
- xfs_inode_t *ip)
-{
- xfs_mount_t *mp = dp->i_mount;
- xfs_trans_t *tp = NULL;
- int is_dir = S_ISDIR(ip->i_d.di_mode);
- int error = 0;
- xfs_bmap_free_t free_list;
- xfs_fsblock_t first_block;
- int cancel_flags;
- int committed;
- int link_zero;
- uint resblks;
- uint log_count;
-
- trace_xfs_remove(dp, name);
-
- if (XFS_FORCED_SHUTDOWN(mp))
- return XFS_ERROR(EIO);
-
- error = xfs_qm_dqattach(dp, 0);
- if (error)
- goto std_return;
-
- error = xfs_qm_dqattach(ip, 0);
- if (error)
- goto std_return;
-
- if (is_dir) {
- tp = xfs_trans_alloc(mp, XFS_TRANS_RMDIR);
- log_count = XFS_DEFAULT_LOG_COUNT;
- } else {
- tp = xfs_trans_alloc(mp, XFS_TRANS_REMOVE);
- log_count = XFS_REMOVE_LOG_COUNT;
- }
- cancel_flags = XFS_TRANS_RELEASE_LOG_RES;
-
- /*
- * We try to get the real space reservation first,
- * allowing for directory btree deletion(s) implying
- * possible bmap insert(s). If we can't get the space
- * reservation then we use 0 instead, and avoid the bmap
- * btree insert(s) in the directory code by, if the bmap
- * insert tries to happen, instead trimming the LAST
- * block from the directory.
- */
- resblks = XFS_REMOVE_SPACE_RES(mp);
- error = xfs_trans_reserve(tp, resblks, XFS_REMOVE_LOG_RES(mp), 0,
- XFS_TRANS_PERM_LOG_RES, log_count);
- if (error == ENOSPC) {
- resblks = 0;
- error = xfs_trans_reserve(tp, 0, XFS_REMOVE_LOG_RES(mp), 0,
- XFS_TRANS_PERM_LOG_RES, log_count);
- }
- if (error) {
- ASSERT(error != ENOSPC);
- cancel_flags = 0;
- goto out_trans_cancel;
- }
-
- xfs_lock_two_inodes(dp, ip, XFS_ILOCK_EXCL);
-
- xfs_trans_ijoin(tp, dp, XFS_ILOCK_EXCL);
- xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
-
- /*
- * If we're removing a directory perform some additional validation.
- */
- if (is_dir) {
- ASSERT(ip->i_d.di_nlink >= 2);
- if (ip->i_d.di_nlink != 2) {
- error = XFS_ERROR(ENOTEMPTY);
- goto out_trans_cancel;
- }
- if (!xfs_dir_isempty(ip)) {
- error = XFS_ERROR(ENOTEMPTY);
- goto out_trans_cancel;
- }
- }
-
- xfs_bmap_init(&free_list, &first_block);
- error = xfs_dir_removename(tp, dp, name, ip->i_ino,
- &first_block, &free_list, resblks);
- if (error) {
- ASSERT(error != ENOENT);
- goto out_bmap_cancel;
- }
- xfs_trans_ichgtime(tp, dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
-
- if (is_dir) {
- /*
- * Drop the link from ip's "..".
- */
- error = xfs_droplink(tp, dp);
- if (error)
- goto out_bmap_cancel;
-
- /*
- * Drop the "." link from ip to self.
- */
- error = xfs_droplink(tp, ip);
- if (error)
- goto out_bmap_cancel;
- } else {
- /*
- * When removing a non-directory we need to log the parent
- * inode here. For a directory this is done implicitly
- * by the xfs_droplink call for the ".." entry.
- */
- xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE);
- }
-
- /*
- * Drop the link from dp to ip.
- */
- error = xfs_droplink(tp, ip);
- if (error)
- goto out_bmap_cancel;
-
- /*
- * Determine if this is the last link while
- * we are in the transaction.
- */
- link_zero = (ip->i_d.di_nlink == 0);
-
- /*
- * If this is a synchronous mount, make sure that the
- * remove transaction goes to disk before returning to
- * the user.
- */
- if (mp->m_flags & (XFS_MOUNT_WSYNC|XFS_MOUNT_DIRSYNC))
- xfs_trans_set_sync(tp);
-
- error = xfs_bmap_finish(&tp, &free_list, &committed);
- if (error)
- goto out_bmap_cancel;
-
- error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
- if (error)
- goto std_return;
-
- /*
- * If we are using filestreams, kill the stream association.
- * If the file is still open it may get a new one but that
- * will get killed on last close in xfs_close() so we don't
- * have to worry about that.
