1 files changed, 278 insertions, 1 deletions

diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 279ac3fdfde5..e83d3af3dfd4 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -46,7 +46,6 @@
 #include "xfs_bmap.h"
 #include "xfs_bmap_util.h"
 #include "xfs_error.h"
-#include "xfs_utils.h"
 #include "xfs_quota.h"
 #include "xfs_filestream.h"
 #include "xfs_cksum.h"
@@ -862,6 +861,284 @@ xfs_ialloc(
 	return 0;
 }
 
+/*
+ * Allocates a new inode from disk and return a pointer to the
+ * incore copy. This routine will internally commit the current
+ * transaction and allocate a new one if the Space Manager needed
+ * to do an allocation to replenish the inode free-list.
+ *
+ * This routine is designed to be called from xfs_create and
+ * xfs_create_dir.
+ *
+ */
+int
+xfs_dir_ialloc(
+	xfs_trans_t	**tpp,		/* input: current transaction;
+					   output: may be a new transaction. */
+	xfs_inode_t	*dp,		/* directory within whose allocate
+					   the inode. */
+	umode_t		mode,
+	xfs_nlink_t	nlink,
+	xfs_dev_t	rdev,
+	prid_t		prid,		/* project id */
+	int		okalloc,	/* ok to allocate new space */
+	xfs_inode_t	**ipp,		/* pointer to inode; it will be
+					   locked. */
+	int		*committed)
+
+{
+	xfs_trans_t	*tp;
+	xfs_trans_t	*ntp;
+	xfs_inode_t	*ip;
+	xfs_buf_t	*ialloc_context = NULL;
+	int		code;
+	uint		log_res;
+	uint		log_count;
+	void		*dqinfo;
+	uint		tflags;
+
+	tp = *tpp;
+	ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);
+
+	/*
+	 * xfs_ialloc will return a pointer to an incore inode if
+	 * the Space Manager has an available inode on the free
+	 * list. Otherwise, it will do an allocation and replenish
+	 * the freelist.  Since we can only do one allocation per
+	 * transaction without deadlocks, we will need to commit the
+	 * current transaction and start a new one.  We will then
+	 * need to call xfs_ialloc again to get the inode.
+	 *
+	 * If xfs_ialloc did an allocation to replenish the freelist,
+	 * it returns the bp containing the head of the freelist as
+	 * ialloc_context. We will hold a lock on it across the
+	 * transaction commit so that no other process can steal
+	 * the inode(s) that we've just allocated.
+	 */
+	code = xfs_ialloc(tp, dp, mode, nlink, rdev, prid, okalloc,
+			  &ialloc_context, &ip);
+
+	/*
+	 * Return an error if we were unable to allocate a new inode.
+	 * This should only happen if we run out of space on disk or
+	 * encounter a disk error.
+	 */
+	if (code) {
+		*ipp = NULL;
+		return code;
+	}
+	if (!ialloc_context && !ip) {
+		*ipp = NULL;
+		return XFS_ERROR(ENOSPC);
+	}
+
+	/*
+	 * If the AGI buffer is non-NULL, then we were unable to get an
+	 * inode in one operation.  We need to commit the current
+	 * transaction and call xfs_ialloc() again.  It is guaranteed
+	 * to succeed the second time.
+	 */
+	if (ialloc_context) {
+		/*
+		 * Normally, xfs_trans_commit releases all the locks.
+		 * We call bhold to hang on to the ialloc_context across
+		 * the commit.  Holding this buffer prevents any other
+		 * processes from doing any allocations in this
+		 * allocation group.
+		 */
+		xfs_trans_bhold(tp, ialloc_context);
+		/*
+		 * Save the log reservation so we can use
+		 * them in the next transaction.
+		 */
+		log_res = xfs_trans_get_log_res(tp);
+		log_count = xfs_trans_get_log_count(tp);
+
+		/*
+		 * We want the quota changes to be associated with the next
+		 * transaction, NOT this one. So, detach the dqinfo from this
+		 * and attach it to the next transaction.
+		 */
+		dqinfo = NULL;
+		tflags = 0;
+		if (tp->t_dqinfo) {
+			dqinfo = (void *)tp->t_dqinfo;
+			tp->t_dqinfo = NULL;
+			tflags = tp->t_flags & XFS_TRANS_DQ_DIRTY;
+			tp->t_flags &= ~(XFS_TRANS_DQ_DIRTY);
+		}
+
+		ntp = xfs_trans_dup(tp);
+		code = xfs_trans_commit(tp, 0);
+		tp = ntp;
+		if (committed != NULL) {
+			*committed = 1;
+		}
+		/*
+		 * If we get an error during the commit processing,
+		 * release the buffer that is still held and return
+		 * to the caller.
