Merge branch 'for-linus' of git://oss.sgi.com:8090/xfs/xfs-2.6

* 'for-linus' of git://oss.sgi.com:8090/xfs/xfs-2.6: (87 commits)
  [XFS] Fix merge failure
  [XFS] The forward declarations for the xfs_ioctl() helpers and the
  [XFS] Update XFS documentation for noikeep/ikeep.
  [XFS] Update XFS Documentation for ikeep and ihashsize
  [XFS] Remove unused HAVE_SPLICE macro.
  [XFS] Remove CONFIG_XFS_SECURITY.
  [XFS] xfs_bmap_compute_maxlevels should be based on di_forkoff
  [XFS] Always use di_forkoff when checking for attr space.
  [XFS] Ensure the inode is joined in xfs_itruncate_finish
  [XFS] Remove periodic logging of in-core superblock counters.
  [XFS] fix logic error in xfs_alloc_ag_vextent_near()
  [XFS] Don't error out on good I/Os.
  [XFS] Catch log unmount failures.
  [XFS] Sanitise xfs_log_force error checking.
  [XFS] Check for errors when changing buffer pointers.
  [XFS] Don't allow silent errors in xfs_inactive().
  [XFS] Catch errors from xfs_imap().
  [XFS] xfs_bulkstat_one_dinode() never returns an error.
  [XFS] xfs_iflush_fork() never returns an error.
  [XFS] Catch unwritten extent conversion errors.
  ...

Documentation/filesystems/xfs.txt

@@ -52,16 +52,15 @@ When mounting an XFS filesystem, the following options are accepted.
 	and also gets the setgid bit set if it is a directory itself.
 
   ihashsize=value
-	Sets the number of hash buckets available for hashing the
-	in-memory inodes of the specified mount point.  If a value
-	of zero is used, the value selected by the default algorithm
-	will be displayed in /proc/mounts.
+	In memory inode hashes have been removed, so this option has
+	no function as of August 2007. Option is deprecated.
 
   ikeep/noikeep
-	When inode clusters are emptied of inodes, keep them around
-	on the disk (ikeep) - this is the traditional XFS behaviour
-	and is still the default for now.  Using the noikeep option,
-	inode clusters are returned to the free space pool.
+	When ikeep is specified, XFS does not delete empty inode clusters
+	and keeps them around on disk. ikeep is the traditional XFS
+	behaviour. When noikeep is specified, empty inode clusters
+	are returned to the free space pool. The default is noikeep for
+	non-DMAPI mounts, while ikeep is the default when DMAPI is in use.
 
   inode64
 	Indicates that XFS is allowed to create inodes at any location

fs/xfs/Kconfig

@@ -35,18 +35,6 @@ config XFS_QUOTA
 	  with or without the generic quota support enabled (CONFIG_QUOTA) -
 	  they are completely independent subsystems.
 
-config XFS_SECURITY
-	bool "XFS Security Label support"
-	depends on XFS_FS
-	help
-	  Security labels support alternative access control models
-	  implemented by security modules like SELinux.  This option
-	  enables an extended attribute namespace for inode security
-	  labels in the XFS filesystem.
-
-	  If you are not using a security module that requires using
-	  extended attributes for inode security labels, say N.
-
 config XFS_POSIX_ACL
 	bool "XFS POSIX ACL support"
 	depends on XFS_FS

fs/xfs/linux-2.6/kmem.c

@@ -37,7 +37,7 @@ kmem_alloc(size_t size, unsigned int __nocast flags)
 #ifdef DEBUG
 	if (unlikely(!(flags & KM_LARGE) && (size > PAGE_SIZE))) {
 		printk(KERN_WARNING "Large %s attempt, size=%ld\n",
-			__FUNCTION__, (long)size);
+			__func__, (long)size);
 		dump_stack();
 	}
 #endif
@@ -52,7 +52,7 @@ kmem_alloc(size_t size, unsigned int __nocast flags)
 		if (!(++retries % 100))
 			printk(KERN_ERR "XFS: possible memory allocation "
 					"deadlock in %s (mode:0x%x)\n",
-					__FUNCTION__, lflags);
+					__func__, lflags);
 		congestion_wait(WRITE, HZ/50);
 	} while (1);
 }
@@ -129,7 +129,7 @@ kmem_zone_alloc(kmem_zone_t *zone, unsigned int __nocast flags)
 		if (!(++retries % 100))
 			printk(KERN_ERR "XFS: possible memory allocation "
 					"deadlock in %s (mode:0x%x)\n",
-					__FUNCTION__, lflags);
+					__func__, lflags);
 		congestion_wait(WRITE, HZ/50);
 	} while (1);
 }

fs/xfs/linux-2.6/xfs_aops.c

@@ -243,8 +243,12 @@ xfs_end_bio_unwritten(
 	size_t			size = ioend->io_size;
 
 	if (likely(!ioend->io_error)) {
-		if (!XFS_FORCED_SHUTDOWN(ip->i_mount))
-			xfs_iomap_write_unwritten(ip, offset, size);
+		if (!XFS_FORCED_SHUTDOWN(ip->i_mount)) {
+			int error;
+			error = xfs_iomap_write_unwritten(ip, offset, size);
+			if (error)
+				ioend->io_error = error;
+		}
 		xfs_setfilesize(ioend);
 	}
 	xfs_destroy_ioend(ioend);
@@ -1532,9 +1536,9 @@ xfs_vm_bmap(
 	struct xfs_inode	*ip = XFS_I(inode);
 
 	xfs_itrace_entry(XFS_I(inode));
-	xfs_rwlock(ip, VRWLOCK_READ);
+	xfs_ilock(ip, XFS_IOLOCK_SHARED);
 	xfs_flush_pages(ip, (xfs_off_t)0, -1, 0, FI_REMAPF);
-	xfs_rwunlock(ip, VRWLOCK_READ);
+	xfs_iunlock(ip, XFS_IOLOCK_SHARED);
 	return generic_block_bmap(mapping, block, xfs_get_blocks);
 }
 

fs/xfs/linux-2.6/xfs_buf.c

@@ -400,7 +400,7 @@ _xfs_buf_lookup_pages(
 				printk(KERN_ERR
 					"XFS: possible memory allocation "
 					"deadlock in %s (mode:0x%x)\n",
-					__FUNCTION__, gfp_mask);
+					__func__, gfp_mask);
 
 			XFS_STATS_INC(xb_page_retries);
 			xfsbufd_wakeup(0, gfp_mask);
@@ -598,7 +598,7 @@ xfs_buf_get_flags(
 		error = _xfs_buf_map_pages(bp, flags);
 		if (unlikely(error)) {
 			printk(KERN_WARNING "%s: failed to map pages\n",
-					__FUNCTION__);
+					__func__);
 			goto no_buffer;
 		}
 	}
@@ -778,7 +778,7 @@ xfs_buf_get_noaddr(
 	error = _xfs_buf_map_pages(bp, XBF_MAPPED);
 	if (unlikely(error)) {
 		printk(KERN_WARNING "%s: failed to map pages\n",
-				__FUNCTION__);
+				__func__);
 		goto fail_free_mem;
 	}
 
@@ -1060,7 +1060,7 @@ xfs_buf_iostart(
 		bp->b_flags &= ~(XBF_READ | XBF_WRITE | XBF_ASYNC);
 		bp->b_flags |= flags & (XBF_DELWRI | XBF_ASYNC);
 		xfs_buf_delwri_queue(bp, 1);
-		return status;
+		return 0;
 	}
 
 	bp->b_flags &= ~(XBF_READ | XBF_WRITE | XBF_ASYNC | XBF_DELWRI | \

fs/xfs/linux-2.6/xfs_buf.h

@@ -387,11 +387,15 @@ static inline int XFS_bwrite(xfs_buf_t *bp)
 	return error;
 }
 
-static inline int xfs_bdwrite(void *mp, xfs_buf_t *bp)
+/*
+ * No error can be returned from xfs_buf_iostart for delwri
+ * buffers as they are queued and no I/O is issued.
+ */
+static inline void xfs_bdwrite(void *mp, xfs_buf_t *bp)
 {
 	bp->b_strat = xfs_bdstrat_cb;
 	bp->b_fspriv3 = mp;
-	return xfs_buf_iostart(bp, XBF_DELWRI | XBF_ASYNC);
+	(void)xfs_buf_iostart(bp, XBF_DELWRI | XBF_ASYNC);
 }
 
 #define XFS_bdstrat(bp) xfs_buf_iorequest(bp)

fs/xfs/linux-2.6/xfs_cred.h

@@ -30,7 +30,7 @@ typedef struct cred {
 extern struct cred *sys_cred;
 
 /* this is a hack.. (assumes sys_cred is the only cred_t in the system) */
-static __inline int capable_cred(cred_t *cr, int cid)
+static inline int capable_cred(cred_t *cr, int cid)
 {
 	return (cr == sys_cred) ? 1 : capable(cid);
 }

fs/xfs/linux-2.6/xfs_export.c

@@ -22,6 +22,7 @@
 #include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
+#include "xfs_dir2.h"
 #include "xfs_dmapi.h"
 #include "xfs_mount.h"
 #include "xfs_export.h"
@@ -30,8 +31,6 @@
 #include "xfs_inode.h"
 #include "xfs_vfsops.h"
 
-static struct dentry dotdot = { .d_name.name = "..", .d_name.len = 2, };
-
 /*
  * Note that we only accept fileids which are long enough rather than allow
  * the parent generation number to default to zero.  XFS considers zero a
@@ -66,7 +65,7 @@ xfs_fs_encode_fh(
 	int			len;
 
 	/* Directories don't need their parent encoded, they have ".." */
-	if (S_ISDIR(inode->i_mode))
+	if (S_ISDIR(inode->i_mode) || !connectable)
 		fileid_type = FILEID_INO32_GEN;
 	else
 		fileid_type = FILEID_INO32_GEN_PARENT;
@@ -213,17 +212,16 @@ xfs_fs_get_parent(
 	struct dentry		*child)
 {
 	int			error;
-	bhv_vnode_t		*cvp;
+	struct xfs_inode	*cip;
 	struct dentry		*parent;
 
-	cvp = NULL;
-	error = xfs_lookup(XFS_I(child->d_inode), &dotdot, &cvp);
+	error = xfs_lookup(XFS_I(child->d_inode), &xfs_name_dotdot, &cip);
 	if (unlikely(error))
 		return ERR_PTR(-error);
 
-	parent = d_alloc_anon(vn_to_inode(cvp));
+	parent = d_alloc_anon(cip->i_vnode);
 	if (unlikely(!parent)) {
-		VN_RELE(cvp);
+		iput(cip->i_vnode);
 		return ERR_PTR(-ENOMEM);
 	}
 	return parent;

fs/xfs/linux-2.6/xfs_file.c

@@ -469,16 +469,11 @@ xfs_file_open_exec(
 	struct inode	*inode)
 {
 	struct xfs_mount *mp = XFS_M(inode->i_sb);
+	struct xfs_inode *ip = XFS_I(inode);
 
-	if (unlikely(mp->m_flags & XFS_MOUNT_DMAPI)) {
-		if (DM_EVENT_ENABLED(XFS_I(inode), DM_EVENT_READ)) {
-			bhv_vnode_t *vp = vn_from_inode(inode);
-
-			return -XFS_SEND_DATA(mp, DM_EVENT_READ,
-						vp, 0, 0, 0, NULL);
-		}
-	}
-
+	if (unlikely(mp->m_flags & XFS_MOUNT_DMAPI) &&
+	             DM_EVENT_ENABLED(ip, DM_EVENT_READ))
+		return -XFS_SEND_DATA(mp, DM_EVENT_READ, ip, 0, 0, 0, NULL);
 	return 0;
 }
 #endif /* HAVE_FOP_OPEN_EXEC */

fs/xfs/linux-2.6/xfs_fs_subr.c

@@ -17,18 +17,7 @@
  */
 #include "xfs.h"
 #include "xfs_vnodeops.h"
-
-/*
- * The following six includes are needed so that we can include
- * xfs_inode.h.  What a mess..
- */
 #include "xfs_bmap_btree.h"
-#include "xfs_inum.h"
-#include "xfs_dir2.h"
-#include "xfs_dir2_sf.h"
-#include "xfs_attr_sf.h"
-#include "xfs_dinode.h"
-
 #include "xfs_inode.h"
 
 int  fs_noerr(void) { return 0; }
@@ -42,11 +31,10 @@ xfs_tosspages(
 	xfs_off_t	last,
 	int		fiopt)
 {
-	bhv_vnode_t	*vp = XFS_ITOV(ip);
-	struct inode	*inode = vn_to_inode(vp);
+	struct address_space *mapping = ip->i_vnode->i_mapping;
 
-	if (VN_CACHED(vp))
-		truncate_inode_pages(inode->i_mapping, first);
+	if (mapping->nrpages)
+		truncate_inode_pages(mapping, first);
 }
 
 int
@@ -56,15 +44,14 @@ xfs_flushinval_pages(
 	xfs_off_t	last,
 	int		fiopt)
 {
-	bhv_vnode_t	*vp = XFS_ITOV(ip);
-	struct inode	*inode = vn_to_inode(vp);
+	struct address_space *mapping = ip->i_vnode->i_mapping;
 	int		ret = 0;
 
-	if (VN_CACHED(vp)) {
+	if (mapping->nrpages) {
 		xfs_iflags_clear(ip, XFS_ITRUNCATED);
-		ret = filemap_write_and_wait(inode->i_mapping);
+		ret = filemap_write_and_wait(mapping);
 		if (!ret)
-			truncate_inode_pages(inode->i_mapping, first);
+			truncate_inode_pages(mapping, first);
 	}
 	return ret;
 }
@@ -77,17 +64,16 @@ xfs_flush_pages(
 	uint64_t	flags,
 	int		fiopt)
 {
-	bhv_vnode_t	*vp = XFS_ITOV(ip);
-	struct inode	*inode = vn_to_inode(vp);
+	struct address_space *mapping = ip->i_vnode->i_mapping;
 	int		ret = 0;
 	int		ret2;
 
-	if (VN_DIRTY(vp)) {
+	if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
 		xfs_iflags_clear(ip, XFS_ITRUNCATED);
-		ret = filemap_fdatawrite(inode->i_mapping);
+		ret = filemap_fdatawrite(mapping);
 		if (flags & XFS_B_ASYNC)
 			return ret;
-		ret2 = filemap_fdatawait(inode->i_mapping);
+		ret2 = filemap_fdatawait(mapping);
 		if (!ret)
 			ret = ret2;
 	}

fs/xfs/linux-2.6/xfs_ioctl.c

@@ -651,314 +651,6 @@ xfs_attrmulti_by_handle(
 	return -error;
 }
 
-/* prototypes for a few of the stack-hungry cases that have
- * their own functions.  Functions are defined after their use
- * so gcc doesn't get fancy and inline them with -03 */
-
-STATIC int
-xfs_ioc_space(
-	struct xfs_inode	*ip,
-	struct inode		*inode,
-	struct file		*filp,
-	int			flags,
-	unsigned int		cmd,
-	void			__user *arg);
-
-STATIC int
-xfs_ioc_bulkstat(
-	xfs_mount_t		*mp,
-	unsigned int		cmd,
-	void			__user *arg);
-
-STATIC int
-xfs_ioc_fsgeometry_v1(
-	xfs_mount_t		*mp,
-	void			__user *arg);
-
-STATIC int
-xfs_ioc_fsgeometry(
-	xfs_mount_t		*mp,
-	void			__user *arg);
-
-STATIC int
-xfs_ioc_xattr(
-	xfs_inode_t		*ip,
-	struct file		*filp,
-	unsigned int		cmd,
-	void			__user *arg);
-
-STATIC int
-xfs_ioc_fsgetxattr(
-	xfs_inode_t		*ip,
-	int			attr,
-	void			__user *arg);
-
-STATIC int
-xfs_ioc_getbmap(
-	struct xfs_inode	*ip,
-	int			flags,
-	unsigned int		cmd,
-	void			__user *arg);
-
-STATIC int
-xfs_ioc_getbmapx(
-	struct xfs_inode	*ip,
-	void			__user *arg);
-
-int
-xfs_ioctl(
-	xfs_inode_t		*ip,
-	struct file		*filp,
-	int			ioflags,
-	unsigned int		cmd,
-	void			__user *arg)
-{
-	struct inode		*inode = filp->f_path.dentry->d_inode;
-	xfs_mount_t		*mp = ip->i_mount;
-	int			error;
-
-	xfs_itrace_entry(XFS_I(inode));
-	switch (cmd) {
-
-	case XFS_IOC_ALLOCSP:
-	case XFS_IOC_FREESP:
-	case XFS_IOC_RESVSP:
-	case XFS_IOC_UNRESVSP:
-	case XFS_IOC_ALLOCSP64:
-	case XFS_IOC_FREESP64:
-	case XFS_IOC_RESVSP64:
-	case XFS_IOC_UNRESVSP64:
-		/*
-		 * Only allow the sys admin to reserve space unless
-		 * unwritten extents are enabled.
-		 */
-		if (!xfs_sb_version_hasextflgbit(&mp->m_sb) &&
-		    !capable(CAP_SYS_ADMIN))
-			return -EPERM;
-
-		return xfs_ioc_space(ip, inode, filp, ioflags, cmd, arg);
-
-	case XFS_IOC_DIOINFO: {
-		struct dioattr	da;
-		xfs_buftarg_t	*target =
-			XFS_IS_REALTIME_INODE(ip) ?
-			mp->m_rtdev_targp : mp->m_ddev_targp;
-
-		da.d_mem = da.d_miniosz = 1 << target->bt_sshift;
-		da.d_maxiosz = INT_MAX & ~(da.d_miniosz - 1);
-
-		if (copy_to_user(arg, &da, sizeof(da)))
-			return -XFS_ERROR(EFAULT);
-		return 0;
-	}
-
-	case XFS_IOC_FSBULKSTAT_SINGLE:
-	case XFS_IOC_FSBULKSTAT:
-	case XFS_IOC_FSINUMBERS:
-		return xfs_ioc_bulkstat(mp, cmd, arg);
-
-	case XFS_IOC_FSGEOMETRY_V1:
-		return xfs_ioc_fsgeometry_v1(mp, arg);
-
-	case XFS_IOC_FSGEOMETRY:
-		return xfs_ioc_fsgeometry(mp, arg);
-
-	case XFS_IOC_GETVERSION:
-		return put_user(inode->i_generation, (int __user *)arg);
-
-	case XFS_IOC_FSGETXATTR:
-		return xfs_ioc_fsgetxattr(ip, 0, arg);
-	case XFS_IOC_FSGETXATTRA:
-		return xfs_ioc_fsgetxattr(ip, 1, arg);
-	case XFS_IOC_GETXFLAGS:
-	case XFS_IOC_SETXFLAGS:
-	case XFS_IOC_FSSETXATTR:
-		return xfs_ioc_xattr(ip, filp, cmd, arg);
-
-	case XFS_IOC_FSSETDM: {
-		struct fsdmidata	dmi;
-
-		if (copy_from_user(&dmi, arg, sizeof(dmi)))
-			return -XFS_ERROR(EFAULT);
-
-		error = xfs_set_dmattrs(ip, dmi.fsd_dmevmask,
-				dmi.fsd_dmstate);
-		return -error;
-	}
-
-	case XFS_IOC_GETBMAP:
-	case XFS_IOC_GETBMAPA:
-		return xfs_ioc_getbmap(ip, ioflags, cmd, arg);
-
-	case XFS_IOC_GETBMAPX:
-		return xfs_ioc_getbmapx(ip, arg);
-
-	case XFS_IOC_FD_TO_HANDLE:
-	case XFS_IOC_PATH_TO_HANDLE:
-	case XFS_IOC_PATH_TO_FSHANDLE:
-		return xfs_find_handle(cmd, arg);
-
-	case XFS_IOC_OPEN_BY_HANDLE:
-		return xfs_open_by_handle(mp, arg, filp, inode);
-
-	case XFS_IOC_FSSETDM_BY_HANDLE:
-		return xfs_fssetdm_by_handle(mp, arg, inode);
-
-	case XFS_IOC_READLINK_BY_HANDLE:
-		return xfs_readlink_by_handle(mp, arg, inode);
-
-	case XFS_IOC_ATTRLIST_BY_HANDLE:
-		return xfs_attrlist_by_handle(mp, arg, inode);
-
-	case XFS_IOC_ATTRMULTI_BY_HANDLE:
-		return xfs_attrmulti_by_handle(mp, arg, inode);
-
-	case XFS_IOC_SWAPEXT: {
-		error = xfs_swapext((struct xfs_swapext __user *)arg);
-		return -error;
-	}
-
-	case XFS_IOC_FSCOUNTS: {
-		xfs_fsop_counts_t out;
-
-		error = xfs_fs_counts(mp, &out);
-		if (error)
-			return -error;
-
-		if (copy_to_user(arg, &out, sizeof(out)))
-			return -XFS_ERROR(EFAULT);
-		return 0;
-	}
-
-	case XFS_IOC_SET_RESBLKS: {
-		xfs_fsop_resblks_t inout;
-		__uint64_t	   in;
-
-		if (!capable(CAP_SYS_ADMIN))
-			return -EPERM;
-
-		if (copy_from_user(&inout, arg, sizeof(inout)))
-			return -XFS_ERROR(EFAULT);
-
-		/* input parameter is passed in resblks field of structure */
-		in = inout.resblks;
-		error = xfs_reserve_blocks(mp, &in, &inout);
-		if (error)
-			return -error;
-
-		if (copy_to_user(arg, &inout, sizeof(inout)))
-			return -XFS_ERROR(EFAULT);
-		return 0;
-	}
-
-	case XFS_IOC_GET_RESBLKS: {
-		xfs_fsop_resblks_t out;
-
-		if (!capable(CAP_SYS_ADMIN))
-			return -EPERM;
-
-		error = xfs_reserve_blocks(mp, NULL, &out);
-		if (error)
-			return -error;
-
-		if (copy_to_user(arg, &out, sizeof(out)))
-			return -XFS_ERROR(EFAULT);
-
-		return 0;
-	}
-
-	case XFS_IOC_FSGROWFSDATA: {
-		xfs_growfs_data_t in;
-
-		if (!capable(CAP_SYS_ADMIN))
-			return -EPERM;
-
-		if (copy_from_user(&in, arg, sizeof(in)))
-			return -XFS_ERROR(EFAULT);
-
-		error = xfs_growfs_data(mp, &in);
-		return -error;
-	}
-
-	case XFS_IOC_FSGROWFSLOG: {
-		xfs_growfs_log_t in;
-
-		if (!capable(CAP_SYS_ADMIN))
-			return -EPERM;
-
-		if (copy_from_user(&in, arg, sizeof(in)))
-			return -XFS_ERROR(EFAULT);
-
-		error = xfs_growfs_log(mp, &in);
-		return -error;
-	}
-
-	case XFS_IOC_FSGROWFSRT: {
-		xfs_growfs_rt_t in;
-
-		if (!capable(CAP_SYS_ADMIN))
-			return -EPERM;
-
-		if (copy_from_user(&in, arg, sizeof(in)))
-			return -XFS_ERROR(EFAULT);
-
-		error = xfs_growfs_rt(mp, &in);
-		return -error;
-	}
-
-	case XFS_IOC_FREEZE:
-		if (!capable(CAP_SYS_ADMIN))
-			return -EPERM;
-
-		if (inode->i_sb->s_frozen == SB_UNFROZEN)
-			freeze_bdev(inode->i_sb->s_bdev);
-		return 0;
-
-	case XFS_IOC_THAW:
-		if (!capable(CAP_SYS_ADMIN))
-			return -EPERM;
-		if (inode->i_sb->s_frozen != SB_UNFROZEN)
-			thaw_bdev(inode->i_sb->s_bdev, inode->i_sb);
-		return 0;
-
-	case XFS_IOC_GOINGDOWN: {
-		__uint32_t in;
-
-		if (!capable(CAP_SYS_ADMIN))
-			return -EPERM;
-
-		if (get_user(in, (__uint32_t __user *)arg))
-			return -XFS_ERROR(EFAULT);
-
-		error = xfs_fs_goingdown(mp, in);
-		return -error;
-	}
-
-	case XFS_IOC_ERROR_INJECTION: {
-		xfs_error_injection_t in;
-
-		if (!capable(CAP_SYS_ADMIN))
-			return -EPERM;
-
-		if (copy_from_user(&in, arg, sizeof(in)))
-			return -XFS_ERROR(EFAULT);
-
-		error = xfs_errortag_add(in.errtag, mp);
-		return -error;
-	}
-
-	case XFS_IOC_ERROR_CLEARALL:
-		if (!capable(CAP_SYS_ADMIN))
-			return -EPERM;
-
-		error = xfs_errortag_clearall(mp, 1);
-		return -error;
-
-	default:
-		return -ENOTTY;
-	}
-}
-
 STATIC int
 xfs_ioc_space(
 	struct xfs_inode	*ip,
@@ -1179,85 +871,85 @@ xfs_ioc_fsgetxattr(
 }
 
 STATIC int
-xfs_ioc_xattr(
+xfs_ioc_fssetxattr(
 	xfs_inode_t		*ip,
 	struct file		*filp,
-	unsigned int		cmd,
 	void			__user *arg)
 {
 	struct fsxattr		fa;
 	struct bhv_vattr	*vattr;
-	int			error = 0;
+	int			error;
 	int			attr_flags;
-	unsigned int		flags;
+
+	if (copy_from_user(&fa, arg, sizeof(fa)))
+		return -EFAULT;
 
 	vattr = kmalloc(sizeof(*vattr), GFP_KERNEL);
 	if (unlikely(!vattr))
 		return -ENOMEM;
 
-	switch (cmd) {
-	case XFS_IOC_FSSETXATTR: {
-		if (copy_from_user(&fa, arg, sizeof(fa))) {
-			error = -EFAULT;
-			break;
-		}
+	attr_flags = 0;
+	if (filp->f_flags & (O_NDELAY|O_NONBLOCK))
+		attr_flags |= ATTR_NONBLOCK;
 
-		attr_flags = 0;
-		if (filp->f_flags & (O_NDELAY|O_NONBLOCK))
-			attr_flags |= ATTR_NONBLOCK;
+	vattr->va_mask = XFS_AT_XFLAGS | XFS_AT_EXTSIZE | XFS_AT_PROJID;
+	vattr->va_xflags  = fa.fsx_xflags;
+	vattr->va_extsize = fa.fsx_extsize;
+	vattr->va_projid  = fa.fsx_projid;
 
-		vattr->va_mask = XFS_AT_XFLAGS | XFS_AT_EXTSIZE | XFS_AT_PROJID;
-		vattr->va_xflags  = fa.fsx_xflags;
-		vattr->va_extsize = fa.fsx_extsize;
-		vattr->va_projid  = fa.fsx_projid;
+	error = -xfs_setattr(ip, vattr, attr_flags, NULL);
+	if (!error)
+		vn_revalidate(XFS_ITOV(ip));	/* update flags */
+	kfree(vattr);
+	return 0;
+}
 
-		error = xfs_setattr(ip, vattr, attr_flags, NULL);
-		if (likely(!error))
-			vn_revalidate(XFS_ITOV(ip));	/* update flags */
-		error = -error;
-		break;
-	}
+STATIC int
+xfs_ioc_getxflags(
+	xfs_inode_t		*ip,
+	void			__user *arg)
+{
+	unsigned int		flags;
 
-	case XFS_IOC_GETXFLAGS: {
-		flags = xfs_di2lxflags(ip->i_d.di_flags);
-		if (copy_to_user(arg, &flags, sizeof(flags)))
-			error = -EFAULT;
-		break;
-	}
+	flags = xfs_di2lxflags(ip->i_d.di_flags);
+	if (copy_to_user(arg, &flags, sizeof(flags)))
+		return -EFAULT;
+	return 0;
+}
 
-	case XFS_IOC_SETXFLAGS: {
-		if (copy_from_user(&flags, arg, sizeof(flags))) {
-			error = -EFAULT;
-			break;
-		}
+STATIC int
+xfs_ioc_setxflags(
+	xfs_inode_t		*ip,
+	struct file		*filp,
+	void			__user *arg)
+{
+	struct bhv_vattr	*vattr;
+	unsigned int		flags;
+	int			attr_flags;
+	int			error;
 
-		if (flags & ~(FS_IMMUTABLE_FL | FS_APPEND_FL | \
-			      FS_NOATIME_FL | FS_NODUMP_FL | \
-			      FS_SYNC_FL)) {
-			error = -EOPNOTSUPP;
-			break;
-		}
+	if (copy_from_user(&flags, arg, sizeof(flags)))
+		return -EFAULT;
 
-		attr_flags = 0;
-		if (filp->f_flags & (O_NDELAY|O_NONBLOCK))
-			attr_flags |= ATTR_NONBLOCK;
+	if (flags & ~(FS_IMMUTABLE_FL | FS_APPEND_FL | \
+		      FS_NOATIME_FL | FS_NODUMP_FL | \
+		      FS_SYNC_FL))
+		return -EOPNOTSUPP;
 
-		vattr->va_mask = XFS_AT_XFLAGS;
-		vattr->va_xflags = xfs_merge_ioc_xflags(flags,
-							xfs_ip2xflags(ip));
+	vattr = kmalloc(sizeof(*vattr), GFP_KERNEL);
+	if (unlikely(!vattr))
+		return -ENOMEM;
 
-		error = xfs_setattr(ip, vattr, attr_flags, NULL);
-		if (likely(!error))
-			vn_revalidate(XFS_ITOV(ip));	/* update flags */
-		error = -error;
-		break;
-	}
+	attr_flags = 0;
+	if (filp->f_flags & (O_NDELAY|O_NONBLOCK))
+		attr_flags |= ATTR_NONBLOCK;
 
-	default:
-		error = -ENOTTY;
-		break;
-	}
+	vattr->va_mask = XFS_AT_XFLAGS;
+	vattr->va_xflags = xfs_merge_ioc_xflags(flags, xfs_ip2xflags(ip));
 
+	error = -xfs_setattr(ip, vattr, attr_flags, NULL);
+	if (likely(!error))
+		vn_revalidate(XFS_ITOV(ip));	/* update flags */
 	kfree(vattr);
 	return error;
 }
@@ -1332,3 +1024,259 @@ xfs_ioc_getbmapx(
 
 	return 0;
 }
+
+int
+xfs_ioctl(
+	xfs_inode_t		*ip,
+	struct file		*filp,
+	int			ioflags,
+	unsigned int		cmd,
+	void			__user *arg)
+{
+	struct inode		*inode = filp->f_path.dentry->d_inode;
+	xfs_mount_t		*mp = ip->i_mount;
+	int			error;
+
+	xfs_itrace_entry(XFS_I(inode));
+	switch (cmd) {
+
+	case XFS_IOC_ALLOCSP:
+	case XFS_IOC_FREESP:
+	case XFS_IOC_RESVSP:
+	case XFS_IOC_UNRESVSP:
+	case XFS_IOC_ALLOCSP64:
+	case XFS_IOC_FREESP64:
+	case XFS_IOC_RESVSP64:
+	case XFS_IOC_UNRESVSP64:
+		/*
+		 * Only allow the sys admin to reserve space unless
+		 * unwritten extents are enabled.
+		 */
+		if (!xfs_sb_version_hasextflgbit(&mp->m_sb) &&
+		    !capable(CAP_SYS_ADMIN))
+			return -EPERM;
+
+		return xfs_ioc_space(ip, inode, filp, ioflags, cmd, arg);
+
+	case XFS_IOC_DIOINFO: {
+		struct dioattr	da;
+		xfs_buftarg_t	*target =
+			XFS_IS_REALTIME_INODE(ip) ?
+			mp->m_rtdev_targp : mp->m_ddev_targp;
+
+		da.d_mem = da.d_miniosz = 1 << target->bt_sshift;
+		da.d_maxiosz = INT_MAX & ~(da.d_miniosz - 1);
+
+		if (copy_to_user(arg, &da, sizeof(da)))
+			return -XFS_ERROR(EFAULT);
+		return 0;
+	}
+
+	case XFS_IOC_FSBULKSTAT_SINGLE:
+	case XFS_IOC_FSBULKSTAT:
+	case XFS_IOC_FSINUMBERS:
+		return xfs_ioc_bulkstat(mp, cmd, arg);
+
+	case XFS_IOC_FSGEOMETRY_V1:
+		return xfs_ioc_fsgeometry_v1(mp, arg);
+
+	case XFS_IOC_FSGEOMETRY:
+		return xfs_ioc_fsgeometry(mp, arg);
+
+	case XFS_IOC_GETVERSION:
+		return put_user(inode->i_generation, (int __user *)arg);
+
+	case XFS_IOC_FSGETXATTR:
+		return xfs_ioc_fsgetxattr(ip, 0, arg);
+	case XFS_IOC_FSGETXATTRA:
+		return xfs_ioc_fsgetxattr(ip, 1, arg);
+	case XFS_IOC_FSSETXATTR:
+		return xfs_ioc_fssetxattr(ip, filp, arg);
+	case XFS_IOC_GETXFLAGS:
+		return xfs_ioc_getxflags(ip, arg);
+	case XFS_IOC_SETXFLAGS:
+		return xfs_ioc_setxflags(ip, filp, arg);
+
+	case XFS_IOC_FSSETDM: {
+		struct fsdmidata	dmi;
+
+		if (copy_from_user(&dmi, arg, sizeof(dmi)))
+			return -XFS_ERROR(EFAULT);
+
+		error = xfs_set_dmattrs(ip, dmi.fsd_dmevmask,
+				dmi.fsd_dmstate);
+		return -error;
+	}
+
+	case XFS_IOC_GETBMAP:
+	case XFS_IOC_GETBMAPA:
+		return xfs_ioc_getbmap(ip, ioflags, cmd, arg);
+
+	case XFS_IOC_GETBMAPX:
+		return xfs_ioc_getbmapx(ip, arg);
+
+	case XFS_IOC_FD_TO_HANDLE:
+	case XFS_IOC_PATH_TO_HANDLE:
+	case XFS_IOC_PATH_TO_FSHANDLE:
+		return xfs_find_handle(cmd, arg);
+
+	case XFS_IOC_OPEN_BY_HANDLE:
+		return xfs_open_by_handle(mp, arg, filp, inode);
+
+	case XFS_IOC_FSSETDM_BY_HANDLE:
+		return xfs_fssetdm_by_handle(mp, arg, inode);
+
+	case XFS_IOC_READLINK_BY_HANDLE:
+		return xfs_readlink_by_handle(mp, arg, inode);
+
+	case XFS_IOC_ATTRLIST_BY_HANDLE:
+		return xfs_attrlist_by_handle(mp, arg, inode);
+
+	case XFS_IOC_ATTRMULTI_BY_HANDLE:
+		return xfs_attrmulti_by_handle(mp, arg, inode);
+
+	case XFS_IOC_SWAPEXT: {
+		error = xfs_swapext((struct xfs_swapext __user *)arg);
+		return -error;
+	}
+
+	case XFS_IOC_FSCOUNTS: {
+		xfs_fsop_counts_t out;
+
+		error = xfs_fs_counts(mp, &out);
+		if (error)
+			return -error;
+
+		if (copy_to_user(arg, &out, sizeof(out)))
+			return -XFS_ERROR(EFAULT);
+		return 0;
+	}
+
+	case XFS_IOC_SET_RESBLKS: {
+		xfs_fsop_resblks_t inout;
+		__uint64_t	   in;
+
+		if (!capable(CAP_SYS_ADMIN))
+			return -EPERM;
+
+		if (copy_from_user(&inout, arg, sizeof(inout)))
+			return -XFS_ERROR(EFAULT);
+
+		/* input parameter is passed in resblks field of structure */
+		in = inout.resblks;
+		error = xfs_reserve_blocks(mp, &in, &inout);
+		if (error)
+			return -error;
+
+		if (copy_to_user(arg, &inout, sizeof(inout)))
+			return -XFS_ERROR(EFAULT);
+		return 0;
+	}
+
+	case XFS_IOC_GET_RESBLKS: {
+		xfs_fsop_resblks_t out;
+
+		if (!capable(CAP_SYS_ADMIN))
+			return -EPERM;
+
+		error = xfs_reserve_blocks(mp, NULL, &out);
+		if (error)
+			return -error;
+
+		if (copy_to_user(arg, &out, sizeof(out)))
+			return -XFS_ERROR(EFAULT);
+
+		return 0;
+	}
+
+	case XFS_IOC_FSGROWFSDATA: {
+		xfs_growfs_data_t in;
+
+		if (!capable(CAP_SYS_ADMIN))
+			return -EPERM;
+
+		if (copy_from_user(&in, arg, sizeof(in)))
+			return -XFS_ERROR(EFAULT);
+
+		error = xfs_growfs_data(mp, &in);
+		return -error;
+	}
+
+	case XFS_IOC_FSGROWFSLOG: {
+		xfs_growfs_log_t in;
+
+		if (!capable(CAP_SYS_ADMIN))
+			return -EPERM;
+
+		if (copy_from_user(&in, arg, sizeof(in)))
+			return -XFS_ERROR(EFAULT);
+
+		error = xfs_growfs_log(mp, &in);
+		return -error;
+	}
+
+	case XFS_IOC_FSGROWFSRT: {
+		xfs_growfs_rt_t in;
+
+		if (!capable(CAP_SYS_ADMIN))
+			return -EPERM;
+
+		if (copy_from_user(&in, arg, sizeof(in)))
+			return -XFS_ERROR(EFAULT);
+
+		error = xfs_growfs_rt(mp, &in);
+		return -error;
+	}
+
+	case XFS_IOC_FREEZE:
+		if (!capable(CAP_SYS_ADMIN))
+			return -EPERM;
+
+		if (inode->i_sb->s_frozen == SB_UNFROZEN)
+			freeze_bdev(inode->i_sb->s_bdev);
+		return 0;
+
+	case XFS_IOC_THAW:
+		if (!capable(CAP_SYS_ADMIN))
+			return -EPERM;
+		if (inode->i_sb->s_frozen != SB_UNFROZEN)
+			thaw_bdev(inode->i_sb->s_bdev, inode->i_sb);
+		return 0;
+
+	case XFS_IOC_GOINGDOWN: {
+		__uint32_t in;
+
+		if (!capable(CAP_SYS_ADMIN))
+			return -EPERM;
+
+		if (get_user(in, (__uint32_t __user *)arg))
+			return -XFS_ERROR(EFAULT);
+
+		error = xfs_fs_goingdown(mp, in);
+		return -error;
+	}
+
+	case XFS_IOC_ERROR_INJECTION: {
+		xfs_error_injection_t in;
+
+		if (!capable(CAP_SYS_ADMIN))
+			return -EPERM;
+
+		if (copy_from_user(&in, arg, sizeof(in)))
+			return -XFS_ERROR(EFAULT);
+
+		error = xfs_errortag_add(in.errtag, mp);
+		return -error;
+	}
+
+	case XFS_IOC_ERROR_CLEARALL:
+		if (!capable(CAP_SYS_ADMIN))
+			return -EPERM;
+
+		error = xfs_errortag_clearall(mp, 1);
+		return -error;
+
+	default:
+		return -ENOTTY;
+	}
+}

fs/xfs/linux-2.6/xfs_iops.c

@@ -62,12 +62,11 @@ void
 xfs_synchronize_atime(
 	xfs_inode_t	*ip)
 {
-	bhv_vnode_t	*vp;
+	struct inode	*inode = ip->i_vnode;
 
-	vp = XFS_ITOV_NULL(ip);
-	if (vp) {
-		ip->i_d.di_atime.t_sec = (__int32_t)vp->i_atime.tv_sec;
-		ip->i_d.di_atime.t_nsec = (__int32_t)vp->i_atime.tv_nsec;
+	if (inode) {
+		ip->i_d.di_atime.t_sec = (__int32_t)inode->i_atime.tv_sec;
+		ip->i_d.di_atime.t_nsec = (__int32_t)inode->i_atime.tv_nsec;
 	}
 }
 
@@ -80,11 +79,10 @@ void
 xfs_mark_inode_dirty_sync(
 	xfs_inode_t	*ip)
 {
-	bhv_vnode_t	*vp;
+	struct inode	*inode = ip->i_vnode;
 
-	vp = XFS_ITOV_NULL(ip);
-	if (vp)
-		mark_inode_dirty_sync(vn_to_inode(vp));
+	if (inode)
+		mark_inode_dirty_sync(inode);
 }
 
 /*
@@ -215,66 +213,62 @@ xfs_validate_fields(
  */
 STATIC int
 xfs_init_security(
-	bhv_vnode_t	*vp,
+	struct inode	*inode,
 	struct inode	*dir)
 {
-	struct inode	*ip = vn_to_inode(vp);
+	struct xfs_inode *ip = XFS_I(inode);
 	size_t		length;
 	void		*value;
 	char		*name;
 	int		error;
 
-	error = security_inode_init_security(ip, dir, &name, &value, &length);
+	error = security_inode_init_security(inode, dir, &name,
+					     &value, &length);
 	if (error) {
 		if (error == -EOPNOTSUPP)
 			return 0;
 		return -error;
 	}
 
-	error = xfs_attr_set(XFS_I(ip), name, value,
-			length, ATTR_SECURE);
+	error = xfs_attr_set(ip, name, value, length, ATTR_SECURE);
 	if (!error)
-		xfs_iflags_set(XFS_I(ip), XFS_IMODIFIED);
+		xfs_iflags_set(ip, XFS_IMODIFIED);
 
 	kfree(name);
 	kfree(value);
 	return error;
 }
 
-/*
- * Determine whether a process has a valid fs_struct (kernel daemons
- * like knfsd don't have an fs_struct).
- *
- * XXX(hch):  nfsd is broken, better fix it instead.
- */
-STATIC_INLINE int
-xfs_has_fs_struct(struct task_struct *task)
+static void
+xfs_dentry_to_name(
+	struct xfs_name	*namep,
+	struct dentry	*dentry)
 {
-	return (task->fs != init_task.fs);
+	namep->name = dentry->d_name.name;
+	namep->len = dentry->d_name.len;
 }
 
 STATIC void
 xfs_cleanup_inode(
 	struct inode	*dir,
-	bhv_vnode_t	*vp,
+	struct inode	*inode,
 	struct dentry	*dentry,
 	int		mode)
 {
-	struct dentry   teardown = {};
+	struct xfs_name	teardown;
 