- */
- if (!is_dir && link_zero && xfs_inode_is_filestream(ip))
- xfs_filestream_deassociate(ip);
-
- return 0;
-
- out_bmap_cancel:
- xfs_bmap_cancel(&free_list);
- cancel_flags |= XFS_TRANS_ABORT;
- out_trans_cancel:
- xfs_trans_cancel(tp, cancel_flags);
- std_return:
- return error;
-}
-
-int
-xfs_link(
- xfs_inode_t *tdp,
- xfs_inode_t *sip,
- struct xfs_name *target_name)
-{
- xfs_mount_t *mp = tdp->i_mount;
- xfs_trans_t *tp;
- int error;
- xfs_bmap_free_t free_list;
- xfs_fsblock_t first_block;
- int cancel_flags;
- int committed;
- int resblks;
-
- trace_xfs_link(tdp, target_name);
-
- ASSERT(!S_ISDIR(sip->i_d.di_mode));
-
- if (XFS_FORCED_SHUTDOWN(mp))
- return XFS_ERROR(EIO);
-
- error = xfs_qm_dqattach(sip, 0);
- if (error)
- goto std_return;
-
- error = xfs_qm_dqattach(tdp, 0);
- if (error)
- goto std_return;
-
- tp = xfs_trans_alloc(mp, XFS_TRANS_LINK);
- cancel_flags = XFS_TRANS_RELEASE_LOG_RES;
- resblks = XFS_LINK_SPACE_RES(mp, target_name->len);
- error = xfs_trans_reserve(tp, resblks, XFS_LINK_LOG_RES(mp), 0,
- XFS_TRANS_PERM_LOG_RES, XFS_LINK_LOG_COUNT);
- if (error == ENOSPC) {
- resblks = 0;
- error = xfs_trans_reserve(tp, 0, XFS_LINK_LOG_RES(mp), 0,
- XFS_TRANS_PERM_LOG_RES, XFS_LINK_LOG_COUNT);
- }
- if (error) {
- cancel_flags = 0;
- goto error_return;
- }
-
- xfs_lock_two_inodes(sip, tdp, XFS_ILOCK_EXCL);
-
- xfs_trans_ijoin(tp, sip, XFS_ILOCK_EXCL);
- xfs_trans_ijoin(tp, tdp, XFS_ILOCK_EXCL);
-
- /*
- * If we are using project inheritance, we only allow hard link
- * creation in our tree when the project IDs are the same; else
- * the tree quota mechanism could be circumvented.
- */
- if (unlikely((tdp->i_d.di_flags & XFS_DIFLAG_PROJINHERIT) &&
- (xfs_get_projid(tdp) != xfs_get_projid(sip)))) {
- error = XFS_ERROR(EXDEV);
- goto error_return;
- }
-
- error = xfs_dir_canenter(tp, tdp, target_name, resblks);
- if (error)
- goto error_return;
-
- xfs_bmap_init(&free_list, &first_block);
-
- error = xfs_dir_createname(tp, tdp, target_name, sip->i_ino,
- &first_block, &free_list, resblks);
- if (error)
- goto abort_return;
- xfs_trans_ichgtime(tp, tdp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
- xfs_trans_log_inode(tp, tdp, XFS_ILOG_CORE);
-
- error = xfs_bumplink(tp, sip);
- if (error)
- goto abort_return;
-
- /*
- * If this is a synchronous mount, make sure that the
- * link transaction goes to disk before returning to
- * the user.
- */
- if (mp->m_flags & (XFS_MOUNT_WSYNC|XFS_MOUNT_DIRSYNC)) {
- xfs_trans_set_sync(tp);
- }
-
- error = xfs_bmap_finish (&tp, &free_list, &committed);
- if (error) {
- xfs_bmap_cancel(&free_list);
- goto abort_return;
- }
-
- return xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
-
- abort_return:
- cancel_flags |= XFS_TRANS_ABORT;
- error_return:
- xfs_trans_cancel(tp, cancel_flags);
- std_return:
- return error;
-}
-
-int
-xfs_set_dmattrs(
- xfs_inode_t *ip,
- u_int evmask,
- u_int16_t state)
-{
- xfs_mount_t *mp = ip->i_mount;
- xfs_trans_t *tp;
- int error;
-
- if (!capable(CAP_SYS_ADMIN))
- return XFS_ERROR(EPERM);
-
- if (XFS_FORCED_SHUTDOWN(mp))
- return XFS_ERROR(EIO);
-
- tp = xfs_trans_alloc(mp, XFS_TRANS_SET_DMATTRS);
- error = xfs_trans_reserve(tp, 0, XFS_ICHANGE_LOG_RES (mp), 0, 0, 0);
- if (error) {
- xfs_trans_cancel(tp, 0);
- return error;
- }
- xfs_ilock(ip, XFS_ILOCK_EXCL);
- xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
-
- ip->i_d.di_dmevmask = evmask;
- ip->i_d.di_dmstate = state;
-
- xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
- error = xfs_trans_commit(tp, 0);
-
- return error;
-}
-
-/*
- * xfs_alloc_file_space()
- * This routine allocates disk space for the given file.