+		 */
+		if (code) {
+			xfs_buf_relse(ialloc_context);
+			if (dqinfo) {
+				tp->t_dqinfo = dqinfo;
+				xfs_trans_free_dqinfo(tp);
+			}
+			*tpp = ntp;
+			*ipp = NULL;
+			return code;
+		}
+
+		/*
+		 * transaction commit worked ok so we can drop the extra ticket
+		 * reference that we gained in xfs_trans_dup()
+		 */
+		xfs_log_ticket_put(tp->t_ticket);
+		code = xfs_trans_reserve(tp, 0, log_res, 0,
+					 XFS_TRANS_PERM_LOG_RES, log_count);
+		/*
+		 * Re-attach the quota info that we detached from prev trx.
+		 */
+		if (dqinfo) {
+			tp->t_dqinfo = dqinfo;
+			tp->t_flags |= tflags;
+		}
+
+		if (code) {
+			xfs_buf_relse(ialloc_context);
+			*tpp = ntp;
+			*ipp = NULL;
+			return code;
+		}
+		xfs_trans_bjoin(tp, ialloc_context);
+
+		/*
+		 * Call ialloc again. Since we've locked out all
+		 * other allocations in this allocation group,
+		 * this call should always succeed.
+		 */
+		code = xfs_ialloc(tp, dp, mode, nlink, rdev, prid,
+				  okalloc, &ialloc_context, &ip);
+
+		/*
+		 * If we get an error at this point, return to the caller
+		 * so that the current transaction can be aborted.
+		 */
+		if (code) {
+			*tpp = tp;
+			*ipp = NULL;
+			return code;
+		}
+		ASSERT(!ialloc_context && ip);
+
+	} else {
+		if (committed != NULL)
+			*committed = 0;
+	}
+
+	*ipp = ip;
+	*tpp = tp;
+
+	return 0;
+}
+
+/*
+ * Decrement the link count on an inode & log the change.
+ * If this causes the link count to go to zero, initiate the
+ * logging activity required to truncate a file.
+ */
+int				/* error */
+xfs_droplink(
+	xfs_trans_t *tp,
+	xfs_inode_t *ip)
+{
+	int	error;
+
+	xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG);
+
+	ASSERT (ip->i_d.di_nlink > 0);
+	ip->i_d.di_nlink--;
+	drop_nlink(VFS_I(ip));
+	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+
+	error = 0;
+	if (ip->i_d.di_nlink == 0) {
+		/*
+		 * We're dropping the last link to this file.
+		 * Move the on-disk inode to the AGI unlinked list.
+		 * From xfs_inactive() we will pull the inode from
+		 * the list and free it.
+		 */
+		error = xfs_iunlink(tp, ip);
+	}
+	return error;
+}
+
+/*
+ * This gets called when the inode's version needs to be changed from 1 to 2.
+ * Currently this happens when the nlink field overflows the old 16-bit value
+ * or when chproj is called to change the project for the first time.
+ * As a side effect the superblock version will also get rev'd
+ * to contain the NLINK bit.
+ */
+void
+xfs_bump_ino_vers2(
+	xfs_trans_t	*tp,
+	xfs_inode_t	*ip)
+{
+	xfs_mount_t	*mp;
+
+	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
+	ASSERT(ip->i_d.di_version == 1);
+
+	ip->i_d.di_version = 2;
+	ip->i_d.di_onlink = 0;
+	memset(&(ip->i_d.di_pad[0]), 0, sizeof(ip->i_d.di_pad));
+	mp = tp->t_mountp;
+	if (!xfs_sb_version_hasnlink(&mp->m_sb)) {
+		spin_lock(&mp->m_sb_lock);
+		if (!xfs_sb_version_hasnlink(&mp->m_sb)) {
+			xfs_sb_version_addnlink(&mp->m_sb);
+			spin_unlock(&mp->m_sb_lock);
+			xfs_mod_sb(tp, XFS_SB_VERSIONNUM);
+		} else {
+			spin_unlock(&mp->m_sb_lock);
+		}
+	}
+	/* Caller must log the inode */
+}
+
+/*
+ * Increment the link count on an inode & log the change.
+ */
+int
+xfs_bumplink(
+	xfs_trans_t *tp,
+	xfs_inode_t *ip)
+{
+	xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG);
+
+	ASSERT(ip->i_d.di_nlink > 0);
+	ip->i_d.di_nlink++;
+	inc_nlink(VFS_I(ip));
+	if ((ip->i_d.di_version == 1) &&
+	    (ip->i_d.di_nlink > XFS_MAXLINK_1)) {
+		/*
+		 * The inode has increased its number of links beyond
+		 * what can fit in an old format inode.  It now needs
+		 * to be converted to a version 2 inode with a 32 bit
+		 * link count.  If this is the first inode in the file
+		 * system to do this, then we need to bump the superblock
+		 * version number as well.
+		 */
+		xfs_bump_ino_vers2(tp, ip);
+	}
+
+	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+	return 0;
+}
+
 int
 xfs_create(
 	xfs_inode_t		*dp,