 	/* Oh, the horror.
 	 * If we can't add the ACL or we fail in
 	 * xfs_init_security we must back out.
 	 * ENOSPC can hit here, among other things.
 	 */
-	teardown.d_inode = vn_to_inode(vp);
-	teardown.d_name = dentry->d_name;
+	xfs_dentry_to_name(&teardown, dentry);
 
 	if (S_ISDIR(mode))
-		xfs_rmdir(XFS_I(dir), &teardown);
+		xfs_rmdir(XFS_I(dir), &teardown, XFS_I(inode));
 	else
-		xfs_remove(XFS_I(dir), &teardown);
-	VN_RELE(vp);
+		xfs_remove(XFS_I(dir), &teardown, XFS_I(inode));
+	iput(inode);
 }
 
 STATIC int
@@ -284,9 +278,10 @@ xfs_vn_mknod(
 	int		mode,
 	dev_t		rdev)
 {
-	struct inode	*ip;
-	bhv_vnode_t	*vp = NULL, *dvp = vn_from_inode(dir);
+	struct inode	*inode;
+	struct xfs_inode *ip = NULL;
 	xfs_acl_t	*default_acl = NULL;
+	struct xfs_name	name;
 	attrexists_t	test_default_acl = _ACL_DEFAULT_EXISTS;
 	int		error;
 
@@ -297,59 +292,67 @@ xfs_vn_mknod(
 	if (unlikely(!sysv_valid_dev(rdev) || MAJOR(rdev) & ~0x1ff))
 		return -EINVAL;
 
-	if (unlikely(test_default_acl && test_default_acl(dvp))) {
+	if (test_default_acl && test_default_acl(dir)) {
 		if (!_ACL_ALLOC(default_acl)) {
 			return -ENOMEM;
 		}
-		if (!_ACL_GET_DEFAULT(dvp, default_acl)) {
+		if (!_ACL_GET_DEFAULT(dir, default_acl)) {
 			_ACL_FREE(default_acl);
 			default_acl = NULL;
 		}
 	}
 
-	if (IS_POSIXACL(dir) && !default_acl && xfs_has_fs_struct(current))
+	xfs_dentry_to_name(&name, dentry);
+
+	if (IS_POSIXACL(dir) && !default_acl)
 		mode &= ~current->fs->umask;
 
 	switch (mode & S_IFMT) {
-	case S_IFCHR: case S_IFBLK: case S_IFIFO: case S_IFSOCK:
+	case S_IFCHR:
+	case S_IFBLK:
+	case S_IFIFO:
+	case S_IFSOCK:
 		rdev = sysv_encode_dev(rdev);
 	case S_IFREG:
-		error = xfs_create(XFS_I(dir), dentry, mode, rdev, &vp, NULL);
+		error = xfs_create(XFS_I(dir), &name, mode, rdev, &ip, NULL);
 		break;
 	case S_IFDIR:
-		error = xfs_mkdir(XFS_I(dir), dentry, mode, &vp, NULL);
+		error = xfs_mkdir(XFS_I(dir), &name, mode, &ip, NULL);
 		break;
 	default:
 		error = EINVAL;
 		break;
 	}
 
-	if (unlikely(!error)) {
-		error = xfs_init_security(vp, dir);
-		if (error)
-			xfs_cleanup_inode(dir, vp, dentry, mode);
-	}
+	if (unlikely(error))
+		goto out_free_acl;
 
-	if (unlikely(default_acl)) {
-		if (!error) {
-			error = _ACL_INHERIT(vp, mode, default_acl);
-			if (!error)
-				xfs_iflags_set(XFS_I(vp), XFS_IMODIFIED);
-			else
-				xfs_cleanup_inode(dir, vp, dentry, mode);
-		}
+	inode = ip->i_vnode;
+
+	error = xfs_init_security(inode, dir);
+	if (unlikely(error))
+		goto out_cleanup_inode;
+
+	if (default_acl) {
+		error = _ACL_INHERIT(inode, mode, default_acl);
+		if (unlikely(error))
+			goto out_cleanup_inode;
+		xfs_iflags_set(ip, XFS_IMODIFIED);
 		_ACL_FREE(default_acl);
 	}
 
-	if (likely(!error)) {
-		ASSERT(vp);
-		ip = vn_to_inode(vp);
 
-		if (S_ISDIR(mode))
-			xfs_validate_fields(ip);
-		d_instantiate(dentry, ip);
-		xfs_validate_fields(dir);
-	}
+	if (S_ISDIR(mode))
+		xfs_validate_fields(inode);
+	d_instantiate(dentry, inode);
+	xfs_validate_fields(dir);
+	return -error;
+
+ out_cleanup_inode:
+	xfs_cleanup_inode(dir, inode, dentry, mode);
+ out_free_acl:
+	if (default_acl)
+		_ACL_FREE(default_acl);
 	return -error;
 }
 
@@ -378,13 +381,15 @@ xfs_vn_lookup(
 	struct dentry	*dentry,
 	struct nameidata *nd)
 {
-	bhv_vnode_t	*cvp;
+	struct xfs_inode *cip;
+	struct xfs_name	name;
 	int		error;
 
 	if (dentry->d_name.len >= MAXNAMELEN)
 		return ERR_PTR(-ENAMETOOLONG);
 
-	error = xfs_lookup(XFS_I(dir), dentry, &cvp);
+	xfs_dentry_to_name(&name, dentry);
+	error = xfs_lookup(XFS_I(dir), &name, &cip);
 	if (unlikely(error)) {
 		if (unlikely(error != ENOENT))
 			return ERR_PTR(-error);
@@ -392,7 +397,7 @@ xfs_vn_lookup(
 		return NULL;
 	}
 
-	return d_splice_alias(vn_to_inode(cvp), dentry);
+	return d_splice_alias(cip->i_vnode, dentry);
 }
 
 STATIC int
@@ -401,23 +406,24 @@ xfs_vn_link(
 	struct inode	*dir,
 	struct dentry	*dentry)
 {
-	struct inode	*ip;	/* inode of guy being linked to */
-	bhv_vnode_t	*vp;	/* vp of name being linked */
+	struct inode	*inode;	/* inode of guy being linked to */
+	struct xfs_name	name;
 	int		error;
 
-	ip = old_dentry->d_inode;	/* inode being linked to */
-	vp = vn_from_inode(ip);
+	inode = old_dentry->d_inode;
+	xfs_dentry_to_name(&name, dentry);
 
-	VN_HOLD(vp);
-	error = xfs_link(XFS_I(dir), vp, dentry);
+	igrab(inode);
+	error = xfs_link(XFS_I(dir), XFS_I(inode), &name);
 	if (unlikely(error)) {
-		VN_RELE(vp);
-	} else {
-		xfs_iflags_set(XFS_I(dir), XFS_IMODIFIED);
-		xfs_validate_fields(ip);
-		d_instantiate(dentry, ip);
+		iput(inode);
+		return -error;
 	}
-	return -error;
+
+	xfs_iflags_set(XFS_I(dir), XFS_IMODIFIED);
+	xfs_validate_fields(inode);
+	d_instantiate(dentry, inode);
+	return 0;
 }
 
 STATIC int
@@ -426,11 +432,13 @@ xfs_vn_unlink(
 	struct dentry	*dentry)
 {
 	struct inode	*inode;
+	struct xfs_name	name;
 	int		error;
 
 	inode = dentry->d_inode;
+	xfs_dentry_to_name(&name, dentry);
 
-	error = xfs_remove(XFS_I(dir), dentry);
+	error = xfs_remove(XFS_I(dir), &name, XFS_I(inode));
 	if (likely(!error)) {
 		xfs_validate_fields(dir);	/* size needs update */
 		xfs_validate_fields(inode);
@@ -444,29 +452,34 @@ xfs_vn_symlink(
 	struct dentry	*dentry,
 	const char	*symname)
 {
-	struct inode	*ip;
-	bhv_vnode_t	*cvp;	/* used to lookup symlink to put in dentry */
+	struct inode	*inode;
+	struct xfs_inode *cip = NULL;
+	struct xfs_name	name;
 	int		error;
 	mode_t		mode;
 
-	cvp = NULL;
-
 	mode = S_IFLNK |
 		(irix_symlink_mode ? 0777 & ~current->fs->umask : S_IRWXUGO);
+	xfs_dentry_to_name(&name, dentry);
 
-	error = xfs_symlink(XFS_I(dir), dentry, (char *)symname, mode,
-			    &cvp, NULL);
-	if (likely(!error && cvp)) {
-		error = xfs_init_security(cvp, dir);
-		if (likely(!error)) {
-			ip = vn_to_inode(cvp);
-			d_instantiate(dentry, ip);
-			xfs_validate_fields(dir);
-			xfs_validate_fields(ip);
-		} else {
-			xfs_cleanup_inode(dir, cvp, dentry, 0);
-		}
-	}
+	error = xfs_symlink(XFS_I(dir), &name, symname, mode, &cip, NULL);
+	if (unlikely(error))
+		goto out;
+
+	inode = cip->i_vnode;
+
+	error = xfs_init_security(inode, dir);
+	if (unlikely(error))
+		goto out_cleanup_inode;
+
+	d_instantiate(dentry, inode);
+	xfs_validate_fields(dir);
+	xfs_validate_fields(inode);
+	return 0;
+
+ out_cleanup_inode:
+	xfs_cleanup_inode(dir, inode, dentry, 0);
+ out:
 	return -error;
 }
 
@@ -476,9 +489,12 @@ xfs_vn_rmdir(
 	struct dentry	*dentry)
 {
 	struct inode	*inode = dentry->d_inode;
+	struct xfs_name	name;
 	int		error;
 
-	error = xfs_rmdir(XFS_I(dir), dentry);
+	xfs_dentry_to_name(&name, dentry);
+
+	error = xfs_rmdir(XFS_I(dir), &name, XFS_I(inode));
 	if (likely(!error)) {
 		xfs_validate_fields(inode);
 		xfs_validate_fields(dir);
@@ -494,12 +510,15 @@ xfs_vn_rename(
 	struct dentry	*ndentry)
 {
 	struct inode	*new_inode = ndentry->d_inode;
-	bhv_vnode_t	*tvp;	/* target directory */
+	struct xfs_name	oname;
+	struct xfs_name	nname;
 	int		error;
 
-	tvp = vn_from_inode(ndir);
+	xfs_dentry_to_name(&oname, odentry);
+	xfs_dentry_to_name(&nname, ndentry);
 
-	error = xfs_rename(XFS_I(odir), odentry, tvp, ndentry);
+	error = xfs_rename(XFS_I(odir), &oname, XFS_I(odentry->d_inode),
+							XFS_I(ndir), &nname);
 	if (likely(!error)) {
 		if (new_inode)
 			xfs_validate_fields(new_inode);
@@ -700,11 +719,19 @@ xfs_vn_setattr(
 	return -error;
 }
 
+/*
+ * block_truncate_page can return an error, but we can't propagate it
+ * at all here. Leave a complaint + stack trace in the syslog because
+ * this could be bad. If it is bad, we need to propagate the error further.
+ */
 STATIC void
 xfs_vn_truncate(
 	struct inode	*inode)
 {
-	block_truncate_page(inode->i_mapping, inode->i_size, xfs_get_blocks);
+	int	error;
+	error = block_truncate_page(inode->i_mapping, inode->i_size,
+							xfs_get_blocks);
+	WARN_ON(error);
 }
 
 STATIC int

fs/xfs/linux-2.6/xfs_linux.h

@@ -99,7 +99,6 @@
 /*
  * Feature macros (disable/enable)
  */
-#undef  HAVE_REFCACHE	/* reference cache not needed for NFS in 2.6 */
 #define HAVE_SPLICE	/* a splice(2) exists in 2.6, but not in 2.4 */
 #ifdef CONFIG_SMP
 #define HAVE_PERCPU_SB	/* per cpu superblock counters are a 2.6 feature */

fs/xfs/linux-2.6/xfs_lrw.c

@@ -176,7 +176,6 @@ xfs_read(
 {
 	struct file		*file = iocb->ki_filp;
 	struct inode		*inode = file->f_mapping->host;
-	bhv_vnode_t		*vp = XFS_ITOV(ip);
 	xfs_mount_t		*mp = ip->i_mount;
 	size_t			size = 0;
 	ssize_t			ret = 0;
@@ -228,11 +227,11 @@ xfs_read(
 	xfs_ilock(ip, XFS_IOLOCK_SHARED);
 
 	if (DM_EVENT_ENABLED(ip, DM_EVENT_READ) && !(ioflags & IO_INVIS)) {
-		bhv_vrwlock_t locktype = VRWLOCK_READ;
 		int dmflags = FILP_DELAY_FLAG(file) | DM_SEM_FLAG_RD(ioflags);
+		int iolock = XFS_IOLOCK_SHARED;
 
-		ret = -XFS_SEND_DATA(mp, DM_EVENT_READ, vp, *offset, size,
-					dmflags, &locktype);
+		ret = -XFS_SEND_DATA(mp, DM_EVENT_READ, ip, *offset, size,
+					dmflags, &iolock);
 		if (ret) {
 			xfs_iunlock(ip, XFS_IOLOCK_SHARED);
 			if (unlikely(ioflags & IO_ISDIRECT))
@@ -242,7 +241,7 @@ xfs_read(
 	}
 
 	if (unlikely(ioflags & IO_ISDIRECT)) {
-		if (VN_CACHED(vp))
+		if (inode->i_mapping->nrpages)
 			ret = xfs_flushinval_pages(ip, (*offset & PAGE_CACHE_MASK),
 						    -1, FI_REMAPF_LOCKED);
 		mutex_unlock(&inode->i_mutex);
@@ -276,7 +275,6 @@ xfs_splice_read(
 	int			flags,
 	int			ioflags)
 {
-	bhv_vnode_t		*vp = XFS_ITOV(ip);
 	xfs_mount_t		*mp = ip->i_mount;
 	ssize_t			ret;
 
@@ -287,11 +285,11 @@ xfs_splice_read(
 	xfs_ilock(ip, XFS_IOLOCK_SHARED);
 
 	if (DM_EVENT_ENABLED(ip, DM_EVENT_READ) && !(ioflags & IO_INVIS)) {
-		bhv_vrwlock_t locktype = VRWLOCK_READ;
+		int iolock = XFS_IOLOCK_SHARED;
 		int error;
 
-		error = XFS_SEND_DATA(mp, DM_EVENT_READ, vp, *ppos, count,
-					FILP_DELAY_FLAG(infilp), &locktype);
+		error = XFS_SEND_DATA(mp, DM_EVENT_READ, ip, *ppos, count,
+					FILP_DELAY_FLAG(infilp), &iolock);
 		if (error) {
 			xfs_iunlock(ip, XFS_IOLOCK_SHARED);
 			return -error;
@@ -317,7 +315,6 @@ xfs_splice_write(
 	int			flags,
 	int			ioflags)
 {
-	bhv_vnode_t		*vp = XFS_ITOV(ip);
 	xfs_mount_t		*mp = ip->i_mount;
 	ssize_t			ret;
 	struct inode		*inode = outfilp->f_mapping->host;
@@ -330,11 +327,11 @@ xfs_splice_write(
 	xfs_ilock(ip, XFS_IOLOCK_EXCL);
 
 	if (DM_EVENT_ENABLED(ip, DM_EVENT_WRITE) && !(ioflags & IO_INVIS)) {
-		bhv_vrwlock_t locktype = VRWLOCK_WRITE;
+		int iolock = XFS_IOLOCK_EXCL;
 		int error;
 
-		error = XFS_SEND_DATA(mp, DM_EVENT_WRITE, vp, *ppos, count,
-					FILP_DELAY_FLAG(outfilp), &locktype);
+		error = XFS_SEND_DATA(mp, DM_EVENT_WRITE, ip, *ppos, count,
+					FILP_DELAY_FLAG(outfilp), &iolock);
 		if (error) {
 			xfs_iunlock(ip, XFS_IOLOCK_EXCL);
 			return -error;
@@ -573,14 +570,12 @@ xfs_write(
 	struct file		*file = iocb->ki_filp;
 	struct address_space	*mapping = file->f_mapping;
 	struct inode		*inode = mapping->host;
-	bhv_vnode_t		*vp = XFS_ITOV(xip);
 	unsigned long		segs = nsegs;
 	xfs_mount_t		*mp;
 	ssize_t			ret = 0, error = 0;
 	xfs_fsize_t		isize, new_size;
 	int			iolock;
 	int			eventsent = 0;
-	bhv_vrwlock_t		locktype;
 	size_t			ocount = 0, count;
 	loff_t			pos;
 	int			need_i_mutex;
@@ -607,11 +602,9 @@ xfs_write(
 relock:
 	if (ioflags & IO_ISDIRECT) {
 		iolock = XFS_IOLOCK_SHARED;
-		locktype = VRWLOCK_WRITE_DIRECT;
 		need_i_mutex = 0;
 	} else {
 		iolock = XFS_IOLOCK_EXCL;
-		locktype = VRWLOCK_WRITE;
 		need_i_mutex = 1;
 		mutex_lock(&inode->i_mutex);
 	}
@@ -634,9 +627,8 @@ start:
 			dmflags |= DM_FLAGS_IMUX;
 
 		xfs_iunlock(xip, XFS_ILOCK_EXCL);
-		error = XFS_SEND_DATA(xip->i_mount, DM_EVENT_WRITE, vp,
-				      pos, count,
-				      dmflags, &locktype);
+		error = XFS_SEND_DATA(xip->i_mount, DM_EVENT_WRITE, xip,
+				      pos, count, dmflags, &iolock);
 		if (error) {
 			goto out_unlock_internal;
 		}
@@ -664,10 +656,9 @@ start:
 			return XFS_ERROR(-EINVAL);
 		}
 
-		if (!need_i_mutex && (VN_CACHED(vp) || pos > xip->i_size)) {
+		if (!need_i_mutex && (mapping->nrpages || pos > xip->i_size)) {
 			xfs_iunlock(xip, XFS_ILOCK_EXCL|iolock);
 			iolock = XFS_IOLOCK_EXCL;
-			locktype = VRWLOCK_WRITE;
 			need_i_mutex = 1;
 			mutex_lock(&inode->i_mutex);
 			xfs_ilock(xip, XFS_ILOCK_EXCL|iolock);
@@ -727,7 +718,7 @@ retry:
 	current->backing_dev_info = mapping->backing_dev_info;
 
 	if ((ioflags & IO_ISDIRECT)) {
-		if (VN_CACHED(vp)) {
+		if (mapping->nrpages) {
 			WARN_ON(need_i_mutex == 0);
 			xfs_inval_cached_trace(xip, pos, -1,
 					(pos & PAGE_CACHE_MASK), -1);
@@ -744,7 +735,6 @@ retry:
 			mutex_unlock(&inode->i_mutex);
 
 			iolock = XFS_IOLOCK_SHARED;
-			locktype = VRWLOCK_WRITE_DIRECT;
 			need_i_mutex = 0;
 		}
 
@@ -781,15 +771,15 @@ retry:
 
 	if (ret == -ENOSPC &&
 	    DM_EVENT_ENABLED(xip, DM_EVENT_NOSPACE) && !(ioflags & IO_INVIS)) {
-		xfs_rwunlock(xip, locktype);
+		xfs_iunlock(xip, iolock);
 		if (need_i_mutex)
 			mutex_unlock(&inode->i_mutex);
-		error = XFS_SEND_NAMESP(xip->i_mount, DM_EVENT_NOSPACE, vp,
-				DM_RIGHT_NULL, vp, DM_RIGHT_NULL, NULL, NULL,
+		error = XFS_SEND_NAMESP(xip->i_mount, DM_EVENT_NOSPACE, xip,
+				DM_RIGHT_NULL, xip, DM_RIGHT_NULL, NULL, NULL,
 				0, 0, 0); /* Delay flag intentionally  unused */
 		if (need_i_mutex)
 			mutex_lock(&inode->i_mutex);
-		xfs_rwlock(xip, locktype);
+		xfs_ilock(xip, iolock);
 		if (error)
 			goto out_unlock_internal;
 		pos = xip->i_size;
@@ -817,7 +807,8 @@ retry:
 	/* Handle various SYNC-type writes */
 	if ((file->f_flags & O_SYNC) || IS_SYNC(inode)) {
 		int error2;
-		xfs_rwunlock(xip, locktype);
+
+		xfs_iunlock(xip, iolock);
 		if (need_i_mutex)
 			mutex_unlock(&inode->i_mutex);
 		error2 = sync_page_range(inode, mapping, pos, ret);
@@ -825,7 +816,7 @@ retry:
 			error = error2;
 		if (need_i_mutex)
 			mutex_lock(&inode->i_mutex);
-		xfs_rwlock(xip, locktype);
+		xfs_ilock(xip, iolock);
 		error2 = xfs_write_sync_logforce(mp, xip);
 		if (!error)
 			error = error2;
@@ -846,7 +837,7 @@ retry:
 			xip->i_d.di_size = xip->i_size;
 		xfs_iunlock(xip, XFS_ILOCK_EXCL);
 	}
-	xfs_rwunlock(xip, locktype);
+	xfs_iunlock(xip, iolock);
  out_unlock_mutex:
 	if (need_i_mutex)
 		mutex_unlock(&inode->i_mutex);
@@ -884,28 +875,23 @@ xfs_bdstrat_cb(struct xfs_buf *bp)
 }
 
 /*
- * Wrapper around bdstrat so that we can stop data
- * from going to disk in case we are shutting down the filesystem.
- * Typically user data goes thru this path; one of the exceptions
- * is the superblock.
+ * Wrapper around bdstrat so that we can stop data from going to disk in case
+ * we are shutting down the filesystem.  Typically user data goes thru this
+ * path; one of the exceptions is the superblock.
  */
-int
+void
 xfsbdstrat(
 	struct xfs_mount	*mp,
 	struct xfs_buf		*bp)
 {
 	ASSERT(mp);
 	if (!XFS_FORCED_SHUTDOWN(mp)) {
-		/* Grio redirection would go here
-		 * if (XFS_BUF_IS_GRIO(bp)) {
-		 */
-
 		xfs_buf_iorequest(bp);
-		return 0;
+		return;
 	}
 
 	xfs_buftrace("XFSBDSTRAT IOERROR", bp);
-	return (xfs_bioerror_relse(bp));
+	xfs_bioerror_relse(bp);
 }
 
 /*

fs/xfs/linux-2.6/xfs_lrw.h

@@ -68,7 +68,8 @@ extern void xfs_inval_cached_trace(struct xfs_inode *,
 #define xfs_inval_cached_trace(ip, offset, len, first, last)
 #endif
 
-extern int xfsbdstrat(struct xfs_mount *, struct xfs_buf *);
+/* errors from xfsbdstrat() must be extracted from the buffer */
+extern void xfsbdstrat(struct xfs_mount *, struct xfs_buf *);
 extern int xfs_bdstrat_cb(struct xfs_buf *);
 extern int xfs_dev_is_read_only(struct xfs_mount *, char *);
 

fs/xfs/linux-2.6/xfs_stats.h

@@ -144,8 +144,8 @@ extern void xfs_cleanup_procfs(void);
 # define XFS_STATS_DEC(count)
 # define XFS_STATS_ADD(count, inc)
 
-static __inline void xfs_init_procfs(void) { };
-static __inline void xfs_cleanup_procfs(void) { };
+static inline void xfs_init_procfs(void) { };
+static inline void xfs_cleanup_procfs(void) { };
 
 #endif	/* !CONFIG_PROC_FS */
 

fs/xfs/linux-2.6/xfs_super.c

@@ -896,7 +896,8 @@ xfs_fs_write_inode(
 	struct inode		*inode,
 	int			sync)
 {
-	int			error = 0, flags = FLUSH_INODE;
+	int			error = 0;
+	int			flags = 0;
 
 	xfs_itrace_entry(XFS_I(inode));
 	if (sync) {
@@ -934,7 +935,7 @@ xfs_fs_clear_inode(
 		xfs_inactive(ip);
 		xfs_iflags_clear(ip, XFS_IMODIFIED);
 		if (xfs_reclaim(ip))
-			panic("%s: cannot reclaim 0x%p\n", __FUNCTION__, inode);
+			panic("%s: cannot reclaim 0x%p\n", __func__, inode);
 	}
 
 	ASSERT(XFS_I(inode) == NULL);
@@ -1027,8 +1028,7 @@ xfs_sync_worker(
 	int		error;
 
 	if (!(mp->m_flags & XFS_MOUNT_RDONLY))
-		error = xfs_sync(mp, SYNC_FSDATA | SYNC_BDFLUSH | SYNC_ATTR |
-				     SYNC_REFCACHE | SYNC_SUPER);
+		error = xfs_sync(mp, SYNC_FSDATA | SYNC_BDFLUSH | SYNC_ATTR);
 	mp->m_sync_seq++;
 	wake_up(&mp->m_wait_single_sync_task);
 }
@@ -1306,7 +1306,7 @@ xfs_fs_fill_super(
 	void			*data,
 	int			silent)
 {
-	struct inode		*rootvp;
+	struct inode		*root;
 	struct xfs_mount	*mp = NULL;
 	struct xfs_mount_args	*args = xfs_args_allocate(sb, silent);
 	int			error;
@@ -1344,19 +1344,18 @@ xfs_fs_fill_super(
 	sb->s_time_gran = 1;
 	set_posix_acl_flag(sb);
 
-	rootvp = igrab(mp->m_rootip->i_vnode);
-	if (!rootvp) {
+	root = igrab(mp->m_rootip->i_vnode);
+	if (!root) {
 		error = ENOENT;
 		goto fail_unmount;
 	}
-
-	sb->s_root = d_alloc_root(vn_to_inode(rootvp));
-	if (!sb->s_root) {
-		error = ENOMEM;
+	if (is_bad_inode(root)) {
+		error = EINVAL;
 		goto fail_vnrele;
 	}
-	if (is_bad_inode(sb->s_root->d_inode)) {
-		error = EINVAL;
+	sb->s_root = d_alloc_root(root);
+	if (!sb->s_root) {
+		error = ENOMEM;
 		goto fail_vnrele;
 	}
 
@@ -1378,7 +1377,7 @@ fail_vnrele:
 		dput(sb->s_root);
 		sb->s_root = NULL;
 	} else {
-		VN_RELE(rootvp);
+		iput(root);
 	}
 
 fail_unmount:

fs/xfs/linux-2.6/xfs_super.h

@@ -50,13 +50,7 @@ extern void xfs_qm_exit(void);
 # define set_posix_acl_flag(sb)	do { } while (0)
 #endif
 
-#ifdef CONFIG_XFS_SECURITY
-# define XFS_SECURITY_STRING	"security attributes, "
-# define ENOSECURITY		0
-#else
-# define XFS_SECURITY_STRING
-# define ENOSECURITY		EOPNOTSUPP
-#endif
+#define XFS_SECURITY_STRING	"security attributes, "
 
 #ifdef CONFIG_XFS_RT
 # define XFS_REALTIME_STRING	"realtime, "

fs/xfs/linux-2.6/xfs_vfs.h

@@ -49,7 +49,6 @@ typedef struct bhv_vfs_sync_work {
 #define SYNC_REFCACHE		0x0040  /* prune some of the nfs ref cache */
 #define SYNC_REMOUNT		0x0080  /* remount readonly, no dummy LRs */
 #define SYNC_IOWAIT		0x0100  /* wait for all I/O to complete */
-#define SYNC_SUPER		0x0200  /* flush superblock to disk */
 
 /*
  * When remounting a filesystem read-only or freezing the filesystem,

fs/xfs/linux-2.6/xfs_vnode.h

@@ -23,8 +23,6 @@ struct bhv_vattr;
 struct xfs_iomap;
 struct attrlist_cursor_kern;
 
-typedef struct dentry	bhv_vname_t;
-typedef __u64		bhv_vnumber_t;
 typedef struct inode	bhv_vnode_t;
 
 #define VN_ISLNK(vp)	S_ISLNK((vp)->i_mode)
@@ -45,18 +43,6 @@ static inline struct inode *vn_to_inode(bhv_vnode_t *vnode)
 	return vnode;
 }
 
-/*
- * Values for the vop_rwlock/rwunlock flags parameter.
- */
-typedef enum bhv_vrwlock {
-	VRWLOCK_NONE,
-	VRWLOCK_READ,
-	VRWLOCK_WRITE,
-	VRWLOCK_WRITE_DIRECT,
-	VRWLOCK_TRY_READ,
-	VRWLOCK_TRY_WRITE
-} bhv_vrwlock_t;
-
 /*
  * Return values for xfs_inactive.  A return value of
  * VN_INACTIVE_NOCACHE implies that the file system behavior
@@ -73,12 +59,9 @@ typedef enum bhv_vrwlock {
 #define IO_INVIS	0x00020		/* don't update inode timestamps */
 
 /*
- * Flags for vop_iflush call
+ * Flags for xfs_inode_flush
  */
 #define FLUSH_SYNC		1	/* wait for flush to complete	*/
-#define FLUSH_INODE		2	/* flush the inode itself	*/
-#define FLUSH_LOG		4	/* force the last log entry for
-					 * this inode out to disk	*/
 
 /*
  * Flush/Invalidate options for vop_toss/flush/flushinval_pages.
@@ -225,13 +208,6 @@ static inline bhv_vnode_t *vn_grab(bhv_vnode_t *vp)
 	return inode ? vn_from_inode(inode) : NULL;
 }
 
-/*
- * Vname handling macros.
- */
-#define VNAME(dentry)		((char *) (dentry)->d_name.name)
-#define VNAMELEN(dentry)	((dentry)->d_name.len)
-#define VNAME_TO_VNODE(dentry)	(vn_from_inode((dentry)->d_inode))
-
 /*
  * Dealing with bad inodes
  */
@@ -303,9 +279,9 @@ extern void xfs_itrace_hold(struct xfs_inode *, char *, int, inst_t *);
 extern void _xfs_itrace_ref(struct xfs_inode *, char *, int, inst_t *);
 extern void xfs_itrace_rele(struct xfs_inode *, char *, int, inst_t *);
 #define xfs_itrace_entry(ip)	\
-	_xfs_itrace_entry(ip, __FUNCTION__, (inst_t *)__return_address)
+	_xfs_itrace_entry(ip, __func__, (inst_t *)__return_address)
 #define xfs_itrace_exit(ip)	\
-	_xfs_itrace_exit(ip, __FUNCTION__, (inst_t *)__return_address)
+	_xfs_itrace_exit(ip, __func__, (inst_t *)__return_address)
 #define xfs_itrace_exit_tag(ip, tag)	\
 	_xfs_itrace_exit(ip, tag, (inst_t *)__return_address)
 #define xfs_itrace_ref(ip)	\

fs/xfs/quota/xfs_dquot.c

@@ -1291,7 +1291,7 @@ xfs_qm_dqflush(
 	if (flags & XFS_QMOPT_DELWRI) {
 		xfs_bdwrite(mp, bp);
 	} else if (flags & XFS_QMOPT_ASYNC) {
-		xfs_bawrite(mp, bp);
+		error = xfs_bawrite(mp, bp);
 	} else {
 		error = xfs_bwrite(mp, bp);
 	}
@@ -1439,9 +1439,7 @@ xfs_qm_dqpurge(
 	uint		flags)
 {
 	xfs_dqhash_t	*thishash;
-	xfs_mount_t	*mp;
-
-	mp = dqp->q_mount;
+	xfs_mount_t	*mp = dqp->q_mount;
 
 	ASSERT(XFS_QM_IS_MPLIST_LOCKED(mp));
 	ASSERT(XFS_DQ_IS_HASH_LOCKED(dqp->q_hash));
@@ -1485,6 +1483,7 @@ xfs_qm_dqpurge(
 	 * we're unmounting, we do care, so we flush it and wait.
 	 */
 	if (XFS_DQ_IS_DIRTY(dqp)) {
+		int	error;
 		xfs_dqtrace_entry(dqp, "DQPURGE ->DQFLUSH: DQDIRTY");
 		/* dqflush unlocks dqflock */
 		/*
@@ -1495,7 +1494,10 @@ xfs_qm_dqpurge(
 		 * We don't care about getting disk errors here. We need
 		 * to purge this dquot anyway, so we go ahead regardless.
 		 */
-		(void) xfs_qm_dqflush(dqp, XFS_QMOPT_SYNC);
+		error = xfs_qm_dqflush(dqp, XFS_QMOPT_SYNC);
+		if (error)
+			xfs_fs_cmn_err(CE_WARN, mp,
+				"xfs_qm_dqpurge: dquot %p flush failed", dqp);
 		xfs_dqflock(dqp);
 	}
 	ASSERT(dqp->q_pincount == 0);
@@ -1580,12 +1582,18 @@ xfs_qm_dqflock_pushbuf_wait(
 		    XFS_INCORE_TRYLOCK);
 	if (bp != NULL) {
 		if (XFS_BUF_ISDELAYWRITE(bp)) {
+			int	error;
 			if (XFS_BUF_ISPINNED(bp)) {
 				xfs_log_force(dqp->q_mount,
 					      (xfs_lsn_t)0,
 					      XFS_LOG_FORCE);
 			}
-			xfs_bawrite(dqp->q_mount, bp);
+			error = xfs_bawrite(dqp->q_mount, bp);
+			if (error)
+				xfs_fs_cmn_err(CE_WARN, dqp->q_mount,
+					"xfs_qm_dqflock_pushbuf_wait: "
+					"pushbuf error %d on dqp %p, bp %p",
+					error, dqp, bp);
 		} else {
 			xfs_buf_relse(bp);
 		}

fs/xfs/quota/xfs_dquot_item.c

@@ -146,6 +146,7 @@ xfs_qm_dquot_logitem_push(
 	xfs_dq_logitem_t	*logitem)
 {
 	xfs_dquot_t	*dqp;
+	int		error;
 
 	dqp = logitem->qli_dquot;
 
@@ -161,7 +162,11 @@ xfs_qm_dquot_logitem_push(
 	 * lock without sleeping, then there must not have been
 	 * anyone in the process of flushing the dquot.
 	 */
-	xfs_qm_dqflush(dqp, XFS_B_DELWRI);
+	error = xfs_qm_dqflush(dqp, XFS_QMOPT_DELWRI);
+	if (error)
+		xfs_fs_cmn_err(CE_WARN, dqp->q_mount,
+			"xfs_qm_dquot_logitem_push: push error %d on dqp %p",
+			error, dqp);
 	xfs_dqunlock(dqp);
 }
 
@@ -262,11 +267,16 @@ xfs_qm_dquot_logitem_pushbuf(
 					      XFS_LOG_FORCE);
 			}
 			if (dopush) {
+				int	error;
 #ifdef XFSRACEDEBUG
 				delay_for_intr();
 				delay(300);
 #endif
-				xfs_bawrite(mp, bp);
+				error = xfs_bawrite(mp, bp);
+				if (error)
+					xfs_fs_cmn_err(CE_WARN, mp,
+	"xfs_qm_dquot_logitem_pushbuf: pushbuf error %d on qip %p, bp %p",
+							error, qip, bp);
 			} else {
 				xfs_buf_relse(bp);
 			}

fs/xfs/quota/xfs_qm.c

@@ -304,8 +304,11 @@ xfs_qm_unmount_quotadestroy(
  * necessary data structures like quotainfo.  This is also responsible for
  * running a quotacheck as necessary.  We are guaranteed that the superblock
  * is consistently read in at this point.
+ *
+ * If we fail here, the mount will continue with quota turned off. We don't
+ * need to inidicate success or failure at all.
  */
-int
+void
 xfs_qm_mount_quotas(
 	xfs_mount_t	*mp,
 	int		mfsi_flags)
@@ -313,7 +316,6 @@ xfs_qm_mount_quotas(
 	int		error = 0;
 	uint		sbf;
 
-
 	/*
 	 * If quotas on realtime volumes is not supported, we disable
 	 * quotas immediately.
@@ -332,7 +334,8 @@ xfs_qm_mount_quotas(
 	 * Allocate the quotainfo structure inside the mount struct, and
 	 * create quotainode(s), and change/rev superblock if necessary.
 	 */
-	if ((error = xfs_qm_init_quotainfo(mp))) {
+	error = xfs_qm_init_quotainfo(mp);
+	if (error) {
 		/*
 		 * We must turn off quotas.
 		 */
@@ -344,12 +347,11 @@ xfs_qm_mount_quotas(
 	 * If any of the quotas are not consistent, do a quotacheck.
 	 */
 	if (XFS_QM_NEED_QUOTACHECK(mp) &&
-		!(mfsi_flags & XFS_MFSI_NO_QUOTACHECK)) {
-		if ((error = xfs_qm_quotacheck(mp))) {
-			/* Quotacheck has failed and quotas have
-			 * been disabled.
-			 */
-			return XFS_ERROR(error);
+	    !(mfsi_flags & XFS_MFSI_NO_QUOTACHECK)) {
+		error = xfs_qm_quotacheck(mp);
+		if (error) {
+			/* Quotacheck failed and disabled quotas. */
+			return;
 		}
 	}
 	/* 
@@ -357,12 +359,10 @@ xfs_qm_mount_quotas(
 	 * quotachecked status, since we won't be doing accounting for
 	 * that type anymore.
 	 */
-	if (!XFS_IS_UQUOTA_ON(mp)) {
+	if (!XFS_IS_UQUOTA_ON(mp))
 		mp->m_qflags &= ~XFS_UQUOTA_CHKD;
-	}
-	if (!(XFS_IS_GQUOTA_ON(mp) || XFS_IS_PQUOTA_ON(mp))) {
+	if (!(XFS_IS_GQUOTA_ON(mp) || XFS_IS_PQUOTA_ON(mp)))
 		mp->m_qflags &= ~XFS_OQUOTA_CHKD;
-	}
 
  write_changes:
 	/*
@@ -392,7 +392,7 @@ xfs_qm_mount_quotas(
 		xfs_fs_cmn_err(CE_WARN, mp,
 			"Failed to initialize disk quotas.");
 	}
-	return XFS_ERROR(error);
+	return;
 }
 
 /*
@@ -1438,7 +1438,7 @@ xfs_qm_qino_alloc(
 }
 
 
-STATIC int
+STATIC void
 xfs_qm_reset_dqcounts(
 	xfs_mount_t	*mp,
 	xfs_buf_t	*bp,
@@ -1478,8 +1478,6 @@ xfs_qm_reset_dqcounts(
 		ddq->d_rtbwarns = 0;
 		ddq = (xfs_disk_dquot_t *) ((xfs_dqblk_t *)ddq + 1);
 	}
-
-	return 0;
 }
 
 STATIC int
@@ -1520,7 +1518,7 @@ xfs_qm_dqiter_bufs(
 		if (error)
 			break;
 
-		(void) xfs_qm_reset_dqcounts(mp, bp, firstid, type);
+		xfs_qm_reset_dqcounts(mp, bp, firstid, type);
 		xfs_bdwrite(mp, bp);
 		/*
 		 * goto the next block.
@@ -1810,7 +1808,7 @@ xfs_qm_dqusage_adjust(
 	 * Now release the inode. This will send it to 'inactive', and
 	 * possibly even free blocks.
 	 */
-	VN_RELE(XFS_ITOV(ip));
+	IRELE(ip);
 
 	/*
 	 * Goto next inode.
@@ -1879,6 +1877,14 @@ xfs_qm_quotacheck(
 
 	} while (! done);
 
+	/*
+	 * We've made all the changes that we need to make incore.
+	 * Flush them down to disk buffers if everything was updated
+	 * successfully.
+	 */
+	if (!error)
+		error = xfs_qm_dqflush_all(mp, XFS_QMOPT_DELWRI);
+
 	/*
 	 * We can get this error if we couldn't do a dquot allocation inside
 	 * xfs_qm_dqusage_adjust (via bulkstat). We don't care about the
@@ -1890,11 +1896,6 @@ xfs_qm_quotacheck(
 		xfs_qm_dqpurge_all(mp, XFS_QMOPT_QUOTALL | XFS_QMOPT_QUOTAOFF);
 		goto error_return;
 	}
-	/*
-	 * We've made all the changes that we need to make incore.
-	 * Now flush_them down to disk buffers.
-	 */
-	xfs_qm_dqflush_all(mp, XFS_QMOPT_DELWRI);
 
 	/*
 	 * We didn't log anything, because if we crashed, we'll have to
@@ -1926,7 +1927,10 @@ xfs_qm_quotacheck(
 		ASSERT(mp->m_quotainfo != NULL);
 		ASSERT(xfs_Gqm != NULL);
 		xfs_qm_destroy_quotainfo(mp);
-		(void)xfs_mount_reset_sbqflags(mp);
+		if (xfs_mount_reset_sbqflags(mp)) {
+			cmn_err(CE_WARN, "XFS quotacheck %s: "
+				"Failed to reset quota flags.", mp->m_fsname);
+		}
 	} else {
 		cmn_err(CE_NOTE, "XFS quotacheck %s: Done.", mp->m_fsname);
 	}
@@ -1968,7 +1972,7 @@ xfs_qm_init_quotainos(
 			if ((error = xfs_iget(mp, NULL, mp->m_sb.sb_gquotino,
 					     0, 0, &gip, 0))) {
 				if (uip)
-					VN_RELE(XFS_ITOV(uip));
+					IRELE(uip);
 				return XFS_ERROR(error);
 			}
 		}
@@ -1999,7 +2003,7 @@ xfs_qm_init_quotainos(
 					  sbflags | XFS_SB_GQUOTINO, flags);
 		if (error) {
 			if (uip)
-				VN_RELE(XFS_ITOV(uip));
+				IRELE(uip);
 
 			return XFS_ERROR(error);
 		}
@@ -2093,12 +2097,17 @@ xfs_qm_shake_freelist(
 		 * dirty dquots.
 		 */
 		if (XFS_DQ_IS_DIRTY(dqp)) {
+			int	error;
 			xfs_dqtrace_entry(dqp, "DQSHAKE: DQDIRTY");
 			/*
 			 * We flush it delayed write, so don't bother
 			 * releasing the mplock.
 			 */
-			(void) xfs_qm_dqflush(dqp, XFS_QMOPT_DELWRI);
+			error = xfs_qm_dqflush(dqp, XFS_QMOPT_DELWRI);
+			if (error) {
+				xfs_fs_cmn_err(CE_WARN, dqp->q_mount,
+			"xfs_qm_dqflush_all: dquot %p flush failed", dqp);
+			}
 			xfs_dqunlock(dqp); /* dqflush unlocks dqflock */
 			dqp = dqp->dq_flnext;
 			continue;
@@ -2265,12 +2274,17 @@ xfs_qm_dqreclaim_one(void)
 		 * dirty dquots.
 		 */
 		if (XFS_DQ_IS_DIRTY(dqp)) {
+			int	error;
 			xfs_dqtrace_entry(dqp, "DQRECLAIM: DQDIRTY");
 			/*
 			 * We flush it delayed write, so don't bother
 			 * releasing the freelist lock.
 			 */
-			(void) xfs_qm_dqflush(dqp, XFS_QMOPT_DELWRI);
+			error = xfs_qm_dqflush(dqp, XFS_QMOPT_DELWRI);
+			if (error) {
+				xfs_fs_cmn_err(CE_WARN, dqp->q_mount,
+			"xfs_qm_dqreclaim: dquot %p flush failed", dqp);
+			}
 			xfs_dqunlock(dqp); /* dqflush unlocks dqflock */
 			continue;
 		}
@@ -2378,9 +2392,9 @@ xfs_qm_write_sb_changes(
 	}
 
 	xfs_mod_sb(tp, flags);
-	(void) xfs_trans_commit(tp, 0);
+	error = xfs_trans_commit(tp, 0);
 