- *
- * If alloc_type == 0, this request is for an ALLOCSP type
- * request which will change the file size. In this case, no
- * DMAPI event will be generated by the call. A TRUNCATE event
- * will be generated later by xfs_setattr.
- *
- * If alloc_type != 0, this request is for a RESVSP type
- * request, and a DMAPI DM_EVENT_WRITE will be generated if the
- * lower block boundary byte address is less than the file's
- * length.
- *
- * RETURNS:
- * 0 on success
- * errno on error
- *
- */
-STATIC int
-xfs_alloc_file_space(
- xfs_inode_t *ip,
- xfs_off_t offset,
- xfs_off_t len,
- int alloc_type,
- int attr_flags)
-{
- xfs_mount_t *mp = ip->i_mount;
- xfs_off_t count;
- xfs_filblks_t allocated_fsb;
- xfs_filblks_t allocatesize_fsb;
- xfs_extlen_t extsz, temp;
- xfs_fileoff_t startoffset_fsb;
- xfs_fsblock_t firstfsb;
- int nimaps;
- int quota_flag;
- int rt;
- xfs_trans_t *tp;
- xfs_bmbt_irec_t imaps[1], *imapp;
- xfs_bmap_free_t free_list;
- uint qblocks, resblks, resrtextents;
- int committed;
- int error;
-
- trace_xfs_alloc_file_space(ip);
-
- if (XFS_FORCED_SHUTDOWN(mp))
- return XFS_ERROR(EIO);
-
- error = xfs_qm_dqattach(ip, 0);
- if (error)
- return error;
-
- if (len <= 0)
- return XFS_ERROR(EINVAL);
-
- rt = XFS_IS_REALTIME_INODE(ip);
- extsz = xfs_get_extsz_hint(ip);
-
- count = len;
- imapp = &imaps[0];
- nimaps = 1;
- startoffset_fsb = XFS_B_TO_FSBT(mp, offset);
- allocatesize_fsb = XFS_B_TO_FSB(mp, count);
-
- /*
- * Allocate file space until done or until there is an error
- */
- while (allocatesize_fsb && !error) {
- xfs_fileoff_t s, e;
-
- /*
- * Determine space reservations for data/realtime.
- */
- if (unlikely(extsz)) {
- s = startoffset_fsb;
- do_div(s, extsz);
- s *= extsz;
- e = startoffset_fsb + allocatesize_fsb;
- if ((temp = do_mod(startoffset_fsb, extsz)))
- e += temp;
- if ((temp = do_mod(e, extsz)))
- e += extsz - temp;
- } else {
- s = 0;
- e = allocatesize_fsb;
- }
-
- /*
- * The transaction reservation is limited to a 32-bit block
- * count, hence we need to limit the number of blocks we are
- * trying to reserve to avoid an overflow. We can't allocate
- * more than @nimaps extents, and an extent is limited on disk
- * to MAXEXTLEN (21 bits), so use that to enforce the limit.
- */
- resblks = min_t(xfs_fileoff_t, (e - s), (MAXEXTLEN * nimaps));
- if (unlikely(rt)) {
- resrtextents = qblocks = resblks;
- resrtextents /= mp->m_sb.sb_rextsize;
- resblks = XFS_DIOSTRAT_SPACE_RES(mp, 0);
- quota_flag = XFS_QMOPT_RES_RTBLKS;
- } else {
- resrtextents = 0;
- resblks = qblocks = XFS_DIOSTRAT_SPACE_RES(mp, resblks);
- quota_flag = XFS_QMOPT_RES_REGBLKS;
- }
-
- /*
- * Allocate and setup the transaction.
- */
- tp = xfs_trans_alloc(mp, XFS_TRANS_DIOSTRAT);
- error = xfs_trans_reserve(tp, resblks,
- XFS_WRITE_LOG_RES(mp), resrtextents,
- XFS_TRANS_PERM_LOG_RES,
- XFS_WRITE_LOG_COUNT);
- /*
- * Check for running out of space
- */
- if (error) {
- /*
- * Free the transaction structure.
