Merge git://oss.sgi.com:8090/oss/git/xfs-2.6

* git://oss.sgi.com:8090/oss/git/xfs-2.6: (71 commits)
  [XFS] Sync up one/two other minor changes missed in previous merges.
  [XFS] Reenable the noikeep (delete inode cluster space) option by default.
  [XFS] Check that a page has dirty buffers before finding it acceptable for
  [XFS] Fixup naming inconsistencies found by Pekka Enberg and one from Jan
  [XFS] Explain the race closed by the addition of vn_iowait() to the start
  [XFS] Fixing the error caused by the conflict between DIO Write's
  [XFS] Fixing KDB's xrwtrc command, also added the current process id into
  [XFS] Fix compiler warning from xfs_file_compat_invis_ioctl prototype. 
  [XFS] remove bogus INT_GET for u8 variables in xfs_dir_leaf.c 
  [XFS] endianess annotations for xfs_da_node_hdr_t 
  [XFS] endianess annotations for xfs_da_node_entry_t 
  [XFS] store xfs_attr_inactive_list_t in native endian 
  [XFS] store xfs_attr_sf_sort in native endian 
  [XFS] endianess annotations for xfs_attr_shortform_t 
  [XFS] endianess annotations for xfs_attr_leaf_name_remote_t 
  [XFS] endianess annotations for xfs_attr_leaf_name_local_t 
  [XFS] endianess annotations for xfs_attr_leaf_entry_t 
  [XFS] endianess annotations for xfs_attr_leaf_hdr_t 
  [XFS] remove bogus INT_GET on u8 variables in xfs_dir2_block.c 
  [XFS] endianess annotations for xfs_da_blkinfo_t 
  ...

68 files changed, 4902 insertions, 3118 deletions

diff --git a/fs/xfs/Makefile-linux-2.6 b/fs/xfs/Makefile-linux-2.6
index 97bd4743b46..5d73eaa1971 100644
--- a/fs/xfs/Makefile-linux-2.6
+++ b/fs/xfs/Makefile-linux-2.6
@@ -1,33 +1,19 @@
 #
-# Copyright (c) 2000-2005 Silicon Graphics, Inc.  All Rights Reserved.
+# Copyright (c) 2000-2005 Silicon Graphics, Inc.
+# All Rights Reserved.
 #
-# This program is free software; you can redistribute it and/or modify it
-# under the terms of version 2 of the GNU General Public License as
+# This program is free software; you can redistribute it and/or
+# modify it under the terms of the GNU General Public License as
 # published by the Free Software Foundation.
 #
-# This program is distributed in the hope that it would be useful, but
-# WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+# This program is distributed in the hope that it would be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
 #
-# Further, this software is distributed without any warranty that it is
-# free of the rightful claim of any third person regarding infringement
-# or the like.  Any license provided herein, whether implied or
-# otherwise, applies only to this software file.  Patent licenses, if
-# any, provided herein do not apply to combinations of this program with
-# other software, or any other product whatsoever.
-#
-# You should have received a copy of the GNU General Public License along
-# with this program; if not, write the Free Software Foundation, Inc., 59
-# Temple Place - Suite 330, Boston MA 02111-1307, USA.
-#
-# Contact information: Silicon Graphics, Inc., 1600 Amphitheatre Pkwy,
-# Mountain View, CA  94043, or:
-#
-# http://www.sgi.com
-#
-# For further information regarding this notice, see:
-#
-# http://oss.sgi.com/projects/GenInfo/SGIGPLNoticeExplan/
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, write the Free Software Foundation,
+# Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
 #
 
 EXTRA_CFLAGS +=	 -Ifs/xfs -Ifs/xfs/linux-2.6 -funsigned-char
@@ -36,7 +22,7 @@ XFS_LINUX := linux-2.6
 
 ifeq ($(CONFIG_XFS_DEBUG),y)
 	EXTRA_CFLAGS += -g -DSTATIC="" -DDEBUG
-	EXTRA_CFLAGS += -DPAGEBUF_LOCK_TRACKING
+	EXTRA_CFLAGS += -DXFS_BUF_LOCK_TRACKING
 endif
 ifeq ($(CONFIG_XFS_TRACE),y)
 	EXTRA_CFLAGS += -DXFS_ALLOC_TRACE
@@ -50,7 +36,7 @@ ifeq ($(CONFIG_XFS_TRACE),y)
 	EXTRA_CFLAGS += -DXFS_ILOCK_TRACE
 	EXTRA_CFLAGS += -DXFS_LOG_TRACE
 	EXTRA_CFLAGS += -DXFS_RW_TRACE
-	EXTRA_CFLAGS += -DPAGEBUF_TRACE
+	EXTRA_CFLAGS += -DXFS_BUF_TRACE
 	EXTRA_CFLAGS += -DXFS_VNODE_TRACE
 endif
 
diff --git a/fs/xfs/linux-2.6/kmem.h b/fs/xfs/linux-2.6/kmem.h
index c64a29cdfff..f0268a84e6f 100644
--- a/fs/xfs/linux-2.6/kmem.h
+++ b/fs/xfs/linux-2.6/kmem.h
@@ -23,17 +23,8 @@
 #include <linux/mm.h>
 