-	return 0;
+	return error;
 }
 
 

fs/xfs/quota/xfs_qm.h

@@ -165,7 +165,7 @@ typedef struct xfs_dquot_acct {
 #define XFS_QM_RELE(xqm)	((xqm)->qm_nrefs--)
 
 extern void		xfs_qm_destroy_quotainfo(xfs_mount_t *);
-extern int		xfs_qm_mount_quotas(xfs_mount_t *, int);
+extern void		xfs_qm_mount_quotas(xfs_mount_t *, int);
 extern int		xfs_qm_quotacheck(xfs_mount_t *);
 extern void		xfs_qm_unmount_quotadestroy(xfs_mount_t *);
 extern int		xfs_qm_unmount_quotas(xfs_mount_t *);

fs/xfs/quota/xfs_qm_stats.h

@@ -45,8 +45,8 @@ extern void xfs_qm_cleanup_procfs(void);
 
 # define XQM_STATS_INC(count)	do { } while (0)
 
-static __inline void xfs_qm_init_procfs(void) { };
-static __inline void xfs_qm_cleanup_procfs(void) { };
+static inline void xfs_qm_init_procfs(void) { };
+static inline void xfs_qm_cleanup_procfs(void) { };
 
 #endif
 

fs/xfs/quota/xfs_qm_syscalls.c

@@ -279,9 +279,12 @@ xfs_qm_scall_quotaoff(
 
 	/*
 	 * Write the LI_QUOTAOFF log record, and do SB changes atomically,
-	 * and synchronously.
+	 * and synchronously. If we fail to write, we should abort the
+	 * operation as it cannot be recovered safely if we crash.
 	 */
-	xfs_qm_log_quotaoff(mp, &qoffstart, flags);
+	error = xfs_qm_log_quotaoff(mp, &qoffstart, flags);
+	if (error)
+		goto out_error;
 
 	/*
 	 * Next we clear the XFS_MOUNT_*DQ_ACTIVE bit(s) in the mount struct
@@ -337,7 +340,12 @@ xfs_qm_scall_quotaoff(
 	 * So, we have QUOTAOFF start and end logitems; the start
 	 * logitem won't get overwritten until the end logitem appears...
 	 */
-	xfs_qm_log_quotaoff_end(mp, qoffstart, flags);
+	error = xfs_qm_log_quotaoff_end(mp, qoffstart, flags);
+	if (error) {
+		/* We're screwed now. Shutdown is the only option. */
+		xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
+		goto out_error;
+	}
 
 	/*
 	 * If quotas is completely disabled, close shop.
@@ -361,6 +369,7 @@ xfs_qm_scall_quotaoff(
 		XFS_PURGE_INODE(XFS_QI_GQIP(mp));
 		XFS_QI_GQIP(mp) = NULL;
 	}
+out_error:
 	mutex_unlock(&(XFS_QI_QOFFLOCK(mp)));
 
 	return (error);
@@ -371,12 +380,11 @@ xfs_qm_scall_trunc_qfiles(
 	xfs_mount_t	*mp,
 	uint		flags)
 {
-	int		error;
+	int		error = 0, error2 = 0;
 	xfs_inode_t	*qip;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return XFS_ERROR(EPERM);
-	error = 0;
 	if (!xfs_sb_version_hasquota(&mp->m_sb) || flags == 0) {
 		qdprintk("qtrunc flags=%x m_qflags=%x\n", flags, mp->m_qflags);
 		return XFS_ERROR(EINVAL);
@@ -384,22 +392,22 @@ xfs_qm_scall_trunc_qfiles(
 
 	if ((flags & XFS_DQ_USER) && mp->m_sb.sb_uquotino != NULLFSINO) {
 		error = xfs_iget(mp, NULL, mp->m_sb.sb_uquotino, 0, 0, &qip, 0);
-		if (! error) {
-			(void) xfs_truncate_file(mp, qip);
-			VN_RELE(XFS_ITOV(qip));
+		if (!error) {
+			error = xfs_truncate_file(mp, qip);
+			IRELE(qip);
 		}
 	}
 
 	if ((flags & (XFS_DQ_GROUP|XFS_DQ_PROJ)) &&
 	    mp->m_sb.sb_gquotino != NULLFSINO) {
-		error = xfs_iget(mp, NULL, mp->m_sb.sb_gquotino, 0, 0, &qip, 0);
-		if (! error) {
-			(void) xfs_truncate_file(mp, qip);
-			VN_RELE(XFS_ITOV(qip));
+		error2 = xfs_iget(mp, NULL, mp->m_sb.sb_gquotino, 0, 0, &qip, 0);
+		if (!error2) {
+			error2 = xfs_truncate_file(mp, qip);
+			IRELE(qip);
 		}
 	}
 
-	return (error);
+	return error ? error : error2;
 }
 
 
@@ -552,13 +560,13 @@ xfs_qm_scall_getqstat(
 		out->qs_uquota.qfs_nblks = uip->i_d.di_nblocks;
 		out->qs_uquota.qfs_nextents = uip->i_d.di_nextents;
 		if (tempuqip)
-			VN_RELE(XFS_ITOV(uip));
+			IRELE(uip);
 	}
 	if (gip) {
 		out->qs_gquota.qfs_nblks = gip->i_d.di_nblocks;
 		out->qs_gquota.qfs_nextents = gip->i_d.di_nextents;
 		if (tempgqip)
-			VN_RELE(XFS_ITOV(gip));
+			IRELE(gip);
 	}
 	if (mp->m_quotainfo) {
 		out->qs_incoredqs = XFS_QI_MPLNDQUOTS(mp);
@@ -726,12 +734,12 @@ xfs_qm_scall_setqlim(
 	xfs_trans_log_dquot(tp, dqp);
 
 	xfs_dqtrace_entry(dqp, "Q_SETQLIM: COMMIT");
-	xfs_trans_commit(tp, 0);
+	error = xfs_trans_commit(tp, 0);
 	xfs_qm_dqprint(dqp);
 	xfs_qm_dqrele(dqp);
 	mutex_unlock(&(XFS_QI_QOFFLOCK(mp)));
 
-	return (0);
+	return error;
 }
 
 STATIC int
@@ -1095,7 +1103,7 @@ again:
 		 * inactive code in hell.
 		 */
 		if (vnode_refd)
-			VN_RELE(vp);
+			IRELE(ip);
 		XFS_MOUNT_ILOCK(mp);
 		/*
 		 * If an inode was inserted or removed, we gotta

fs/xfs/support/ktrace.c

@@ -24,7 +24,7 @@ static int          ktrace_zentries;
 void __init
 ktrace_init(int zentries)
 {
-	ktrace_zentries = zentries;
+	ktrace_zentries = roundup_pow_of_two(zentries);
 
 	ktrace_hdr_zone = kmem_zone_init(sizeof(ktrace_t),
 					"ktrace_hdr");
@@ -47,13 +47,16 @@ ktrace_uninit(void)
  * ktrace_alloc()
  *
  * Allocate a ktrace header and enough buffering for the given
- * number of entries.
+ * number of entries. Round the number of entries up to a
+ * power of 2 so we can do fast masking to get the index from
+ * the atomic index counter.
  */
 ktrace_t *
 ktrace_alloc(int nentries, unsigned int __nocast sleep)
 {
 	ktrace_t        *ktp;
 	ktrace_entry_t  *ktep;
+	int		entries;
 
 	ktp = (ktrace_t*)kmem_zone_alloc(ktrace_hdr_zone, sleep);
 
@@ -70,11 +73,12 @@ ktrace_alloc(int nentries, unsigned int __nocast sleep)
 	/*
 	 * Special treatment for buffers with the ktrace_zentries entries
 	 */
-	if (nentries == ktrace_zentries) {
+	entries = roundup_pow_of_two(nentries);
+	if (entries == ktrace_zentries) {
 		ktep = (ktrace_entry_t*)kmem_zone_zalloc(ktrace_ent_zone,
 							    sleep);
 	} else {
-		ktep = (ktrace_entry_t*)kmem_zalloc((nentries * sizeof(*ktep)),
+		ktep = (ktrace_entry_t*)kmem_zalloc((entries * sizeof(*ktep)),
 							    sleep | KM_LARGE);
 	}
 
@@ -91,8 +95,10 @@ ktrace_alloc(int nentries, unsigned int __nocast sleep)
 	}
 
 	ktp->kt_entries  = ktep;
-	ktp->kt_nentries = nentries;
-	ktp->kt_index    = 0;
+	ktp->kt_nentries = entries;
+	ASSERT(is_power_of_2(entries));
+	ktp->kt_index_mask = entries - 1;
+	atomic_set(&ktp->kt_index, 0);
 	ktp->kt_rollover = 0;
 	return ktp;
 }
@@ -151,8 +157,6 @@ ktrace_enter(
 	void            *val14,
 	void            *val15)
 {
-	static DEFINE_SPINLOCK(wrap_lock);
-	unsigned long	flags;
 	int             index;
 	ktrace_entry_t  *ktep;
 
@@ -161,12 +165,8 @@ ktrace_enter(
 	/*
 	 * Grab an entry by pushing the index up to the next one.
 	 */
-	spin_lock_irqsave(&wrap_lock, flags);
-	index = ktp->kt_index;
-	if (++ktp->kt_index == ktp->kt_nentries)
-		ktp->kt_index = 0;
-	spin_unlock_irqrestore(&wrap_lock, flags);
-
+	index = atomic_add_return(1, &ktp->kt_index);
+	index = (index - 1) & ktp->kt_index_mask;
 	if (!ktp->kt_rollover && index == ktp->kt_nentries - 1)
 		ktp->kt_rollover = 1;
 
@@ -199,11 +199,12 @@ int
 ktrace_nentries(
 	ktrace_t        *ktp)
 {
-	if (ktp == NULL) {
+	int	index;
+	if (ktp == NULL)
 		return 0;
-	}
 
-	return (ktp->kt_rollover ? ktp->kt_nentries : ktp->kt_index);
+	index = atomic_read(&ktp->kt_index) & ktp->kt_index_mask;
+	return (ktp->kt_rollover ? ktp->kt_nentries : index);
 }
 
 /*
@@ -228,7 +229,7 @@ ktrace_first(ktrace_t   *ktp, ktrace_snap_t     *ktsp)
 	int             nentries;
 
 	if (ktp->kt_rollover)
-		index = ktp->kt_index;
+		index = atomic_read(&ktp->kt_index) & ktp->kt_index_mask;
 	else
 		index = 0;
 

fs/xfs/support/ktrace.h

@@ -30,7 +30,8 @@ typedef struct ktrace_entry {
  */
 typedef struct ktrace {
 	int		kt_nentries;	/* number of entries in trace buf */
-	int		kt_index;	/* current index in entries */
+	atomic_t	kt_index;	/* current index in entries */
+	unsigned int	kt_index_mask;
 	int		kt_rollover;
 	ktrace_entry_t	*kt_entries;	/* buffer of entries */
 } ktrace_t;

fs/xfs/xfs.h

@@ -22,7 +22,7 @@
 #define STATIC
 #define DEBUG 1
 #define XFS_BUF_LOCK_TRACKING 1
-/* #define QUOTADEBUG 1 */
+#define QUOTADEBUG 1
 #endif
 
 #ifdef CONFIG_XFS_TRACE

fs/xfs/xfs_acl.c

@@ -307,12 +307,13 @@ xfs_acl_vset(
 
 	VN_HOLD(vp);
 	error = xfs_acl_allow_set(vp, kind);
-	if (error)
-		goto out;
 
 	/* Incoming ACL exists, set file mode based on its value */
-	if (kind == _ACL_TYPE_ACCESS)
-		xfs_acl_setmode(vp, xfs_acl, &basicperms);
+	if (!error && kind == _ACL_TYPE_ACCESS)
+		error = xfs_acl_setmode(vp, xfs_acl, &basicperms);
+
+	if (error)
+		goto out;
 
 	/*
 	 * If we have more than std unix permissions, set up the actual attr.
@@ -323,7 +324,7 @@ xfs_acl_vset(
 	if (!basicperms) {
 		xfs_acl_set_attr(vp, xfs_acl, kind, &error);
 	} else {
-		xfs_acl_vremove(vp, _ACL_TYPE_ACCESS);
+		error = -xfs_acl_vremove(vp, _ACL_TYPE_ACCESS);
 	}
 
 out:
@@ -707,7 +708,9 @@ xfs_acl_inherit(
 
 	memcpy(cacl, pdaclp, sizeof(xfs_acl_t));
 	xfs_acl_filter_mode(mode, cacl);
-	xfs_acl_setmode(vp, cacl, &basicperms);
+	error = xfs_acl_setmode(vp, cacl, &basicperms);
+	if (error)
+		goto out_error;
 
 	/*
 	 * Set the Default and Access ACL on the file.  The mode is already
@@ -720,6 +723,7 @@ xfs_acl_inherit(
 		xfs_acl_set_attr(vp, pdaclp, _ACL_TYPE_DEFAULT, &error);
 	if (!error && !basicperms)
 		xfs_acl_set_attr(vp, cacl, _ACL_TYPE_ACCESS, &error);
+out_error:
 	_ACL_FREE(cacl);
 	return error;
 }

fs/xfs/xfs_alloc.c

@@ -45,7 +45,7 @@
 #define	XFSA_FIXUP_BNO_OK	1
 #define	XFSA_FIXUP_CNT_OK	2
 
-STATIC int
+STATIC void
 xfs_alloc_search_busy(xfs_trans_t *tp,
 		    xfs_agnumber_t agno,
 		    xfs_agblock_t bno,
@@ -55,24 +55,24 @@ xfs_alloc_search_busy(xfs_trans_t *tp,
 ktrace_t *xfs_alloc_trace_buf;
 
 #define	TRACE_ALLOC(s,a)	\
-	xfs_alloc_trace_alloc(__FUNCTION__, s, a, __LINE__)
+	xfs_alloc_trace_alloc(__func__, s, a, __LINE__)
 #define	TRACE_FREE(s,a,b,x,f)	\
-	xfs_alloc_trace_free(__FUNCTION__, s, mp, a, b, x, f, __LINE__)
+	xfs_alloc_trace_free(__func__, s, mp, a, b, x, f, __LINE__)
 #define	TRACE_MODAGF(s,a,f)	\
-	xfs_alloc_trace_modagf(__FUNCTION__, s, mp, a, f, __LINE__)
-#define	TRACE_BUSY(__FUNCTION__,s,ag,agb,l,sl,tp)	\
-	xfs_alloc_trace_busy(__FUNCTION__, s, mp, ag, agb, l, sl, tp, XFS_ALLOC_KTRACE_BUSY, __LINE__)
-#define	TRACE_UNBUSY(__FUNCTION__,s,ag,sl,tp)	\
-	xfs_alloc_trace_busy(__FUNCTION__, s, mp, ag, -1, -1, sl, tp, XFS_ALLOC_KTRACE_UNBUSY, __LINE__)
-#define	TRACE_BUSYSEARCH(__FUNCTION__,s,ag,agb,l,sl,tp)	\
-	xfs_alloc_trace_busy(__FUNCTION__, s, mp, ag, agb, l, sl, tp, XFS_ALLOC_KTRACE_BUSYSEARCH, __LINE__)
+	xfs_alloc_trace_modagf(__func__, s, mp, a, f, __LINE__)
+#define	TRACE_BUSY(__func__,s,ag,agb,l,sl,tp)	\
+	xfs_alloc_trace_busy(__func__, s, mp, ag, agb, l, sl, tp, XFS_ALLOC_KTRACE_BUSY, __LINE__)
+#define	TRACE_UNBUSY(__func__,s,ag,sl,tp)	\
+	xfs_alloc_trace_busy(__func__, s, mp, ag, -1, -1, sl, tp, XFS_ALLOC_KTRACE_UNBUSY, __LINE__)
+#define	TRACE_BUSYSEARCH(__func__,s,ag,agb,l,tp)	\
+	xfs_alloc_trace_busy(__func__, s, mp, ag, agb, l, 0, tp, XFS_ALLOC_KTRACE_BUSYSEARCH, __LINE__)
 #else
 #define	TRACE_ALLOC(s,a)
 #define	TRACE_FREE(s,a,b,x,f)
 #define	TRACE_MODAGF(s,a,f)
 #define	TRACE_BUSY(s,a,ag,agb,l,sl,tp)
 #define	TRACE_UNBUSY(fname,s,ag,sl,tp)
-#define	TRACE_BUSYSEARCH(fname,s,ag,agb,l,sl,tp)
+#define	TRACE_BUSYSEARCH(fname,s,ag,agb,l,tp)
 #endif	/* XFS_ALLOC_TRACE */
 
 /*
@@ -93,7 +93,7 @@ STATIC int xfs_alloc_ag_vextent_small(xfs_alloc_arg_t *,
  * Compute aligned version of the found extent.
  * Takes alignment and min length into account.
  */
-STATIC int				/* success (>= minlen) */
+STATIC void
 xfs_alloc_compute_aligned(
 	xfs_agblock_t	foundbno,	/* starting block in found extent */
 	xfs_extlen_t	foundlen,	/* length in found extent */
@@ -116,7 +116,6 @@ xfs_alloc_compute_aligned(
 	}
 	*resbno = bno;
 	*reslen = len;
-	return len >= minlen;
 }
 
 /*
@@ -837,9 +836,9 @@ xfs_alloc_ag_vextent_near(
 			if ((error = xfs_alloc_get_rec(cnt_cur, &ltbno, &ltlen, &i)))
 				goto error0;
 			XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
-			if (!xfs_alloc_compute_aligned(ltbno, ltlen,
-					args->alignment, args->minlen,
-					&ltbnoa, &ltlena))
+			xfs_alloc_compute_aligned(ltbno, ltlen, args->alignment,
+					args->minlen, &ltbnoa, &ltlena);
+			if (ltlena < args->minlen)
 				continue;
 			args->len = XFS_EXTLEN_MIN(ltlena, args->maxlen);
 			xfs_alloc_fix_len(args);
@@ -958,9 +957,9 @@ xfs_alloc_ag_vextent_near(
 			if ((error = xfs_alloc_get_rec(bno_cur_lt, &ltbno, &ltlen, &i)))
 				goto error0;
 			XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
-			if (xfs_alloc_compute_aligned(ltbno, ltlen,
-					args->alignment, args->minlen,
-					&ltbnoa, &ltlena))
+			xfs_alloc_compute_aligned(ltbno, ltlen, args->alignment,
+					args->minlen, &ltbnoa, &ltlena);
+			if (ltlena >= args->minlen)
 				break;
 			if ((error = xfs_alloc_decrement(bno_cur_lt, 0, &i)))
 				goto error0;
@@ -974,9 +973,9 @@ xfs_alloc_ag_vextent_near(
 			if ((error = xfs_alloc_get_rec(bno_cur_gt, &gtbno, &gtlen, &i)))
 				goto error0;
 			XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
-			if (xfs_alloc_compute_aligned(gtbno, gtlen,
-					args->alignment, args->minlen,
-					&gtbnoa, &gtlena))
+			xfs_alloc_compute_aligned(gtbno, gtlen, args->alignment,
+					args->minlen, &gtbnoa, &gtlena);
+			if (gtlena >= args->minlen)
 				break;
 			if ((error = xfs_alloc_increment(bno_cur_gt, 0, &i)))
 				goto error0;
@@ -2562,9 +2561,10 @@ xfs_alloc_clear_busy(xfs_trans_t *tp,
 
 
 /*
- * returns non-zero if any of (agno,bno):len is in a busy list
+ * If we find the extent in the busy list, force the log out to get the
+ * extent out of the busy list so the caller can use it straight away.
  */
-STATIC int
+STATIC void
 xfs_alloc_search_busy(xfs_trans_t *tp,
 		    xfs_agnumber_t agno,
 		    xfs_agblock_t bno,
@@ -2572,7 +2572,6 @@ xfs_alloc_search_busy(xfs_trans_t *tp,
 {
 	xfs_mount_t		*mp;
 	xfs_perag_busy_t	*bsy;
-	int			n;
 	xfs_agblock_t		uend, bend;
 	xfs_lsn_t		lsn;
 	int			cnt;
@@ -2585,21 +2584,18 @@ xfs_alloc_search_busy(xfs_trans_t *tp,
 	uend = bno + len - 1;
 
 	/* search pagb_list for this slot, skipping open slots */
-	for (bsy = mp->m_perag[agno].pagb_list, n = 0;
-	     cnt; bsy++, n++) {
+	for (bsy = mp->m_perag[agno].pagb_list; cnt; bsy++) {
 
 		/*
 		 * (start1,length1) within (start2, length2)
 		 */
 		if (bsy->busy_tp != NULL) {
 			bend = bsy->busy_start + bsy->busy_length - 1;
-			if ((bno > bend) ||
-			    (uend < bsy->busy_start)) {
+			if ((bno > bend) || (uend < bsy->busy_start)) {
 				cnt--;
 			} else {
 				TRACE_BUSYSEARCH("xfs_alloc_search_busy",
-						 "found1", agno, bno, len, n,
-						 tp);
+					 "found1", agno, bno, len, tp);
 				break;
 			}
 		}
@@ -2610,15 +2606,12 @@ xfs_alloc_search_busy(xfs_trans_t *tp,
 	 * transaction that freed the block
 	 */
 	if (cnt) {
-		TRACE_BUSYSEARCH("xfs_alloc_search_busy", "found", agno, bno, len, n, tp);
+		TRACE_BUSYSEARCH("xfs_alloc_search_busy", "found", agno, bno, len, tp);
 		lsn = bsy->busy_tp->t_commit_lsn;
 		spin_unlock(&mp->m_perag[agno].pagb_lock);
 		xfs_log_force(mp, lsn, XFS_LOG_FORCE|XFS_LOG_SYNC);
 	} else {
-		TRACE_BUSYSEARCH("xfs_alloc_search_busy", "not-found", agno, bno, len, n, tp);
-		n = -1;
+		TRACE_BUSYSEARCH("xfs_alloc_search_busy", "not-found", agno, bno, len, tp);
 		spin_unlock(&mp->m_perag[agno].pagb_lock);
 	}
-
-	return n;
 }

fs/xfs/xfs_attr.c

@@ -2646,14 +2646,6 @@ attr_trusted_capable(
 	return 0;
 }
 
-STATIC int
-attr_secure_capable(
-	bhv_vnode_t	*vp,
-	cred_t		*cred)
-{
-	return -ENOSECURITY;
-}
-
 STATIC int
 attr_system_set(
 	bhv_vnode_t *vp, char *name, void *data, size_t size, int xflags)
@@ -2724,7 +2716,7 @@ struct attrnames attr_secure = {
 	.attr_get	= attr_generic_get,
 	.attr_set	= attr_generic_set,
 	.attr_remove	= attr_generic_remove,
-	.attr_capable	= attr_secure_capable,
+	.attr_capable	= (attrcapable_t)fs_noerr,
 };
 
 struct attrnames attr_user = {

fs/xfs/xfs_attr_leaf.c

@@ -166,7 +166,7 @@ xfs_attr_shortform_bytesfit(xfs_inode_t *dp, int bytes)
 
 	if (!(mp->m_flags & XFS_MOUNT_ATTR2)) {
 		if (bytes <= XFS_IFORK_ASIZE(dp))
-			return mp->m_attroffset >> 3;
+			return dp->i_d.di_forkoff;
 		return 0;
 	}
 

fs/xfs/xfs_bmap.c

@@ -323,13 +323,13 @@ xfs_bmap_trace_pre_update(
 	int		whichfork);	/* data or attr fork */
 
 #define	XFS_BMAP_TRACE_DELETE(d,ip,i,c,w)	\
-	xfs_bmap_trace_delete(__FUNCTION__,d,ip,i,c,w)
+	xfs_bmap_trace_delete(__func__,d,ip,i,c,w)
 #define	XFS_BMAP_TRACE_INSERT(d,ip,i,c,r1,r2,w)	\
-	xfs_bmap_trace_insert(__FUNCTION__,d,ip,i,c,r1,r2,w)
+	xfs_bmap_trace_insert(__func__,d,ip,i,c,r1,r2,w)
 #define	XFS_BMAP_TRACE_POST_UPDATE(d,ip,i,w)	\
-	xfs_bmap_trace_post_update(__FUNCTION__,d,ip,i,w)
+	xfs_bmap_trace_post_update(__func__,d,ip,i,w)
 #define	XFS_BMAP_TRACE_PRE_UPDATE(d,ip,i,w)	\
-	xfs_bmap_trace_pre_update(__FUNCTION__,d,ip,i,w)
+	xfs_bmap_trace_pre_update(__func__,d,ip,i,w)
 #else
 #define	XFS_BMAP_TRACE_DELETE(d,ip,i,c,w)
 #define	XFS_BMAP_TRACE_INSERT(d,ip,i,c,r1,r2,w)
@@ -2402,7 +2402,7 @@ xfs_bmap_extsize_align(
 
 #define XFS_ALLOC_GAP_UNITS	4
 
-STATIC int
+STATIC void
 xfs_bmap_adjacent(
 	xfs_bmalloca_t	*ap)		/* bmap alloc argument struct */
 {
@@ -2548,7 +2548,6 @@ xfs_bmap_adjacent(
 			ap->rval = gotbno;
 	}
 #undef ISVALID
-	return 0;
 }
 
 STATIC int
@@ -4154,16 +4153,21 @@ xfs_bmap_compute_maxlevels(
 	 * number of leaf entries, is controlled by the type of di_nextents
 	 * (a signed 32-bit number, xfs_extnum_t), or by di_anextents
 	 * (a signed 16-bit number, xfs_aextnum_t).
+	 *
+	 * Note that we can no longer assume that if we are in ATTR1 that
+	 * the fork offset of all the inodes will be (m_attroffset >> 3)
+	 * because we could have mounted with ATTR2 and then mounted back
+	 * with ATTR1, keeping the di_forkoff's fixed but probably at
+	 * various positions. Therefore, for both ATTR1 and ATTR2
+	 * we have to assume the worst case scenario of a minimum size
+	 * available.
 	 */
 	if (whichfork == XFS_DATA_FORK) {
 		maxleafents = MAXEXTNUM;
-		sz = (mp->m_flags & XFS_MOUNT_ATTR2) ?
-			XFS_BMDR_SPACE_CALC(MINDBTPTRS) : mp->m_attroffset;
+		sz = XFS_BMDR_SPACE_CALC(MINDBTPTRS);
 	} else {
 		maxleafents = MAXAEXTNUM;
-		sz = (mp->m_flags & XFS_MOUNT_ATTR2) ?
-			XFS_BMDR_SPACE_CALC(MINABTPTRS) :
-			mp->m_sb.sb_inodesize - mp->m_attroffset;
+		sz = XFS_BMDR_SPACE_CALC(MINABTPTRS);
 	}
 	maxrootrecs = (int)XFS_BTREE_BLOCK_MAXRECS(sz, xfs_bmdr, 0);
 	minleafrecs = mp->m_bmap_dmnr[0];
@@ -5772,7 +5776,6 @@ xfs_getbmap(
 	int			error;		/* return value */
 	__int64_t		fixlen;		/* length for -1 case */
 	int			i;		/* extent number */
-	bhv_vnode_t		*vp;		/* corresponding vnode */
 	int			lock;		/* lock state */
 	xfs_bmbt_irec_t		*map;		/* buffer for user's data */
 	xfs_mount_t		*mp;		/* file system mount point */
@@ -5789,7 +5792,6 @@ xfs_getbmap(
 	int			bmapi_flags;	/* flags for xfs_bmapi */
 	__int32_t		oflags;		/* getbmapx bmv_oflags field */
 
-	vp = XFS_ITOV(ip);
 	mp = ip->i_mount;
 
 	whichfork = interface & BMV_IF_ATTRFORK ? XFS_ATTR_FORK : XFS_DATA_FORK;
@@ -5811,7 +5813,7 @@ xfs_getbmap(
 	if ((interface & BMV_IF_NO_DMAPI_READ) == 0 &&
 	    DM_EVENT_ENABLED(ip, DM_EVENT_READ) &&
 	    whichfork == XFS_DATA_FORK) {
-		error = XFS_SEND_DATA(mp, DM_EVENT_READ, vp, 0, 0, 0, NULL);
+		error = XFS_SEND_DATA(mp, DM_EVENT_READ, ip, 0, 0, 0, NULL);
 		if (error)
 			return XFS_ERROR(error);
 	}
@@ -5869,6 +5871,10 @@ xfs_getbmap(
 		/* xfs_fsize_t last_byte = xfs_file_last_byte(ip); */
 		error = xfs_flush_pages(ip, (xfs_off_t)0,
 					       -1, 0, FI_REMAPF);
+		if (error) {
+			xfs_iunlock(ip, XFS_IOLOCK_SHARED);
+		return error;
+		}
 	}
 
 	ASSERT(whichfork == XFS_ATTR_FORK || ip->i_delayed_blks == 0);
@@ -6162,10 +6168,10 @@ xfs_check_block(
 			}
 			if (*thispa == *pp) {
 				cmn_err(CE_WARN, "%s: thispa(%d) == pp(%d) %Ld",
-					__FUNCTION__, j, i,
+					__func__, j, i,
 					(unsigned long long)be64_to_cpu(*thispa));
 				panic("%s: ptrs are equal in node\n",
-					__FUNCTION__);
+					__func__);
 			}
 		}
 	}
@@ -6192,7 +6198,7 @@ xfs_bmap_check_leaf_extents(
 	xfs_mount_t		*mp;	/* file system mount structure */
 	__be64			*pp;	/* pointer to block address */
 	xfs_bmbt_rec_t		*ep;	/* pointer to current extent */
-	xfs_bmbt_rec_t		*lastp; /* pointer to previous extent */
+	xfs_bmbt_rec_t		last = {0, 0}; /* last extent in prev block */
 	xfs_bmbt_rec_t		*nextp;	/* pointer to next extent */
 	int			bp_release = 0;
 
@@ -6262,7 +6268,6 @@ xfs_bmap_check_leaf_extents(
 	/*
 	 * Loop over all leaf nodes checking that all extents are in the right order.
 	 */
-	lastp = NULL;
 	for (;;) {
 		xfs_fsblock_t	nextbno;
 		xfs_extnum_t	num_recs;
@@ -6283,18 +6288,16 @@ xfs_bmap_check_leaf_extents(
 		 */
 
 		ep = XFS_BTREE_REC_ADDR(xfs_bmbt, block, 1);
+		if (i) {
+			xfs_btree_check_rec(XFS_BTNUM_BMAP, &last, ep);
+		}
 		for (j = 1; j < num_recs; j++) {
 			nextp = XFS_BTREE_REC_ADDR(xfs_bmbt, block, j + 1);
-			if (lastp) {
-				xfs_btree_check_rec(XFS_BTNUM_BMAP,
-					(void *)lastp, (void *)ep);
-			}
-			xfs_btree_check_rec(XFS_BTNUM_BMAP, (void *)ep,
-				(void *)(nextp));
-			lastp = ep;
+			xfs_btree_check_rec(XFS_BTNUM_BMAP, ep, nextp);
 			ep = nextp;
 		}
 
+		last = *ep;
 		i += num_recs;
 		if (bp_release) {
 			bp_release = 0;
@@ -6325,13 +6328,13 @@ xfs_bmap_check_leaf_extents(
 	return;
 
 error0:
-	cmn_err(CE_WARN, "%s: at error0", __FUNCTION__);
+	cmn_err(CE_WARN, "%s: at error0", __func__);
 	if (bp_release)
 		xfs_trans_brelse(NULL, bp);
 error_norelse:
 	cmn_err(CE_WARN, "%s: BAD after btree leaves for %d extents",
-		__FUNCTION__, i);
-	panic("%s: CORRUPTED BTREE OR SOMETHING", __FUNCTION__);
+		__func__, i);
+	panic("%s: CORRUPTED BTREE OR SOMETHING", __func__);
 	return;
 }
 #endif

fs/xfs/xfs_bmap.h

@@ -151,7 +151,7 @@ xfs_bmap_trace_exlist(
 	xfs_extnum_t		cnt,		/* count of entries in list */
 	int			whichfork);	/* data or attr fork */
 #define	XFS_BMAP_TRACE_EXLIST(ip,c,w)	\
-	xfs_bmap_trace_exlist(__FUNCTION__,ip,c,w)
+	xfs_bmap_trace_exlist(__func__,ip,c,w)
 #else
 #define	XFS_BMAP_TRACE_EXLIST(ip,c,w)
 #endif

fs/xfs/xfs_bmap_btree.c

@@ -275,21 +275,21 @@ xfs_bmbt_trace_cursor(
 }
 
 #define	XFS_BMBT_TRACE_ARGBI(c,b,i)	\
-	xfs_bmbt_trace_argbi(__FUNCTION__, c, b, i, __LINE__)
+	xfs_bmbt_trace_argbi(__func__, c, b, i, __LINE__)
 #define	XFS_BMBT_TRACE_ARGBII(c,b,i,j)	\
-	xfs_bmbt_trace_argbii(__FUNCTION__, c, b, i, j, __LINE__)
+	xfs_bmbt_trace_argbii(__func__, c, b, i, j, __LINE__)
 #define	XFS_BMBT_TRACE_ARGFFFI(c,o,b,i,j)	\
-	xfs_bmbt_trace_argfffi(__FUNCTION__, c, o, b, i, j, __LINE__)
+	xfs_bmbt_trace_argfffi(__func__, c, o, b, i, j, __LINE__)
 #define	XFS_BMBT_TRACE_ARGI(c,i)	\
-	xfs_bmbt_trace_argi(__FUNCTION__, c, i, __LINE__)
+	xfs_bmbt_trace_argi(__func__, c, i, __LINE__)
 #define	XFS_BMBT_TRACE_ARGIFK(c,i,f,s)	\
-	xfs_bmbt_trace_argifk(__FUNCTION__, c, i, f, s, __LINE__)
+	xfs_bmbt_trace_argifk(__func__, c, i, f, s, __LINE__)
 #define	XFS_BMBT_TRACE_ARGIFR(c,i,f,r)	\
-	xfs_bmbt_trace_argifr(__FUNCTION__, c, i, f, r, __LINE__)
+	xfs_bmbt_trace_argifr(__func__, c, i, f, r, __LINE__)
 #define	XFS_BMBT_TRACE_ARGIK(c,i,k)	\
-	xfs_bmbt_trace_argik(__FUNCTION__, c, i, k, __LINE__)
+	xfs_bmbt_trace_argik(__func__, c, i, k, __LINE__)
 #define	XFS_BMBT_TRACE_CURSOR(c,s)	\
-	xfs_bmbt_trace_cursor(__FUNCTION__, c, s, __LINE__)
+	xfs_bmbt_trace_cursor(__func__, c, s, __LINE__)
 #else
 #define	XFS_BMBT_TRACE_ARGBI(c,b,i)
 #define	XFS_BMBT_TRACE_ARGBII(c,b,i,j)
@@ -2027,6 +2027,24 @@ xfs_bmbt_increment(
 
 /*
  * Insert the current record at the point referenced by cur.
+ *
+ * A multi-level split of the tree on insert will invalidate the original
+ * cursor. It appears, however, that some callers assume that the cursor is
+ * always valid. Hence if we do a multi-level split we need to revalidate the
+ * cursor.
+ *
+ * When a split occurs, we will see a new cursor returned. Use that as a
+ * trigger to determine if we need to revalidate the original cursor. If we get
+ * a split, then use the original irec to lookup up the path of the record we
+ * just inserted.
+ *
+ * Note that the fact that the btree root is in the inode means that we can
+ * have the level of the tree change without a "split" occurring at the root
+ * level. What happens is that the root is migrated to an allocated block and
+ * the inode root is pointed to it. This means a single split can change the
+ * level of the tree (level 2 -> level 3) and invalidate the old cursor. Hence
+ * the level change should be accounted as a split so as to correctly trigger a
+ * revalidation of the old cursor.
  */
 int					/* error */
 xfs_bmbt_insert(
@@ -2039,11 +2057,14 @@ xfs_bmbt_insert(
 	xfs_fsblock_t	nbno;
 	xfs_btree_cur_t	*ncur;
 	xfs_bmbt_rec_t	nrec;
+	xfs_bmbt_irec_t	oirec;		/* original irec */
 	xfs_btree_cur_t	*pcur;
+	int		splits = 0;
 
 	XFS_BMBT_TRACE_CURSOR(cur, ENTRY);
 	level = 0;
 	nbno = NULLFSBLOCK;
+	oirec = cur->bc_rec.b;
 	xfs_bmbt_disk_set_all(&nrec, &cur->bc_rec.b);
 	ncur = NULL;
 	pcur = cur;
@@ -2052,11 +2073,13 @@ xfs_bmbt_insert(
 				&i))) {
 			if (pcur != cur)
 				xfs_btree_del_cursor(pcur, XFS_BTREE_ERROR);
-			XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-			return error;
+			goto error0;
 		}
 		XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
 		if (pcur != cur && (ncur || nbno == NULLFSBLOCK)) {
+			/* allocating a new root is effectively a split */
+			if (cur->bc_nlevels != pcur->bc_nlevels)
+				splits++;
 			cur->bc_nlevels = pcur->bc_nlevels;
 			cur->bc_private.b.allocated +=
 				pcur->bc_private.b.allocated;
@@ -2070,10 +2093,21 @@ xfs_bmbt_insert(
 			xfs_btree_del_cursor(pcur, XFS_BTREE_NOERROR);
 		}
 		if (ncur) {
+			splits++;
 			pcur = ncur;
 			ncur = NULL;
 		}
 	} while (nbno != NULLFSBLOCK);
+
+	if (splits > 1) {
+		/* revalidate the old cursor as we had a multi-level split */
+		error = xfs_bmbt_lookup_eq(cur, oirec.br_startoff,
+				oirec.br_startblock, oirec.br_blockcount, &i);
+		if (error)
+			goto error0;
+		ASSERT(i == 1);
+	}
+
 	XFS_BMBT_TRACE_CURSOR(cur, EXIT);
 	*stat = i;
 	return 0;

fs/xfs/xfs_buf_item.c

@@ -645,7 +645,12 @@ xfs_buf_item_push(
 	bp = bip->bli_buf;
 
 	if (XFS_BUF_ISDELAYWRITE(bp)) {
-		xfs_bawrite(bip->bli_item.li_mountp, bp);
+		int	error;
+		error = xfs_bawrite(bip->bli_item.li_mountp, bp);
+		if (error)
+			xfs_fs_cmn_err(CE_WARN, bip->bli_item.li_mountp,
+			"xfs_buf_item_push: pushbuf error %d on bip %p, bp %p",
+					error, bip, bp);
 	} else {
 		xfs_buf_relse(bp);
 	}

fs/xfs/xfs_dir2.c

@@ -44,6 +44,7 @@
 #include "xfs_error.h"
 #include "xfs_vnodeops.h"
 
+struct xfs_name xfs_name_dotdot = {"..", 2};
 
 void
 xfs_dir_mount(
@@ -146,8 +147,7 @@ int
 xfs_dir_createname(
 	xfs_trans_t		*tp,
 	xfs_inode_t		*dp,
-	char			*name,
-	int			namelen,
+	struct xfs_name		*name,
 	xfs_ino_t		inum,		/* new entry inode number */
 	xfs_fsblock_t		*first,		/* bmap's firstblock */
 	xfs_bmap_free_t		*flist,		/* bmap's freeblock list */
@@ -162,9 +162,9 @@ xfs_dir_createname(
 		return rval;
 	XFS_STATS_INC(xs_dir_create);
 
-	args.name = name;
-	args.namelen = namelen;
-	args.hashval = xfs_da_hashname(name, namelen);
+	args.name = name->name;
+	args.namelen = name->len;
+	args.hashval = xfs_da_hashname(name->name, name->len);
 	args.inumber = inum;
 	args.dp = dp;
 	args.firstblock = first;
@@ -197,8 +197,7 @@ int
 xfs_dir_lookup(
 	xfs_trans_t	*tp,
 	xfs_inode_t	*dp,
-	char		*name,
-	int		namelen,
+	struct xfs_name	*name,
 	xfs_ino_t	*inum)		/* out: inode number */
 {
 	xfs_da_args_t	args;
@@ -207,18 +206,14 @@ xfs_dir_lookup(
 
 	ASSERT((dp->i_d.di_mode & S_IFMT) == S_IFDIR);
 	XFS_STATS_INC(xs_dir_lookup);
+	memset(&args, 0, sizeof(xfs_da_args_t));
 
-	args.name = name;
-	args.namelen = namelen;
-	args.hashval = xfs_da_hashname(name, namelen);
-	args.inumber = 0;
+	args.name = name->name;
+	args.namelen = name->len;
+	args.hashval = xfs_da_hashname(name->name, name->len);
 	args.dp = dp;
-	args.firstblock = NULL;
-	args.flist = NULL;
-	args.total = 0;
 	args.whichfork = XFS_DATA_FORK;
 	args.trans = tp;
-	args.justcheck = args.addname = 0;
 	args.oknoent = 1;
 
 	if (dp->i_d.di_format == XFS_DINODE_FMT_LOCAL)
@@ -247,8 +242,7 @@ int
 xfs_dir_removename(
 	xfs_trans_t	*tp,
 	xfs_inode_t	*dp,
-	char		*name,
-	int		namelen,
+	struct xfs_name	*name,
 	xfs_ino_t	ino,
 	xfs_fsblock_t	*first,		/* bmap's firstblock */
 	xfs_bmap_free_t	*flist,		/* bmap's freeblock list */
@@ -261,9 +255,9 @@ xfs_dir_removename(
 	ASSERT((dp->i_d.di_mode & S_IFMT) == S_IFDIR);
 	XFS_STATS_INC(xs_dir_remove);
 
-	args.name = name;
-	args.namelen = namelen;
-	args.hashval = xfs_da_hashname(name, namelen);
+	args.name = name->name;
+	args.namelen = name->len;
+	args.hashval = xfs_da_hashname(name->name, name->len);
 	args.inumber = ino;
 	args.dp = dp;
 	args.firstblock = first;
@@ -329,8 +323,7 @@ int
 xfs_dir_replace(
 	xfs_trans_t	*tp,
 	xfs_inode_t	*dp,
-	char		*name,		/* name of entry to replace */
-	int		namelen,
+	struct xfs_name	*name,		/* name of entry to replace */
 	xfs_ino_t	inum,		/* new inode number */
 	xfs_fsblock_t	*first,		/* bmap's firstblock */
 	xfs_bmap_free_t	*flist,		/* bmap's freeblock list */
@@ -345,9 +338,9 @@ xfs_dir_replace(
 	if ((rval = xfs_dir_ino_validate(tp->t_mountp, inum)))
 		return rval;
 