- */
- ASSERT(error == ENOSPC || XFS_FORCED_SHUTDOWN(mp));
- xfs_trans_cancel(tp, 0);
- break;
- }
- xfs_ilock(ip, XFS_ILOCK_EXCL);
- error = xfs_trans_reserve_quota_nblks(tp, ip, qblocks,
- 0, quota_flag);
- if (error)
- goto error1;
-
- xfs_trans_ijoin(tp, ip, 0);
-
- xfs_bmap_init(&free_list, &firstfsb);
- error = xfs_bmapi_write(tp, ip, startoffset_fsb,
- allocatesize_fsb, alloc_type, &firstfsb,
- 0, imapp, &nimaps, &free_list);
- if (error) {
- goto error0;
- }
-
- /*
- * Complete the transaction
- */
- error = xfs_bmap_finish(&tp, &free_list, &committed);
- if (error) {
- goto error0;
- }
-
- error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
- xfs_iunlock(ip, XFS_ILOCK_EXCL);
- if (error) {
- break;
- }
-
- allocated_fsb = imapp->br_blockcount;
-
- if (nimaps == 0) {
- error = XFS_ERROR(ENOSPC);
- break;
- }
-
- startoffset_fsb += allocated_fsb;
- allocatesize_fsb -= allocated_fsb;
- }
-
- return error;
-
-error0: /* Cancel bmap, unlock inode, unreserve quota blocks, cancel trans */
- xfs_bmap_cancel(&free_list);
- xfs_trans_unreserve_quota_nblks(tp, ip, (long)qblocks, 0, quota_flag);
-
-error1: /* Just cancel transaction */
- xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT);
- xfs_iunlock(ip, XFS_ILOCK_EXCL);
- return error;
-}
-
-/*
- * Zero file bytes between startoff and endoff inclusive.
- * The iolock is held exclusive and no blocks are buffered.
- *
- * This function is used by xfs_free_file_space() to zero
- * partial blocks when the range to free is not block aligned.
- * When unreserving space with boundaries that are not block
- * aligned we round up the start and round down the end
- * boundaries and then use this function to zero the parts of
- * the blocks that got dropped during the rounding.
- */
-STATIC int
-xfs_zero_remaining_bytes(
- xfs_inode_t *ip,
- xfs_off_t startoff,
- xfs_off_t endoff)
-{
- xfs_bmbt_irec_t imap;
- xfs_fileoff_t offset_fsb;
- xfs_off_t lastoffset;
- xfs_off_t offset;
- xfs_buf_t *bp;
- xfs_mount_t *mp = ip->i_mount;
- int nimap;
- int error = 0;
-
- /*
- * Avoid doing I/O beyond eof - it's not necessary
- * since nothing can read beyond eof. The space will
- * be zeroed when the file is extended anyway.
- */
- if (startoff >= XFS_ISIZE(ip))
- return 0;
-
- if (endoff > XFS_ISIZE(ip))
- endoff = XFS_ISIZE(ip);
-
- bp = xfs_buf_get_uncached(XFS_IS_REALTIME_INODE(ip) ?
- mp->m_rtdev_targp : mp->m_ddev_targp,
- BTOBB(mp->m_sb.sb_blocksize), 0);
- if (!bp)
- return XFS_ERROR(ENOMEM);
-
- xfs_buf_unlock(bp);
-
- for (offset = startoff; offset <= endoff; offset = lastoffset + 1) {
- offset_fsb = XFS_B_TO_FSBT(mp, offset);
- nimap = 1;
- error = xfs_bmapi_read(ip, offset_fsb, 1, &imap, &nimap, 0);
- if (error || nimap < 1)
- break;
- ASSERT(imap.br_blockcount >= 1);
- ASSERT(imap.br_startoff == offset_fsb);
- lastoffset = XFS_FSB_TO_B(mp, imap.br_startoff + 1) - 1;
- if (lastoffset > endoff)
- lastoffset = endoff;
- if (imap.br_startblock == HOLESTARTBLOCK)
- continue;
- ASSERT(imap.br_startblock != DELAYSTARTBLOCK);
- if (imap.br_state == XFS_EXT_UNWRITTEN)
- continue;
- XFS_BUF_UNDONE(bp);
- XFS_BUF_UNWRITE(bp);
- XFS_BUF_READ(bp);
- XFS_BUF_SET_ADDR(bp, xfs_fsb_to_db(ip, imap.br_startblock));
- xfsbdstrat(mp, bp);
- error = xfs_buf_iowait(bp);
- if (error) {
- xfs_buf_ioerror_alert(bp,
- "xfs_zero_remaining_bytes(read)");
- break;
- }
- memset(bp->b_addr +
- (offset - XFS_FSB_TO_B(mp, imap.br_startoff)),
- 0, lastoffset - offset + 1);
- XFS_BUF_UNDONE(bp);
- XFS_BUF_UNREAD(bp);
- XFS_BUF_WRITE(bp);
- xfsbdstrat(mp, bp);
- error = xfs_buf_iowait(bp);
- if (error) {
- xfs_buf_ioerror_alert(bp,
- "xfs_zero_remaining_bytes(write)");
- break;
- }
- }
- xfs_buf_free(bp);
- return error;
-}
-
-/*
- * xfs_free_file_space()
- * This routine frees disk space for the given file.
- *
- * This routine is only called by xfs_change_file_space
- * for an UNRESVSP type call.
- *
- * RETURNS:
- * 0 on success
- * errno on error
- *
- */
-STATIC int
-xfs_free_file_space(
- xfs_inode_t *ip,
- xfs_off_t offset,
- xfs_off_t len,
- int attr_flags)
-{
- int committed;
- int done;
- xfs_fileoff_t endoffset_fsb;
- int error;
- xfs_fsblock_t firstfsb;
- xfs_bmap_free_t free_list;
- xfs_bmbt_irec_t imap;
- xfs_off_t ioffset;
- xfs_extlen_t mod=0;
- xfs_mount_t *mp;
- int nimap;
- uint resblks;
- xfs_off_t rounding;
- int rt;
- xfs_fileoff_t startoffset_fsb;
- xfs_trans_t *tp;
- int need_iolock = 1;
-
- mp = ip->i_mount;
-
- trace_xfs_free_file_space(ip);
-
- error = xfs_qm_dqattach(ip, 0);
- if (error)
- return error;
-
- error = 0;
- if (len <= 0) /* if nothing being freed */
- return error;
- rt = XFS_IS_REALTIME_INODE(ip);
- startoffset_fsb = XFS_B_TO_FSB(mp, offset);
- endoffset_fsb = XFS_B_TO_FSBT(mp, offset + len);
-
- if (attr_flags & XFS_ATTR_NOLOCK)
- need_iolock = 0;
- if (need_iolock) {
- xfs_ilock(ip, XFS_IOLOCK_EXCL);
- /* wait for the completion of any pending DIOs */
- inode_dio_wait(VFS_I(ip));
- }
-
- rounding = max_t(xfs_off_t, 1 << mp->m_sb.sb_blocklog, PAGE_CACHE_SIZE);
- ioffset = offset & ~(rounding - 1);
- error = -filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
- ioffset, -1);
- if (error)
- goto out_unlock_iolock;
- truncate_pagecache_range(VFS_I(ip), ioffset, -1);
-
- /*
- * Need to zero the stuff we're not freeing, on disk.
- * If it's a realtime file & can't use unwritten extents then we
- * actually need to zero the extent edges. Otherwise xfs_bunmapi
- * will take care of it for us.
- */
- if (rt && !xfs_sb_version_hasextflgbit(&mp->m_sb)) {
- nimap = 1;
- error = xfs_bmapi_read(ip, startoffset_fsb, 1,
- &imap, &nimap, 0);
- if (error)
- goto out_unlock_iolock;
- ASSERT(nimap == 0 || nimap == 1);
- 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);
- if (mod)
- startoffset_fsb += mp->m_sb.sb_rextsize - mod;
- }
- nimap = 1;
- error = xfs_bmapi_read(ip, endoffset_fsb - 1, 1,
- &imap, &nimap, 0);
- if (error)
- goto out_unlock_iolock;
- ASSERT(nimap == 0 || nimap == 1);
- if (nimap && imap.br_startblock != HOLESTARTBLOCK) {
- ASSERT(imap.br_startblock != DELAYSTARTBLOCK);
- mod++;
- if (mod && (mod != mp->m_sb.sb_rextsize))
- endoffset_fsb -= mod;
- }
- }
- if ((done = (endoffset_fsb <= startoffset_fsb)))
- /*
- * One contiguous piece to clear
- */
- error = xfs_zero_remaining_bytes(ip, offset, offset + len - 1);
- else {
- /*
- * Some full blocks, possibly two pieces to clear
- */
- if (offset < XFS_FSB_TO_B(mp, startoffset_fsb))
- error = xfs_zero_remaining_bytes(ip, offset,
- XFS_FSB_TO_B(mp, startoffset_fsb) - 1);
- if (!error &&
- XFS_FSB_TO_B(mp, endoffset_fsb) < offset + len)
- error = xfs_zero_remaining_bytes(ip,
- XFS_FSB_TO_B(mp, endoffset_fsb),
- offset + len - 1);
- }
-
- /*
- * free file space until done or until there is an error
- */
- resblks = XFS_DIOSTRAT_SPACE_RES(mp, 0);
- while (!error && !done) {
-
- /*
- * allocate and setup the transaction. Allow this
- * transaction to dip into the reserve blocks to ensure
- * the freeing of the space succeeds at ENOSPC.