-	args.name = name;
-	args.namelen = namelen;
-	args.hashval = xfs_da_hashname(name, namelen);
+	args.name = name->name;
+	args.namelen = name->len;
+	args.hashval = xfs_da_hashname(name->name, name->len);
 	args.inumber = inum;
 	args.dp = dp;
 	args.firstblock = first;
@@ -374,28 +367,29 @@ xfs_dir_replace(
 
 /*
  * See if this entry can be added to the directory without allocating space.
+ * First checks that the caller couldn't reserve enough space (resblks = 0).
  */
 int
 xfs_dir_canenter(
 	xfs_trans_t	*tp,
 	xfs_inode_t	*dp,
-	char		*name,		/* name of entry to add */
-	int		namelen)
+	struct xfs_name	*name,		/* name of entry to add */
+	uint		resblks)
 {
 	xfs_da_args_t	args;
 	int		rval;
 	int		v;		/* type-checking value */
 
+	if (resblks)
+		return 0;
+
 	ASSERT((dp->i_d.di_mode & S_IFMT) == S_IFDIR);
+	memset(&args, 0, sizeof(xfs_da_args_t));
 
-	args.name = name;
-	args.namelen = namelen;
-	args.hashval = xfs_da_hashname(name, namelen);
-	args.inumber = 0;
+	args.name = name->name;
+	args.namelen = name->len;
+	args.hashval = xfs_da_hashname(name->name, name->len);
 	args.dp = dp;
-	args.firstblock = NULL;
-	args.flist = NULL;
-	args.total = 0;
 	args.whichfork = XFS_DATA_FORK;
 	args.trans = tp;
 	args.justcheck = args.addname = args.oknoent = 1;

fs/xfs/xfs_dir2.h

@@ -59,6 +59,8 @@ typedef	__uint32_t	xfs_dir2_db_t;
  */
 typedef	xfs_off_t	xfs_dir2_off_t;
 
+extern struct xfs_name	xfs_name_dotdot;
+
 /*
  * Generic directory interface routines
  */
@@ -68,21 +70,21 @@ extern int xfs_dir_isempty(struct xfs_inode *dp);
 extern int xfs_dir_init(struct xfs_trans *tp, struct xfs_inode *dp,
 				struct xfs_inode *pdp);
 extern int xfs_dir_createname(struct xfs_trans *tp, struct xfs_inode *dp,
-				char *name, int namelen, xfs_ino_t inum,
+				struct xfs_name *name, xfs_ino_t inum,
 				xfs_fsblock_t *first,
 				struct xfs_bmap_free *flist, xfs_extlen_t tot);
 extern int xfs_dir_lookup(struct xfs_trans *tp, struct xfs_inode *dp,
-				char *name, int namelen, xfs_ino_t *inum);
+				struct xfs_name *name, xfs_ino_t *inum);
 extern int xfs_dir_removename(struct xfs_trans *tp, struct xfs_inode *dp,
-				char *name, int namelen, xfs_ino_t ino,
+				struct xfs_name *name, xfs_ino_t ino,
 				xfs_fsblock_t *first,
 				struct xfs_bmap_free *flist, xfs_extlen_t tot);
 extern int xfs_dir_replace(struct xfs_trans *tp, struct xfs_inode *dp,
-				char *name, int namelen, xfs_ino_t inum,
+				struct xfs_name *name, xfs_ino_t inum,
 				xfs_fsblock_t *first,
 				struct xfs_bmap_free *flist, xfs_extlen_t tot);
 extern int xfs_dir_canenter(struct xfs_trans *tp, struct xfs_inode *dp,
-				char *name, int namelen);
+				struct xfs_name *name, uint resblks);
 extern int xfs_dir_ino_validate(struct xfs_mount *mp, xfs_ino_t ino);
 
 /*

fs/xfs/xfs_filestream.c

@@ -73,7 +73,7 @@ xfs_filestreams_trace(
 #define TRACE4(mp,t,a0,a1,a2,a3)	TRACE6(mp,t,a0,a1,a2,a3,0,0)
 #define TRACE5(mp,t,a0,a1,a2,a3,a4)	TRACE6(mp,t,a0,a1,a2,a3,a4,0)
 #define TRACE6(mp,t,a0,a1,a2,a3,a4,a5) \
-	xfs_filestreams_trace(mp, t, __FUNCTION__, __LINE__, \
+	xfs_filestreams_trace(mp, t, __func__, __LINE__, \
 				(__psunsigned_t)a0, (__psunsigned_t)a1, \
 				(__psunsigned_t)a2, (__psunsigned_t)a3, \
 				(__psunsigned_t)a4, (__psunsigned_t)a5)

fs/xfs/xfs_ialloc.c

@@ -107,6 +107,16 @@ xfs_ialloc_log_di(
 /*
  * Allocation group level functions.
  */
+static inline int
+xfs_ialloc_cluster_alignment(
+	xfs_alloc_arg_t	*args)
+{
+	if (xfs_sb_version_hasalign(&args->mp->m_sb) &&
+	    args->mp->m_sb.sb_inoalignmt >=
+	     XFS_B_TO_FSBT(args->mp, XFS_INODE_CLUSTER_SIZE(args->mp)))
+		return args->mp->m_sb.sb_inoalignmt;
+	return 1;
+}
 
 /*
  * Allocate new inodes in the allocation group specified by agbp.
@@ -167,10 +177,24 @@ xfs_ialloc_ag_alloc(
 		args.mod = args.total = args.wasdel = args.isfl =
 			args.userdata = args.minalignslop = 0;
 		args.prod = 1;
-		args.alignment = 1;
+
 		/*
-		 * Allow space for the inode btree to split.
+		 * We need to take into account alignment here to ensure that
+		 * we don't modify the free list if we fail to have an exact
+		 * block. If we don't have an exact match, and every oher
+		 * attempt allocation attempt fails, we'll end up cancelling
+		 * a dirty transaction and shutting down.
+		 *
+		 * For an exact allocation, alignment must be 1,
+		 * however we need to take cluster alignment into account when
+		 * fixing up the freelist. Use the minalignslop field to
+		 * indicate that extra blocks might be required for alignment,
+		 * but not to use them in the actual exact allocation.
 		 */
+		args.alignment = 1;
+		args.minalignslop = xfs_ialloc_cluster_alignment(&args) - 1;
+
+		/* Allow space for the inode btree to split. */
 		args.minleft = XFS_IN_MAXLEVELS(args.mp) - 1;
 		if ((error = xfs_alloc_vextent(&args)))
 			return error;
@@ -191,13 +215,8 @@ xfs_ialloc_ag_alloc(
 			ASSERT(!(args.mp->m_flags & XFS_MOUNT_NOALIGN));
 			args.alignment = args.mp->m_dalign;
 			isaligned = 1;
-		} else if (xfs_sb_version_hasalign(&args.mp->m_sb) &&
-			   args.mp->m_sb.sb_inoalignmt >=
-			   XFS_B_TO_FSBT(args.mp,
-			  	XFS_INODE_CLUSTER_SIZE(args.mp)))
-				args.alignment = args.mp->m_sb.sb_inoalignmt;
-		else
-			args.alignment = 1;
+		} else
+			args.alignment = xfs_ialloc_cluster_alignment(&args);
 		/*
 		 * Need to figure out where to allocate the inode blocks.
 		 * Ideally they should be spaced out through the a.g.
@@ -230,12 +249,7 @@ xfs_ialloc_ag_alloc(
 		args.agbno = be32_to_cpu(agi->agi_root);
 		args.fsbno = XFS_AGB_TO_FSB(args.mp,
 				be32_to_cpu(agi->agi_seqno), args.agbno);
-		if (xfs_sb_version_hasalign(&args.mp->m_sb) &&
-			args.mp->m_sb.sb_inoalignmt >=
-			XFS_B_TO_FSBT(args.mp, XFS_INODE_CLUSTER_SIZE(args.mp)))
-				args.alignment = args.mp->m_sb.sb_inoalignmt;
-		else
-			args.alignment = 1;
+		args.alignment = xfs_ialloc_cluster_alignment(&args);
 		if ((error = xfs_alloc_vextent(&args)))
 			return error;
 	}

fs/xfs/xfs_iget.c

@@ -78,7 +78,6 @@ xfs_iget_core(
 	xfs_inode_t	*ip;
 	xfs_inode_t	*iq;
 	int		error;
-	xfs_icluster_t	*icl, *new_icl = NULL;
 	unsigned long	first_index, mask;
 	xfs_perag_t	*pag;
 	xfs_agino_t	agino;
@@ -229,11 +228,9 @@ finish_inode:
 	}
 
 	/*
-	 * This is a bit messy - we preallocate everything we _might_
-	 * need before we pick up the ici lock. That way we don't have to
-	 * juggle locks and go all the way back to the start.
+	 * Preload the radix tree so we can insert safely under the
+	 * write spinlock.
 	 */
-	new_icl = kmem_zone_alloc(xfs_icluster_zone, KM_SLEEP);
 	if (radix_tree_preload(GFP_KERNEL)) {
 		xfs_idestroy(ip);
 		delay(1);
@@ -242,17 +239,6 @@ finish_inode:
 	mask = ~(((XFS_INODE_CLUSTER_SIZE(mp) >> mp->m_sb.sb_inodelog)) - 1);
 	first_index = agino & mask;
 	write_lock(&pag->pag_ici_lock);
-
-	/*
-	 * Find the cluster if it exists
-	 */
-	icl = NULL;
-	if (radix_tree_gang_lookup(&pag->pag_ici_root, (void**)&iq,
-							first_index, 1)) {
-		if ((XFS_INO_TO_AGINO(mp, iq->i_ino) & mask) == first_index)
-			icl = iq->i_cluster;
-	}
-
 	/*
 	 * insert the new inode
 	 */
@@ -267,30 +253,13 @@ finish_inode:
 	}
 
 	/*
-	 * These values _must_ be set before releasing ihlock!
+	 * These values _must_ be set before releasing the radix tree lock!
 	 */
 	ip->i_udquot = ip->i_gdquot = NULL;
 	xfs_iflags_set(ip, XFS_INEW);
 
-	ASSERT(ip->i_cluster == NULL);
-
-	if (!icl) {
-		spin_lock_init(&new_icl->icl_lock);
-		INIT_HLIST_HEAD(&new_icl->icl_inodes);
-		icl = new_icl;
-		new_icl = NULL;
-	} else {
-		ASSERT(!hlist_empty(&icl->icl_inodes));
-	}
-	spin_lock(&icl->icl_lock);
-	hlist_add_head(&ip->i_cnode, &icl->icl_inodes);
-	ip->i_cluster = icl;
-	spin_unlock(&icl->icl_lock);
-
 	write_unlock(&pag->pag_ici_lock);
 	radix_tree_preload_end();
-	if (new_icl)
-		kmem_zone_free(xfs_icluster_zone, new_icl);
 
 	/*
 	 * Link ip to its mount and thread it on the mount's inode list.
@@ -528,18 +497,6 @@ xfs_iextract(
 	write_unlock(&pag->pag_ici_lock);
 	xfs_put_perag(mp, pag);
 
-	/*
-	 * Remove from cluster list
-	 */
-	mp = ip->i_mount;
-	spin_lock(&ip->i_cluster->icl_lock);
-	hlist_del(&ip->i_cnode);
-	spin_unlock(&ip->i_cluster->icl_lock);
-
-	/* was last inode in cluster? */
-	if (hlist_empty(&ip->i_cluster->icl_inodes))
-		kmem_zone_free(xfs_icluster_zone, ip->i_cluster);
-
 	/*
 	 * Remove from mount's inode list.
 	 */

fs/xfs/xfs_inode.c

@@ -55,7 +55,6 @@
 
 kmem_zone_t *xfs_ifork_zone;
 kmem_zone_t *xfs_inode_zone;
-kmem_zone_t *xfs_icluster_zone;
 
 /*
  * Used in xfs_itruncate().  This is the maximum number of extents
@@ -125,6 +124,90 @@ xfs_inobp_check(
 }
 #endif
 
+/*
+ * Find the buffer associated with the given inode map
+ * We do basic validation checks on the buffer once it has been
+ * retrieved from disk.
+ */
+STATIC int
+xfs_imap_to_bp(
+	xfs_mount_t	*mp,
+	xfs_trans_t	*tp,
+	xfs_imap_t	*imap,
+	xfs_buf_t	**bpp,
+	uint		buf_flags,
+	uint		imap_flags)
+{
+	int		error;
+	int		i;
+	int		ni;
+	xfs_buf_t	*bp;
+
+	error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, imap->im_blkno,
+				   (int)imap->im_len, buf_flags, &bp);
+	if (error) {
+		if (error != EAGAIN) {
+			cmn_err(CE_WARN,
+				"xfs_imap_to_bp: xfs_trans_read_buf()returned "
+				"an error %d on %s.  Returning error.",
+				error, mp->m_fsname);
+		} else {
+			ASSERT(buf_flags & XFS_BUF_TRYLOCK);
+		}
+		return error;
+	}
+
+	/*
+	 * Validate the magic number and version of every inode in the buffer
+	 * (if DEBUG kernel) or the first inode in the buffer, otherwise.
+	 */
+#ifdef DEBUG
+	ni = BBTOB(imap->im_len) >> mp->m_sb.sb_inodelog;
+#else	/* usual case */
+	ni = 1;
+#endif
+
+	for (i = 0; i < ni; i++) {
+		int		di_ok;
+		xfs_dinode_t	*dip;
+
+		dip = (xfs_dinode_t *)xfs_buf_offset(bp,
+					(i << mp->m_sb.sb_inodelog));
+		di_ok = be16_to_cpu(dip->di_core.di_magic) == XFS_DINODE_MAGIC &&
+			    XFS_DINODE_GOOD_VERSION(dip->di_core.di_version);
+		if (unlikely(XFS_TEST_ERROR(!di_ok, mp,
+						XFS_ERRTAG_ITOBP_INOTOBP,
+						XFS_RANDOM_ITOBP_INOTOBP))) {
+			if (imap_flags & XFS_IMAP_BULKSTAT) {
+				xfs_trans_brelse(tp, bp);
+				return XFS_ERROR(EINVAL);
+			}
+			XFS_CORRUPTION_ERROR("xfs_imap_to_bp",
+						XFS_ERRLEVEL_HIGH, mp, dip);
+#ifdef DEBUG
+			cmn_err(CE_PANIC,
+					"Device %s - bad inode magic/vsn "
+					"daddr %lld #%d (magic=%x)",
+				XFS_BUFTARG_NAME(mp->m_ddev_targp),
+				(unsigned long long)imap->im_blkno, i,
+				be16_to_cpu(dip->di_core.di_magic));
+#endif
+			xfs_trans_brelse(tp, bp);
+			return XFS_ERROR(EFSCORRUPTED);
+		}
+	}
+
+	xfs_inobp_check(mp, bp);
+
+	/*
+	 * Mark the buffer as an inode buffer now that it looks good
+	 */
+	XFS_BUF_SET_VTYPE(bp, B_FS_INO);
+
+	*bpp = bp;
+	return 0;
+}
+
 /*
  * This routine is called to map an inode number within a file
  * system to the buffer containing the on-disk version of the
@@ -147,72 +230,19 @@ xfs_inotobp(
 	xfs_buf_t	**bpp,
 	int		*offset)
 {
-	int		di_ok;
 	xfs_imap_t	imap;
 	xfs_buf_t	*bp;
 	int		error;
-	xfs_dinode_t	*dip;
 
-	/*
-	 * Call the space management code to find the location of the
-	 * inode on disk.
-	 */
 	imap.im_blkno = 0;
 	error = xfs_imap(mp, tp, ino, &imap, XFS_IMAP_LOOKUP);
-	if (error != 0) {
-		cmn_err(CE_WARN,
-	"xfs_inotobp: xfs_imap()  returned an "
-	"error %d on %s.  Returning error.", error, mp->m_fsname);
+	if (error)
 		return error;
-	}
 
-	/*
-	 * If the inode number maps to a block outside the bounds of the
-	 * file system then return NULL rather than calling read_buf
-	 * and panicing when we get an error from the driver.
-	 */
-	if ((imap.im_blkno + imap.im_len) >
-	    XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks)) {
-		cmn_err(CE_WARN,
-	"xfs_inotobp: inode number (%llu + %d) maps to a block outside the bounds "
-	"of the file system %s.  Returning EINVAL.",
-			(unsigned long long)imap.im_blkno,
-			imap.im_len, mp->m_fsname);
-		return XFS_ERROR(EINVAL);
-	}
-
-	/*
-	 * Read in the buffer.  If tp is NULL, xfs_trans_read_buf() will
-	 * default to just a read_buf() call.
-	 */
-	error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, imap.im_blkno,
-				   (int)imap.im_len, XFS_BUF_LOCK, &bp);
-
-	if (error) {
-		cmn_err(CE_WARN,
-	"xfs_inotobp: xfs_trans_read_buf()  returned an "
-	"error %d on %s.  Returning error.", error, mp->m_fsname);
+	error = xfs_imap_to_bp(mp, tp, &imap, &bp, XFS_BUF_LOCK, 0);
+	if (error)
 		return error;
-	}
-	dip = (xfs_dinode_t *)xfs_buf_offset(bp, 0);
-	di_ok =
-		be16_to_cpu(dip->di_core.di_magic) == XFS_DINODE_MAGIC &&
-		XFS_DINODE_GOOD_VERSION(dip->di_core.di_version);
-	if (unlikely(XFS_TEST_ERROR(!di_ok, mp, XFS_ERRTAG_ITOBP_INOTOBP,
-			XFS_RANDOM_ITOBP_INOTOBP))) {
-		XFS_CORRUPTION_ERROR("xfs_inotobp", XFS_ERRLEVEL_LOW, mp, dip);
-		xfs_trans_brelse(tp, bp);
-		cmn_err(CE_WARN,
-	"xfs_inotobp: XFS_TEST_ERROR()  returned an "
-	"error on %s.  Returning EFSCORRUPTED.",  mp->m_fsname);
-		return XFS_ERROR(EFSCORRUPTED);
-	}
 
-	xfs_inobp_check(mp, bp);
-
-	/*
-	 * Set *dipp to point to the on-disk inode in the buffer.
-	 */
 	*dipp = (xfs_dinode_t *)xfs_buf_offset(bp, imap.im_boffset);
 	*bpp = bp;
 	*offset = imap.im_boffset;
@@ -248,45 +278,20 @@ xfs_itobp(
 	xfs_dinode_t	**dipp,
 	xfs_buf_t	**bpp,
 	xfs_daddr_t	bno,
-	uint		imap_flags)
+	uint		imap_flags,
+	uint		buf_flags)
 {
 	xfs_imap_t	imap;
 	xfs_buf_t	*bp;
 	int		error;
-	int		i;
-	int		ni;
 
 	if (ip->i_blkno == (xfs_daddr_t)0) {
-		/*
-		 * Call the space management code to find the location of the
-		 * inode on disk.
-		 */
 		imap.im_blkno = bno;
-		if ((error = xfs_imap(mp, tp, ip->i_ino, &imap,
-					XFS_IMAP_LOOKUP | imap_flags)))
+		error = xfs_imap(mp, tp, ip->i_ino, &imap,
+					XFS_IMAP_LOOKUP | imap_flags);
+		if (error)
 			return error;
 
-		/*
-		 * If the inode number maps to a block outside the bounds
-		 * of the file system then return NULL rather than calling
-		 * read_buf and panicing when we get an error from the
-		 * driver.
-		 */
-		if ((imap.im_blkno + imap.im_len) >
-		    XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks)) {
-#ifdef DEBUG
-			xfs_fs_cmn_err(CE_ALERT, mp, "xfs_itobp: "
-					"(imap.im_blkno (0x%llx) "
-					"+ imap.im_len (0x%llx)) > "
-					" XFS_FSB_TO_BB(mp, "
-					"mp->m_sb.sb_dblocks) (0x%llx)",
-					(unsigned long long) imap.im_blkno,
-					(unsigned long long) imap.im_len,
-					XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks));
-#endif /* DEBUG */
-			return XFS_ERROR(EINVAL);
-		}
-
 		/*
 		 * Fill in the fields in the inode that will be used to
 		 * map the inode to its buffer from now on.
@@ -305,76 +310,17 @@ xfs_itobp(
 	}
 	ASSERT(bno == 0 || bno == imap.im_blkno);
 
-	/*
-	 * Read in the buffer.  If tp is NULL, xfs_trans_read_buf() will
-	 * default to just a read_buf() call.
-	 */
-	error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, imap.im_blkno,
-				   (int)imap.im_len, XFS_BUF_LOCK, &bp);
-	if (error) {
-#ifdef DEBUG
-		xfs_fs_cmn_err(CE_ALERT, mp, "xfs_itobp: "
-				"xfs_trans_read_buf() returned error %d, "
-				"imap.im_blkno 0x%llx, imap.im_len 0x%llx",
-				error, (unsigned long long) imap.im_blkno,
-				(unsigned long long) imap.im_len);
-#endif /* DEBUG */
+	error = xfs_imap_to_bp(mp, tp, &imap, &bp, buf_flags, imap_flags);
+	if (error)
 		return error;
-	}
-
-	/*
-	 * Validate the magic number and version of every inode in the buffer
-	 * (if DEBUG kernel) or the first inode in the buffer, otherwise.
-	 * No validation is done here in userspace (xfs_repair).
-	 */
-#if !defined(__KERNEL__)
-	ni = 0;
-#elif defined(DEBUG)
-	ni = BBTOB(imap.im_len) >> mp->m_sb.sb_inodelog;
-#else	/* usual case */
-	ni = 1;
-#endif
-
-	for (i = 0; i < ni; i++) {
-		int		di_ok;
-		xfs_dinode_t	*dip;
 
-		dip = (xfs_dinode_t *)xfs_buf_offset(bp,
-					(i << mp->m_sb.sb_inodelog));
-		di_ok = be16_to_cpu(dip->di_core.di_magic) == XFS_DINODE_MAGIC &&
-			    XFS_DINODE_GOOD_VERSION(dip->di_core.di_version);
-		if (unlikely(XFS_TEST_ERROR(!di_ok, mp,
-						XFS_ERRTAG_ITOBP_INOTOBP,
-						XFS_RANDOM_ITOBP_INOTOBP))) {
-			if (imap_flags & XFS_IMAP_BULKSTAT) {
-				xfs_trans_brelse(tp, bp);
-				return XFS_ERROR(EINVAL);
-			}
-#ifdef DEBUG
-			cmn_err(CE_ALERT,
-					"Device %s - bad inode magic/vsn "
-					"daddr %lld #%d (magic=%x)",
-				XFS_BUFTARG_NAME(mp->m_ddev_targp),
-				(unsigned long long)imap.im_blkno, i,
-				be16_to_cpu(dip->di_core.di_magic));
-#endif
-			XFS_CORRUPTION_ERROR("xfs_itobp", XFS_ERRLEVEL_HIGH,
-					     mp, dip);
-			xfs_trans_brelse(tp, bp);
-			return XFS_ERROR(EFSCORRUPTED);
-		}
+	if (!bp) {
+		ASSERT(buf_flags & XFS_BUF_TRYLOCK);
+		ASSERT(tp == NULL);
+		*bpp = NULL;
+		return EAGAIN;
 	}
 
-	xfs_inobp_check(mp, bp);
-
-	/*
-	 * Mark the buffer as an inode buffer now that it looks good
-	 */
-	XFS_BUF_SET_VTYPE(bp, B_FS_INO);
-
-	/*
-	 * Set *dipp to point to the on-disk inode in the buffer.
-	 */
 	*dipp = (xfs_dinode_t *)xfs_buf_offset(bp, imap.im_boffset);
 	*bpp = bp;
 	return 0;
@@ -878,7 +824,7 @@ xfs_iread(
 	 * return NULL as well.  Set i_blkno to 0 so that xfs_itobp() will
 	 * know that this is a new incore inode.
 	 */
-	error = xfs_itobp(mp, tp, ip, &dip, &bp, bno, imap_flags);
+	error = xfs_itobp(mp, tp, ip, &dip, &bp, bno, imap_flags, XFS_BUF_LOCK);
 	if (error) {
 		kmem_zone_free(xfs_inode_zone, ip);
 		return error;
@@ -1518,51 +1464,50 @@ xfs_itruncate_start(
 }
 
 /*
- * Shrink the file to the given new_size.  The new
- * size must be smaller than the current size.
- * This will free up the underlying blocks
- * in the removed range after a call to xfs_itruncate_start()
- * or xfs_atruncate_start().
+ * Shrink the file to the given new_size.  The new size must be smaller than
+ * the current size.  This will free up the underlying blocks in the removed
+ * range after a call to xfs_itruncate_start() or xfs_atruncate_start().
  *
- * The transaction passed to this routine must have made
- * a permanent log reservation of at least XFS_ITRUNCATE_LOG_RES.
- * This routine may commit the given transaction and
- * start new ones, so make sure everything involved in
- * the transaction is tidy before calling here.
- * Some transaction will be returned to the caller to be
- * committed.  The incoming transaction must already include
- * the inode, and both inode locks must be held exclusively.
- * The inode must also be "held" within the transaction.  On
- * return the inode will be "held" within the returned transaction.
- * This routine does NOT require any disk space to be reserved
- * for it within the transaction.
+ * The transaction passed to this routine must have made a permanent log
+ * reservation of at least XFS_ITRUNCATE_LOG_RES.  This routine may commit the
+ * given transaction and start new ones, so make sure everything involved in
+ * the transaction is tidy before calling here.  Some transaction will be
+ * returned to the caller to be committed.  The incoming transaction must
+ * already include the inode, and both inode locks must be held exclusively.
+ * The inode must also be "held" within the transaction.  On return the inode
+ * will be "held" within the returned transaction.  This routine does NOT
+ * require any disk space to be reserved for it within the transaction.
  *
- * The fork parameter must be either xfs_attr_fork or xfs_data_fork,
- * and it indicates the fork which is to be truncated.  For the
- * attribute fork we only support truncation to size 0.
+ * The fork parameter must be either xfs_attr_fork or xfs_data_fork, and it
+ * indicates the fork which is to be truncated.  For the attribute fork we only
+ * support truncation to size 0.
  *
- * We use the sync parameter to indicate whether or not the first
- * transaction we perform might have to be synchronous.  For the attr fork,
- * it needs to be so if the unlink of the inode is not yet known to be
- * permanent in the log.  This keeps us from freeing and reusing the
- * blocks of the attribute fork before the unlink of the inode becomes
- * permanent.
+ * We use the sync parameter to indicate whether or not the first transaction
+ * we perform might have to be synchronous.  For the attr fork, it needs to be
+ * so if the unlink of the inode is not yet known to be permanent in the log.
+ * This keeps us from freeing and reusing the blocks of the attribute fork
+ * before the unlink of the inode becomes permanent.
  *
- * For the data fork, we normally have to run synchronously if we're
- * being called out of the inactive path or we're being called
- * out of the create path where we're truncating an existing file.
- * Either way, the truncate needs to be sync so blocks don't reappear
- * in the file with altered data in case of a crash.  wsync filesystems
- * can run the first case async because anything that shrinks the inode
- * has to run sync so by the time we're called here from inactive, the
- * inode size is permanently set to 0.
+ * For the data fork, we normally have to run synchronously if we're being
+ * called out of the inactive path or we're being called out of the create path
+ * where we're truncating an existing file.  Either way, the truncate needs to
+ * be sync so blocks don't reappear in the file with altered data in case of a
+ * crash.  wsync filesystems can run the first case async because anything that
+ * shrinks the inode has to run sync so by the time we're called here from
+ * inactive, the inode size is permanently set to 0.
  *
- * Calls from the truncate path always need to be sync unless we're
- * in a wsync filesystem and the file has already been unlinked.
+ * Calls from the truncate path always need to be sync unless we're in a wsync
+ * filesystem and the file has already been unlinked.
  *
- * The caller is responsible for correctly setting the sync parameter.
- * It gets too hard for us to guess here which path we're being called
- * out of just based on inode state.
+ * The caller is responsible for correctly setting the sync parameter.  It gets
+ * too hard for us to guess here which path we're being called out of just
+ * based on inode state.
+ *
+ * If we get an error, we must return with the inode locked and linked into the
+ * current transaction. This keeps things simple for the higher level code,
+ * because it always knows that the inode is locked and held in the transaction
+ * that returns to it whether errors occur or not.  We don't mark the inode
+ * dirty on error so that transactions can be easily aborted if possible.
  */
 int
 xfs_itruncate_finish(
@@ -1741,65 +1686,51 @@ xfs_itruncate_finish(
 		 */
 		error = xfs_bmap_finish(tp, &free_list, &committed);
 		ntp = *tp;
+		if (committed) {
+			/* link the inode into the next xact in the chain */
+			xfs_trans_ijoin(ntp, ip,
+					XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
+			xfs_trans_ihold(ntp, ip);
+		}
+
 		if (error) {
 			/*
-			 * If the bmap finish call encounters an error,
-			 * return to the caller where the transaction
-			 * can be properly aborted.  We just need to
-			 * make sure we're not holding any resources
-			 * that we were not when we came in.
+			 * If the bmap finish call encounters an error, return
+			 * to the caller where the transaction can be properly
+			 * aborted.  We just need to make sure we're not
+			 * holding any resources that we were not when we came
+			 * in.
 			 *
-			 * Aborting from this point might lose some
-			 * blocks in the file system, but oh well.
+			 * Aborting from this point might lose some blocks in
+			 * the file system, but oh well.
 			 */
 			xfs_bmap_cancel(&free_list);
-			if (committed) {
-				/*
-				 * If the passed in transaction committed
-				 * in xfs_bmap_finish(), then we want to
-				 * add the inode to this one before returning.
-				 * This keeps things simple for the higher
-				 * level code, because it always knows that
-				 * the inode is locked and held in the
-				 * transaction that returns to it whether
-				 * errors occur or not.  We don't mark the
-				 * inode dirty so that this transaction can
-				 * be easily aborted if possible.
-				 */
-				xfs_trans_ijoin(ntp, ip,
-					XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
-				xfs_trans_ihold(ntp, ip);
-			}
 			return error;
 		}
 
 		if (committed) {
 			/*
-			 * The first xact was committed,
-			 * so add the inode to the new one.
-			 * Mark it dirty so it will be logged
-			 * and moved forward in the log as
-			 * part of every commit.
+			 * Mark the inode dirty so it will be logged and
+			 * moved forward in the log as part of every commit.
 			 */
-			xfs_trans_ijoin(ntp, ip,
-					XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
-			xfs_trans_ihold(ntp, ip);
 			xfs_trans_log_inode(ntp, ip, XFS_ILOG_CORE);
 		}
+
 		ntp = xfs_trans_dup(ntp);
-		(void) xfs_trans_commit(*tp, 0);
+		error = xfs_trans_commit(*tp, 0);
 		*tp = ntp;
-		error = xfs_trans_reserve(ntp, 0, XFS_ITRUNCATE_LOG_RES(mp), 0,
-					  XFS_TRANS_PERM_LOG_RES,
-					  XFS_ITRUNCATE_LOG_COUNT);
-		/*
-		 * Add the inode being truncated to the next chained
-		 * transaction.
-		 */
+
+		/* link the inode into the next transaction in the chain */
 		xfs_trans_ijoin(ntp, ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
 		xfs_trans_ihold(ntp, ip);
+
+		if (!error)
+			error = xfs_trans_reserve(ntp, 0,
+					XFS_ITRUNCATE_LOG_RES(mp), 0,
+					XFS_TRANS_PERM_LOG_RES,
+					XFS_ITRUNCATE_LOG_COUNT);
 		if (error)
-			return (error);
+			return error;
 	}
 	/*
 	 * Only update the size in the case of the data fork, but
@@ -1967,7 +1898,7 @@ xfs_iunlink(
 		 * Here we put the head pointer into our next pointer,
 		 * and then we fall through to point the head at us.
 		 */
-		error = xfs_itobp(mp, tp, ip, &dip, &ibp, 0, 0);
+		error = xfs_itobp(mp, tp, ip, &dip, &ibp, 0, 0, XFS_BUF_LOCK);
 		if (error)
 			return error;
 
@@ -2075,7 +2006,7 @@ xfs_iunlink_remove(
 		 * of dealing with the buffer when there is no need to
 		 * change it.
 		 */
-		error = xfs_itobp(mp, tp, ip, &dip, &ibp, 0, 0);
+		error = xfs_itobp(mp, tp, ip, &dip, &ibp, 0, 0, XFS_BUF_LOCK);
 		if (error) {
 			cmn_err(CE_WARN,
 				"xfs_iunlink_remove: xfs_itobp()  returned an error %d on %s.  Returning error.",
@@ -2137,7 +2068,7 @@ xfs_iunlink_remove(
 		 * Now last_ibp points to the buffer previous to us on
 		 * the unlinked list.  Pull us from the list.
 		 */
-		error = xfs_itobp(mp, tp, ip, &dip, &ibp, 0, 0);
+		error = xfs_itobp(mp, tp, ip, &dip, &ibp, 0, 0, XFS_BUF_LOCK);
 		if (error) {
 			cmn_err(CE_WARN,
 				"xfs_iunlink_remove: xfs_itobp()  returned an error %d on %s.  Returning error.",
@@ -2172,13 +2103,6 @@ xfs_iunlink_remove(
 	return 0;
 }
 
-STATIC_INLINE int xfs_inode_clean(xfs_inode_t *ip)
-{
-	return (((ip->i_itemp == NULL) ||
-		!(ip->i_itemp->ili_format.ilf_fields & XFS_ILOG_ALL)) &&
-		(ip->i_update_core == 0));
-}
-
 STATIC void
 xfs_ifree_cluster(
 	xfs_inode_t	*free_ip,
@@ -2400,7 +2324,7 @@ xfs_ifree(
 
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 
-	error = xfs_itobp(ip->i_mount, tp, ip, &dip, &ibp, 0, 0);
+	error = xfs_itobp(ip->i_mount, tp, ip, &dip, &ibp, 0, 0, XFS_BUF_LOCK);
 	if (error)
 		return error;
 
@@ -2678,14 +2602,31 @@ xfs_imap(
 	fsbno = imap->im_blkno ?
 		XFS_DADDR_TO_FSB(mp, imap->im_blkno) : NULLFSBLOCK;
 	error = xfs_dilocate(mp, tp, ino, &fsbno, &len, &off, flags);
-	if (error != 0) {
+	if (error)
 		return error;
-	}
+
 	imap->im_blkno = XFS_FSB_TO_DADDR(mp, fsbno);
 	imap->im_len = XFS_FSB_TO_BB(mp, len);
 	imap->im_agblkno = XFS_FSB_TO_AGBNO(mp, fsbno);
 	imap->im_ioffset = (ushort)off;
 	imap->im_boffset = (ushort)(off << mp->m_sb.sb_inodelog);
+
+	/*
+	 * If the inode number maps to a block outside the bounds
+	 * of the file system then return NULL rather than calling
+	 * read_buf and panicing when we get an error from the
+	 * driver.
+	 */
+	if ((imap->im_blkno + imap->im_len) >
+	    XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks)) {
+		xfs_fs_cmn_err(CE_ALERT, mp, "xfs_imap: "
+			"(imap->im_blkno (0x%llx) + imap->im_len (0x%llx)) > "
+			" XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks) (0x%llx)",
+			(unsigned long long) imap->im_blkno,
+			(unsigned long long) imap->im_len,
+			XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks));
+		return EINVAL;
+	}
 	return 0;
 }
 
@@ -2826,38 +2767,41 @@ xfs_iunpin(
 }
 
 /*
- * This is called to wait for the given inode to be unpinned.
- * It will sleep until this happens.  The caller must have the
- * inode locked in at least shared mode so that the buffer cannot
- * be subsequently pinned once someone is waiting for it to be
- * unpinned.
+ * This is called to unpin an inode. It can be directed to wait or to return
+ * immediately without waiting for the inode to be unpinned.  The caller must
+ * have the inode locked in at least shared mode so that the buffer cannot be
+ * subsequently pinned once someone is waiting for it to be unpinned.
  */
 STATIC void
-xfs_iunpin_wait(
-	xfs_inode_t	*ip)
+__xfs_iunpin_wait(
+	xfs_inode_t	*ip,
+	int		wait)
 {
-	xfs_inode_log_item_t	*iip;
-	xfs_lsn_t	lsn;
+	xfs_inode_log_item_t	*iip = ip->i_itemp;
 
 	ASSERT(ismrlocked(&ip->i_lock, MR_UPDATE | MR_ACCESS));
-
-	if (atomic_read(&ip->i_pincount) == 0) {
+	if (atomic_read(&ip->i_pincount) == 0)
 		return;
-	}
 
-	iip = ip->i_itemp;
-	if (iip && iip->ili_last_lsn) {
-		lsn = iip->ili_last_lsn;
-	} else {
-		lsn = (xfs_lsn_t)0;
-	}
+	/* Give the log a push to start the unpinning I/O */
+	xfs_log_force(ip->i_mount, (iip && iip->ili_last_lsn) ?
+				iip->ili_last_lsn : 0, XFS_LOG_FORCE);
+	if (wait)
+		wait_event(ip->i_ipin_wait, (atomic_read(&ip->i_pincount) == 0));
+}
 
-	/*
-	 * Give the log a push so we don't wait here too long.
-	 */
-	xfs_log_force(ip->i_mount, lsn, XFS_LOG_FORCE);
+static inline void
+xfs_iunpin_wait(
+	xfs_inode_t	*ip)
+{
+	__xfs_iunpin_wait(ip, 1);
+}
 
-	wait_event(ip->i_ipin_wait, (atomic_read(&ip->i_pincount) == 0));
+static inline void
+xfs_iunpin_nowait(
+	xfs_inode_t	*ip)
+{
+	__xfs_iunpin_wait(ip, 0);
 }
 
 
@@ -2932,7 +2876,7 @@ xfs_iextents_copy(
  * format indicates the current state of the fork.
  */
 /*ARGSUSED*/
-STATIC int
+STATIC void
 xfs_iflush_fork(
 	xfs_inode_t		*ip,
 	xfs_dinode_t		*dip,
@@ -2953,16 +2897,16 @@ xfs_iflush_fork(
 	static const short	extflag[2] =
 		{ XFS_ILOG_DEXT, XFS_ILOG_AEXT };
 
-	if (iip == NULL)
-		return 0;
+	if (!iip)
+		return;
 	ifp = XFS_IFORK_PTR(ip, whichfork);
 	/*
 	 * This can happen if we gave up in iformat in an error path,
 	 * for the attribute fork.
 	 */
-	if (ifp == NULL) {
+	if (!ifp) {
 		ASSERT(whichfork == XFS_ATTR_FORK);
-		return 0;
+		return;
 	}
 	cp = XFS_DFORK_PTR(dip, whichfork);
 	mp = ip->i_mount;
@@ -3023,8 +2967,145 @@ xfs_iflush_fork(
 		ASSERT(0);
 		break;
 	}
+}
+
+STATIC int
+xfs_iflush_cluster(
+	xfs_inode_t	*ip,
+	xfs_buf_t	*bp)
+{
+	xfs_mount_t		*mp = ip->i_mount;
+	xfs_perag_t		*pag = xfs_get_perag(mp, ip->i_ino);
+	unsigned long		first_index, mask;
+	int			ilist_size;
+	xfs_inode_t		**ilist;
+	xfs_inode_t		*iq;
+	int			nr_found;
+	int			clcount = 0;
+	int			bufwasdelwri;
+	int			i;
+
+	ASSERT(pag->pagi_inodeok);
+	ASSERT(pag->pag_ici_init);
+
+	ilist_size = XFS_INODE_CLUSTER_SIZE(mp) * sizeof(xfs_inode_t *);
+	ilist = kmem_alloc(ilist_size, KM_MAYFAIL);
+	if (!ilist)
+		return 0;
+
+	mask = ~(((XFS_INODE_CLUSTER_SIZE(mp) >> mp->m_sb.sb_inodelog)) - 1);
+	first_index = XFS_INO_TO_AGINO(mp, ip->i_ino) & mask;
+	read_lock(&pag->pag_ici_lock);
+	/* really need a gang lookup range call here */
+	nr_found = radix_tree_gang_lookup(&pag->pag_ici_root, (void**)ilist,
+					first_index,
+					XFS_INODE_CLUSTER_SIZE(mp));
+	if (nr_found == 0)
+		goto out_free;
+
+	for (i = 0; i < nr_found; i++) {
+		iq = ilist[i];
+		if (iq == ip)
+			continue;
+		/* if the inode lies outside this cluster, we're done. */
+		if ((XFS_INO_TO_AGINO(mp, iq->i_ino) & mask) != first_index)
+			break;
+		/*
+		 * Do an un-protected check to see if the inode is dirty and
+		 * is a candidate for flushing.  These checks will be repeated
+		 * later after the appropriate locks are acquired.
+		 */
+		if (xfs_inode_clean(iq) && xfs_ipincount(iq) == 0)
+			continue;
+
+		/*
+		 * Try to get locks.  If any are unavailable or it is pinned,
+		 * then this inode cannot be flushed and is skipped.
+		 */
+
+		if (!xfs_ilock_nowait(iq, XFS_ILOCK_SHARED))
+			continue;
+		if (!xfs_iflock_nowait(iq)) {
+			xfs_iunlock(iq, XFS_ILOCK_SHARED);
+			continue;
+		}
+		if (xfs_ipincount(iq)) {
+			xfs_ifunlock(iq);
+			xfs_iunlock(iq, XFS_ILOCK_SHARED);
+			continue;
+		}
+
+		/*
+		 * arriving here means that this inode can be flushed.  First
+		 * re-check that it's dirty before flushing.
+		 */
+		if (!xfs_inode_clean(iq)) {
+			int	error;
+			error = xfs_iflush_int(iq, bp);
+			if (error) {
+				xfs_iunlock(iq, XFS_ILOCK_SHARED);
+				goto cluster_corrupt_out;
+			}
+			clcount++;
+		} else {
+			xfs_ifunlock(iq);
+		}
+		xfs_iunlock(iq, XFS_ILOCK_SHARED);
+	}
+
+	if (clcount) {
+		XFS_STATS_INC(xs_icluster_flushcnt);
+		XFS_STATS_ADD(xs_icluster_flushinode, clcount);
+	}
 