- */
- tp = xfs_trans_alloc(mp, XFS_TRANS_DIOSTRAT);
- tp->t_flags |= XFS_TRANS_RESERVE;
- error = xfs_trans_reserve(tp,
- resblks,
- XFS_WRITE_LOG_RES(mp),
- 0,
- XFS_TRANS_PERM_LOG_RES,
- XFS_WRITE_LOG_COUNT);
-
- /*
- * check for running out of space
- */
- if (error) {
- /*
- * Free the transaction structure.
- */
- ASSERT(error == ENOSPC || XFS_FORCED_SHUTDOWN(mp));
- xfs_trans_cancel(tp, 0);
- break;
- }
- xfs_ilock(ip, XFS_ILOCK_EXCL);
- error = xfs_trans_reserve_quota(tp, mp,
- ip->i_udquot, ip->i_gdquot, ip->i_pdquot,
- resblks, 0, XFS_QMOPT_RES_REGBLKS);
- if (error)
- goto error1;
-
- xfs_trans_ijoin(tp, ip, 0);
-
- /*
- * issue the bunmapi() call to free the blocks
- */
- xfs_bmap_init(&free_list, &firstfsb);
- error = xfs_bunmapi(tp, ip, startoffset_fsb,
- endoffset_fsb - startoffset_fsb,
- 0, 2, &firstfsb, &free_list, &done);
- if (error) {
- goto error0;
- }
-
- /*
- * complete the transaction
- */
- error = xfs_bmap_finish(&tp, &free_list, &committed);
- if (error) {
- goto error0;
- }
-
- error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
- xfs_iunlock(ip, XFS_ILOCK_EXCL);
- }
-
- out_unlock_iolock:
- if (need_iolock)
- xfs_iunlock(ip, XFS_IOLOCK_EXCL);
- return error;
-
- error0:
- xfs_bmap_cancel(&free_list);
- error1:
- xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT);
- xfs_iunlock(ip, need_iolock ? (XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL) :
- XFS_ILOCK_EXCL);
- return error;
-}
-
-
-STATIC int
-xfs_zero_file_space(
- struct xfs_inode *ip,
- xfs_off_t offset,
- xfs_off_t len,
- int attr_flags)
-{
- struct xfs_mount *mp = ip->i_mount;
- uint granularity;
- xfs_off_t start_boundary;
- xfs_off_t end_boundary;
- int error;
-
- granularity = max_t(uint, 1 << mp->m_sb.sb_blocklog, PAGE_CACHE_SIZE);
-
- /*
- * Round the range of extents we are going to convert inwards. If the
- * offset is aligned, then it doesn't get changed so we zero from the
- * start of the block offset points to.
- */
- start_boundary = round_up(offset, granularity);
- end_boundary = round_down(offset + len, granularity);
-
- ASSERT(start_boundary >= offset);
- ASSERT(end_boundary <= offset + len);
-
- if (!(attr_flags & XFS_ATTR_NOLOCK))
- xfs_ilock(ip, XFS_IOLOCK_EXCL);
-
- if (start_boundary < end_boundary - 1) {
- /* punch out the page cache over the conversion range */
- truncate_pagecache_range(VFS_I(ip), start_boundary,
- end_boundary - 1);
- /* convert the blocks */
- error = xfs_alloc_file_space(ip, start_boundary,
- end_boundary - start_boundary - 1,
- XFS_BMAPI_PREALLOC | XFS_BMAPI_CONVERT,
- attr_flags);
- if (error)
- goto out_unlock;
-
- /* We've handled the interior of the range, now for the edges */
- if (start_boundary != offset)
- error = xfs_iozero(ip, offset, start_boundary - offset);
- if (error)
- goto out_unlock;
-
- if (end_boundary != offset + len)
- error = xfs_iozero(ip, end_boundary,
- offset + len - end_boundary);
-
- } else {
- /*
- * It's either a sub-granularity range or the range spanned lies
- * partially across two adjacent blocks.
- */
- error = xfs_iozero(ip, offset, len);
- }
-
-out_unlock:
- if (!(attr_flags & XFS_ATTR_NOLOCK))
- xfs_iunlock(ip, XFS_IOLOCK_EXCL);
- return error;
-
-}
-
-/*
- * xfs_change_file_space()
- * This routine allocates or frees disk space for the given file.
- * The user specified parameters are checked for alignment and size
- * limitations.