+out_free:
+	read_unlock(&pag->pag_ici_lock);
+	kmem_free(ilist, ilist_size);
 	return 0;
+
+
+cluster_corrupt_out:
+	/*
+	 * Corruption detected in the clustering loop.  Invalidate the
+	 * inode buffer and shut down the filesystem.
+	 */
+	read_unlock(&pag->pag_ici_lock);
+	/*
+	 * Clean up the buffer.  If it was B_DELWRI, just release it --
+	 * brelse can handle it with no problems.  If not, shut down the
+	 * filesystem before releasing the buffer.
+	 */
+	bufwasdelwri = XFS_BUF_ISDELAYWRITE(bp);
+	if (bufwasdelwri)
+		xfs_buf_relse(bp);
+
+	xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
+
+	if (!bufwasdelwri) {
+		/*
+		 * Just like incore_relse: if we have b_iodone functions,
+		 * mark the buffer as an error and call them.  Otherwise
+		 * mark it as stale and brelse.
+		 */
+		if (XFS_BUF_IODONE_FUNC(bp)) {
+			XFS_BUF_CLR_BDSTRAT_FUNC(bp);
+			XFS_BUF_UNDONE(bp);
+			XFS_BUF_STALE(bp);
+			XFS_BUF_SHUT(bp);
+			XFS_BUF_ERROR(bp,EIO);
+			xfs_biodone(bp);
+		} else {
+			XFS_BUF_STALE(bp);
+			xfs_buf_relse(bp);
+		}
+	}
+
+	/*
+	 * Unlocks the flush lock
+	 */
+	xfs_iflush_abort(iq);
+	kmem_free(ilist, ilist_size);
+	return XFS_ERROR(EFSCORRUPTED);
 }
 
 /*
@@ -3046,11 +3127,7 @@ xfs_iflush(
 	xfs_dinode_t		*dip;
 	xfs_mount_t		*mp;
 	int			error;
-	/* REFERENCED */
-	xfs_inode_t		*iq;
-	int			clcount;	/* count of inodes clustered */
-	int			bufwasdelwri;
-	struct hlist_node	*entry;
+	int			noblock = (flags == XFS_IFLUSH_ASYNC_NOBLOCK);
 	enum { INT_DELWRI = (1 << 0), INT_ASYNC = (1 << 1) };
 
 	XFS_STATS_INC(xs_iflush_count);
@@ -3067,8 +3144,7 @@ xfs_iflush(
 	 * If the inode isn't dirty, then just release the inode
 	 * flush lock and do nothing.
 	 */
-	if ((ip->i_update_core == 0) &&
-	    ((iip == NULL) || !(iip->ili_format.ilf_fields & XFS_ILOG_ALL))) {
+	if (xfs_inode_clean(ip)) {
 		ASSERT((iip != NULL) ?
 			 !(iip->ili_item.li_flags & XFS_LI_IN_AIL) : 1);
 		xfs_ifunlock(ip);
@@ -3076,11 +3152,21 @@ xfs_iflush(
 	}
 
 	/*
-	 * We can't flush the inode until it is unpinned, so
-	 * wait for it.  We know noone new can pin it, because
-	 * we are holding the inode lock shared and you need
-	 * to hold it exclusively to pin the inode.
+	 * We can't flush the inode until it is unpinned, so wait for it if we
+	 * are allowed to block.  We know noone new can pin it, because we are
+	 * holding the inode lock shared and you need to hold it exclusively to
+	 * pin the inode.
+	 *
+	 * If we are not allowed to block, force the log out asynchronously so
+	 * that when we come back the inode will be unpinned. If other inodes
+	 * in the same cluster are dirty, they will probably write the inode
+	 * out for us if they occur after the log force completes.
 	 */
+	if (noblock && xfs_ipincount(ip)) {
+		xfs_iunpin_nowait(ip);
+		xfs_ifunlock(ip);
+		return EAGAIN;
+	}
 	xfs_iunpin_wait(ip);
 
 	/*
@@ -3096,15 +3182,6 @@ xfs_iflush(
 		return XFS_ERROR(EIO);
 	}
 
-	/*
-	 * Get the buffer containing the on-disk inode.
-	 */
-	error = xfs_itobp(mp, NULL, ip, &dip, &bp, 0, 0);
-	if (error) {
-		xfs_ifunlock(ip);
-		return error;
-	}
-
 	/*
 	 * Decide how buffer will be flushed out.  This is done before
 	 * the call to xfs_iflush_int because this field is zeroed by it.
@@ -3121,6 +3198,7 @@ xfs_iflush(
 		case XFS_IFLUSH_DELWRI_ELSE_SYNC:
 			flags = 0;
 			break;
+		case XFS_IFLUSH_ASYNC_NOBLOCK:
 		case XFS_IFLUSH_ASYNC:
 		case XFS_IFLUSH_DELWRI_ELSE_ASYNC:
 			flags = INT_ASYNC;
@@ -3140,6 +3218,7 @@ xfs_iflush(
 		case XFS_IFLUSH_DELWRI:
 			flags = INT_DELWRI;
 			break;
+		case XFS_IFLUSH_ASYNC_NOBLOCK:
 		case XFS_IFLUSH_ASYNC:
 			flags = INT_ASYNC;
 			break;
@@ -3154,94 +3233,41 @@ xfs_iflush(
 	}
 
 	/*
-	 * First flush out the inode that xfs_iflush was called with.
+	 * Get the buffer containing the on-disk inode.
 	 */
-	error = xfs_iflush_int(ip, bp);
-	if (error) {
-		goto corrupt_out;
+	error = xfs_itobp(mp, NULL, ip, &dip, &bp, 0, 0,
+				noblock ? XFS_BUF_TRYLOCK : XFS_BUF_LOCK);
+	if (error || !bp) {
+		xfs_ifunlock(ip);
+		return error;
 	}
 
 	/*
-	 * inode clustering:
-	 * see if other inodes can be gathered into this write
+	 * First flush out the inode that xfs_iflush was called with.
 	 */
-	spin_lock(&ip->i_cluster->icl_lock);
-	ip->i_cluster->icl_buf = bp;
-
-	clcount = 0;
-	hlist_for_each_entry(iq, entry, &ip->i_cluster->icl_inodes, i_cnode) {
-		if (iq == ip)
-			continue;
-
-		/*
-		 * Do an un-protected check to see if the inode is dirty and
-		 * is a candidate for flushing.  These checks will be repeated
-		 * later after the appropriate locks are acquired.
-		 */
-		iip = iq->i_itemp;
-		if ((iq->i_update_core == 0) &&
-		    ((iip == NULL) ||
-		     !(iip->ili_format.ilf_fields & XFS_ILOG_ALL)) &&
-		      xfs_ipincount(iq) == 0) {
-			continue;
-		}
-
-		/*
-		 * Try to get locks.  If any are unavailable,
-		 * then this inode cannot be flushed and is skipped.
-		 */
-
-		/* get inode locks (just i_lock) */
-		if (xfs_ilock_nowait(iq, XFS_ILOCK_SHARED)) {
-			/* get inode flush lock */
-			if (xfs_iflock_nowait(iq)) {
-				/* check if pinned */
-				if (xfs_ipincount(iq) == 0) {
-					/* arriving here means that
-					 * this inode can be flushed.
-					 * first re-check that it's
-					 * dirty
-					 */
-					iip = iq->i_itemp;
-					if ((iq->i_update_core != 0)||
-					    ((iip != NULL) &&
-					     (iip->ili_format.ilf_fields & XFS_ILOG_ALL))) {
-						clcount++;
-						error = xfs_iflush_int(iq, bp);
-						if (error) {
-							xfs_iunlock(iq,
-								    XFS_ILOCK_SHARED);
-							goto cluster_corrupt_out;
-						}
-					} else {
-						xfs_ifunlock(iq);
-					}
-				} else {
-					xfs_ifunlock(iq);
-				}
-			}
-			xfs_iunlock(iq, XFS_ILOCK_SHARED);
-		}
-	}
-	spin_unlock(&ip->i_cluster->icl_lock);
-
-	if (clcount) {
-		XFS_STATS_INC(xs_icluster_flushcnt);
-		XFS_STATS_ADD(xs_icluster_flushinode, clcount);
-	}
+	error = xfs_iflush_int(ip, bp);
+	if (error)
+		goto corrupt_out;
 
 	/*
-	 * If the buffer is pinned then push on the log so we won't
+	 * If the buffer is pinned then push on the log now so we won't
 	 * get stuck waiting in the write for too long.
 	 */
-	if (XFS_BUF_ISPINNED(bp)){
+	if (XFS_BUF_ISPINNED(bp))
 		xfs_log_force(mp, (xfs_lsn_t)0, XFS_LOG_FORCE);
-	}
+
+	/*
+	 * inode clustering:
+	 * see if other inodes can be gathered into this write
+	 */
+	error = xfs_iflush_cluster(ip, bp);
+	if (error)
+		goto cluster_corrupt_out;
 
 	if (flags & INT_DELWRI) {
 		xfs_bdwrite(mp, bp);
 	} else if (flags & INT_ASYNC) {
-		xfs_bawrite(mp, bp);
+		error = xfs_bawrite(mp, bp);
 	} else {
 		error = xfs_bwrite(mp, bp);
 	}
@@ -3250,52 +3276,11 @@ xfs_iflush(
 corrupt_out:
 	xfs_buf_relse(bp);
 	xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
-	xfs_iflush_abort(ip);
-	/*
-	 * Unlocks the flush lock
-	 */
-	return XFS_ERROR(EFSCORRUPTED);
-
 cluster_corrupt_out:
-	/* Corruption detected in the clustering loop.  Invalidate the
-	 * inode buffer and shut down the filesystem.
-	 */
-	spin_unlock(&ip->i_cluster->icl_lock);
-
-	/*
-	 * Clean up the buffer.  If it was B_DELWRI, just release it --
-	 * brelse can handle it with no problems.  If not, shut down the
-	 * filesystem before releasing the buffer.
-	 */
-	if ((bufwasdelwri= XFS_BUF_ISDELAYWRITE(bp))) {
-		xfs_buf_relse(bp);
-	}
-
-	xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
-
-	if(!bufwasdelwri)  {
-		/*
-		 * Just like incore_relse: if we have b_iodone functions,
-		 * mark the buffer as an error and call them.  Otherwise
-		 * mark it as stale and brelse.
-		 */
-		if (XFS_BUF_IODONE_FUNC(bp)) {
-			XFS_BUF_CLR_BDSTRAT_FUNC(bp);
-			XFS_BUF_UNDONE(bp);
-			XFS_BUF_STALE(bp);
-			XFS_BUF_SHUT(bp);
-			XFS_BUF_ERROR(bp,EIO);
-			xfs_biodone(bp);
-		} else {
-			XFS_BUF_STALE(bp);
-			xfs_buf_relse(bp);
-		}
-	}
-
-	xfs_iflush_abort(iq);
 	/*
 	 * Unlocks the flush lock
 	 */
+	xfs_iflush_abort(ip);
 	return XFS_ERROR(EFSCORRUPTED);
 }
 
@@ -3325,8 +3310,7 @@ xfs_iflush_int(
 	 * If the inode isn't dirty, then just release the inode
 	 * flush lock and do nothing.
 	 */
-	if ((ip->i_update_core == 0) &&
-	    ((iip == NULL) || !(iip->ili_format.ilf_fields & XFS_ILOG_ALL))) {
+	if (xfs_inode_clean(ip)) {
 		xfs_ifunlock(ip);
 		return 0;
 	}
@@ -3459,16 +3443,9 @@ xfs_iflush_int(
 		}
 	}
 
-	if (xfs_iflush_fork(ip, dip, iip, XFS_DATA_FORK, bp) == EFSCORRUPTED) {
-		goto corrupt_out;
-	}
-
-	if (XFS_IFORK_Q(ip)) {
-		/*
-		 * The only error from xfs_iflush_fork is on the data fork.
-		 */
-		(void) xfs_iflush_fork(ip, dip, iip, XFS_ATTR_FORK, bp);
-	}
+	xfs_iflush_fork(ip, dip, iip, XFS_DATA_FORK, bp);
+	if (XFS_IFORK_Q(ip))
+		xfs_iflush_fork(ip, dip, iip, XFS_ATTR_FORK, bp);
 	xfs_inobp_check(mp, bp);
 
 	/*

fs/xfs/xfs_inode.h

@@ -132,19 +132,6 @@ typedef struct dm_attrs_s {
 	__uint16_t	da_pad;		/* DMIG extra padding */
 } dm_attrs_t;
 
-/*
- * This is the xfs inode cluster structure.  This structure is used by
- * xfs_iflush to find inodes that share a cluster and can be flushed to disk at
- * the same time.
- */
-typedef struct xfs_icluster {
-	struct hlist_head	icl_inodes;	/* list of inodes on cluster */
-	xfs_daddr_t		icl_blkno;	/* starting block number of
-						 * the cluster */
-	struct xfs_buf		*icl_buf;	/* the inode buffer */
-	spinlock_t		icl_lock;	/* inode list lock */
-} xfs_icluster_t;
-
 /*
  * This is the xfs in-core inode structure.
  * Most of the on-disk inode is embedded in the i_d field.
@@ -240,10 +227,6 @@ typedef struct xfs_inode {
 	atomic_t		i_pincount;	/* inode pin count */
 	wait_queue_head_t	i_ipin_wait;	/* inode pinning wait queue */
 	spinlock_t		i_flags_lock;	/* inode i_flags lock */
-#ifdef HAVE_REFCACHE
-	struct xfs_inode	**i_refcache;	/* ptr to entry in ref cache */
-	struct xfs_inode	*i_release;	/* inode to unref */
-#endif
 	/* Miscellaneous state. */
 	unsigned short		i_flags;	/* see defined flags below */
 	unsigned char		i_update_core;	/* timestamps/size is dirty */
@@ -252,8 +235,6 @@ typedef struct xfs_inode {
 	unsigned int		i_delayed_blks;	/* count of delay alloc blks */
 
 	xfs_icdinode_t		i_d;		/* most of ondisk inode */
-	xfs_icluster_t		*i_cluster;	/* cluster list header */
-	struct hlist_node	i_cnode;	/* cluster link node */
 
 	xfs_fsize_t		i_size;		/* in-memory size */
 	xfs_fsize_t		i_new_size;	/* size when write completes */
@@ -461,6 +442,7 @@ xfs_iflags_test_and_clear(xfs_inode_t *ip, unsigned short flags)
 #define	XFS_IFLUSH_SYNC			3
 #define	XFS_IFLUSH_ASYNC		4
 #define	XFS_IFLUSH_DELWRI		5
+#define	XFS_IFLUSH_ASYNC_NOBLOCK	6
 
 /*
  * Flags for xfs_itruncate_start().
@@ -515,7 +497,7 @@ int		xfs_finish_reclaim_all(struct xfs_mount *, int);
  */
 int		xfs_itobp(struct xfs_mount *, struct xfs_trans *,
 			  xfs_inode_t *, struct xfs_dinode **, struct xfs_buf **,
-			  xfs_daddr_t, uint);
+			  xfs_daddr_t, uint, uint);
 int		xfs_iread(struct xfs_mount *, struct xfs_trans *, xfs_ino_t,
 			  xfs_inode_t **, xfs_daddr_t, uint);
 int		xfs_iread_extents(struct xfs_trans *, xfs_inode_t *, int);
@@ -597,7 +579,6 @@ void		xfs_inobp_check(struct xfs_mount *, struct xfs_buf *);
 #define	xfs_inobp_check(mp, bp)
 #endif /* DEBUG */
 
-extern struct kmem_zone	*xfs_icluster_zone;
 extern struct kmem_zone	*xfs_ifork_zone;
 extern struct kmem_zone	*xfs_inode_zone;
 extern struct kmem_zone	*xfs_ili_zone;

fs/xfs/xfs_inode_item.c

@@ -40,6 +40,7 @@
 #include "xfs_btree.h"
 #include "xfs_ialloc.h"
 #include "xfs_rw.h"
+#include "xfs_error.h"
 
 
 kmem_zone_t	*xfs_ili_zone;		/* inode log item zone */
@@ -813,7 +814,12 @@ xfs_inode_item_pushbuf(
 					      XFS_LOG_FORCE);
 			}
 			if (dopush) {
-				xfs_bawrite(mp, bp);
+				int	error;
+				error = xfs_bawrite(mp, bp);
+				if (error)
+					xfs_fs_cmn_err(CE_WARN, mp,
+		"xfs_inode_item_pushbuf: pushbuf error %d on iip %p, bp %p",
+							error, iip, bp);
 			} else {
 				xfs_buf_relse(bp);
 			}

fs/xfs/xfs_inode_item.h

@@ -168,6 +168,14 @@ static inline int xfs_ilog_fext(int w)
 	return (w == XFS_DATA_FORK ? XFS_ILOG_DEXT : XFS_ILOG_AEXT);
 }
 
+static inline int xfs_inode_clean(xfs_inode_t *ip)
+{
+	return (!ip->i_itemp ||
+		!(ip->i_itemp->ili_format.ilf_fields & XFS_ILOG_ALL)) &&
+	       !ip->i_update_core;
+}
+
+
 #ifdef __KERNEL__
 
 extern void xfs_inode_item_init(struct xfs_inode *, struct xfs_mount *);

fs/xfs/xfs_iomap.c

@@ -802,8 +802,11 @@ xfs_iomap_write_allocate(
 			 */
 			nimaps = 1;
 			end_fsb = XFS_B_TO_FSB(mp, ip->i_size);
-			xfs_bmap_last_offset(NULL, ip, &last_block,
-				XFS_DATA_FORK);
+			error = xfs_bmap_last_offset(NULL, ip, &last_block,
+							XFS_DATA_FORK);
+			if (error)
+				goto trans_cancel;
+
 			last_block = XFS_FILEOFF_MAX(last_block, end_fsb);
 			if ((map_start_fsb + count_fsb) > last_block) {
 				count_fsb = last_block - map_start_fsb;

fs/xfs/xfs_itable.c

@@ -129,7 +129,7 @@ xfs_bulkstat_one_iget(
 	return error;
 }
 
-STATIC int
+STATIC void
 xfs_bulkstat_one_dinode(
 	xfs_mount_t	*mp,		/* mount point for filesystem */
 	xfs_ino_t	ino,		/* inode number to get data for */
@@ -198,8 +198,6 @@ xfs_bulkstat_one_dinode(
 		buf->bs_blocks = be64_to_cpu(dic->di_nblocks);
 		break;
 	}
-
-	return 0;
 }
 
 STATIC int
@@ -614,7 +612,8 @@ xfs_bulkstat(
 							xfs_buf_relse(bp);
 						error = xfs_itobp(mp, NULL, ip,
 								&dip, &bp, bno,
-								XFS_IMAP_BULKSTAT);
+								XFS_IMAP_BULKSTAT,
+								XFS_BUF_LOCK);
 						if (!error)
 							clustidx = ip->i_boffset / mp->m_sb.sb_inodesize;
 						kmem_zone_free(xfs_inode_zone, ip);

fs/xfs/xfs_log.c

@@ -41,6 +41,7 @@
 #include "xfs_inode.h"
 #include "xfs_rw.h"
 
+kmem_zone_t	*xfs_log_ticket_zone;
 
 #define xlog_write_adv_cnt(ptr, len, off, bytes) \
 	{ (ptr) += (bytes); \
@@ -73,8 +74,6 @@ STATIC int  xlog_state_get_iclog_space(xlog_t		*log,
 				       xlog_ticket_t	*ticket,
 				       int		*continued_write,
 				       int		*logoffsetp);
-STATIC void xlog_state_put_ticket(xlog_t	*log,
-				  xlog_ticket_t *tic);
 STATIC int  xlog_state_release_iclog(xlog_t		*log,
 				     xlog_in_core_t	*iclog);
 STATIC void xlog_state_switch_iclogs(xlog_t		*log,
@@ -101,7 +100,6 @@ STATIC void xlog_ungrant_log_space(xlog_t	 *log,
 
 
 /* local ticket functions */
-STATIC void		xlog_state_ticket_alloc(xlog_t *log);
 STATIC xlog_ticket_t	*xlog_ticket_get(xlog_t *log,
 					 int	unit_bytes,
 					 int	count,
@@ -330,7 +328,7 @@ xfs_log_done(xfs_mount_t	*mp,
 		 */
 		xlog_trace_loggrant(log, ticket, "xfs_log_done: (non-permanent)");
 		xlog_ungrant_log_space(log, ticket);
-		xlog_state_put_ticket(log, ticket);
+		xlog_ticket_put(log, ticket);
 	} else {
 		xlog_trace_loggrant(log, ticket, "xfs_log_done: (permanent)");
 		xlog_regrant_reserve_log_space(log, ticket);
@@ -384,7 +382,27 @@ _xfs_log_force(
 		return xlog_state_sync_all(log, flags, log_flushed);
 	else
 		return xlog_state_sync(log, lsn, flags, log_flushed);
-}	/* xfs_log_force */
+}	/* _xfs_log_force */
+
+/*
+ * Wrapper for _xfs_log_force(), to be used when caller doesn't care
+ * about errors or whether the log was flushed or not. This is the normal
+ * interface to use when trying to unpin items or move the log forward.
+ */
+void
+xfs_log_force(
+	xfs_mount_t	*mp,
+	xfs_lsn_t	lsn,
+	uint		flags)
+{
+	int	error;
+	error = _xfs_log_force(mp, lsn, flags, NULL);
+	if (error) {
+		xfs_fs_cmn_err(CE_WARN, mp, "xfs_log_force: "
+			"error %d returned.", error);
+	}
+}
+
 
 /*
  * Attaches a new iclog I/O completion callback routine during
@@ -397,12 +415,10 @@ xfs_log_notify(xfs_mount_t	  *mp,		/* mount of partition */
 	       void		  *iclog_hndl,	/* iclog to hang callback off */
 	       xfs_log_callback_t *cb)
 {
-	xlog_t *log = mp->m_log;
 	xlog_in_core_t	  *iclog = (xlog_in_core_t *)iclog_hndl;
 	int	abortflg;
 
-	cb->cb_next = NULL;
-	spin_lock(&log->l_icloglock);
+	spin_lock(&iclog->ic_callback_lock);
 	abortflg = (iclog->ic_state & XLOG_STATE_IOERROR);
 	if (!abortflg) {
 		ASSERT_ALWAYS((iclog->ic_state == XLOG_STATE_ACTIVE) ||
@@ -411,7 +427,7 @@ xfs_log_notify(xfs_mount_t	  *mp,		/* mount of partition */
 		*(iclog->ic_callback_tail) = cb;
 		iclog->ic_callback_tail = &(cb->cb_next);
 	}
-	spin_unlock(&log->l_icloglock);
+	spin_unlock(&iclog->ic_callback_lock);
 	return abortflg;
 }	/* xfs_log_notify */
 
@@ -471,6 +487,8 @@ xfs_log_reserve(xfs_mount_t	 *mp,
 		/* may sleep if need to allocate more tickets */
 		internal_ticket = xlog_ticket_get(log, unit_bytes, cnt,
 						  client, flags);
+		if (!internal_ticket)
+			return XFS_ERROR(ENOMEM);
 		internal_ticket->t_trans_type = t_type;
 		*ticket = internal_ticket;
 		xlog_trace_loggrant(log, internal_ticket, 
@@ -636,7 +654,8 @@ xfs_log_unmount_write(xfs_mount_t *mp)
 	if (mp->m_flags & XFS_MOUNT_RDONLY)
 		return 0;
 
-	xfs_log_force(mp, 0, XFS_LOG_FORCE|XFS_LOG_SYNC);
+	error = _xfs_log_force(mp, 0, XFS_LOG_FORCE|XFS_LOG_SYNC, NULL);
+	ASSERT(error || !(XLOG_FORCED_SHUTDOWN(log)));
 
 #ifdef DEBUG
 	first_iclog = iclog = log->l_iclog;
@@ -675,10 +694,10 @@ xfs_log_unmount_write(xfs_mount_t *mp)
 
 		spin_lock(&log->l_icloglock);
 		iclog = log->l_iclog;
-		iclog->ic_refcnt++;
+		atomic_inc(&iclog->ic_refcnt);
 		spin_unlock(&log->l_icloglock);
 		xlog_state_want_sync(log, iclog);
-		(void) xlog_state_release_iclog(log, iclog);
+		error = xlog_state_release_iclog(log, iclog);
 
 		spin_lock(&log->l_icloglock);
 		if (!(iclog->ic_state == XLOG_STATE_ACTIVE ||
@@ -695,7 +714,7 @@ xfs_log_unmount_write(xfs_mount_t *mp)
 		if (tic) {
 			xlog_trace_loggrant(log, tic, "unmount rec");
 			xlog_ungrant_log_space(log, tic);
-			xlog_state_put_ticket(log, tic);
+			xlog_ticket_put(log, tic);
 		}
 	} else {
 		/*
@@ -713,11 +732,11 @@ xfs_log_unmount_write(xfs_mount_t *mp)
 		 */
 		spin_lock(&log->l_icloglock);
 		iclog = log->l_iclog;
-		iclog->ic_refcnt++;
+		atomic_inc(&iclog->ic_refcnt);
 		spin_unlock(&log->l_icloglock);
 
 		xlog_state_want_sync(log, iclog);
-		(void) xlog_state_release_iclog(log, iclog);
+		error =  xlog_state_release_iclog(log, iclog);
 
 		spin_lock(&log->l_icloglock);
 
@@ -732,7 +751,7 @@ xfs_log_unmount_write(xfs_mount_t *mp)
 		}
 	}
 
-	return 0;
+	return error;
 }	/* xfs_log_unmount_write */
 
 /*
@@ -1210,7 +1229,6 @@ xlog_alloc_log(xfs_mount_t	*mp,
 	spin_lock_init(&log->l_icloglock);
 	spin_lock_init(&log->l_grant_lock);
 	initnsema(&log->l_flushsema, 0, "ic-flush");
-	xlog_state_ticket_alloc(log);  /* wait until after icloglock inited */
 
 	/* log record size must be multiple of BBSIZE; see xlog_rec_header_t */
 	ASSERT((XFS_BUF_SIZE(bp) & BBMASK) == 0);
@@ -1240,9 +1258,9 @@ xlog_alloc_log(xfs_mount_t	*mp,
 		XFS_BUF_SET_FSPRIVATE2(bp, (unsigned long)1);
 		iclog->ic_bp = bp;
 		iclog->hic_data = bp->b_addr;
-
+#ifdef DEBUG
 		log->l_iclog_bak[i] = (xfs_caddr_t)&(iclog->ic_header);
-
+#endif
 		head = &iclog->ic_header;
 		memset(head, 0, sizeof(xlog_rec_header_t));
 		head->h_magicno = cpu_to_be32(XLOG_HEADER_MAGIC_NUM);
@@ -1253,10 +1271,11 @@ xlog_alloc_log(xfs_mount_t	*mp,
 		head->h_fmt = cpu_to_be32(XLOG_FMT);
 		memcpy(&head->h_fs_uuid, &mp->m_sb.sb_uuid, sizeof(uuid_t));
 
-
 		iclog->ic_size = XFS_BUF_SIZE(bp) - log->l_iclog_hsize;
 		iclog->ic_state = XLOG_STATE_ACTIVE;
 		iclog->ic_log = log;
+		atomic_set(&iclog->ic_refcnt, 0);
+		spin_lock_init(&iclog->ic_callback_lock);
 		iclog->ic_callback_tail = &(iclog->ic_callback);
 		iclog->ic_datap = (char *)iclog->hic_data + log->l_iclog_hsize;
 
@@ -1405,7 +1424,7 @@ xlog_sync(xlog_t		*log,
 	int		v2 = xfs_sb_version_haslogv2(&log->l_mp->m_sb);
 
 	XFS_STATS_INC(xs_log_writes);
-	ASSERT(iclog->ic_refcnt == 0);
+	ASSERT(atomic_read(&iclog->ic_refcnt) == 0);
 
 	/* Add for LR header */
 	count_init = log->l_iclog_hsize + iclog->ic_offset;
@@ -1538,7 +1557,6 @@ STATIC void
 xlog_dealloc_log(xlog_t *log)
 {
 	xlog_in_core_t	*iclog, *next_iclog;
-	xlog_ticket_t	*tic, *next_tic;
 	int		i;
 
 	iclog = log->l_iclog;
@@ -1559,22 +1577,6 @@ xlog_dealloc_log(xlog_t *log)
 	spinlock_destroy(&log->l_icloglock);
 	spinlock_destroy(&log->l_grant_lock);
 
-	/* XXXsup take a look at this again. */
-	if ((log->l_ticket_cnt != log->l_ticket_tcnt)  &&
-	    !XLOG_FORCED_SHUTDOWN(log)) {
-		xfs_fs_cmn_err(CE_WARN, log->l_mp,
-			"xlog_dealloc_log: (cnt: %d, total: %d)",
-			log->l_ticket_cnt, log->l_ticket_tcnt);
-		/* ASSERT(log->l_ticket_cnt == log->l_ticket_tcnt); */
-
-	} else {
-		tic = log->l_unmount_free;
-		while (tic) {
-			next_tic = tic->t_next;
-			kmem_free(tic, PAGE_SIZE);
-			tic = next_tic;
-		}
-	}
 	xfs_buf_free(log->l_xbuf);
 #ifdef XFS_LOG_TRACE
 	if (log->l_trace != NULL) {
@@ -1987,7 +1989,7 @@ xlog_state_clean_log(xlog_t *log)
 		if (iclog->ic_state == XLOG_STATE_DIRTY) {
 			iclog->ic_state	= XLOG_STATE_ACTIVE;
 			iclog->ic_offset       = 0;
-			iclog->ic_callback	= NULL;   /* don't need to free */
+			ASSERT(iclog->ic_callback == NULL);
 			/*
 			 * If the number of ops in this iclog indicate it just
 			 * contains the dummy transaction, we can
@@ -2190,37 +2192,40 @@ xlog_state_do_callback(
 					be64_to_cpu(iclog->ic_header.h_lsn);
 				spin_unlock(&log->l_grant_lock);
 
-				/*
-				 * Keep processing entries in the callback list
-				 * until we come around and it is empty.  We
-				 * need to atomically see that the list is
-				 * empty and change the state to DIRTY so that
-				 * we don't miss any more callbacks being added.
-				 */
-				spin_lock(&log->l_icloglock);
 			} else {
+				spin_unlock(&log->l_icloglock);
 				ioerrors++;
 			}
-			cb = iclog->ic_callback;
 
+			/*
+			 * Keep processing entries in the callback list until
+			 * we come around and it is empty.  We need to
+			 * atomically see that the list is empty and change the
+			 * state to DIRTY so that we don't miss any more
+			 * callbacks being added.
+			 */
+			spin_lock(&iclog->ic_callback_lock);
+			cb = iclog->ic_callback;
 			while (cb) {
 				iclog->ic_callback_tail = &(iclog->ic_callback);
 				iclog->ic_callback = NULL;
-				spin_unlock(&log->l_icloglock);
+				spin_unlock(&iclog->ic_callback_lock);
 
 				/* perform callbacks in the order given */
 				for (; cb; cb = cb_next) {
 					cb_next = cb->cb_next;
 					cb->cb_func(cb->cb_arg, aborted);
 				}
-				spin_lock(&log->l_icloglock);
+				spin_lock(&iclog->ic_callback_lock);
 				cb = iclog->ic_callback;
 			}
 
 			loopdidcallbacks++;
 			funcdidcallbacks++;
 
+			spin_lock(&log->l_icloglock);
 			ASSERT(iclog->ic_callback == NULL);
+			spin_unlock(&iclog->ic_callback_lock);
 			if (!(iclog->ic_state & XLOG_STATE_IOERROR))
 				iclog->ic_state = XLOG_STATE_DIRTY;
 
@@ -2241,7 +2246,7 @@ xlog_state_do_callback(
 			repeats = 0;
 			xfs_fs_cmn_err(CE_WARN, log->l_mp,
 				"%s: possible infinite loop (%d iterations)",
-				__FUNCTION__, flushcnt);
+				__func__, flushcnt);
 		}
 	} while (!ioerrors && loopdidcallbacks);
 
@@ -2309,7 +2314,7 @@ xlog_state_done_syncing(
 
 	ASSERT(iclog->ic_state == XLOG_STATE_SYNCING ||
 	       iclog->ic_state == XLOG_STATE_IOERROR);
-	ASSERT(iclog->ic_refcnt == 0);
+	ASSERT(atomic_read(&iclog->ic_refcnt) == 0);
 	ASSERT(iclog->ic_bwritecnt == 1 || iclog->ic_bwritecnt == 2);
 
 
@@ -2391,7 +2396,7 @@ restart:
 	ASSERT(iclog->ic_state == XLOG_STATE_ACTIVE);
 	head = &iclog->ic_header;
 
-	iclog->ic_refcnt++;			/* prevents sync */
+	atomic_inc(&iclog->ic_refcnt);	/* prevents sync */
 	log_offset = iclog->ic_offset;
 
 	/* On the 1st write to an iclog, figure out lsn.  This works
@@ -2423,12 +2428,12 @@ restart:
 		xlog_state_switch_iclogs(log, iclog, iclog->ic_size);
 
 		/* If I'm the only one writing to this iclog, sync it to disk */
-		if (iclog->ic_refcnt == 1) {
+		if (atomic_read(&iclog->ic_refcnt) == 1) {
 			spin_unlock(&log->l_icloglock);
 			if ((error = xlog_state_release_iclog(log, iclog)))
 				return error;
 		} else {
-			iclog->ic_refcnt--;
+			atomic_dec(&iclog->ic_refcnt);
 			spin_unlock(&log->l_icloglock);
 		}
 		goto restart;
@@ -2791,18 +2796,6 @@ xlog_ungrant_log_space(xlog_t	     *log,
 }	/* xlog_ungrant_log_space */
 
 
-/*
- * Atomically put back used ticket.
- */
-STATIC void
-xlog_state_put_ticket(xlog_t	    *log,
-		      xlog_ticket_t *tic)
-{
-	spin_lock(&log->l_icloglock);
-	xlog_ticket_put(log, tic);
-	spin_unlock(&log->l_icloglock);
-}	/* xlog_state_put_ticket */
-
 /*
  * Flush iclog to disk if this is the last reference to the given iclog and
  * the WANT_SYNC bit is set.
@@ -2813,33 +2806,35 @@ xlog_state_put_ticket(xlog_t	    *log,
  *
  */
 STATIC int
-xlog_state_release_iclog(xlog_t		*log,
-			 xlog_in_core_t	*iclog)
+xlog_state_release_iclog(
+	xlog_t		*log,
+	xlog_in_core_t	*iclog)
 {
 	int		sync = 0;	/* do we sync? */
 
-	xlog_assign_tail_lsn(log->l_mp);
+	if (iclog->ic_state & XLOG_STATE_IOERROR)
+		return XFS_ERROR(EIO);
 
-	spin_lock(&log->l_icloglock);
+	ASSERT(atomic_read(&iclog->ic_refcnt) > 0);
+	if (!atomic_dec_and_lock(&iclog->ic_refcnt, &log->l_icloglock))
+		return 0;
 
 	if (iclog->ic_state & XLOG_STATE_IOERROR) {
 		spin_unlock(&log->l_icloglock);
 		return XFS_ERROR(EIO);
 	}
-
-	ASSERT(iclog->ic_refcnt > 0);
 	ASSERT(iclog->ic_state == XLOG_STATE_ACTIVE ||
 	       iclog->ic_state == XLOG_STATE_WANT_SYNC);
 
-	if (--iclog->ic_refcnt == 0 &&
-	    iclog->ic_state == XLOG_STATE_WANT_SYNC) {
+	if (iclog->ic_state == XLOG_STATE_WANT_SYNC) {
+		/* update tail before writing to iclog */
+		xlog_assign_tail_lsn(log->l_mp);
 		sync++;
 		iclog->ic_state = XLOG_STATE_SYNCING;
 		iclog->ic_header.h_tail_lsn = cpu_to_be64(log->l_tail_lsn);
 		xlog_verify_tail_lsn(log, iclog, log->l_tail_lsn);
 		/* cycle incremented when incrementing curr_block */
 	}
-
 	spin_unlock(&log->l_icloglock);
 
 	/*
@@ -2849,11 +2844,9 @@ xlog_state_release_iclog(xlog_t		*log,
 	 * this iclog has consistent data, so we ignore IOERROR
 	 * flags after this point.
 	 */
-	if (sync) {
+	if (sync)
 		return xlog_sync(log, iclog);
-	}
 	return 0;
-
 }	/* xlog_state_release_iclog */
 
 
@@ -2953,7 +2946,8 @@ xlog_state_sync_all(xlog_t *log, uint flags, int *log_flushed)
 		 * previous iclog and go to sleep.
 		 */
 		if (iclog->ic_state == XLOG_STATE_DIRTY ||
-		    (iclog->ic_refcnt == 0 && iclog->ic_offset == 0)) {
+		    (atomic_read(&iclog->ic_refcnt) == 0
+		     && iclog->ic_offset == 0)) {
 			iclog = iclog->ic_prev;
 			if (iclog->ic_state == XLOG_STATE_ACTIVE ||
 			    iclog->ic_state == XLOG_STATE_DIRTY)
@@ -2961,14 +2955,14 @@ xlog_state_sync_all(xlog_t *log, uint flags, int *log_flushed)
 			else
 				goto maybe_sleep;
 		} else {
-			if (iclog->ic_refcnt == 0) {
+			if (atomic_read(&iclog->ic_refcnt) == 0) {
 				/* We are the only one with access to this
 				 * iclog.  Flush it out now.  There should
 				 * be a roundoff of zero to show that someone
 				 * has already taken care of the roundoff from
 				 * the previous sync.
 				 */
-				iclog->ic_refcnt++;
+				atomic_inc(&iclog->ic_refcnt);
 				lsn = be64_to_cpu(iclog->ic_header.h_lsn);
 				xlog_state_switch_iclogs(log, iclog, 0);
 				spin_unlock(&log->l_icloglock);
@@ -3100,7 +3094,7 @@ try_again:
 			already_slept = 1;
 			goto try_again;
 		} else {
-			iclog->ic_refcnt++;
+			atomic_inc(&iclog->ic_refcnt);
 			xlog_state_switch_iclogs(log, iclog, 0);
 			spin_unlock(&log->l_icloglock);
 			if (xlog_state_release_iclog(log, iclog))
@@ -3172,92 +3166,19 @@ xlog_state_want_sync(xlog_t *log, xlog_in_core_t *iclog)
  */
 
 /*
- *	Algorithm doesn't take into account page size. ;-(
- */
-STATIC void
-xlog_state_ticket_alloc(xlog_t *log)
-{
-	xlog_ticket_t	*t_list;
-	xlog_ticket_t	*next;
-	xfs_caddr_t	buf;
-	uint		i = (PAGE_SIZE / sizeof(xlog_ticket_t)) - 2;
-
-	/*
-	 * The kmem_zalloc may sleep, so we shouldn't be holding the
-	 * global lock.  XXXmiken: may want to use zone allocator.
-	 */
-	buf = (xfs_caddr_t) kmem_zalloc(PAGE_SIZE, KM_SLEEP);
-
-	spin_lock(&log->l_icloglock);
-
-	/* Attach 1st ticket to Q, so we can keep track of allocated memory */
-	t_list = (xlog_ticket_t *)buf;
-	t_list->t_next = log->l_unmount_free;
-	log->l_unmount_free = t_list++;
-	log->l_ticket_cnt++;
-	log->l_ticket_tcnt++;
-
-	/* Next ticket becomes first ticket attached to ticket free list */
-	if (log->l_freelist != NULL) {
-		ASSERT(log->l_tail != NULL);
-		log->l_tail->t_next = t_list;
-	} else {
-		log->l_freelist = t_list;
-	}
-	log->l_ticket_cnt++;
-	log->l_ticket_tcnt++;
-
-	/* Cycle through rest of alloc'ed memory, building up free Q */
-	for ( ; i > 0; i--) {
-		next = t_list + 1;
-		t_list->t_next = next;
-		t_list = next;
-		log->l_ticket_cnt++;
-		log->l_ticket_tcnt++;
-	}
-	t_list->t_next = NULL;
-	log->l_tail = t_list;
-	spin_unlock(&log->l_icloglock);
-}	/* xlog_state_ticket_alloc */
-
-
-/*
- * Put ticket into free list
- *
- * Assumption: log lock is held around this call.
+ * Free a used ticket.
  */
 STATIC void
 xlog_ticket_put(xlog_t		*log,
 		xlog_ticket_t	*ticket)
 {
 	sv_destroy(&ticket->t_sema);
-
-	/*
-	 * Don't think caching will make that much difference.  It's
-	 * more important to make debug easier.
-	 */
-#if 0
-	/* real code will want to use LIFO for caching */
-	ticket->t_next = log->l_freelist;
-	log->l_freelist = ticket;
-	/* no need to clear fields */
-#else
-	/* When we debug, it is easier if tickets are cycled */
-	ticket->t_next     = NULL;
-	if (log->l_tail) {
-		log->l_tail->t_next = ticket;
-	} else {
-		ASSERT(log->l_freelist == NULL);
-		log->l_freelist = ticket;
-	}
-	log->l_tail	    = ticket;
-#endif /* DEBUG */
-	log->l_ticket_cnt++;
+	kmem_zone_free(xfs_log_ticket_zone, ticket);
 }	/* xlog_ticket_put */
 
 
 /*
- * Grab ticket off freelist or allocation some more
+ * Allocate and initialise a new log ticket.
  */
 STATIC xlog_ticket_t *
 xlog_ticket_get(xlog_t		*log,
@@ -3269,21 +3190,9 @@ xlog_ticket_get(xlog_t		*log,
 	xlog_ticket_t	*tic;
 	uint		num_headers;
 
- alloc:
-	if (log->l_freelist == NULL)
-		xlog_state_ticket_alloc(log);		/* potentially sleep */
-
-	spin_lock(&log->l_icloglock);
-	if (log->l_freelist == NULL) {
-		spin_unlock(&log->l_icloglock);
-		goto alloc;
-	}
-	tic		= log->l_freelist;
-	log->l_freelist	= tic->t_next;
-	if (log->l_freelist == NULL)
-		log->l_tail = NULL;
-	log->l_ticket_cnt--;
-	spin_unlock(&log->l_icloglock);
+	tic = kmem_zone_zalloc(xfs_log_ticket_zone, KM_SLEEP|KM_MAYFAIL);
+	if (!tic)
+		return NULL;
 
 	/*
 	 * Permanent reservations have up to 'cnt'-1 active log operations
@@ -3611,8 +3520,8 @@ xfs_log_force_umount(
 	 * before we mark the filesystem SHUTDOWN and wake
 	 * everybody up to tell the bad news.
 	 */
-	spin_lock(&log->l_grant_lock);
 	spin_lock(&log->l_icloglock);
+	spin_lock(&log->l_grant_lock);
 	mp->m_flags |= XFS_MOUNT_FS_SHUTDOWN;
 	XFS_BUF_DONE(mp->m_sb_bp);
 	/*

fs/xfs/xfs_log.h

@@ -142,8 +142,9 @@ int	  _xfs_log_force(struct xfs_mount *mp,
 			 xfs_lsn_t	lsn,
 			 uint		flags,
 			 int		*log_forced);
-#define xfs_log_force(mp, lsn, flags) \
-	_xfs_log_force(mp, lsn, flags, NULL);
+void	  xfs_log_force(struct xfs_mount	*mp,
+			xfs_lsn_t		lsn,
+			uint			flags);
 int	  xfs_log_mount(struct xfs_mount	*mp,
 			struct xfs_buftarg	*log_target,
 			xfs_daddr_t		start_block,

fs/xfs/xfs_log_priv.h

@@ -242,7 +242,7 @@ typedef struct xlog_res {
 
 typedef struct xlog_ticket {
 	sv_t		   t_sema;	 /* sleep on this semaphore      : 20 */
- 	struct xlog_ticket *t_next;	 /*			         :4|8 */
+	struct xlog_ticket *t_next;	 /*			         :4|8 */
 	struct xlog_ticket *t_prev;	 /*				 :4|8 */
 	xlog_tid_t	   t_tid;	 /* transaction identifier	 : 4  */
 	int		   t_curr_res;	 /* current reservation in bytes : 4  */
@@ -324,6 +324,19 @@ typedef struct xlog_rec_ext_header {
  * - ic_offset is the current number of bytes written to in this iclog.
  * - ic_refcnt is bumped when someone is writing to the log.
  * - ic_state is the state of the iclog.
+ *
+ * Because of cacheline contention on large machines, we need to separate
+ * various resources onto different cachelines. To start with, make the
+ * structure cacheline aligned. The following fields can be contended on
+ * by independent processes:
+ *
+ *	- ic_callback_*
+ *	- ic_refcnt
+ *	- fields protected by the global l_icloglock
+ *
+ * so we need to ensure that these fields are located in separate cachelines.
+ * We'll put all the read-only and l_icloglock fields in the first cacheline,
+ * and move everything else out to subsequent cachelines.
  */
 typedef struct xlog_iclog_fields {
 	sv_t			ic_forcesema;
@@ -332,17 +345,22 @@ typedef struct xlog_iclog_fields {
 	struct xlog_in_core	*ic_prev;
 	struct xfs_buf		*ic_bp;
 	struct log		*ic_log;
-	xfs_log_callback_t	*ic_callback;
-	xfs_log_callback_t	**ic_callback_tail;
-#ifdef XFS_LOG_TRACE
-	struct ktrace		*ic_trace;
-#endif
 	int			ic_size;
 	int			ic_offset;
-	int			ic_refcnt;
 	int			ic_bwritecnt;
 	ushort_t		ic_state;
 	char			*ic_datap;	/* pointer to iclog data */
+#ifdef XFS_LOG_TRACE
+	struct ktrace		*ic_trace;
+#endif
+
+	/* Callback structures need their own cacheline */
+	spinlock_t		ic_callback_lock ____cacheline_aligned_in_smp;
+	xfs_log_callback_t	*ic_callback;
+	xfs_log_callback_t	**ic_callback_tail;
+
+	/* reference counts need their own cacheline */
+	atomic_t		ic_refcnt ____cacheline_aligned_in_smp;
 } xlog_iclog_fields_t;
 
 typedef union xlog_in_core2 {
@@ -366,6 +384,7 @@ typedef struct xlog_in_core {
 #define	ic_bp		hic_fields.ic_bp
 #define	ic_log		hic_fields.ic_log
 #define	ic_callback	hic_fields.ic_callback
+#define	ic_callback_lock hic_fields.ic_callback_lock
 #define	ic_callback_tail hic_fields.ic_callback_tail
 #define	ic_trace	hic_fields.ic_trace
 #define	ic_size		hic_fields.ic_size
@@ -383,43 +402,46 @@ typedef struct xlog_in_core {
  * that round off problems won't occur when releasing partial reservations.
  */
 typedef struct log {
+	/* The following fields don't need locking */
+	struct xfs_mount	*l_mp;	        /* mount point */
+	struct xfs_buf		*l_xbuf;        /* extra buffer for log
+						 * wrapping */
+	struct xfs_buftarg	*l_targ;        /* buftarg of log */
+	uint			l_flags;
+	uint			l_quotaoffs_flag; /* XFS_DQ_*, for QUOTAOFFs */
+	struct xfs_buf_cancel	**l_buf_cancel_table;
+	int			l_iclog_hsize;  /* size of iclog header */
+	int			l_iclog_heads;  /* # of iclog header sectors */
+	uint			l_sectbb_log;   /* log2 of sector size in BBs */
+	uint			l_sectbb_mask;  /* sector size (in BBs)
+						 * alignment mask */
+	int			l_iclog_size;	/* size of log in bytes */
+	int			l_iclog_size_log; /* log power size of log */
+	int			l_iclog_bufs;	/* number of iclog buffers */
+	xfs_daddr_t		l_logBBstart;   /* start block of log */
+	int			l_logsize;      /* size of log in bytes */
+	int			l_logBBsize;    /* size of log in BB chunks */
+
 	/* The following block of fields are changed while holding icloglock */
-	sema_t			l_flushsema;    /* iclog flushing semaphore */
+	sema_t			l_flushsema ____cacheline_aligned_in_smp;
+						/* iclog flushing semaphore */
 	int			l_flushcnt;	/* # of procs waiting on this
 						 * sema */
-	int			l_ticket_cnt;	/* free ticket count */
-	int			l_ticket_tcnt;	/* total ticket count */
 	int			l_covered_state;/* state of "covering disk
 						 * log entries" */
-	xlog_ticket_t		*l_freelist;    /* free list of tickets */
-	xlog_ticket_t		*l_unmount_free;/* kmem_free these addresses */
-	xlog_ticket_t		*l_tail;        /* free list of tickets */
 	xlog_in_core_t		*l_iclog;       /* head log queue	*/
 	spinlock_t		l_icloglock;    /* grab to change iclog state */
 	xfs_lsn_t		l_tail_lsn;     /* lsn of 1st LR with unflushed
 						 * buffers */
 	xfs_lsn_t		l_last_sync_lsn;/* lsn of last LR on disk */
-	struct xfs_mount	*l_mp;	        /* mount point */
-	struct xfs_buf		*l_xbuf;        /* extra buffer for log
-						 * wrapping */
-	struct xfs_buftarg	*l_targ;        /* buftarg of log */
-	xfs_daddr_t		l_logBBstart;   /* start block of log */
-	int			l_logsize;      /* size of log in bytes */
-	int			l_logBBsize;    /* size of log in BB chunks */
 	int			l_curr_cycle;   /* Cycle number of log writes */
 	int			l_prev_cycle;   /* Cycle number before last
 						 * block increment */
 	int			l_curr_block;   /* current logical log block */
 	int			l_prev_block;   /* previous logical log block */
-	int			l_iclog_size;	/* size of log in bytes */
-	int			l_iclog_size_log; /* log power size of log */
-	int			l_iclog_bufs;	/* number of iclog buffers */
-
-	/* The following field are used for debugging; need to hold icloglock */
-	char			*l_iclog_bak[XLOG_MAX_ICLOGS];
 
 	/* The following block of fields are changed while holding grant_lock */
-	spinlock_t		l_grant_lock;
+	spinlock_t		l_grant_lock ____cacheline_aligned_in_smp;
 	xlog_ticket_t		*l_reserve_headq;
 	xlog_ticket_t		*l_write_headq;
 	int			l_grant_reserve_cycle;
@@ -427,19 +449,16 @@ typedef struct log {
 	int			l_grant_write_cycle;
 	int			l_grant_write_bytes;
 
-	/* The following fields don't need locking */
 #ifdef XFS_LOG_TRACE
 	struct ktrace		*l_trace;
 	struct ktrace		*l_grant_trace;
 #endif
-	uint			l_flags;
-	uint			l_quotaoffs_flag; /* XFS_DQ_*, for QUOTAOFFs */
-	struct xfs_buf_cancel	**l_buf_cancel_table;
-	int			l_iclog_hsize;  /* size of iclog header */
-	int			l_iclog_heads;  /* # of iclog header sectors */
-	uint			l_sectbb_log;   /* log2 of sector size in BBs */
-	uint			l_sectbb_mask;  /* sector size (in BBs)
-						 * alignment mask */
+
+	/* The following field are used for debugging; need to hold icloglock */
+#ifdef DEBUG
+	char			*l_iclog_bak[XLOG_MAX_ICLOGS];
+#endif
+
 } xlog_t;
 
 #define XLOG_FORCED_SHUTDOWN(log)	((log)->l_flags & XLOG_IO_ERROR)
@@ -459,6 +478,8 @@ extern struct xfs_buf *xlog_get_bp(xlog_t *, int);
 extern void	 xlog_put_bp(struct xfs_buf *);
 extern int	 xlog_bread(xlog_t *, xfs_daddr_t, int, struct xfs_buf *);
 
+extern kmem_zone_t	*xfs_log_ticket_zone;
+
 /* iclog tracing */
 #define XLOG_TRACE_GRAB_FLUSH  1
 #define XLOG_TRACE_REL_FLUSH   2

fs/xfs/xfs_log_recover.c

@@ -46,6 +46,7 @@
 #include "xfs_trans_priv.h"
 #include "xfs_quota.h"
 #include "xfs_rw.h"
+#include "xfs_utils.h"
 
 STATIC int	xlog_find_zeroed(xlog_t *, xfs_daddr_t *);
 STATIC int	xlog_clear_stale_blocks(xlog_t *, xfs_lsn_t);
@@ -120,7 +121,8 @@ xlog_bread(
 	XFS_BUF_SET_TARGET(bp, log->l_mp->m_logdev_targp);
 
 	xfsbdstrat(log->l_mp, bp);
-	if ((error = xfs_iowait(bp)))
+	error = xfs_iowait(bp);
+	if (error)
 		xfs_ioerror_alert("xlog_bread", log->l_mp,
 				  bp, XFS_BUF_ADDR(bp));
 	return error;
@@ -191,7 +193,7 @@ xlog_header_check_dump(
 {
 	int			b;
 
-	cmn_err(CE_DEBUG, "%s:  SB : uuid = ", __FUNCTION__);
+	cmn_err(CE_DEBUG, "%s:  SB : uuid = ", __func__);
 	for (b = 0; b < 16; b++)
 		cmn_err(CE_DEBUG, "%02x", ((uchar_t *)&mp->m_sb.sb_uuid)[b]);
 	cmn_err(CE_DEBUG, ", fmt = %d\n", XLOG_FMT);
@@ -1160,10 +1162,14 @@ xlog_write_log_records(
 		if (j == 0 && (start_block + endcount > ealign)) {
 			offset = XFS_BUF_PTR(bp);
 			balign = BBTOB(ealign - start_block);
-			XFS_BUF_SET_PTR(bp, offset + balign, BBTOB(sectbb));
-			if ((error = xlog_bread(log, ealign, sectbb, bp)))
+			error = XFS_BUF_SET_PTR(bp, offset + balign,
+						BBTOB(sectbb));
+			if (!error)
+				error = xlog_bread(log, ealign, sectbb, bp);
+			if (!error)
+				error = XFS_BUF_SET_PTR(bp, offset, bufblks);
+			if (error)
 				break;
-			XFS_BUF_SET_PTR(bp, offset, bufblks);
 		}
 
 		offset = xlog_align(log, start_block, endcount, bp);
@@ -2280,7 +2286,9 @@ xlog_recover_do_inode_trans(
 		 * invalidate the buffer when we write it out below.
 		 */
 		imap.im_blkno = 0;
-		xfs_imap(log->l_mp, NULL, ino, &imap, 0);
+		error = xfs_imap(log->l_mp, NULL, ino, &imap, 0);
+		if (error)
+			goto error;
 	}
 
 	/*
@@ -2964,7 +2972,7 @@ xlog_recover_process_data(
  * Process an extent free intent item that was recovered from
  * the log.  We need to free the extents that it describes.
  */
-STATIC void
+STATIC int
 xlog_recover_process_efi(
 	xfs_mount_t		*mp,
 	xfs_efi_log_item_t	*efip)
@@ -2972,6 +2980,7 @@ xlog_recover_process_efi(
 	xfs_efd_log_item_t	*efdp;
 	xfs_trans_t		*tp;
 	int			i;
+	int			error = 0;
 	xfs_extent_t		*extp;
 	xfs_fsblock_t		startblock_fsb;
 
@@ -2995,23 +3004,32 @@ xlog_recover_process_efi(
 			 * free the memory associated with it.
 			 */
 			xfs_efi_release(efip, efip->efi_format.efi_nextents);
-			return;
+			return XFS_ERROR(EIO);
 		}
 	}
 
 	tp = xfs_trans_alloc(mp, 0);
-	xfs_trans_reserve(tp, 0, XFS_ITRUNCATE_LOG_RES(mp), 0, 0, 0);
+	error = xfs_trans_reserve(tp, 0, XFS_ITRUNCATE_LOG_RES(mp), 0, 0, 0);
+	if (error)
+		goto abort_error;
 	efdp = xfs_trans_get_efd(tp, efip, efip->efi_format.efi_nextents);
 
 	for (i = 0; i < efip->efi_format.efi_nextents; i++) {
 		extp = &(efip->efi_format.efi_extents[i]);
-		xfs_free_extent(tp, extp->ext_start, extp->ext_len);
+		error = xfs_free_extent(tp, extp->ext_start, extp->ext_len);
+		if (error)
+			goto abort_error;
 		xfs_trans_log_efd_extent(tp, efdp, extp->ext_start,
 					 extp->ext_len);
 	}
 
 	efip->efi_flags |= XFS_EFI_RECOVERED;
-	xfs_trans_commit(tp, 0);
+	error = xfs_trans_commit(tp, 0);
+	return error;
+
+abort_error:
+	xfs_trans_cancel(tp, XFS_TRANS_ABORT);
+	return error;
 }
 
 /*
@@ -3059,7 +3077,7 @@ xlog_recover_check_ail(
  * everything already in the AIL, we stop processing as soon as
  * we see something other than an EFI in the AIL.
  */
-STATIC void
+STATIC int
 xlog_recover_process_efis(
 	xlog_t			*log)
 {
@@ -3067,6 +3085,7 @@ xlog_recover_process_efis(
 	xfs_efi_log_item_t	*efip;
 	int			gen;
 	xfs_mount_t		*mp;
+	int			error = 0;
 
 	mp = log->l_mp;
 	spin_lock(&mp->m_ail_lock);
@@ -3091,11 +3110,14 @@ xlog_recover_process_efis(
 		}
 
 		spin_unlock(&mp->m_ail_lock);
-		xlog_recover_process_efi(mp, efip);
+		error = xlog_recover_process_efi(mp, efip);
+		if (error)
+			return error;
 		spin_lock(&mp->m_ail_lock);
 		lip = xfs_trans_next_ail(mp, lip, &gen, NULL);
 	}
 	spin_unlock(&mp->m_ail_lock);
+	return error;
 }
 
 /*
@@ -3115,21 +3137,18 @@ xlog_recover_clear_agi_bucket(
 	int		error;
 
 	tp = xfs_trans_alloc(mp, XFS_TRANS_CLEAR_AGI_BUCKET);
-	xfs_trans_reserve(tp, 0, XFS_CLEAR_AGI_BUCKET_LOG_RES(mp), 0, 0, 0);
-
-	error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
+	error = xfs_trans_reserve(tp, 0, XFS_CLEAR_AGI_BUCKET_LOG_RES(mp), 0, 0, 0);
+	if (!error)
+		error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
 				   XFS_AG_DADDR(mp, agno, XFS_AGI_DADDR(mp)),
 				   XFS_FSS_TO_BB(mp, 1), 0, &agibp);
-	if (error) {
-		xfs_trans_cancel(tp, XFS_TRANS_ABORT);
-		return;
-	}
+	if (error)
+		goto out_abort;
 
+	error = EINVAL;
 	agi = XFS_BUF_TO_AGI(agibp);
-	if (be32_to_cpu(agi->agi_magicnum) != XFS_AGI_MAGIC) {
-		xfs_trans_cancel(tp, XFS_TRANS_ABORT);
-		return;
-	}
+	if (be32_to_cpu(agi->agi_magicnum) != XFS_AGI_MAGIC)
+		goto out_abort;
 
 	agi->agi_unlinked[bucket] = cpu_to_be32(NULLAGINO);
 	offset = offsetof(xfs_agi_t, agi_unlinked) +
@@ -3137,7 +3156,17 @@ xlog_recover_clear_agi_bucket(
 	xfs_trans_log_buf(tp, agibp, offset,
 			  (offset + sizeof(xfs_agino_t) - 1));
 
-	(void) xfs_trans_commit(tp, 0);
+	error = xfs_trans_commit(tp, 0);
+	if (error)
+		goto out_error;
+	return;
+
+out_abort:
+	xfs_trans_cancel(tp, XFS_TRANS_ABORT);
+out_error:
+	xfs_fs_cmn_err(CE_WARN, mp, "xlog_recover_clear_agi_bucket: "
+			"failed to clear agi %d. Continuing.", agno);
+	return;
 }
 
 /*
@@ -3214,7 +3243,8 @@ xlog_recover_process_iunlinks(
 					 * next inode in the bucket.
 					 */
 					error = xfs_itobp(mp, NULL, ip, &dip,
-							&ibp, 0, 0);
+							&ibp, 0, 0,
+							XFS_BUF_LOCK);
 					ASSERT(error || (dip != NULL));
 				}
 
@@ -3247,7 +3277,7 @@ xlog_recover_process_iunlinks(
 					if (ip->i_d.di_mode == 0)
 						xfs_iput_new(ip, 0);
 					else
-						VN_RELE(XFS_ITOV(ip));
+						IRELE(ip);
 				} else {
 					/*
 					 * We can't read in the inode
@@ -3445,7 +3475,7 @@ xlog_valid_rec_header(
 	    (!rhead->h_version ||
 	    (be32_to_cpu(rhead->h_version) & (~XLOG_VERSION_OKBITS))))) {
 		xlog_warn("XFS: %s: unrecognised log version (%d).",
-			__FUNCTION__, be32_to_cpu(rhead->h_version));
+			__func__, be32_to_cpu(rhead->h_version));
 		return XFS_ERROR(EIO);
 	}
 
@@ -3604,15 +3634,19 @@ xlog_do_recovery_pass(
 				 *   _first_, then the log start (LR header end)
 				 *   - order is important.
 				 */
+				wrapped_hblks = hblks - split_hblks;
 				bufaddr = XFS_BUF_PTR(hbp);
-				XFS_BUF_SET_PTR(hbp,
+				error = XFS_BUF_SET_PTR(hbp,
 						bufaddr + BBTOB(split_hblks),
 						BBTOB(hblks - split_hblks));
-				wrapped_hblks = hblks - split_hblks;
-				error = xlog_bread(log, 0, wrapped_hblks, hbp);
+				if (!error)
+					error = xlog_bread(log, 0,
+							wrapped_hblks, hbp);
+				if (!error)
+					error = XFS_BUF_SET_PTR(hbp, bufaddr,
+							BBTOB(hblks));
 				if (error)
 					goto bread_err2;
-				XFS_BUF_SET_PTR(hbp, bufaddr, BBTOB(hblks));
 				if (!offset)
 					offset = xlog_align(log, 0,
 							wrapped_hblks, hbp);
@@ -3664,13 +3698,18 @@ xlog_do_recovery_pass(
 				 *   - order is important.
 				 */
 				bufaddr = XFS_BUF_PTR(dbp);
-				XFS_BUF_SET_PTR(dbp,
+				error = XFS_BUF_SET_PTR(dbp,
 						bufaddr + BBTOB(split_bblks),
 						BBTOB(bblks - split_bblks));
-				if ((error = xlog_bread(log, wrapped_hblks,
-						bblks - split_bblks, dbp)))
+				if (!error)
+					error = xlog_bread(log, wrapped_hblks,
+							bblks - split_bblks,
+							dbp);
+				if (!error)
+					error = XFS_BUF_SET_PTR(dbp, bufaddr,
+							h_size);
+				if (error)
 					goto bread_err2;
-				XFS_BUF_SET_PTR(dbp, bufaddr, h_size);
 				if (!offset)
 					offset = xlog_align(log, wrapped_hblks,
 						bblks - split_bblks, dbp);
@@ -3826,7 +3865,8 @@ xlog_do_recover(
 	XFS_BUF_READ(bp);
 	XFS_BUF_UNASYNC(bp);
 	xfsbdstrat(log->l_mp, bp);
-	if ((error = xfs_iowait(bp))) {
+	error = xfs_iowait(bp);
+	if (error) {
 		xfs_ioerror_alert("xlog_do_recover",
 				  log->l_mp, bp, XFS_BUF_ADDR(bp));
 		ASSERT(0);
@@ -3917,7 +3957,14 @@ xlog_recover_finish(
 	 * rather than accepting new requests.
 	 */
 	if (log->l_flags & XLOG_RECOVERY_NEEDED) {
-		xlog_recover_process_efis(log);
+		int	error;
+		error = xlog_recover_process_efis(log);
+		if (error) {
+			cmn_err(CE_ALERT,
+				"Failed to recover EFIs on filesystem: %s",
+				log->l_mp->m_fsname);
+			return error;
+		}
 		/*
 		 * Sync the log to get all the EFIs out of the AIL.
 		 * This isn't absolutely necessary, but it helps in

fs/xfs/xfs_mount.c

@@ -43,8 +43,9 @@
 #include "xfs_rw.h"
 #include "xfs_quota.h"
 #include "xfs_fsops.h"
+#include "xfs_utils.h"
 
-STATIC void	xfs_mount_log_sb(xfs_mount_t *, __int64_t);
+STATIC int	xfs_mount_log_sb(xfs_mount_t *, __int64_t);
 STATIC int	xfs_uuid_mount(xfs_mount_t *);
 STATIC void	xfs_uuid_unmount(xfs_mount_t *mp);
 STATIC void	xfs_unmountfs_wait(xfs_mount_t *);
@@ -57,7 +58,7 @@ STATIC void	xfs_icsb_balance_counter(xfs_mount_t *, xfs_sb_field_t,
 STATIC void	xfs_icsb_sync_counters(xfs_mount_t *);
 STATIC int	xfs_icsb_modify_counters(xfs_mount_t *, xfs_sb_field_t,
 						int64_t, int);
-STATIC int	xfs_icsb_disable_counter(xfs_mount_t *, xfs_sb_field_t);
+STATIC void	xfs_icsb_disable_counter(xfs_mount_t *, xfs_sb_field_t);
 
 #else
 
@@ -956,7 +957,6 @@ xfs_mountfs(
 {
 	xfs_sb_t	*sbp = &(mp->m_sb);
 	xfs_inode_t	*rip;
-	bhv_vnode_t	*rvp = NULL;
 	__uint64_t	resblks;
 	__int64_t	update_flags = 0LL;
 	uint		quotamount, quotaflags;
@@ -964,11 +964,6 @@ xfs_mountfs(
 	int		uuid_mounted = 0;
 	int		error = 0;
 
-	if (mp->m_sb_bp == NULL) {
-		error = xfs_readsb(mp, mfsi_flags);
-		if (error)
-			return error;
-	}
 	xfs_mount_common(mp, sbp);
 
 	/*
@@ -1163,7 +1158,6 @@ xfs_mountfs(
 	}
 
 	ASSERT(rip != NULL);
-	rvp = XFS_ITOV(rip);
 
 	if (unlikely((rip->i_d.di_mode & S_IFMT) != S_IFDIR)) {
 		cmn_err(CE_WARN, "XFS: corrupted root inode");
@@ -1195,8 +1189,13 @@ xfs_mountfs(
 	/*
 	 * If fs is not mounted readonly, then update the superblock changes.
 	 */
-	if (update_flags && !(mp->m_flags & XFS_MOUNT_RDONLY))
-		xfs_mount_log_sb(mp, update_flags);
+	if (update_flags && !(mp->m_flags & XFS_MOUNT_RDONLY)) {
+		error = xfs_mount_log_sb(mp, update_flags);
+		if (error) {
+			cmn_err(CE_WARN, "XFS: failed to write sb changes");
+			goto error4;
+		}
+	}
 
 	/*
 	 * Initialise the XFS quota management subsystem for this mount
@@ -1233,12 +1232,15 @@ xfs_mountfs(
 	 *
 	 * We default to 5% or 1024 fsbs of space reserved, whichever is smaller.
 	 * This may drive us straight to ENOSPC on mount, but that implies
-	 * we were already there on the last unmount.
+	 * we were already there on the last unmount. Warn if this occurs.
 	 */
 	resblks = mp->m_sb.sb_dblocks;
 	do_div(resblks, 20);
 	resblks = min_t(__uint64_t, resblks, 1024);
-	xfs_reserve_blocks(mp, &resblks, NULL);
+	error = xfs_reserve_blocks(mp, &resblks, NULL);
+	if (error)
+		cmn_err(CE_WARN, "XFS: Unable to allocate reserve blocks. "
+				"Continuing without a reserve pool.");
 
 	return 0;
 
@@ -1246,7 +1248,7 @@ xfs_mountfs(
 	/*
 	 * Free up the root inode.
 	 */
-	VN_RELE(rvp);
+	IRELE(rip);
  error3:
 	xfs_log_unmount_dealloc(mp);
  error2:
@@ -1274,6 +1276,7 @@ int
 xfs_unmountfs(xfs_mount_t *mp, struct cred *cr)
 {
 	__uint64_t	resblks;
+	int		error = 0;
 
 	/*
 	 * We can potentially deadlock here if we have an inode cluster
@@ -1317,9 +1320,15 @@ xfs_unmountfs(xfs_mount_t *mp, struct cred *cr)
 	 * value does not matter....
 	 */
 	resblks = 0;
-	xfs_reserve_blocks(mp, &resblks, NULL);
+	error = xfs_reserve_blocks(mp, &resblks, NULL);
+	if (error)
+		cmn_err(CE_WARN, "XFS: Unable to free reserved block pool. "
+				"Freespace may not be correct on next mount.");
 
-	xfs_log_sbcount(mp, 1);
+	error = xfs_log_sbcount(mp, 1);
+	if (error)
+		cmn_err(CE_WARN, "XFS: Unable to update superblock counters. "
+				"Freespace may not be correct on next mount.");
 	xfs_unmountfs_writesb(mp);
 	xfs_unmountfs_wait(mp); 		/* wait for async bufs */
 	xfs_log_unmount(mp);			/* Done! No more fs ops. */
@@ -1411,9 +1420,8 @@ xfs_log_sbcount(
 	xfs_mod_sb(tp, XFS_SB_IFREE | XFS_SB_ICOUNT | XFS_SB_FDBLOCKS);
 	if (sync)
 		xfs_trans_set_sync(tp);
-	xfs_trans_commit(tp, 0);
-
-	return 0;
+	error = xfs_trans_commit(tp, 0);
+	return error;
 }
 
 STATIC void
@@ -1462,7 +1470,6 @@ xfs_unmountfs_writesb(xfs_mount_t *mp)
 		XFS_BUF_UNASYNC(sbp);
 		ASSERT(XFS_BUF_TARGET(sbp) == mp->m_ddev_targp);
 		xfsbdstrat(mp, sbp);
-		/* Nevermind errors we might get here. */
 		error = xfs_iowait(sbp);
 		if (error)
 			xfs_ioerror_alert("xfs_unmountfs_writesb",
@@ -1911,24 +1918,27 @@ xfs_uuid_unmount(
  * be altered by the mount options, as well as any potential sb_features2
  * fixup. Only the first superblock is updated.
  */
-STATIC void
+STATIC int
 xfs_mount_log_sb(
 	xfs_mount_t	*mp,
 	__int64_t	fields)
 {
 	xfs_trans_t	*tp;
+	int		error;
 
 	ASSERT(fields & (XFS_SB_UNIT | XFS_SB_WIDTH | XFS_SB_UUID |
 			 XFS_SB_FEATURES2 | XFS_SB_BAD_FEATURES2));
 
 	tp = xfs_trans_alloc(mp, XFS_TRANS_SB_UNIT);
-	if (xfs_trans_reserve(tp, 0, mp->m_sb.sb_sectsize + 128, 0, 0,
-				XFS_DEFAULT_LOG_COUNT)) {
+	error = xfs_trans_reserve(tp, 0, mp->m_sb.sb_sectsize + 128, 0, 0,
+				XFS_DEFAULT_LOG_COUNT);
+	if (error) {
 		xfs_trans_cancel(tp, 0);
-		return;
+		return error;
 	}
 	xfs_mod_sb(tp, fields);
-	xfs_trans_commit(tp, 0);
+	error = xfs_trans_commit(tp, 0);
+	return error;
 }
 
 
@@ -2189,7 +2199,7 @@ xfs_icsb_counter_disabled(
 	return test_bit(field, &mp->m_icsb_counters);
 }
 
-STATIC int
+STATIC void
 xfs_icsb_disable_counter(
 	xfs_mount_t	*mp,
 	xfs_sb_field_t	field)
@@ -2207,7 +2217,7 @@ xfs_icsb_disable_counter(
 	 * the m_icsb_mutex.
 	 */
 	if (xfs_icsb_counter_disabled(mp, field))
-		return 0;
+		return;
 
 	xfs_icsb_lock_all_counters(mp);
 	if (!test_and_set_bit(field, &mp->m_icsb_counters)) {
@@ -2230,8 +2240,6 @@ xfs_icsb_disable_counter(
 	}
 
 	xfs_icsb_unlock_all_counters(mp);
-
-	return 0;
 }
 
 STATIC void

fs/xfs/xfs_mount.h

@@ -66,17 +66,17 @@ struct xfs_mru_cache;
  * Prototypes and functions for the Data Migration subsystem.
  */
 
-typedef int	(*xfs_send_data_t)(int, bhv_vnode_t *,
-			xfs_off_t, size_t, int, bhv_vrwlock_t *);
+typedef int	(*xfs_send_data_t)(int, struct xfs_inode *,
+			xfs_off_t, size_t, int, int *);
 typedef int	(*xfs_send_mmap_t)(struct vm_area_struct *, uint);
-typedef int	(*xfs_send_destroy_t)(bhv_vnode_t *, dm_right_t);
+typedef int	(*xfs_send_destroy_t)(struct xfs_inode *, dm_right_t);
 typedef int	(*xfs_send_namesp_t)(dm_eventtype_t, struct xfs_mount *,
-			bhv_vnode_t *,
-			dm_right_t, bhv_vnode_t *, dm_right_t,
-			char *, char *, mode_t, int, int);
+			struct xfs_inode *, dm_right_t,
+			struct xfs_inode *, dm_right_t,
+			const char *, const char *, mode_t, int, int);
 typedef int	(*xfs_send_mount_t)(struct xfs_mount *, dm_right_t,
 			char *, char *);
-typedef void	(*xfs_send_unmount_t)(struct xfs_mount *, bhv_vnode_t *,
+typedef void	(*xfs_send_unmount_t)(struct xfs_mount *, struct xfs_inode *,
 			dm_right_t, mode_t, int, int);
 
 typedef struct xfs_dmops {
@@ -88,20 +88,20 @@ typedef struct xfs_dmops {
 	xfs_send_unmount_t	xfs_send_unmount;
 } xfs_dmops_t;
 
-#define XFS_SEND_DATA(mp, ev,vp,off,len,fl,lock) \
-	(*(mp)->m_dm_ops->xfs_send_data)(ev,vp,off,len,fl,lock)
+#define XFS_SEND_DATA(mp, ev,ip,off,len,fl,lock) \
+	(*(mp)->m_dm_ops->xfs_send_data)(ev,ip,off,len,fl,lock)
 #define XFS_SEND_MMAP(mp, vma,fl) \
 	(*(mp)->m_dm_ops->xfs_send_mmap)(vma,fl)
-#define XFS_SEND_DESTROY(mp, vp,right) \
-	(*(mp)->m_dm_ops->xfs_send_destroy)(vp,right)
+#define XFS_SEND_DESTROY(mp, ip,right) \
+	(*(mp)->m_dm_ops->xfs_send_destroy)(ip,right)
 #define XFS_SEND_NAMESP(mp, ev,b1,r1,b2,r2,n1,n2,mode,rval,fl) \
 	(*(mp)->m_dm_ops->xfs_send_namesp)(ev,NULL,b1,r1,b2,r2,n1,n2,mode,rval,fl)
 #define XFS_SEND_PREUNMOUNT(mp,b1,r1,b2,r2,n1,n2,mode,rval,fl) \
 	(*(mp)->m_dm_ops->xfs_send_namesp)(DM_EVENT_PREUNMOUNT,mp,b1,r1,b2,r2,n1,n2,mode,rval,fl)
 #define XFS_SEND_MOUNT(mp,right,path,name) \
 	(*(mp)->m_dm_ops->xfs_send_mount)(mp,right,path,name)
-#define XFS_SEND_UNMOUNT(mp, vp,right,mode,rval,fl) \
-	(*(mp)->m_dm_ops->xfs_send_unmount)(mp,vp,right,mode,rval,fl)
+#define XFS_SEND_UNMOUNT(mp, ip,right,mode,rval,fl) \
+	(*(mp)->m_dm_ops->xfs_send_unmount)(mp,ip,right,mode,rval,fl)
 
 
 /*
@@ -220,7 +220,7 @@ extern void	xfs_icsb_sync_counters_flags(struct xfs_mount *, int);
 #endif
 
 typedef struct xfs_ail {
-	xfs_ail_entry_t		xa_ail;
+	struct list_head	xa_ail;
 	uint			xa_gen;
 	struct task_struct	*xa_task;
 	xfs_lsn_t		xa_target;
@@ -401,7 +401,7 @@ typedef struct xfs_mount {
 
 /*
  * Allow large block sizes to be reported to userspace programs if the
- * "largeio" mount option is used. 
+ * "largeio" mount option is used.
  *
  * If compatibility mode is specified, simply return the basic unit of caching
  * so that we don't get inefficient read/modify/write I/O from user apps.

fs/xfs/xfs_rename.c

@@ -36,7 +36,6 @@
 #include "xfs_bmap.h"
 #include "xfs_error.h"
 #include "xfs_quota.h"
-#include "xfs_refcache.h"
 #include "xfs_utils.h"
 #include "xfs_trans_space.h"
 #include "xfs_vnodeops.h"
@@ -84,25 +83,23 @@ int xfs_rename_skip, xfs_rename_nskip;
  */
 STATIC int
 xfs_lock_for_rename(
-	xfs_inode_t	*dp1,	/* old (source) directory inode */
-	xfs_inode_t	*dp2,	/* new (target) directory inode */
-	bhv_vname_t	*vname1,/* old entry name */
-	bhv_vname_t	*vname2,/* new entry name */
-	xfs_inode_t	**ipp1,	/* inode of old entry */
-	xfs_inode_t	**ipp2,	/* inode of new entry, if it
+	xfs_inode_t	*dp1,	/* in: old (source) directory inode */
+	xfs_inode_t	*dp2,	/* in: new (target) directory inode */
+	xfs_inode_t	*ip1,	/* in: inode of old entry */
+	struct xfs_name	*name2,	/* in: new entry name */
+	xfs_inode_t	**ipp2,	/* out: inode of new entry, if it
 				   already exists, NULL otherwise. */
-	xfs_inode_t	**i_tab,/* array of inode returned, sorted */
-	int		*num_inodes)  /* number of inodes in array */
+	xfs_inode_t	**i_tab,/* out: array of inode returned, sorted */
+	int		*num_inodes)  /* out: number of inodes in array */
 {
-	xfs_inode_t		*ip1, *ip2, *temp;
+	xfs_inode_t		*ip2 = NULL;
+	xfs_inode_t		*temp;
 	xfs_ino_t		inum1, inum2;
 	int			error;
 	int			i, j;
 	uint			lock_mode;
 	int			diff_dirs = (dp1 != dp2);
 
-	ip2 = NULL;
-
 	/*
 	 * First, find out the current inums of the entries so that we
 	 * can determine the initial locking order.  We'll have to
@@ -110,27 +107,20 @@ xfs_lock_for_rename(
 	 * to see if we still have the right inodes, directories, etc.
 	 */
 	lock_mode = xfs_ilock_map_shared(dp1);
-	error = xfs_get_dir_entry(vname1, &ip1);
-	if (error) {
-		xfs_iunlock_map_shared(dp1, lock_mode);
-		return error;
-	}
+	IHOLD(ip1);
+	xfs_itrace_ref(ip1);
 
 	inum1 = ip1->i_ino;
 
-	ASSERT(ip1);
-	xfs_itrace_ref(ip1);
-
 	/*
 	 * Unlock dp1 and lock dp2 if they are different.
 	 */
-
 	if (diff_dirs) {
 		xfs_iunlock_map_shared(dp1, lock_mode);
 		lock_mode = xfs_ilock_map_shared(dp2);
 	}
 
-	error = xfs_dir_lookup_int(dp2, lock_mode, vname2, &inum2, &ip2);
+	error = xfs_dir_lookup_int(dp2, lock_mode, name2, &inum2, &ip2);
 	if (error == ENOENT) {		/* target does not need to exist. */
 		inum2 = 0;
 	} else if (error) {
@@ -162,6 +152,7 @@ xfs_lock_for_rename(
 		*num_inodes = 4;
 		i_tab[3] = ip2;
 	}
+	*ipp2 = i_tab[3];
 
 	/*
 	 * Sort the elements via bubble sort.  (Remember, there are at
@@ -199,21 +190,6 @@ xfs_lock_for_rename(
 		xfs_lock_inodes(i_tab, *num_inodes, 0, XFS_ILOCK_SHARED);
 	}
 
-	/*
-	 * Set the return value. Null out any unused entries in i_tab.
-	 */
-	*ipp1 = *ipp2 = NULL;
-	for (i=0; i < *num_inodes; i++) {
-		if (i_tab[i]->i_ino == inum1) {
-			*ipp1 = i_tab[i];
-		}
-		if (i_tab[i]->i_ino == inum2) {
-			*ipp2 = i_tab[i];
-		}
-	}
-	for (;i < 4; i++) {
-		i_tab[i] = NULL;
-	}
 	return 0;
 }
 
@@ -223,13 +199,13 @@ xfs_lock_for_rename(
 int
 xfs_rename(
 	xfs_inode_t	*src_dp,
-	bhv_vname_t	*src_vname,
-	bhv_vnode_t	*target_dir_vp,
-	bhv_vname_t	*target_vname)
+	struct xfs_name	*src_name,
+	xfs_inode_t	*src_ip,
+	xfs_inode_t	*target_dp,
+	struct xfs_name	*target_name)
 {
-	bhv_vnode_t	*src_dir_vp = XFS_ITOV(src_dp);
 	xfs_trans_t	*tp;
-	xfs_inode_t	*target_dp, *src_ip, *target_ip;
+	xfs_inode_t	*target_ip;
 	xfs_mount_t	*mp = src_dp->i_mount;
 	int		new_parent;		/* moving to a new dir */
 	int		src_is_directory;	/* src_name is a directory */
@@ -243,29 +219,16 @@ xfs_rename(
 	int		spaceres;
 	int		target_link_zero = 0;
 	int		num_inodes;
-	char		*src_name = VNAME(src_vname);
-	char		*target_name = VNAME(target_vname);
-	int		src_namelen = VNAMELEN(src_vname);
-	int		target_namelen = VNAMELEN(target_vname);
 
 	xfs_itrace_entry(src_dp);
-	xfs_itrace_entry(xfs_vtoi(target_dir_vp));
-
-	/*
-	 * Find the XFS behavior descriptor for the target directory
-	 * vnode since it was not handed to us.
-	 */
-	target_dp = xfs_vtoi(target_dir_vp);
-	if (target_dp == NULL) {
-		return XFS_ERROR(EXDEV);
-	}
+	xfs_itrace_entry(target_dp);
 
 	if (DM_EVENT_ENABLED(src_dp, DM_EVENT_RENAME) ||
 	    DM_EVENT_ENABLED(target_dp, DM_EVENT_RENAME)) {
 		error = XFS_SEND_NAMESP(mp, DM_EVENT_RENAME,
-					src_dir_vp, DM_RIGHT_NULL,
-					target_dir_vp, DM_RIGHT_NULL,
-					src_name, target_name,
+					src_dp, DM_RIGHT_NULL,
+					target_dp, DM_RIGHT_NULL,
+					src_name->name, target_name->name,
 					0, 0, 0);
 		if (error) {
 			return error;
@@ -282,10 +245,8 @@ xfs_rename(
 	 * does not exist in the source directory.
 	 */
 	tp = NULL;
-	error = xfs_lock_for_rename(src_dp, target_dp, src_vname,
-			target_vname, &src_ip, &target_ip, inodes,
-			&num_inodes);
-
+	error = xfs_lock_for_rename(src_dp, target_dp, src_ip, target_name,
+					&target_ip, inodes, &num_inodes);
 	if (error) {
 		/*
 		 * We have nothing locked, no inode references, and
@@ -331,7 +292,7 @@ xfs_rename(
 	XFS_BMAP_INIT(&free_list, &first_block);
 	tp = xfs_trans_alloc(mp, XFS_TRANS_RENAME);
 	cancel_flags = XFS_TRANS_RELEASE_LOG_RES;
-	spaceres = XFS_RENAME_SPACE_RES(mp, target_namelen);
+	spaceres = XFS_RENAME_SPACE_RES(mp, target_name->len);
 	error = xfs_trans_reserve(tp, spaceres, XFS_RENAME_LOG_RES(mp), 0,
 			XFS_TRANS_PERM_LOG_RES, XFS_RENAME_LOG_COUNT);
 	if (error == ENOSPC) {
@@ -365,10 +326,10 @@ xfs_rename(
 	 * them when they unlock the inodes.  Also, we need to be careful
 	 * not to add an inode to the transaction more than once.
 	 */
-	VN_HOLD(src_dir_vp);
+	IHOLD(src_dp);
 	xfs_trans_ijoin(tp, src_dp, XFS_ILOCK_EXCL);
 	if (new_parent) {
-		VN_HOLD(target_dir_vp);
+		IHOLD(target_dp);
 		xfs_trans_ijoin(tp, target_dp, XFS_ILOCK_EXCL);
 	}
 	if ((src_ip != src_dp) && (src_ip != target_dp)) {
@@ -389,9 +350,8 @@ xfs_rename(
 		 * If there's no space reservation, check the entry will
 		 * fit before actually inserting it.
 		 */
-		if (spaceres == 0 &&
-		    (error = xfs_dir_canenter(tp, target_dp, target_name,
-						target_namelen)))
+		error = xfs_dir_canenter(tp, target_dp, target_name, spaceres);
+		if (error)
 			goto error_return;
 		/*
 		 * If target does not exist and the rename crosses
@@ -399,8 +359,8 @@ xfs_rename(
 		 * to account for the ".." reference from the new entry.
 		 */
 		error = xfs_dir_createname(tp, target_dp, target_name,
-					   target_namelen, src_ip->i_ino,
-					   &first_block, &free_list, spaceres);
+						src_ip->i_ino, &first_block,
+						&free_list, spaceres);
 		if (error == ENOSPC)
 			goto error_return;
 		if (error)
@@ -439,7 +399,7 @@ xfs_rename(
 		 * name at the destination directory, remove it first.
 		 */
 		error = xfs_dir_replace(tp, target_dp, target_name,
-					target_namelen, src_ip->i_ino,
+					src_ip->i_ino,
 					&first_block, &free_list, spaceres);
 		if (error)
 			goto abort_return;
@@ -476,7 +436,8 @@ xfs_rename(
 		 * Rewrite the ".." entry to point to the new
 		 * directory.
 		 */
-		error = xfs_dir_replace(tp, src_ip, "..", 2, target_dp->i_ino,
+		error = xfs_dir_replace(tp, src_ip, &xfs_name_dotdot,
+					target_dp->i_ino,
 					&first_block, &free_list, spaceres);
 		ASSERT(error != EEXIST);
 		if (error)
@@ -512,8 +473,8 @@ xfs_rename(
 			goto abort_return;
 	}
 