- *
- * RETURNS:
- * 0 on success
- * errno on error
- *
- */
-int
-xfs_change_file_space(
- xfs_inode_t *ip,
- int cmd,
- xfs_flock64_t *bf,
- xfs_off_t offset,
- int attr_flags)
-{
- xfs_mount_t *mp = ip->i_mount;
- int clrprealloc;
- int error;
- xfs_fsize_t fsize;
- int setprealloc;
- xfs_off_t startoffset;
- xfs_trans_t *tp;
- struct iattr iattr;
-
- if (!S_ISREG(ip->i_d.di_mode))
- return XFS_ERROR(EINVAL);
-
- switch (bf->l_whence) {
- case 0: /*SEEK_SET*/
- break;
- case 1: /*SEEK_CUR*/
- bf->l_start += offset;
- break;
- case 2: /*SEEK_END*/
- bf->l_start += XFS_ISIZE(ip);
- break;
- default:
- return XFS_ERROR(EINVAL);
- }
-
- /*
- * length of <= 0 for resv/unresv/zero is invalid. length for
- * alloc/free is ignored completely and we have no idea what userspace
- * might have set it to, so set it to zero to allow range
- * checks to pass.
- */
- switch (cmd) {
- case XFS_IOC_ZERO_RANGE:
- case XFS_IOC_RESVSP:
- case XFS_IOC_RESVSP64:
- case XFS_IOC_UNRESVSP:
- case XFS_IOC_UNRESVSP64:
- if (bf->l_len <= 0)
- return XFS_ERROR(EINVAL);
- break;
- default:
- bf->l_len = 0;
- break;
- }
-
- if (bf->l_start < 0 ||
- bf->l_start > mp->m_super->s_maxbytes ||
- bf->l_start + bf->l_len < 0 ||
- bf->l_start + bf->l_len >= mp->m_super->s_maxbytes)
- return XFS_ERROR(EINVAL);
-
- bf->l_whence = 0;
-
- startoffset = bf->l_start;
- fsize = XFS_ISIZE(ip);
-
- setprealloc = clrprealloc = 0;
- switch (cmd) {
- case XFS_IOC_ZERO_RANGE:
- error = xfs_zero_file_space(ip, startoffset, bf->l_len,
- attr_flags);
- if (error)
- return error;
- setprealloc = 1;
- break;
-
- case XFS_IOC_RESVSP:
- case XFS_IOC_RESVSP64:
- error = xfs_alloc_file_space(ip, startoffset, bf->l_len,
- XFS_BMAPI_PREALLOC, attr_flags);
- if (error)
- return error;
- setprealloc = 1;
- break;
-
- case XFS_IOC_UNRESVSP:
- case XFS_IOC_UNRESVSP64:
- if ((error = xfs_free_file_space(ip, startoffset, bf->l_len,
- attr_flags)))
- return error;
- break;
-
- case XFS_IOC_ALLOCSP:
- case XFS_IOC_ALLOCSP64:
- case XFS_IOC_FREESP:
- case XFS_IOC_FREESP64:
- /*
- * These operations actually do IO when extending the file, but
- * the allocation is done seperately to the zeroing that is
- * done. This set of operations need to be serialised against
- * other IO operations, such as truncate and buffered IO. We
- * need to take the IOLOCK here to serialise the allocation and
- * zeroing IO to prevent other IOLOCK holders (e.g. getbmap,
- * truncate, direct IO) from racing against the transient
- * allocated but not written state we can have here.
- */
- xfs_ilock(ip, XFS_IOLOCK_EXCL);
- if (startoffset > fsize) {
- error = xfs_alloc_file_space(ip, fsize,
- startoffset - fsize, 0,
- attr_flags | XFS_ATTR_NOLOCK);
- if (error) {
- xfs_iunlock(ip, XFS_IOLOCK_EXCL);
- break;
- }
- }
-
- iattr.ia_valid = ATTR_SIZE;
- iattr.ia_size = startoffset;
-
- error = xfs_setattr_size(ip, &iattr,
- attr_flags | XFS_ATTR_NOLOCK);
- xfs_iunlock(ip, XFS_IOLOCK_EXCL);
-
- if (error)
- return error;
-
- clrprealloc = 1;
- break;
-
- default:
- ASSERT(0);
- return XFS_ERROR(EINVAL);
- }
-
- /*
- * update the inode timestamp, mode, and prealloc flag bits
- */
- tp = xfs_trans_alloc(mp, XFS_TRANS_WRITEID);
-
- if ((error = xfs_trans_reserve(tp, 0, XFS_WRITEID_LOG_RES(mp),
- 0, 0, 0))) {
- /* ASSERT(0); */
- xfs_trans_cancel(tp, 0);
- return error;
- }
-
- xfs_ilock(ip, XFS_ILOCK_EXCL);
- xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
-
- if ((attr_flags & XFS_ATTR_DMI) == 0) {
- ip->i_d.di_mode &= ~S_ISUID;
-
- /*
- * Note that we don't have to worry about mandatory
- * file locking being disabled here because we only
- * clear the S_ISGID bit if the Group execute bit is
- * on, but if it was on then mandatory locking wouldn't
- * have been enabled.
- */
- if (ip->i_d.di_mode & S_IXGRP)
- ip->i_d.di_mode &= ~S_ISGID;
-
- xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
- }
- if (setprealloc)
- ip->i_d.di_flags |= XFS_DIFLAG_PREALLOC;
- else if (clrprealloc)
- ip->i_d.di_flags &= ~XFS_DIFLAG_PREALLOC;
-
- xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
- if (attr_flags & XFS_ATTR_SYNC)
- xfs_trans_set_sync(tp);
- return xfs_trans_commit(tp, 0);
-}
diff --git a/fs/xfs/xfs_vnodeops.h b/fs/xfs/xfs_vnodeops.h
deleted file mode 100644
index 38c67c34d73f..000000000000
--- a/fs/xfs/xfs_vnodeops.h
+++ /dev/null
@@ -1,55 +0,0 @@
-#ifndef _XFS_VNODEOPS_H
-#define _XFS_VNODEOPS_H 1
-
-struct attrlist_cursor_kern;
-struct file;
-struct iattr;
-struct inode;
-struct iovec;
-struct kiocb;
-struct pipe_inode_info;
-struct uio;
-struct xfs_inode;
-
-
-int xfs_setattr_nonsize(struct xfs_inode *ip, struct iattr *vap, int flags);
-int xfs_setattr_size(struct xfs_inode *ip, struct iattr *vap, int flags);
-#define XFS_ATTR_DMI 0x01 /* invocation from a DMI function */
-#define XFS_ATTR_NONBLOCK 0x02 /* return EAGAIN if operation would block */
-#define XFS_ATTR_NOLOCK 0x04 /* Don't grab any conflicting locks */
-#define XFS_ATTR_NOACL 0x08 /* Don't call xfs_acl_chmod */
-#define XFS_ATTR_SYNC 0x10 /* synchronous operation required */
-
-int xfs_readlink(struct xfs_inode *ip, char *link);
-int xfs_release(struct xfs_inode *ip);
-int xfs_inactive(struct xfs_inode *ip);
-int xfs_lookup(struct xfs_inode *dp, struct xfs_name *name,
- struct xfs_inode **ipp, struct xfs_name *ci_name);
-int xfs_create(struct xfs_inode *dp, struct xfs_name *name, umode_t mode,
- xfs_dev_t rdev, struct xfs_inode **ipp);
-int xfs_remove(struct xfs_inode *dp, struct xfs_name *name,
- struct xfs_inode *ip);
-int xfs_link(struct xfs_inode *tdp, struct xfs_inode *sip,
- struct xfs_name *target_name);
-int xfs_readdir(struct xfs_inode *dp, struct dir_context *ctx, size_t bufsize);
-int xfs_symlink(struct xfs_inode *dp, struct xfs_name *link_name,
- const char *target_path, umode_t mode, struct xfs_inode **ipp);
-int xfs_set_dmattrs(struct xfs_inode *ip, u_int evmask, u_int16_t state);
-int xfs_change_file_space(struct xfs_inode *ip, int cmd,
- xfs_flock64_t *bf, xfs_off_t offset, int attr_flags);
-int xfs_rename(struct xfs_inode *src_dp, struct xfs_name *src_name,
- struct xfs_inode *src_ip, struct xfs_inode *target_dp,
- struct xfs_name *target_name, struct xfs_inode *target_ip);
-int xfs_attr_get(struct xfs_inode *ip, const unsigned char *name,
- unsigned char *value, int *valuelenp, int flags);
-int xfs_attr_set(struct xfs_inode *dp, const unsigned char *name,
- unsigned char *value, int valuelen, int flags);
-int xfs_attr_remove(struct xfs_inode *dp, const unsigned char *name, int flags);
-int xfs_attr_list(struct xfs_inode *dp, char *buffer, int bufsize,
- int flags, struct attrlist_cursor_kern *cursor);
-
-int xfs_iozero(struct xfs_inode *, loff_t, size_t);
-int xfs_zero_eof(struct xfs_inode *, xfs_off_t, xfs_fsize_t);
-int xfs_free_eofblocks(struct xfs_mount *, struct xfs_inode *, bool);
-
-#endif /* _XFS_VNODEOPS_H */
diff --git a/fs/xfs/xfs_xattr.c b/fs/xfs/xfs_xattr.c
index b7311aaa5f0e..e01f35ea76ba 100644
--- a/fs/xfs/xfs_xattr.c
+++ b/fs/xfs/xfs_xattr.c
@@ -24,7 +24,6 @@
#include "xfs_attr.h"
#include "xfs_attr_leaf.h"
#include "xfs_acl.h"
-#include "xfs_vnodeops.h"
#include <linux/posix_acl_xattr.h>
#include <linux/xattr.h>