-	error = xfs_dir_removename(tp, src_dp, src_name, src_namelen,
-			src_ip->i_ino, &first_block, &free_list, spaceres);
+	error = xfs_dir_removename(tp, src_dp, src_name, src_ip->i_ino,
+					&first_block, &free_list, spaceres);
 	if (error)
 		goto abort_return;
 	xfs_ichgtime(src_dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
@@ -580,10 +541,8 @@ xfs_rename(
 	 * the vnode references.
 	 */
 	error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
-	if (target_ip != NULL) {
-		xfs_refcache_purge_ip(target_ip);
+	if (target_ip != NULL)
 		IRELE(target_ip);
-	}
 	/*
 	 * Let interposed file systems know about removed links.
 	 */
@@ -598,9 +557,9 @@ std_return:
 	if (DM_EVENT_ENABLED(src_dp, DM_EVENT_POSTRENAME) ||
 	    DM_EVENT_ENABLED(target_dp, DM_EVENT_POSTRENAME)) {
 		(void) XFS_SEND_NAMESP (mp, DM_EVENT_POSTRENAME,
-					src_dir_vp, DM_RIGHT_NULL,
-					target_dir_vp, DM_RIGHT_NULL,
-					src_name, target_name,
+					src_dp, DM_RIGHT_NULL,
+					target_dp, DM_RIGHT_NULL,
+					src_name->name, target_name->name,
 					0, error, 0);
 	}
 	return error;

fs/xfs/xfs_rtalloc.c

@@ -44,6 +44,7 @@
 #include "xfs_rw.h"
 #include "xfs_inode_item.h"
 #include "xfs_trans_space.h"
+#include "xfs_utils.h"
 
 
 /*
@@ -123,14 +124,14 @@ xfs_growfs_rt_alloc(
 				XFS_GROWRTALLOC_LOG_RES(mp), 0,
 				XFS_TRANS_PERM_LOG_RES,
 				XFS_DEFAULT_PERM_LOG_COUNT)))
-			goto error_exit;
+			goto error_cancel;
 		cancelflags = XFS_TRANS_RELEASE_LOG_RES;
 		/*
 		 * Lock the inode.
 		 */
 		if ((error = xfs_trans_iget(mp, tp, ino, 0,
 						XFS_ILOCK_EXCL, &ip)))
-			goto error_exit;
+			goto error_cancel;
 		XFS_BMAP_INIT(&flist, &firstblock);
 		/*
 		 * Allocate blocks to the bitmap file.
@@ -143,14 +144,16 @@ xfs_growfs_rt_alloc(
 		if (!error && nmap < 1)
 			error = XFS_ERROR(ENOSPC);
 		if (error)
-			goto error_exit;
+			goto error_cancel;
 		/*
 		 * Free any blocks freed up in the transaction, then commit.
 		 */
 		error = xfs_bmap_finish(&tp, &flist, &committed);
 		if (error)
-			goto error_exit;
-		xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
+			goto error_cancel;
+		error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
+		if (error)
+			goto error;
 		/*
 		 * Now we need to clear the allocated blocks.
 		 * Do this one block per transaction, to keep it simple.
@@ -165,13 +168,13 @@ xfs_growfs_rt_alloc(
 			 */
 			if ((error = xfs_trans_reserve(tp, 0,
 					XFS_GROWRTZERO_LOG_RES(mp), 0, 0, 0)))
-				goto error_exit;
+				goto error_cancel;
 			/*
 			 * Lock the bitmap inode.
 			 */
 			if ((error = xfs_trans_iget(mp, tp, ino, 0,
 							XFS_ILOCK_EXCL, &ip)))
-				goto error_exit;
+				goto error_cancel;
 			/*
 			 * Get a buffer for the block.
 			 */
@@ -180,14 +183,16 @@ xfs_growfs_rt_alloc(
 				mp->m_bsize, 0);
 			if (bp == NULL) {
 				error = XFS_ERROR(EIO);
-				goto error_exit;
+				goto error_cancel;
 			}
 			memset(XFS_BUF_PTR(bp), 0, mp->m_sb.sb_blocksize);
 			xfs_trans_log_buf(tp, bp, 0, mp->m_sb.sb_blocksize - 1);
 			/*
 			 * Commit the transaction.
 			 */
-			xfs_trans_commit(tp, 0);
+			error = xfs_trans_commit(tp, 0);
+			if (error)
+				goto error;
 		}
 		/*
 		 * Go on to the next extent, if any.
@@ -195,8 +200,9 @@ xfs_growfs_rt_alloc(
 		oblocks = map.br_startoff + map.br_blockcount;
 	}
 	return 0;
-error_exit:
+error_cancel:
 	xfs_trans_cancel(tp, cancelflags);
+error:
 	return error;
 }
 
@@ -1875,6 +1881,7 @@ xfs_growfs_rt(
 	xfs_trans_t	*tp;		/* transaction pointer */
 
 	sbp = &mp->m_sb;
+	cancelflags = 0;
 	/*
 	 * Initial error checking.
 	 */
@@ -2041,13 +2048,15 @@ xfs_growfs_rt(
 		 */
 		mp->m_rsumlevels = nrsumlevels;
 		mp->m_rsumsize = nrsumsize;
-		/*
-		 * Commit the transaction.
-		 */
-		xfs_trans_commit(tp, 0);
+
+		error = xfs_trans_commit(tp, 0);
+		if (error) {
+			tp = NULL;
+			break;
+		}
 	}
 
-	if (error)
+	if (error && tp)
 		xfs_trans_cancel(tp, cancelflags);
 
 	/*
@@ -2278,7 +2287,7 @@ xfs_rtmount_inodes(
 	ASSERT(sbp->sb_rsumino != NULLFSINO);
 	error = xfs_iget(mp, NULL, sbp->sb_rsumino, 0, 0, &mp->m_rsumip, 0);
 	if (error) {
-		VN_RELE(XFS_ITOV(mp->m_rbmip));
+		IRELE(mp->m_rbmip);
 		return error;
 	}
 	ASSERT(mp->m_rsumip != NULL);

fs/xfs/xfs_rw.c

@@ -126,11 +126,11 @@ xfs_write_sync_logforce(
 		 * when we return.
 		 */
 		if (iip && iip->ili_last_lsn) {
-			xfs_log_force(mp, iip->ili_last_lsn,
-					XFS_LOG_FORCE | XFS_LOG_SYNC);
+			error = _xfs_log_force(mp, iip->ili_last_lsn,
+					XFS_LOG_FORCE | XFS_LOG_SYNC, NULL);
 		} else if (xfs_ipincount(ip) > 0) {
-			xfs_log_force(mp, (xfs_lsn_t)0,
-					XFS_LOG_FORCE | XFS_LOG_SYNC);
+			error = _xfs_log_force(mp, (xfs_lsn_t)0,
+					XFS_LOG_FORCE | XFS_LOG_SYNC, NULL);
 		}
 
 	} else {

fs/xfs/xfs_trans.h

@@ -113,13 +113,8 @@ struct xfs_mount;
 struct xfs_trans;
 struct xfs_dquot_acct;
 
-typedef struct xfs_ail_entry {
-	struct xfs_log_item	*ail_forw;	/* AIL forw pointer */
-	struct xfs_log_item	*ail_back;	/* AIL back pointer */
-} xfs_ail_entry_t;
-
 typedef struct xfs_log_item {
-	xfs_ail_entry_t			li_ail;		/* AIL pointers */
+	struct list_head		li_ail;		/* AIL pointers */
 	xfs_lsn_t			li_lsn;		/* last on-disk lsn */
 	struct xfs_log_item_desc	*li_desc;	/* ptr to current desc*/
 	struct xfs_mount		*li_mountp;	/* ptr to fs mount */
@@ -341,7 +336,6 @@ typedef struct xfs_trans {
 	unsigned int		t_rtx_res;	/* # of rt extents resvd */
 	unsigned int		t_rtx_res_used;	/* # of resvd rt extents used */
 	xfs_log_ticket_t	t_ticket;	/* log mgr ticket */
-	sema_t			t_sema;		/* sema for commit completion */
 	xfs_lsn_t		t_lsn;		/* log seq num of start of
 						 * transaction. */
 	xfs_lsn_t		t_commit_lsn;	/* log seq num of end of

fs/xfs/xfs_trans_ail.c

@@ -28,13 +28,13 @@
 #include "xfs_trans_priv.h"
 #include "xfs_error.h"
 
-STATIC void xfs_ail_insert(xfs_ail_entry_t *, xfs_log_item_t *);
-STATIC xfs_log_item_t * xfs_ail_delete(xfs_ail_entry_t *, xfs_log_item_t *);
-STATIC xfs_log_item_t * xfs_ail_min(xfs_ail_entry_t *);
-STATIC xfs_log_item_t * xfs_ail_next(xfs_ail_entry_t *, xfs_log_item_t *);
+STATIC void xfs_ail_insert(xfs_ail_t *, xfs_log_item_t *);
+STATIC xfs_log_item_t * xfs_ail_delete(xfs_ail_t *, xfs_log_item_t *);
+STATIC xfs_log_item_t * xfs_ail_min(xfs_ail_t *);
+STATIC xfs_log_item_t * xfs_ail_next(xfs_ail_t *, xfs_log_item_t *);
 
 #ifdef DEBUG
-STATIC void xfs_ail_check(xfs_ail_entry_t *, xfs_log_item_t *);
+STATIC void xfs_ail_check(xfs_ail_t *, xfs_log_item_t *);
 #else
 #define	xfs_ail_check(a,l)
 #endif /* DEBUG */
@@ -57,7 +57,7 @@ xfs_trans_tail_ail(
 	xfs_log_item_t	*lip;
 
 	spin_lock(&mp->m_ail_lock);
-	lip = xfs_ail_min(&(mp->m_ail.xa_ail));
+	lip = xfs_ail_min(&mp->m_ail);
 	if (lip == NULL) {
 		lsn = (xfs_lsn_t)0;
 	} else {
@@ -91,7 +91,7 @@ xfs_trans_push_ail(
 {
 	xfs_log_item_t		*lip;
 
-	lip = xfs_ail_min(&mp->m_ail.xa_ail);
+	lip = xfs_ail_min(&mp->m_ail);
 	if (lip && !XFS_FORCED_SHUTDOWN(mp)) {
 		if (XFS_LSN_CMP(threshold_lsn, mp->m_ail.xa_target) > 0)
 			xfsaild_wakeup(mp, threshold_lsn);
@@ -111,15 +111,17 @@ xfs_trans_first_push_ail(
 {
 	xfs_log_item_t	*lip;
 
-	lip = xfs_ail_min(&(mp->m_ail.xa_ail));
+	lip = xfs_ail_min(&mp->m_ail);
 	*gen = (int)mp->m_ail.xa_gen;
 	if (lsn == 0)
 		return lip;
 
-	while (lip && (XFS_LSN_CMP(lip->li_lsn, lsn) < 0))
-		lip = lip->li_ail.ail_forw;
+	list_for_each_entry(lip, &mp->m_ail.xa_ail, li_ail) {
+		if (XFS_LSN_CMP(lip->li_lsn, lsn) >= 0)
+			return lip;
+	}
 
-	return lip;
+	return NULL;
 }
 
 /*
@@ -329,7 +331,7 @@ xfs_trans_unlocked_item(
 	 * the call to xfs_log_move_tail() doesn't do anything if there's
 	 * not enough free space to wake people up so we're safe calling it.
 	 */
-	min_lip = xfs_ail_min(&mp->m_ail.xa_ail);
+	min_lip = xfs_ail_min(&mp->m_ail);
 
 	if (min_lip == lip)
 		xfs_log_move_tail(mp, 1);
@@ -357,15 +359,13 @@ xfs_trans_update_ail(
 	xfs_log_item_t	*lip,
 	xfs_lsn_t	lsn) __releases(mp->m_ail_lock)
 {
-	xfs_ail_entry_t		*ailp;
 	xfs_log_item_t		*dlip=NULL;
 	xfs_log_item_t		*mlip;	/* ptr to minimum lip */
 
-	ailp = &(mp->m_ail.xa_ail);
-	mlip = xfs_ail_min(ailp);
+	mlip = xfs_ail_min(&mp->m_ail);
 
 	if (lip->li_flags & XFS_LI_IN_AIL) {
-		dlip = xfs_ail_delete(ailp, lip);
+		dlip = xfs_ail_delete(&mp->m_ail, lip);
 		ASSERT(dlip == lip);
 	} else {
 		lip->li_flags |= XFS_LI_IN_AIL;
@@ -373,11 +373,11 @@ xfs_trans_update_ail(
 
 	lip->li_lsn = lsn;
 
-	xfs_ail_insert(ailp, lip);
+	xfs_ail_insert(&mp->m_ail, lip);
 	mp->m_ail.xa_gen++;
 
 	if (mlip == dlip) {
-		mlip = xfs_ail_min(&(mp->m_ail.xa_ail));
+		mlip = xfs_ail_min(&mp->m_ail);
 		spin_unlock(&mp->m_ail_lock);
 		xfs_log_move_tail(mp, mlip->li_lsn);
 	} else {
@@ -407,14 +407,12 @@ xfs_trans_delete_ail(
 	xfs_mount_t	*mp,
 	xfs_log_item_t	*lip) __releases(mp->m_ail_lock)
 {
-	xfs_ail_entry_t		*ailp;
 	xfs_log_item_t		*dlip;
 	xfs_log_item_t		*mlip;
 
 	if (lip->li_flags & XFS_LI_IN_AIL) {
-		ailp = &(mp->m_ail.xa_ail);
-		mlip = xfs_ail_min(ailp);
-		dlip = xfs_ail_delete(ailp, lip);
+		mlip = xfs_ail_min(&mp->m_ail);
+		dlip = xfs_ail_delete(&mp->m_ail, lip);
 		ASSERT(dlip == lip);
 
 
@@ -423,7 +421,7 @@ xfs_trans_delete_ail(
 		mp->m_ail.xa_gen++;
 
 		if (mlip == dlip) {
-			mlip = xfs_ail_min(&(mp->m_ail.xa_ail));
+			mlip = xfs_ail_min(&mp->m_ail);
 			spin_unlock(&mp->m_ail_lock);
 			xfs_log_move_tail(mp, (mlip ? mlip->li_lsn : 0));
 		} else {
@@ -440,7 +438,7 @@ xfs_trans_delete_ail(
 		else {
 			xfs_cmn_err(XFS_PTAG_AILDELETE, CE_ALERT, mp,
 		"%s: attempting to delete a log item that is not in the AIL",
-					__FUNCTION__);
+					__func__);
 			spin_unlock(&mp->m_ail_lock);
 			xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
 		}
@@ -461,7 +459,7 @@ xfs_trans_first_ail(
 {
 	xfs_log_item_t	*lip;
 
-	lip = xfs_ail_min(&(mp->m_ail.xa_ail));
+	lip = xfs_ail_min(&mp->m_ail);
 	*gen = (int)mp->m_ail.xa_gen;
 
 	return lip;
@@ -485,9 +483,9 @@ xfs_trans_next_ail(
 
 	ASSERT(mp && lip && gen);
 	if (mp->m_ail.xa_gen == *gen) {
-		nlip = xfs_ail_next(&(mp->m_ail.xa_ail), lip);
+		nlip = xfs_ail_next(&mp->m_ail, lip);
 	} else {
-		nlip = xfs_ail_min(&(mp->m_ail).xa_ail);
+		nlip = xfs_ail_min(&mp->m_ail);
 		*gen = (int)mp->m_ail.xa_gen;
 		if (restarts != NULL) {
 			XFS_STATS_INC(xs_push_ail_restarts);
@@ -517,8 +515,7 @@ int
 xfs_trans_ail_init(
 	xfs_mount_t	*mp)
 {
-	mp->m_ail.xa_ail.ail_forw = (xfs_log_item_t*)&mp->m_ail.xa_ail;
-	mp->m_ail.xa_ail.ail_back = (xfs_log_item_t*)&mp->m_ail.xa_ail;
+	INIT_LIST_HEAD(&mp->m_ail.xa_ail);
 	return xfsaild_start(mp);
 }
 
@@ -537,7 +534,7 @@ xfs_trans_ail_destroy(
  */
 STATIC void
 xfs_ail_insert(
-	xfs_ail_entry_t	*base,
+	xfs_ail_t	*ailp,
 	xfs_log_item_t	*lip)
 /* ARGSUSED */
 {
@@ -546,27 +543,22 @@ xfs_ail_insert(
 	/*
 	 * If the list is empty, just insert the item.
 	 */
-	if (base->ail_back == (xfs_log_item_t*)base) {
-		base->ail_forw = lip;
-		base->ail_back = lip;
-		lip->li_ail.ail_forw = (xfs_log_item_t*)base;
-		lip->li_ail.ail_back = (xfs_log_item_t*)base;
+	if (list_empty(&ailp->xa_ail)) {
+		list_add(&lip->li_ail, &ailp->xa_ail);
 		return;
 	}
 
-	next_lip = base->ail_back;
-	while ((next_lip != (xfs_log_item_t*)base) &&
-	       (XFS_LSN_CMP(next_lip->li_lsn, lip->li_lsn) > 0)) {
-		next_lip = next_lip->li_ail.ail_back;
+	list_for_each_entry_reverse(next_lip, &ailp->xa_ail, li_ail) {
+		if (XFS_LSN_CMP(next_lip->li_lsn, lip->li_lsn) <= 0)
+			break;
 	}
-	ASSERT((next_lip == (xfs_log_item_t*)base) ||
+
+	ASSERT((&next_lip->li_ail == &ailp->xa_ail) ||
 	       (XFS_LSN_CMP(next_lip->li_lsn, lip->li_lsn) <= 0));
-	lip->li_ail.ail_forw = next_lip->li_ail.ail_forw;
-	lip->li_ail.ail_back = next_lip;
-	next_lip->li_ail.ail_forw = lip;
-	lip->li_ail.ail_forw->li_ail.ail_back = lip;
 
-	xfs_ail_check(base, lip);
+	list_add(&lip->li_ail, &next_lip->li_ail);
+
+	xfs_ail_check(ailp, lip);
 	return;
 }
 
@@ -576,15 +568,13 @@ xfs_ail_insert(
 /*ARGSUSED*/
 STATIC xfs_log_item_t *
 xfs_ail_delete(
-	xfs_ail_entry_t	*base,
+	xfs_ail_t	*ailp,
 	xfs_log_item_t	*lip)
 /* ARGSUSED */
 {
-	xfs_ail_check(base, lip);
-	lip->li_ail.ail_forw->li_ail.ail_back = lip->li_ail.ail_back;
-	lip->li_ail.ail_back->li_ail.ail_forw = lip->li_ail.ail_forw;
-	lip->li_ail.ail_forw = NULL;
-	lip->li_ail.ail_back = NULL;
+	xfs_ail_check(ailp, lip);
+
+	list_del(&lip->li_ail);
 
 	return lip;
 }
@@ -595,14 +585,13 @@ xfs_ail_delete(
  */
 STATIC xfs_log_item_t *
 xfs_ail_min(
-	xfs_ail_entry_t	*base)
+	xfs_ail_t	*ailp)
 /* ARGSUSED */
 {
-	register xfs_log_item_t *forw = base->ail_forw;
-	if (forw == (xfs_log_item_t*)base) {
+	if (list_empty(&ailp->xa_ail))
 		return NULL;
-	}
-	return forw;
+
+	return list_first_entry(&ailp->xa_ail, xfs_log_item_t, li_ail);
 }
 
 /*
@@ -612,15 +601,14 @@ xfs_ail_min(
  */
 STATIC xfs_log_item_t *
 xfs_ail_next(
-	xfs_ail_entry_t	*base,
+	xfs_ail_t	*ailp,
 	xfs_log_item_t	*lip)
 /* ARGSUSED */
 {
-	if (lip->li_ail.ail_forw == (xfs_log_item_t*)base) {
+	if (lip->li_ail.next == &ailp->xa_ail)
 		return NULL;
-	}
-	return lip->li_ail.ail_forw;
 
+	return list_first_entry(&lip->li_ail, xfs_log_item_t, li_ail);
 }
 
 #ifdef DEBUG
@@ -629,57 +617,40 @@ xfs_ail_next(
  */
 STATIC void
 xfs_ail_check(
-	xfs_ail_entry_t *base,
+	xfs_ail_t 	*ailp,
 	xfs_log_item_t	*lip)
 {
 	xfs_log_item_t	*prev_lip;
 
-	prev_lip = base->ail_forw;
-	if (prev_lip == (xfs_log_item_t*)base) {
-		/*
-		 * Make sure the pointers are correct when the list
-		 * is empty.
-		 */
-		ASSERT(base->ail_back == (xfs_log_item_t*)base);
+	if (list_empty(&ailp->xa_ail))
 		return;
-	}
 
 	/*
 	 * Check the next and previous entries are valid.
 	 */
 	ASSERT((lip->li_flags & XFS_LI_IN_AIL) != 0);
-	prev_lip = lip->li_ail.ail_back;
-	if (prev_lip != (xfs_log_item_t*)base) {
-		ASSERT(prev_lip->li_ail.ail_forw == lip);
+	prev_lip = list_entry(lip->li_ail.prev, xfs_log_item_t, li_ail);
+	if (&prev_lip->li_ail != &ailp->xa_ail)
 		ASSERT(XFS_LSN_CMP(prev_lip->li_lsn, lip->li_lsn) <= 0);
-	}
-	prev_lip = lip->li_ail.ail_forw;
-	if (prev_lip != (xfs_log_item_t*)base) {
-		ASSERT(prev_lip->li_ail.ail_back == lip);
+
+	prev_lip = list_entry(lip->li_ail.next, xfs_log_item_t, li_ail);
+	if (&prev_lip->li_ail != &ailp->xa_ail)
 		ASSERT(XFS_LSN_CMP(prev_lip->li_lsn, lip->li_lsn) >= 0);
-	}
 
 
 #ifdef XFS_TRANS_DEBUG
 	/*
-	 * Walk the list checking forward and backward pointers,
-	 * lsn ordering, and that every entry has the XFS_LI_IN_AIL
-	 * flag set. This is really expensive, so only do it when
-	 * specifically debugging the transaction subsystem.
+	 * Walk the list checking lsn ordering, and that every entry has the
+	 * XFS_LI_IN_AIL flag set. This is really expensive, so only do it
+	 * when specifically debugging the transaction subsystem.
 	 */
-	prev_lip = (xfs_log_item_t*)base;
-	while (lip != (xfs_log_item_t*)base) {
-		if (prev_lip != (xfs_log_item_t*)base) {
-			ASSERT(prev_lip->li_ail.ail_forw == lip);
+	prev_lip = list_entry(&ailp->xa_ail, xfs_log_item_t, li_ail);
+	list_for_each_entry(lip, &ailp->xa_ail, li_ail) {
+		if (&prev_lip->li_ail != &ailp->xa_ail)
 			ASSERT(XFS_LSN_CMP(prev_lip->li_lsn, lip->li_lsn) <= 0);
-		}
-		ASSERT(lip->li_ail.ail_back == prev_lip);
 		ASSERT((lip->li_flags & XFS_LI_IN_AIL) != 0);
 		prev_lip = lip;
-		lip = lip->li_ail.ail_forw;
 	}
-	ASSERT(lip == (xfs_log_item_t*)base);
-	ASSERT(base->ail_back == prev_lip);
 #endif /* XFS_TRANS_DEBUG */
 }
 #endif /* DEBUG */

fs/xfs/xfs_trans_buf.c

@@ -304,7 +304,8 @@ xfs_trans_read_buf(
 	if (tp == NULL) {
 		bp = xfs_buf_read_flags(target, blkno, len, flags | BUF_BUSY);
 		if (!bp)
-			return XFS_ERROR(ENOMEM);
+			return (flags & XFS_BUF_TRYLOCK) ?
+					EAGAIN : XFS_ERROR(ENOMEM);
 
 		if ((bp != NULL) && (XFS_BUF_GETERROR(bp) != 0)) {
 			xfs_ioerror_alert("xfs_trans_read_buf", mp,
@@ -353,17 +354,15 @@ xfs_trans_read_buf(
 			ASSERT(!XFS_BUF_ISASYNC(bp));
 			XFS_BUF_READ(bp);
 			xfsbdstrat(tp->t_mountp, bp);
-			xfs_iowait(bp);
-			if (XFS_BUF_GETERROR(bp) != 0) {
+			error = xfs_iowait(bp);
+			if (error) {
 				xfs_ioerror_alert("xfs_trans_read_buf", mp,
 						  bp, blkno);
-				error = XFS_BUF_GETERROR(bp);
 				xfs_buf_relse(bp);
 				/*
-				 * We can gracefully recover from most
-				 * read errors. Ones we can't are those
-				 * that happen after the transaction's
-				 * already dirty.
+				 * We can gracefully recover from most read
+				 * errors. Ones we can't are those that happen
+				 * after the transaction's already dirty.
 				 */
 				if (tp->t_flags & XFS_TRANS_DIRTY)
 					xfs_force_shutdown(tp->t_mountp,

fs/xfs/xfs_types.h

@@ -160,4 +160,9 @@ typedef enum {
 	XFS_BTNUM_MAX
 } xfs_btnum_t;
 
+struct xfs_name {
+	const char	*name;
+	int		len;
+};
+
 #endif	/* __XFS_TYPES_H__ */

fs/xfs/xfs_utils.c

@@ -40,34 +40,12 @@
 #include "xfs_itable.h"
 #include "xfs_utils.h"
 
-/*
- * xfs_get_dir_entry is used to get a reference to an inode given
- * its parent directory inode and the name of the file.	 It does
- * not lock the child inode, and it unlocks the directory before
- * returning.  The directory's generation number is returned for
- * use by a later call to xfs_lock_dir_and_entry.
- */
-int
-xfs_get_dir_entry(
-	bhv_vname_t	*dentry,
-	xfs_inode_t	**ipp)
-{
-	bhv_vnode_t	*vp;
-
-	vp = VNAME_TO_VNODE(dentry);
-
-	*ipp = xfs_vtoi(vp);
-	if (!*ipp)
-		return XFS_ERROR(ENOENT);
-	VN_HOLD(vp);
-	return 0;
-}
 
 int
 xfs_dir_lookup_int(
 	xfs_inode_t	*dp,
 	uint		lock_mode,
-	bhv_vname_t	*dentry,
+	struct xfs_name	*name,
 	xfs_ino_t	*inum,
 	xfs_inode_t	**ipp)
 {
@@ -75,7 +53,7 @@ xfs_dir_lookup_int(
 
 	xfs_itrace_entry(dp);
 
-	error = xfs_dir_lookup(NULL, dp, VNAME(dentry), VNAMELEN(dentry), inum);
+	error = xfs_dir_lookup(NULL, dp, name, inum);
 	if (!error) {
 		/*
 		 * Unlock the directory. We do this because we can't

fs/xfs/xfs_utils.h

@@ -21,15 +21,14 @@
 #define IRELE(ip)	VN_RELE(XFS_ITOV(ip))
 #define IHOLD(ip)	VN_HOLD(XFS_ITOV(ip))
 
-extern int xfs_get_dir_entry (bhv_vname_t *, xfs_inode_t **);
-extern int xfs_dir_lookup_int (xfs_inode_t *, uint, bhv_vname_t *, xfs_ino_t *,
-				xfs_inode_t **);
-extern int xfs_truncate_file (xfs_mount_t *, xfs_inode_t *);
-extern int xfs_dir_ialloc (xfs_trans_t **, xfs_inode_t *, mode_t, xfs_nlink_t,
+extern int xfs_dir_lookup_int(xfs_inode_t *, uint, struct xfs_name *,
+				xfs_ino_t *, xfs_inode_t **);
+extern int xfs_truncate_file(xfs_mount_t *, xfs_inode_t *);
+extern int xfs_dir_ialloc(xfs_trans_t **, xfs_inode_t *, mode_t, xfs_nlink_t,
 				xfs_dev_t, cred_t *, prid_t, int,
 				xfs_inode_t **, int *);
-extern int xfs_droplink (xfs_trans_t *, xfs_inode_t *);
-extern int xfs_bumplink (xfs_trans_t *, xfs_inode_t *);
-extern void xfs_bump_ino_vers2 (xfs_trans_t *, xfs_inode_t *);
+extern int xfs_droplink(xfs_trans_t *, xfs_inode_t *);
+extern int xfs_bumplink(xfs_trans_t *, xfs_inode_t *);
+extern void xfs_bump_ino_vers2(xfs_trans_t *, xfs_inode_t *);
 
 #endif	/* __XFS_UTILS_H__ */

fs/xfs/xfs_vfsops.c

@@ -43,7 +43,6 @@
 #include "xfs_error.h"
 #include "xfs_bmap.h"
 #include "xfs_rw.h"
-#include "xfs_refcache.h"
 #include "xfs_buf_item.h"
 #include "xfs_log_priv.h"
 #include "xfs_dir2_trace.h"
@@ -56,6 +55,7 @@
 #include "xfs_fsops.h"
 #include "xfs_vnodeops.h"
 #include "xfs_vfsops.h"
+#include "xfs_utils.h"
 
 
 int __init
@@ -69,15 +69,17 @@ xfs_init(void)
 	/*
 	 * Initialize all of the zone allocators we use.
 	 */
+	xfs_log_ticket_zone = kmem_zone_init(sizeof(xlog_ticket_t),
+						"xfs_log_ticket");
 	xfs_bmap_free_item_zone = kmem_zone_init(sizeof(xfs_bmap_free_item_t),
-						 "xfs_bmap_free_item");
+						"xfs_bmap_free_item");
 	xfs_btree_cur_zone = kmem_zone_init(sizeof(xfs_btree_cur_t),
-					    "xfs_btree_cur");
-	xfs_trans_zone = kmem_zone_init(sizeof(xfs_trans_t), "xfs_trans");
-	xfs_da_state_zone =
-		kmem_zone_init(sizeof(xfs_da_state_t), "xfs_da_state");
+						"xfs_btree_cur");
+	xfs_da_state_zone = kmem_zone_init(sizeof(xfs_da_state_t),
+						"xfs_da_state");
 	xfs_dabuf_zone = kmem_zone_init(sizeof(xfs_dabuf_t), "xfs_dabuf");
 	xfs_ifork_zone = kmem_zone_init(sizeof(xfs_ifork_t), "xfs_ifork");
+	xfs_trans_zone = kmem_zone_init(sizeof(xfs_trans_t), "xfs_trans");
 	xfs_acl_zone_init(xfs_acl_zone, "xfs_acl");
 	xfs_mru_cache_init();
 	xfs_filestream_init();
@@ -113,9 +115,6 @@ xfs_init(void)
 	xfs_ili_zone =
 		kmem_zone_init_flags(sizeof(xfs_inode_log_item_t), "xfs_ili",
 					KM_ZONE_SPREAD, NULL);
-	xfs_icluster_zone =
-		kmem_zone_init_flags(sizeof(xfs_icluster_t), "xfs_icluster",
-					KM_ZONE_SPREAD, NULL);
 
 	/*
 	 * Allocate global trace buffers.
@@ -153,11 +152,9 @@ xfs_cleanup(void)
 	extern kmem_zone_t	*xfs_inode_zone;
 	extern kmem_zone_t	*xfs_efd_zone;
 	extern kmem_zone_t	*xfs_efi_zone;
-	extern kmem_zone_t	*xfs_icluster_zone;
 
 	xfs_cleanup_procfs();
 	xfs_sysctl_unregister();
-	xfs_refcache_destroy();
 	xfs_filestream_uninit();
 	xfs_mru_cache_uninit();
 	xfs_acl_zone_destroy(xfs_acl_zone);
@@ -189,7 +186,6 @@ xfs_cleanup(void)
 	kmem_zone_destroy(xfs_efi_zone);
 	kmem_zone_destroy(xfs_ifork_zone);
 	kmem_zone_destroy(xfs_ili_zone);
-	kmem_zone_destroy(xfs_icluster_zone);
 }
 
 /*
@@ -573,7 +569,7 @@ xfs_unmount(
 #ifdef HAVE_DMAPI
 	if (mp->m_flags & XFS_MOUNT_DMAPI) {
 		error = XFS_SEND_PREUNMOUNT(mp,
-				rvp, DM_RIGHT_NULL, rvp, DM_RIGHT_NULL,
+				rip, DM_RIGHT_NULL, rip, DM_RIGHT_NULL,
 				NULL, NULL, 0, 0,
 				(mp->m_dmevmask & (1<<DM_EVENT_PREUNMOUNT))?
 					0:DM_FLAGS_UNWANTED);
@@ -584,11 +580,6 @@ xfs_unmount(
 					0 : DM_FLAGS_UNWANTED;
 	}
 #endif
-	/*
-	 * First blow any referenced inode from this file system
-	 * out of the reference cache, and delete the timer.
-	 */
-	xfs_refcache_purge_mp(mp);
 
 	/*
 	 * Blow away any referenced inode in the filestreams cache.
@@ -607,7 +598,7 @@ xfs_unmount(
 	/*
 	 * Drop the reference count
 	 */
-	VN_RELE(rvp);
+	IRELE(rip);
 
 	/*
 	 * If we're forcing a shutdown, typically because of a media error,
@@ -629,7 +620,7 @@ out:
 		/* Note: mp structure must still exist for
 		 * XFS_SEND_UNMOUNT() call.
 		 */
-		XFS_SEND_UNMOUNT(mp, error == 0 ? rvp : NULL,
+		XFS_SEND_UNMOUNT(mp, error == 0 ? rip : NULL,
 			DM_RIGHT_NULL, 0, error, unmount_event_flags);
 	}
 	if (xfs_unmountfs_needed) {
@@ -646,13 +637,12 @@ out:
 	return XFS_ERROR(error);
 }
 
-STATIC int
+STATIC void
 xfs_quiesce_fs(
 	xfs_mount_t		*mp)
 {
 	int			count = 0, pincount;
 
-	xfs_refcache_purge_mp(mp);
 	xfs_flush_buftarg(mp->m_ddev_targp, 0);
 	xfs_finish_reclaim_all(mp, 0);
 
@@ -671,8 +661,6 @@ xfs_quiesce_fs(
 			count++;
 		}
 	} while (count < 2);
-
-	return 0;
 }
 
 /*
@@ -684,6 +672,8 @@ void
 xfs_attr_quiesce(
 	xfs_mount_t	*mp)
 {
+	int	error = 0;
+
 	/* wait for all modifications to complete */
 	while (atomic_read(&mp->m_active_trans) > 0)
 		delay(100);
@@ -694,7 +684,11 @@ xfs_attr_quiesce(
 	ASSERT_ALWAYS(atomic_read(&mp->m_active_trans) == 0);
 
 	/* Push the superblock and write an unmount record */
-	xfs_log_sbcount(mp, 1);
+	error = xfs_log_sbcount(mp, 1);
+	if (error)
+		xfs_fs_cmn_err(CE_WARN, mp,
+				"xfs_attr_quiesce: failed to log sb changes. "
+				"Frozen image may not be consistent.");
 	xfs_log_unmount_write(mp);
 	xfs_unmountfs_writesb(mp);
 }
@@ -790,8 +784,8 @@ xfs_unmount_flush(
 		goto fscorrupt_out2;
 
 	if (rbmip) {
-		VN_RELE(XFS_ITOV(rbmip));
-		VN_RELE(XFS_ITOV(rsumip));
+		IRELE(rbmip);
+		IRELE(rsumip);
 	}
 
 	xfs_iunlock(rip, XFS_ILOCK_EXCL);
@@ -1169,10 +1163,10 @@ xfs_sync_inodes(
 			 * above, then wait until after we've unlocked
 			 * the inode to release the reference.  This is
 			 * because we can be already holding the inode
-			 * lock when VN_RELE() calls xfs_inactive().
+			 * lock when IRELE() calls xfs_inactive().
 			 *
 			 * Make sure to drop the mount lock before calling
-			 * VN_RELE() so that we don't trip over ourselves if
+			 * IRELE() so that we don't trip over ourselves if
 			 * we have to go for the mount lock again in the
 			 * inactive code.
 			 */
@@ -1180,7 +1174,7 @@ xfs_sync_inodes(
 				IPOINTER_INSERT(ip, mp);
 			}
 
-			VN_RELE(vp);
+			IRELE(ip);
 
 			vnode_refed = B_FALSE;
 		}
@@ -1322,31 +1316,9 @@ xfs_syncsub(
 		}
 	}
 
-	/*
-	 * If this is the periodic sync, then kick some entries out of
-	 * the reference cache.  This ensures that idle entries are
-	 * eventually kicked out of the cache.
-	 */
-	if (flags & SYNC_REFCACHE) {
-		if (flags & SYNC_WAIT)
-			xfs_refcache_purge_mp(mp);
-		else
-			xfs_refcache_purge_some(mp);
-	}
-
-	/*
-	 * If asked, update the disk superblock with incore counter values if we
-	 * are using non-persistent counters so that they don't get too far out
-	 * of sync if we crash or get a forced shutdown. We don't want to force
-	 * this to disk, just get a transaction into the iclogs....
-	 */
-	if (flags & SYNC_SUPER)
-		xfs_log_sbcount(mp, 0);
-
 	/*
 	 * Now check to see if the log needs a "dummy" transaction.
 	 */
-
 	if (!(flags & SYNC_REMOUNT) && xfs_log_need_covered(mp)) {
 		xfs_trans_t *tp;
 		xfs_inode_t *ip;

fs/xfs/xfs_vnodeops.c

@@ -48,7 +48,6 @@
 #include "xfs_quota.h"
 #include "xfs_utils.h"
 #include "xfs_rtalloc.h"
-#include "xfs_refcache.h"
 #include "xfs_trans_space.h"
 #include "xfs_log_priv.h"
 #include "xfs_filestream.h"
@@ -327,7 +326,7 @@ xfs_setattr(
 		if (DM_EVENT_ENABLED(ip, DM_EVENT_TRUNCATE) &&
 		    !(flags & ATTR_DMI)) {
 			int dmflags = AT_DELAY_FLAG(flags) | DM_SEM_FLAG_WR;
-			code = XFS_SEND_DATA(mp, DM_EVENT_TRUNCATE, vp,
+			code = XFS_SEND_DATA(mp, DM_EVENT_TRUNCATE, ip,
 				vap->va_size, 0, dmflags, NULL);
 			if (code) {
 				lock_flags = 0;
@@ -634,6 +633,15 @@ xfs_setattr(
 	 * Truncate file.  Must have write permission and not be a directory.
 	 */
 	if (mask & XFS_AT_SIZE) {
+		/*
+		 * Only change the c/mtime if we are changing the size
+		 * or we are explicitly asked to change it. This handles
+		 * the semantic difference between truncate() and ftruncate()
+		 * as implemented in the VFS.
+		 */
+		if (vap->va_size != ip->i_size || (mask & XFS_AT_CTIME))
+			timeflags |= XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG;
+
 		if (vap->va_size > ip->i_size) {
 			xfs_igrow_finish(tp, ip, vap->va_size,
 			    !(flags & ATTR_DMI));
@@ -662,10 +670,6 @@ xfs_setattr(
 			 */
 			xfs_iflags_set(ip, XFS_ITRUNCATED);
 		}
-		/*
-		 * Have to do this even if the file's size doesn't change.
-		 */
-		timeflags |= XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG;
 	}
 
 	/*
@@ -877,7 +881,7 @@ xfs_setattr(
 
 	if (DM_EVENT_ENABLED(ip, DM_EVENT_ATTRIBUTE) &&
 	    !(flags & ATTR_DMI)) {
-		(void) XFS_SEND_NAMESP(mp, DM_EVENT_ATTRIBUTE, vp, DM_RIGHT_NULL,
+		(void) XFS_SEND_NAMESP(mp, DM_EVENT_ATTRIBUTE, ip, DM_RIGHT_NULL,
 					NULL, DM_RIGHT_NULL, NULL, NULL,
 					0, 0, AT_DELAY_FLAG(flags));
 	}
@@ -1443,28 +1447,22 @@ xfs_inactive_attrs(
 	tp = *tpp;
 	mp = ip->i_mount;
 	ASSERT(ip->i_d.di_forkoff != 0);
-	xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
+	error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	if (error)
+		goto error_unlock;
 
 	error = xfs_attr_inactive(ip);
-	if (error) {
-		*tpp = NULL;
-		xfs_iunlock(ip, XFS_IOLOCK_EXCL);
-		return error; /* goto out */
-	}
+	if (error)
+		goto error_unlock;
 
 	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) {
-		ASSERT(XFS_FORCED_SHUTDOWN(mp));
-		xfs_trans_cancel(tp, 0);
-		*tpp = NULL;
-		xfs_iunlock(ip, XFS_IOLOCK_EXCL);
-		return error;
-	}
+	if (error)
+		goto error_cancel;
 
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	xfs_trans_ijoin(tp, ip, XFS_IOLOCK_EXCL | XFS_ILOCK_EXCL);
@@ -1475,6 +1473,14 @@ xfs_inactive_attrs(
 
 	*tpp = tp;
 	return 0;
+
+error_cancel:
+	ASSERT(XFS_FORCED_SHUTDOWN(mp));
+	xfs_trans_cancel(tp, 0);
+error_unlock:
+	*tpp = NULL;
+	xfs_iunlock(ip, XFS_IOLOCK_EXCL);
+	return error;
 }
 
 int
@@ -1520,12 +1526,6 @@ xfs_release(
 			xfs_flush_pages(ip, 0, -1, XFS_B_ASYNC, FI_NONE);
 	}
 
-#ifdef HAVE_REFCACHE
-	/* If we are in the NFS reference cache then don't do this now */
-	if (ip->i_refcache)
-		return 0;
-#endif
-
 	if (ip->i_d.di_nlink != 0) {
 		if ((((ip->i_d.di_mode & S_IFMT) == S_IFREG) &&
 		     ((ip->i_size > 0) || (VN_CACHED(vp) > 0 ||
@@ -1588,9 +1588,8 @@ xfs_inactive(
 
 	mp = ip->i_mount;
 
-	if (ip->i_d.di_nlink == 0 && DM_EVENT_ENABLED(ip, DM_EVENT_DESTROY)) {
-		(void) XFS_SEND_DESTROY(mp, vp, DM_RIGHT_NULL);
-	}
+	if (ip->i_d.di_nlink == 0 && DM_EVENT_ENABLED(ip, DM_EVENT_DESTROY))
+		XFS_SEND_DESTROY(mp, ip, DM_RIGHT_NULL);
 
 	error = 0;
 
@@ -1744,11 +1743,18 @@ xfs_inactive(
 		XFS_TRANS_MOD_DQUOT_BYINO(mp, 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.
+		 * 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.
 		 */
-		(void) xfs_bmap_finish(&tp,  &free_list, &committed);
-		(void) xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
+		error = xfs_bmap_finish(&tp,  &free_list, &committed);
+		if (error)
+			xfs_fs_cmn_err(CE_NOTE, mp, "xfs_inactive: "
+				"xfs_bmap_finish() returned error %d", error);
+		error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
+		if (error)
+			xfs_fs_cmn_err(CE_NOTE, mp, "xfs_inactive: "
+				"xfs_trans_commit() returned error %d", error);
 	}
 	/*
 	 * Release the dquots held by inode, if any.
@@ -1765,8 +1771,8 @@ xfs_inactive(
 int
 xfs_lookup(
 	xfs_inode_t		*dp,
-	bhv_vname_t		*dentry,
-	bhv_vnode_t		**vpp)
+	struct xfs_name		*name,
+	xfs_inode_t		**ipp)
 {
 	xfs_inode_t		*ip;
 	xfs_ino_t		e_inum;
@@ -1779,9 +1785,9 @@ xfs_lookup(
 		return XFS_ERROR(EIO);
 
 	lock_mode = xfs_ilock_map_shared(dp);
-	error = xfs_dir_lookup_int(dp, lock_mode, dentry, &e_inum, &ip);
+	error = xfs_dir_lookup_int(dp, lock_mode, name, &e_inum, &ip);
 	if (!error) {
-		*vpp = XFS_ITOV(ip);
+		*ipp = ip;
 		xfs_itrace_ref(ip);
 	}
 	xfs_iunlock_map_shared(dp, lock_mode);
@@ -1791,19 +1797,16 @@ xfs_lookup(
 int
 xfs_create(
 	xfs_inode_t		*dp,
-	bhv_vname_t		*dentry,
+	struct xfs_name		*name,
 	mode_t			mode,
 	xfs_dev_t		rdev,
-	bhv_vnode_t		**vpp,
+	xfs_inode_t		**ipp,
 	cred_t			*credp)
 {
-	char			*name = VNAME(dentry);
-	xfs_mount_t	        *mp = dp->i_mount;
-	bhv_vnode_t		*dir_vp = XFS_ITOV(dp);
+	xfs_mount_t		*mp = dp->i_mount;
 	xfs_inode_t		*ip;
-	bhv_vnode_t	        *vp = NULL;
 	xfs_trans_t		*tp;
-	int                     error;
+	int			error;
 	xfs_bmap_free_t		free_list;
 	xfs_fsblock_t		first_block;
 	boolean_t		unlock_dp_on_error = B_FALSE;
@@ -1813,17 +1816,14 @@ xfs_create(
 	xfs_prid_t		prid;
 	struct xfs_dquot	*udqp, *gdqp;
 	uint			resblks;
-	int			namelen;
 
-	ASSERT(!*vpp);
+	ASSERT(!*ipp);
 	xfs_itrace_entry(dp);
 
-	namelen = VNAMELEN(dentry);
-
 	if (DM_EVENT_ENABLED(dp, DM_EVENT_CREATE)) {
 		error = XFS_SEND_NAMESP(mp, DM_EVENT_CREATE,
-				dir_vp, DM_RIGHT_NULL, NULL,
-				DM_RIGHT_NULL, name, NULL,
+				dp, DM_RIGHT_NULL, NULL,
+				DM_RIGHT_NULL, name->name, NULL,
 				mode, 0, 0);
 
 		if (error)
@@ -1855,7 +1855,7 @@ xfs_create(
 
 	tp = xfs_trans_alloc(mp, XFS_TRANS_CREATE);
 	cancel_flags = XFS_TRANS_RELEASE_LOG_RES;
-	resblks = XFS_CREATE_SPACE_RES(mp, namelen);
+	resblks = XFS_CREATE_SPACE_RES(mp, name->len);
 	/*
 	 * Initially assume that the file does not exist and
 	 * reserve the resources for that case.  If that is not
@@ -1888,7 +1888,8 @@ xfs_create(
 	if (error)
 		goto error_return;
 
-	if (resblks == 0 && (error = xfs_dir_canenter(tp, dp, name, namelen)))
+	error = xfs_dir_canenter(tp, dp, name, resblks);
+	if (error)
 		goto error_return;
 	error = xfs_dir_ialloc(&tp, dp, mode, 1,
 			rdev, credp, prid, resblks > 0,
@@ -1914,11 +1915,11 @@ xfs_create(
 	 * the transaction cancel unlocking dp so don't do it explicitly in the
 	 * error path.
 	 */
-	VN_HOLD(dir_vp);
+	IHOLD(dp);
 	xfs_trans_ijoin(tp, dp, XFS_ILOCK_EXCL);
 	unlock_dp_on_error = B_FALSE;
 
-	error = xfs_dir_createname(tp, dp, name, namelen, ip->i_ino,
+	error = xfs_dir_createname(tp, dp, name, ip->i_ino,
 					&first_block, &free_list, resblks ?
 					resblks - XFS_IALLOC_SPACE_RES(mp) : 0);
 	if (error) {
@@ -1952,7 +1953,6 @@ xfs_create(
 	 * vnode to the caller, we bump the vnode ref count now.
 	 */
 	IHOLD(ip);
-	vp = XFS_ITOV(ip);
 
 	error = xfs_bmap_finish(&tp, &free_list, &committed);
 	if (error) {
@@ -1970,17 +1970,17 @@ xfs_create(
 	XFS_QM_DQRELE(mp, udqp);
 	XFS_QM_DQRELE(mp, gdqp);
 
-	*vpp = vp;
+	*ipp = ip;
 
 	/* Fallthrough to std_return with error = 0  */
 
 std_return:
-	if ((*vpp || (error != 0 && dm_event_sent != 0)) &&
+	if ((*ipp || (error != 0 && dm_event_sent != 0)) &&
 	    DM_EVENT_ENABLED(dp, DM_EVENT_POSTCREATE)) {
 		(void) XFS_SEND_NAMESP(mp, DM_EVENT_POSTCREATE,
-			dir_vp, DM_RIGHT_NULL,
-			*vpp ? vp:NULL,
-			DM_RIGHT_NULL, name, NULL,
+			dp, DM_RIGHT_NULL,
+			*ipp ? ip : NULL,
+			DM_RIGHT_NULL, name->name, NULL,
 			mode, error, 0);
 	}
 	return error;
@@ -2272,46 +2272,32 @@ int remove_which_error_return = 0;
 int
 xfs_remove(
 	xfs_inode_t             *dp,
-	bhv_vname_t		*dentry)
+	struct xfs_name		*name,
+	xfs_inode_t		*ip)
 {
-	bhv_vnode_t		*dir_vp = XFS_ITOV(dp);
-	char			*name = VNAME(dentry);
 	xfs_mount_t		*mp = dp->i_mount;
-	xfs_inode_t             *ip;
 	xfs_trans_t             *tp = NULL;
 	int                     error = 0;
 	xfs_bmap_free_t         free_list;
 	xfs_fsblock_t           first_block;
 	int			cancel_flags;
 	int			committed;
-	int			dm_di_mode = 0;
 	int			link_zero;
 	uint			resblks;
-	int			namelen;
 
 	xfs_itrace_entry(dp);
 
 	if (XFS_FORCED_SHUTDOWN(mp))
 		return XFS_ERROR(EIO);
 
-	namelen = VNAMELEN(dentry);
-
-	if (!xfs_get_dir_entry(dentry, &ip)) {
-	        dm_di_mode = ip->i_d.di_mode;
-		IRELE(ip);
-	}
-
 	if (DM_EVENT_ENABLED(dp, DM_EVENT_REMOVE)) {
-		error = XFS_SEND_NAMESP(mp, DM_EVENT_REMOVE, dir_vp,
-					DM_RIGHT_NULL, NULL, DM_RIGHT_NULL,
-					name, NULL, dm_di_mode, 0, 0);
+		error = XFS_SEND_NAMESP(mp, DM_EVENT_REMOVE, dp, DM_RIGHT_NULL,
+					NULL, DM_RIGHT_NULL, name->name, NULL,
+					ip->i_d.di_mode, 0, 0);
 		if (error)
 			return error;
 	}
 
-	/* From this point on, return through std_return */
-	ip = NULL;
-
 	/*
 	 * We need to get a reference to ip before we get our log
 	 * reservation. The reason for this is that we cannot call
@@ -2324,13 +2310,7 @@ xfs_remove(
 	 * when we call xfs_iget.  Instead we get an unlocked reference
 	 * to the inode before getting our log reservation.
 	 */
-	error = xfs_get_dir_entry(dentry, &ip);
-	if (error) {
-		REMOVE_DEBUG_TRACE(__LINE__);
-		goto std_return;
-	}
-
-	dm_di_mode = ip->i_d.di_mode;
+	IHOLD(ip);
 
 	xfs_itrace_entry(ip);
 	xfs_itrace_ref(ip);
@@ -2398,7 +2378,7 @@ xfs_remove(
 	 * Entry must exist since we did a lookup in xfs_lock_dir_and_entry.
 	 */
 	XFS_BMAP_INIT(&free_list, &first_block);
-	error = xfs_dir_removename(tp, dp, name, namelen, ip->i_ino,
+	error = xfs_dir_removename(tp, dp, name, ip->i_ino,
 					&first_block, &free_list, 0);
 	if (error) {
 		ASSERT(error != ENOENT);
@@ -2448,14 +2428,6 @@ xfs_remove(
 		goto std_return;
 	}
 
-	/*
-	 * Before we drop our extra reference to the inode, purge it
-	 * from the refcache if it is there.  By waiting until afterwards
-	 * to do the IRELE, we ensure that we won't go inactive in the
-	 * xfs_refcache_purge_ip routine (although that would be OK).
-	 */
-	xfs_refcache_purge_ip(ip);
-
 	/*
 	 * If we are using filestreams, kill the stream association.
 	 * If the file is still open it may get a new one but that
@@ -2472,9 +2444,9 @@ xfs_remove(
  std_return:
 	if (DM_EVENT_ENABLED(dp, DM_EVENT_POSTREMOVE)) {
 		(void) XFS_SEND_NAMESP(mp, DM_EVENT_POSTREMOVE,
-				dir_vp, DM_RIGHT_NULL,
+				dp, DM_RIGHT_NULL,
 				NULL, DM_RIGHT_NULL,
-				name, NULL, dm_di_mode, error, 0);
+				name->name, NULL, ip->i_d.di_mode, error, 0);
 	}
 	return error;
 
@@ -2495,14 +2467,6 @@ xfs_remove(
 	cancel_flags |= XFS_TRANS_ABORT;
 	xfs_trans_cancel(tp, cancel_flags);
 
-	/*
-	 * Before we drop our extra reference to the inode, purge it
-	 * from the refcache if it is there.  By waiting until afterwards
-	 * to do the IRELE, we ensure that we won't go inactive in the
-	 * xfs_refcache_purge_ip routine (although that would be OK).
-	 */
-	xfs_refcache_purge_ip(ip);
-
 	IRELE(ip);
 
 	goto std_return;
@@ -2511,12 +2475,10 @@ xfs_remove(
 int
 xfs_link(
 	xfs_inode_t		*tdp,
-	bhv_vnode_t		*src_vp,
-	bhv_vname_t		*dentry)
+	xfs_inode_t		*sip,
+	struct xfs_name		*target_name)
 {
-	bhv_vnode_t		*target_dir_vp = XFS_ITOV(tdp);
 	xfs_mount_t		*mp = tdp->i_mount;
-	xfs_inode_t		*sip = xfs_vtoi(src_vp);
 	xfs_trans_t		*tp;
 	xfs_inode_t		*ips[2];
 	int			error;
@@ -2525,23 +2487,20 @@ xfs_link(
 	int			cancel_flags;
 	int			committed;
 	int			resblks;
-	char			*target_name = VNAME(dentry);
-	int			target_namelen;
 
 	xfs_itrace_entry(tdp);
-	xfs_itrace_entry(xfs_vtoi(src_vp));
+	xfs_itrace_entry(sip);
 
-	target_namelen = VNAMELEN(dentry);
-	ASSERT(!VN_ISDIR(src_vp));
+	ASSERT(!S_ISDIR(sip->i_d.di_mode));
 
 	if (XFS_FORCED_SHUTDOWN(mp))
 		return XFS_ERROR(EIO);
 
 	if (DM_EVENT_ENABLED(tdp, DM_EVENT_LINK)) {
 		error = XFS_SEND_NAMESP(mp, DM_EVENT_LINK,
-					target_dir_vp, DM_RIGHT_NULL,
-					src_vp, DM_RIGHT_NULL,
-					target_name, NULL, 0, 0, 0);
+					tdp, DM_RIGHT_NULL,
+					sip, DM_RIGHT_NULL,
+					target_name->name, NULL, 0, 0, 0);
 		if (error)
 			return error;
 	}
@@ -2556,7 +2515,7 @@ xfs_link(
 
 	tp = xfs_trans_alloc(mp, XFS_TRANS_LINK);
 	cancel_flags = XFS_TRANS_RELEASE_LOG_RES;
-	resblks = XFS_LINK_SPACE_RES(mp, target_namelen);
+	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) {
@@ -2584,8 +2543,8 @@ xfs_link(
 	 * xfs_trans_cancel will both unlock the inodes and
 	 * decrement the associated ref counts.
 	 */
-	VN_HOLD(src_vp);
-	VN_HOLD(target_dir_vp);
+	IHOLD(sip);
+	IHOLD(tdp);
 	xfs_trans_ijoin(tp, sip, XFS_ILOCK_EXCL);
 	xfs_trans_ijoin(tp, tdp, XFS_ILOCK_EXCL);
 
@@ -2608,15 +2567,14 @@ xfs_link(
 		goto error_return;
 	}
 
-	if (resblks == 0 &&
-	    (error = xfs_dir_canenter(tp, tdp, target_name, target_namelen)))
+	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, target_namelen,
-				   sip->i_ino, &first_block, &free_list,
-				   resblks);
+	error = xfs_dir_createname(tp, tdp, target_name, sip->i_ino,
+					&first_block, &free_list, resblks);
 	if (error)
 		goto abort_return;
 	xfs_ichgtime(tdp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
@@ -2650,9 +2608,9 @@ xfs_link(
 std_return:
 	if (DM_EVENT_ENABLED(sip, DM_EVENT_POSTLINK)) {
 		(void) XFS_SEND_NAMESP(mp, DM_EVENT_POSTLINK,
-				target_dir_vp, DM_RIGHT_NULL,
-				src_vp, DM_RIGHT_NULL,
-				target_name, NULL, 0, error, 0);
+				tdp, DM_RIGHT_NULL,
+				sip, DM_RIGHT_NULL,
+				target_name->name, NULL, 0, error, 0);
 	}
 	return error;
 
@@ -2669,17 +2627,13 @@ std_return:
 int
 xfs_mkdir(
 	xfs_inode_t             *dp,
-	bhv_vname_t		*dentry,
+	struct xfs_name		*dir_name,
 	mode_t			mode,
-	bhv_vnode_t		**vpp,
+	xfs_inode_t		**ipp,
 	cred_t			*credp)
 {
-	bhv_vnode_t		*dir_vp = XFS_ITOV(dp);
-	char			*dir_name = VNAME(dentry);
-	int			dir_namelen = VNAMELEN(dentry);
 	xfs_mount_t		*mp = dp->i_mount;
 	xfs_inode_t		*cdp;	/* inode of created dir */
-	bhv_vnode_t		*cvp;	/* vnode of created dir */
 	xfs_trans_t		*tp;
 	int			cancel_flags;
 	int			error;
@@ -2700,8 +2654,8 @@ xfs_mkdir(
 
 	if (DM_EVENT_ENABLED(dp, DM_EVENT_CREATE)) {
 		error = XFS_SEND_NAMESP(mp, DM_EVENT_CREATE,
-					dir_vp, DM_RIGHT_NULL, NULL,
-					DM_RIGHT_NULL, dir_name, NULL,
+					dp, DM_RIGHT_NULL, NULL,
+					DM_RIGHT_NULL, dir_name->name, NULL,
 					mode, 0, 0);
 		if (error)
 			return error;
@@ -2730,7 +2684,7 @@ xfs_mkdir(
 
 	tp = xfs_trans_alloc(mp, XFS_TRANS_MKDIR);
 	cancel_flags = XFS_TRANS_RELEASE_LOG_RES;
-	resblks = XFS_MKDIR_SPACE_RES(mp, dir_namelen);
+	resblks = XFS_MKDIR_SPACE_RES(mp, dir_name->len);
 	error = xfs_trans_reserve(tp, resblks, XFS_MKDIR_LOG_RES(mp), 0,
 				  XFS_TRANS_PERM_LOG_RES, XFS_MKDIR_LOG_COUNT);
 	if (error == ENOSPC) {
@@ -2762,8 +2716,8 @@ xfs_mkdir(
 	if (error)
 		goto error_return;
 
-	if (resblks == 0 &&
-	    (error = xfs_dir_canenter(tp, dp, dir_name, dir_namelen)))
+	error = xfs_dir_canenter(tp, dp, dir_name, resblks);
+	if (error)
 		goto error_return;
 	/*
 	 * create the directory inode.
@@ -2786,15 +2740,15 @@ xfs_mkdir(
 	 * from here on will result in the transaction cancel
 	 * unlocking dp so don't do it explicitly in the error path.
 	 */
-	VN_HOLD(dir_vp);
+	IHOLD(dp);
 	xfs_trans_ijoin(tp, dp, XFS_ILOCK_EXCL);
 	unlock_dp_on_error = B_FALSE;
 
 	XFS_BMAP_INIT(&free_list, &first_block);
 
-	error = xfs_dir_createname(tp, dp, dir_name, dir_namelen, cdp->i_ino,
-				   &first_block, &free_list, resblks ?
-				   resblks - XFS_IALLOC_SPACE_RES(mp) : 0);
+	error = xfs_dir_createname(tp, dp, dir_name, cdp->i_ino,
+					&first_block, &free_list, resblks ?
+					resblks - XFS_IALLOC_SPACE_RES(mp) : 0);
 	if (error) {
 		ASSERT(error != ENOSPC);
 		goto error1;
@@ -2817,11 +2771,9 @@ xfs_mkdir(
 	if (error)
 		goto error2;
 
-	cvp = XFS_ITOV(cdp);
-
 	created = B_TRUE;
 
-	*vpp = cvp;
+	*ipp = cdp;
 	IHOLD(cdp);
 
 	/*
@@ -2858,10 +2810,10 @@ std_return:
 	if ((created || (error != 0 && dm_event_sent != 0)) &&
 	    DM_EVENT_ENABLED(dp, DM_EVENT_POSTCREATE)) {
 		(void) XFS_SEND_NAMESP(mp, DM_EVENT_POSTCREATE,
-					dir_vp, DM_RIGHT_NULL,
-					created ? XFS_ITOV(cdp):NULL,
+					dp, DM_RIGHT_NULL,
+					created ? cdp : NULL,
 					DM_RIGHT_NULL,
-					dir_name, NULL,
+					dir_name->name, NULL,
 					mode, error, 0);
 	}
 	return error;
@@ -2885,20 +2837,17 @@ std_return:
 int
 xfs_rmdir(
 	xfs_inode_t             *dp,
-	bhv_vname_t		*dentry)
+	struct xfs_name		*name,
+	xfs_inode_t		*cdp)
 {
 	bhv_vnode_t		*dir_vp = XFS_ITOV(dp);
-	char			*name = VNAME(dentry);
-	int			namelen = VNAMELEN(dentry);
 	xfs_mount_t		*mp = dp->i_mount;
-  	xfs_inode_t             *cdp;   /* child directory */
 	xfs_trans_t             *tp;
 	int                     error;
 	xfs_bmap_free_t         free_list;
 	xfs_fsblock_t           first_block;
 	int			cancel_flags;
 	int			committed;
-	int			dm_di_mode = S_IFDIR;
 	int			last_cdp_link;
 	uint			resblks;
 
@@ -2907,24 +2856,15 @@ xfs_rmdir(
 	if (XFS_FORCED_SHUTDOWN(mp))
 		return XFS_ERROR(EIO);
 
-	if (!xfs_get_dir_entry(dentry, &cdp)) {
-	        dm_di_mode = cdp->i_d.di_mode;
-		IRELE(cdp);
-	}
-
 	if (DM_EVENT_ENABLED(dp, DM_EVENT_REMOVE)) {
 		error = XFS_SEND_NAMESP(mp, DM_EVENT_REMOVE,
-					dir_vp, DM_RIGHT_NULL,
-					NULL, DM_RIGHT_NULL,
-					name, NULL, dm_di_mode, 0, 0);
+					dp, DM_RIGHT_NULL,
+					NULL, DM_RIGHT_NULL, name->name,
+					NULL, cdp->i_d.di_mode, 0, 0);
 		if (error)
 			return XFS_ERROR(error);
 	}
 
-	/* Return through std_return after this point. */
-
-	cdp = NULL;
-
 	/*
 	 * We need to get a reference to cdp before we get our log
 	 * reservation.  The reason for this is that we cannot call
@@ -2937,13 +2877,7 @@ xfs_rmdir(
 	 * when we call xfs_iget.  Instead we get an unlocked reference
 	 * to the inode before getting our log reservation.
 	 */
-	error = xfs_get_dir_entry(dentry, &cdp);
-	if (error) {
-		REMOVE_DEBUG_TRACE(__LINE__);
-		goto std_return;
-	}
-	mp = dp->i_mount;
-	dm_di_mode = cdp->i_d.di_mode;
+	IHOLD(cdp);
 
 	/*
 	 * Get the dquots for the inodes.
@@ -3020,7 +2954,7 @@ xfs_rmdir(
 		goto error_return;
 	}
 
-	error = xfs_dir_removename(tp, dp, name, namelen, cdp->i_ino,
+	error = xfs_dir_removename(tp, dp, name, cdp->i_ino,
 					&first_block, &free_list, resblks);
 	if (error)
 		goto error1;
@@ -3098,9 +3032,9 @@ xfs_rmdir(
  std_return:
 	if (DM_EVENT_ENABLED(dp, DM_EVENT_POSTREMOVE)) {
 		(void) XFS_SEND_NAMESP(mp, DM_EVENT_POSTREMOVE,
-					dir_vp, DM_RIGHT_NULL,
+					dp, DM_RIGHT_NULL,
 					NULL, DM_RIGHT_NULL,
-					name, NULL, dm_di_mode,
+					name->name, NULL, cdp->i_d.di_mode,
 					error, 0);
 	}
 	return error;
@@ -3118,13 +3052,12 @@ xfs_rmdir(
 int
 xfs_symlink(
 	xfs_inode_t		*dp,
-	bhv_vname_t		*dentry,
-	char			*target_path,
+	struct xfs_name		*link_name,
+	const char		*target_path,
 	mode_t			mode,
-	bhv_vnode_t		**vpp,
+	xfs_inode_t		**ipp,
 	cred_t			*credp)
 {
-	bhv_vnode_t		*dir_vp = XFS_ITOV(dp);
 	xfs_mount_t		*mp = dp->i_mount;
 	xfs_trans_t		*tp;
 	xfs_inode_t		*ip;
@@ -3140,17 +3073,15 @@ xfs_symlink(
 	int			nmaps;
 	xfs_bmbt_irec_t		mval[SYMLINK_MAPS];
 	xfs_daddr_t		d;
-	char			*cur_chunk;
+	const char		*cur_chunk;
 	int			byte_cnt;
 	int			n;
 	xfs_buf_t		*bp;
 	xfs_prid_t		prid;
 	struct xfs_dquot	*udqp, *gdqp;
 	uint			resblks;
-	char			*link_name = VNAME(dentry);
-	int			link_namelen;
 
-	*vpp = NULL;
+	*ipp = NULL;
 	error = 0;
 	ip = NULL;
 	tp = NULL;
@@ -3160,44 +3091,17 @@ xfs_symlink(
 	if (XFS_FORCED_SHUTDOWN(mp))
 		return XFS_ERROR(EIO);
 
-	link_namelen = VNAMELEN(dentry);
-
 	/*
 	 * Check component lengths of the target path name.
 	 */
 	pathlen = strlen(target_path);
 	if (pathlen >= MAXPATHLEN)      /* total string too long */
 		return XFS_ERROR(ENAMETOOLONG);
-	if (pathlen >= MAXNAMELEN) {    /* is any component too long? */
-		int len, total;
-		char *path;
-
-		for (total = 0, path = target_path; total < pathlen;) {
-			/*
-			 * Skip any slashes.
-			 */
-			while(*path == '/') {
-				total++;
-				path++;
-			}
-
-			/*
-			 * Count up to the next slash or end of path.
-			 * Error out if the component is bigger than MAXNAMELEN.
-			 */
-			for(len = 0; *path != '/' && total < pathlen;total++, path++) {
-				if (++len >= MAXNAMELEN) {
-					error = ENAMETOOLONG;
-					return error;
-				}
-			}
-		}
-	}
 
 	if (DM_EVENT_ENABLED(dp, DM_EVENT_SYMLINK)) {
-		error = XFS_SEND_NAMESP(mp, DM_EVENT_SYMLINK, dir_vp,
+		error = XFS_SEND_NAMESP(mp, DM_EVENT_SYMLINK, dp,
 					DM_RIGHT_NULL, NULL, DM_RIGHT_NULL,
-					link_name, target_path, 0, 0, 0);
+					link_name->name, target_path, 0, 0, 0);
 		if (error)
 			return error;
 	}
@@ -3229,7 +3133,7 @@ xfs_symlink(
 		fs_blocks = 0;
 	else
 		fs_blocks = XFS_B_TO_FSB(mp, pathlen);
-	resblks = XFS_SYMLINK_SPACE_RES(mp, link_namelen, fs_blocks);
+	resblks = XFS_SYMLINK_SPACE_RES(mp, link_name->len, fs_blocks);
 	error = xfs_trans_reserve(tp, resblks, XFS_SYMLINK_LOG_RES(mp), 0,
 			XFS_TRANS_PERM_LOG_RES, XFS_SYMLINK_LOG_COUNT);
 	if (error == ENOSPC && fs_blocks == 0) {
@@ -3263,8 +3167,8 @@ xfs_symlink(
 	/*
 	 * Check for ability to enter directory entry, if no space reserved.
 	 */
-	if (resblks == 0 &&
-	    (error = xfs_dir_canenter(tp, dp, link_name, link_namelen)))
+	error = xfs_dir_canenter(tp, dp, link_name, resblks);
+	if (error)
 		goto error_return;
 	/*
 	 * Initialize the bmap freelist prior to calling either
@@ -3289,7 +3193,7 @@ xfs_symlink(
 	 * transaction cancel unlocking dp so don't do it explicitly in the
 	 * error path.
 	 */
-	VN_HOLD(dir_vp);
+	IHOLD(dp);
 	xfs_trans_ijoin(tp, dp, XFS_ILOCK_EXCL);
 	unlock_dp_on_error = B_FALSE;
 
@@ -3356,8 +3260,8 @@ xfs_symlink(
 	/*
 	 * Create the directory entry for the symlink.
 	 */
-	error = xfs_dir_createname(tp, dp, link_name, link_namelen, ip->i_ino,
-				   &first_block, &free_list, resblks);
+	error = xfs_dir_createname(tp, dp, link_name, ip->i_ino,
+					&first_block, &free_list, resblks);
 	if (error)
 		goto error1;
 	xfs_ichgtime(dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
@@ -3399,19 +3303,14 @@ xfs_symlink(
 std_return:
 	if (DM_EVENT_ENABLED(dp, DM_EVENT_POSTSYMLINK)) {
 		(void) XFS_SEND_NAMESP(mp, DM_EVENT_POSTSYMLINK,
-					dir_vp, DM_RIGHT_NULL,
-					error ? NULL : XFS_ITOV(ip),
-					DM_RIGHT_NULL, link_name, target_path,
-					0, error, 0);
+					dp, DM_RIGHT_NULL,
+					error ? NULL : ip,
+					DM_RIGHT_NULL, link_name->name,
+					target_path, 0, error, 0);
 	}
 
-	if (!error) {
-		bhv_vnode_t *vp;
-
-		ASSERT(ip);
-		vp = XFS_ITOV(ip);
-		*vpp = vp;
-	}
+	if (!error)
+		*ipp = ip;
 	return error;
 
  error2:
@@ -3430,61 +3329,12 @@ std_return:
 	goto std_return;
 }
 
-int
-xfs_rwlock(
-	xfs_inode_t	*ip,
-	bhv_vrwlock_t	locktype)
-{
-	if (S_ISDIR(ip->i_d.di_mode))
-		return 1;
-	if (locktype == VRWLOCK_WRITE) {
-		xfs_ilock(ip, XFS_IOLOCK_EXCL);
-	} else if (locktype == VRWLOCK_TRY_READ) {
-		return xfs_ilock_nowait(ip, XFS_IOLOCK_SHARED);
-	} else if (locktype == VRWLOCK_TRY_WRITE) {
-		return xfs_ilock_nowait(ip, XFS_IOLOCK_EXCL);
-	} else {
-		ASSERT((locktype == VRWLOCK_READ) ||
-		       (locktype == VRWLOCK_WRITE_DIRECT));
-		xfs_ilock(ip, XFS_IOLOCK_SHARED);
-	}
-
-	return 1;
-}
-
-
-void
-xfs_rwunlock(
-	xfs_inode_t     *ip,
-	bhv_vrwlock_t	locktype)
-{
- 	if (S_ISDIR(ip->i_d.di_mode))
-  		return;
-	if (locktype == VRWLOCK_WRITE) {
-		/*
-		 * In the write case, we may have added a new entry to
-		 * the reference cache.  This might store a pointer to
-		 * an inode to be released in this inode.  If it is there,
-		 * clear the pointer and release the inode after unlocking
-		 * this one.
-		 */
-		xfs_refcache_iunlock(ip, XFS_IOLOCK_EXCL);
-	} else {
-		ASSERT((locktype == VRWLOCK_READ) ||
-		       (locktype == VRWLOCK_WRITE_DIRECT));
-		xfs_iunlock(ip, XFS_IOLOCK_SHARED);
-	}
-	return;
-}
-
-
 int
 xfs_inode_flush(
 	xfs_inode_t	*ip,
 	int		flags)
 {
 	xfs_mount_t	*mp = ip->i_mount;
-	xfs_inode_log_item_t *iip = ip->i_itemp;
 	int		error = 0;
 
 	if (XFS_FORCED_SHUTDOWN(mp))
@@ -3494,33 +3344,9 @@ xfs_inode_flush(
 	 * Bypass inodes which have already been cleaned by
 	 * the inode flush clustering code inside xfs_iflush
 	 */
-	if ((ip->i_update_core == 0) &&
-	    ((iip == NULL) || !(iip->ili_format.ilf_fields & XFS_ILOG_ALL)))
+	if (xfs_inode_clean(ip))
 		return 0;
 
-	if (flags & FLUSH_LOG) {
-		if (iip && iip->ili_last_lsn) {
-			xlog_t		*log = mp->m_log;
-			xfs_lsn_t	sync_lsn;
-			int		log_flags = XFS_LOG_FORCE;
-
-			spin_lock(&log->l_grant_lock);
-			sync_lsn = log->l_last_sync_lsn;
-			spin_unlock(&log->l_grant_lock);
-
-			if ((XFS_LSN_CMP(iip->ili_last_lsn, sync_lsn) > 0)) {
-				if (flags & FLUSH_SYNC)
-					log_flags |= XFS_LOG_SYNC;
-				error = xfs_log_force(mp, iip->ili_last_lsn, log_flags);
-				if (error)
-					return error;
-			}
-
-			if (ip->i_update_core == 0)
-				return 0;
-		}
-	}
-
 	/*
 	 * We make this non-blocking if the inode is contended,
 	 * return EAGAIN to indicate to the caller that they
@@ -3528,30 +3354,22 @@ xfs_inode_flush(
 	 * blocking on inodes inside another operation right
 	 * now, they get caught later by xfs_sync.
 	 */
-	if (flags & FLUSH_INODE) {
-		int	flush_flags;
-
-		if (flags & FLUSH_SYNC) {
-			xfs_ilock(ip, XFS_ILOCK_SHARED);
-			xfs_iflock(ip);
-		} else if (xfs_ilock_nowait(ip, XFS_ILOCK_SHARED)) {
-			if (xfs_ipincount(ip) || !xfs_iflock_nowait(ip)) {
-				xfs_iunlock(ip, XFS_ILOCK_SHARED);
-				return EAGAIN;
-			}
-		} else {
+	if (flags & FLUSH_SYNC) {
+		xfs_ilock(ip, XFS_ILOCK_SHARED);
+		xfs_iflock(ip);
+	} else if (xfs_ilock_nowait(ip, XFS_ILOCK_SHARED)) {
+		if (xfs_ipincount(ip) || !xfs_iflock_nowait(ip)) {
+			xfs_iunlock(ip, XFS_ILOCK_SHARED);
 			return EAGAIN;
 		}
-
-		if (flags & FLUSH_SYNC)
-			flush_flags = XFS_IFLUSH_SYNC;
-		else
-			flush_flags = XFS_IFLUSH_ASYNC;
-
-		error = xfs_iflush(ip, flush_flags);
-		xfs_iunlock(ip, XFS_ILOCK_SHARED);
+	} else {
+		return EAGAIN;
 	}
 
+	error = xfs_iflush(ip, (flags & FLUSH_SYNC) ? XFS_IFLUSH_SYNC
+						    : XFS_IFLUSH_ASYNC_NOBLOCK);
+	xfs_iunlock(ip, XFS_ILOCK_SHARED);
+
 	return error;
 }
 
@@ -3694,12 +3512,12 @@ xfs_finish_reclaim(
 	 * We get the flush lock regardless, though, just to make sure
 	 * we don't free it while it is being flushed.
 	 */
-	if (!XFS_FORCED_SHUTDOWN(ip->i_mount)) {
-		if (!locked) {
-			xfs_ilock(ip, XFS_ILOCK_EXCL);
-			xfs_iflock(ip);
-		}
+	if (!locked) {
+		xfs_ilock(ip, XFS_ILOCK_EXCL);
+		xfs_iflock(ip);
+	}
 
+	if (!XFS_FORCED_SHUTDOWN(ip->i_mount)) {
 		if (ip->i_update_core ||
 		    ((ip->i_itemp != NULL) &&
 		     (ip->i_itemp->ili_format.ilf_fields != 0))) {
@@ -3719,17 +3537,11 @@ xfs_finish_reclaim(
 		ASSERT(ip->i_update_core == 0);
 		ASSERT(ip->i_itemp == NULL ||
 		       ip->i_itemp->ili_format.ilf_fields == 0);
-		xfs_iunlock(ip, XFS_ILOCK_EXCL);
-	} else if (locked) {
-		/*
-		 * We are not interested in doing an iflush if we're
-		 * in the process of shutting down the filesystem forcibly.
-		 * So, just reclaim the inode.
-		 */
-		xfs_ifunlock(ip);
-		xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	}
 
+	xfs_ifunlock(ip);
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+
  reclaim:
 	xfs_ireclaim(ip);
 	return 0;
@@ -3845,9 +3657,8 @@ xfs_alloc_file_space(
 		end_dmi_offset = offset+len;
 		if (end_dmi_offset > ip->i_size)
 			end_dmi_offset = ip->i_size;
-		error = XFS_SEND_DATA(mp, DM_EVENT_WRITE, XFS_ITOV(ip),
-			offset, end_dmi_offset - offset,
-			0, NULL);
+		error = XFS_SEND_DATA(mp, DM_EVENT_WRITE, ip, offset,
+				      end_dmi_offset - offset, 0, NULL);
 		if (error)
 			return error;
 	}
@@ -3956,8 +3767,8 @@ dmapi_enospc_check:
 	if (error == ENOSPC && (attr_flags & ATTR_DMI) == 0 &&
 	    DM_EVENT_ENABLED(ip, DM_EVENT_NOSPACE)) {
 		error = XFS_SEND_NAMESP(mp, DM_EVENT_NOSPACE,
-				XFS_ITOV(ip), DM_RIGHT_NULL,
-				XFS_ITOV(ip), DM_RIGHT_NULL,
+				ip, DM_RIGHT_NULL,
+				ip, DM_RIGHT_NULL,
 				NULL, NULL, 0, 0, 0); /* Delay flag intentionally unused */
 		if (error == 0)
 			goto retry;	/* Maybe DMAPI app. has made space */
@@ -4021,7 +3832,8 @@ xfs_zero_remaining_bytes(
 		XFS_BUF_READ(bp);
 		XFS_BUF_SET_ADDR(bp, XFS_FSB_TO_DB(ip, imap.br_startblock));
 		xfsbdstrat(mp, bp);
-		if ((error = xfs_iowait(bp))) {
+		error = xfs_iowait(bp);
+		if (error) {
 			xfs_ioerror_alert("xfs_zero_remaining_bytes(read)",
 					  mp, bp, XFS_BUF_ADDR(bp));
 			break;
@@ -4033,7 +3845,8 @@ xfs_zero_remaining_bytes(
 		XFS_BUF_UNREAD(bp);
 		XFS_BUF_WRITE(bp);
 		xfsbdstrat(mp, bp);
-		if ((error = xfs_iowait(bp))) {
+		error = xfs_iowait(bp);
+		if (error) {
 			xfs_ioerror_alert("xfs_zero_remaining_bytes(write)",
 					  mp, bp, XFS_BUF_ADDR(bp));
 			break;
@@ -4102,7 +3915,7 @@ xfs_free_file_space(
 	    DM_EVENT_ENABLED(ip, DM_EVENT_WRITE)) {
 		if (end_dmi_offset > ip->i_size)
 			end_dmi_offset = ip->i_size;
-		error = XFS_SEND_DATA(mp, DM_EVENT_WRITE, vp,
+		error = XFS_SEND_DATA(mp, DM_EVENT_WRITE, ip,
 				offset, end_dmi_offset - offset,
 				AT_DELAY_FLAG(attr_flags), NULL);
 		if (error)

fs/xfs/xfs_vnodeops.h

@@ -23,31 +23,32 @@ int xfs_fsync(struct xfs_inode *ip, int flag, xfs_off_t start,
 		xfs_off_t stop);
 int xfs_release(struct xfs_inode *ip);
 int xfs_inactive(struct xfs_inode *ip);
-int xfs_lookup(struct xfs_inode *dp, bhv_vname_t *dentry,
-		bhv_vnode_t **vpp);
-int xfs_create(struct xfs_inode *dp, bhv_vname_t *dentry, mode_t mode,
-		xfs_dev_t rdev, bhv_vnode_t **vpp, struct cred *credp);
-int xfs_remove(struct xfs_inode *dp, bhv_vname_t	*dentry);
-int xfs_link(struct xfs_inode *tdp, bhv_vnode_t *src_vp,
-		bhv_vname_t *dentry);
-int xfs_mkdir(struct xfs_inode *dp, bhv_vname_t *dentry,
-		mode_t mode, bhv_vnode_t **vpp, struct cred *credp);
-int xfs_rmdir(struct xfs_inode *dp, bhv_vname_t *dentry);
+int xfs_lookup(struct xfs_inode *dp, struct xfs_name *name,
+		struct xfs_inode **ipp);
+int xfs_create(struct xfs_inode *dp, struct xfs_name *name, mode_t mode,
+		xfs_dev_t rdev, struct xfs_inode **ipp, struct cred *credp);
+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_mkdir(struct xfs_inode *dp, struct xfs_name *dir_name,
+		mode_t mode, struct xfs_inode **ipp, struct cred *credp);
+int xfs_rmdir(struct xfs_inode *dp, struct xfs_name *name,
+		struct xfs_inode *cdp);
 int xfs_readdir(struct xfs_inode	*dp, void *dirent, size_t bufsize,
 		       xfs_off_t *offset, filldir_t filldir);
-int xfs_symlink(struct xfs_inode *dp, bhv_vname_t *dentry,
-		char *target_path, mode_t mode, bhv_vnode_t **vpp,
+int xfs_symlink(struct xfs_inode *dp, struct xfs_name *link_name,
+		const char *target_path, mode_t mode, struct xfs_inode **ipp,
 		struct cred *credp);
-int xfs_rwlock(struct xfs_inode *ip, bhv_vrwlock_t locktype);
-void xfs_rwunlock(struct xfs_inode *ip, bhv_vrwlock_t locktype);
 int xfs_inode_flush(struct xfs_inode *ip, int flags);
 int xfs_set_dmattrs(struct xfs_inode *ip, u_int evmask, u_int16_t state);
 int xfs_reclaim(struct xfs_inode *ip);
 int xfs_change_file_space(struct xfs_inode *ip, int cmd,
 		xfs_flock64_t *bf, xfs_off_t offset,
 		struct cred *credp, int	attr_flags);
-int xfs_rename(struct xfs_inode *src_dp, bhv_vname_t *src_vname,
-		bhv_vnode_t *target_dir_vp, bhv_vname_t *target_vname);
+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);
 int xfs_attr_get(struct xfs_inode *ip, const char *name, char *value,
 		int *valuelenp, int flags, cred_t *cred);
 int xfs_attr_set(struct xfs_inode *dp, const char *name, char *value,