 /*
- * memory management routines
+ * Process flags handling
  */
-#define KM_SLEEP	0x0001u
-#define KM_NOSLEEP	0x0002u
-#define KM_NOFS		0x0004u
-#define KM_MAYFAIL	0x0008u
-
-#define	kmem_zone	kmem_cache
-#define kmem_zone_t	struct kmem_cache
-
-typedef unsigned long xfs_pflags_t;
 
 #define PFLAGS_TEST_NOIO()              (current->flags & PF_NOIO)
 #define PFLAGS_TEST_FSTRANS()           (current->flags & PF_FSTRANS)
@@ -67,74 +58,102 @@ typedef unsigned long xfs_pflags_t;
 	*(NSTATEP) = *(OSTATEP);	\
 } while (0)
 
-static __inline gfp_t kmem_flags_convert(unsigned int __nocast flags)
+/*
+ * General memory allocation interfaces
+ */
+
+#define KM_SLEEP	0x0001u
+#define KM_NOSLEEP	0x0002u
+#define KM_NOFS		0x0004u
+#define KM_MAYFAIL	0x0008u
+
+/*
+ * We use a special process flag to avoid recursive callbacks into
+ * the filesystem during transactions.  We will also issue our own
+ * warnings, so we explicitly skip any generic ones (silly of us).
+ */
+static inline gfp_t
+kmem_flags_convert(unsigned int __nocast flags)
 {
-	gfp_t	lflags = __GFP_NOWARN;	/* we'll report problems, if need be */
+	gfp_t	lflags;
 
-#ifdef DEBUG
-	if (unlikely(flags & ~(KM_SLEEP|KM_NOSLEEP|KM_NOFS|KM_MAYFAIL))) {
-		printk(KERN_WARNING
-		    "XFS: memory allocation with wrong flags (%x)\n", flags);
-		BUG();
-	}
-#endif
+	BUG_ON(flags & ~(KM_SLEEP|KM_NOSLEEP|KM_NOFS|KM_MAYFAIL));
 
 	if (flags & KM_NOSLEEP) {
-		lflags |= GFP_ATOMIC;
+		lflags = GFP_ATOMIC | __GFP_NOWARN;
 	} else {
-		lflags |= GFP_KERNEL;
-
-		/* avoid recusive callbacks to filesystem during transactions */
+		lflags = GFP_KERNEL | __GFP_NOWARN;
 		if (PFLAGS_TEST_FSTRANS() || (flags & KM_NOFS))
 			lflags &= ~__GFP_FS;
 	}
-
-        return lflags;
+	return lflags;
 }
 
-static __inline kmem_zone_t *
+extern void *kmem_alloc(size_t, unsigned int __nocast);
+extern void *kmem_realloc(void *, size_t, size_t, unsigned int __nocast);
+extern void *kmem_zalloc(size_t, unsigned int __nocast);
+extern void  kmem_free(void *, size_t);
+
+/*
+ * Zone interfaces
+ */
+
+#define KM_ZONE_HWALIGN	SLAB_HWCACHE_ALIGN
+#define KM_ZONE_RECLAIM	SLAB_RECLAIM_ACCOUNT
+#define KM_ZONE_SPREAD	0
+
+#define kmem_zone	kmem_cache
+#define kmem_zone_t	struct kmem_cache
+
+static inline kmem_zone_t *
 kmem_zone_init(int size, char *zone_name)
 {
 	return kmem_cache_create(zone_name, size, 0, 0, NULL, NULL);
 }
 
-static __inline void
+static inline kmem_zone_t *
+kmem_zone_init_flags(int size, char *zone_name, unsigned long flags,
+		     void (*construct)(void *, kmem_zone_t *, unsigned long))
+{
+	return kmem_cache_create(zone_name, size, 0, flags, construct, NULL);
+}
+
+static inline void
 kmem_zone_free(kmem_zone_t *zone, void *ptr)
 {
 	kmem_cache_free(zone, ptr);
 }
 
-static __inline void
+static inline void
 kmem_zone_destroy(kmem_zone_t *zone)
 {
 	if (zone && kmem_cache_destroy(zone))
 		BUG();
 }
 
-extern void *kmem_zone_zalloc(kmem_zone_t *, unsigned int __nocast);
 extern void *kmem_zone_alloc(kmem_zone_t *, unsigned int __nocast);
+extern void *kmem_zone_zalloc(kmem_zone_t *, unsigned int __nocast);
 
-extern void *kmem_alloc(size_t, unsigned int __nocast);
-extern void *kmem_realloc(void *, size_t, size_t, unsigned int __nocast);
-extern void *kmem_zalloc(size_t, unsigned int __nocast);
-extern void  kmem_free(void *, size_t);
+/*
+ * Low memory cache shrinkers
+ */
 
 typedef struct shrinker *kmem_shaker_t;
 typedef int (*kmem_shake_func_t)(int, gfp_t);
 
-static __inline kmem_shaker_t
+static inline kmem_shaker_t
 kmem_shake_register(kmem_shake_func_t sfunc)
 {
 	return set_shrinker(DEFAULT_SEEKS, sfunc);
 }
 
-static __inline void
+static inline void
 kmem_shake_deregister(kmem_shaker_t shrinker)
 {
 	remove_shrinker(shrinker);
 }
 
-static __inline int
+static inline int
 kmem_shake_allow(gfp_t gfp_mask)
 {
 	return (gfp_mask & __GFP_WAIT);
diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c
index 74d8be87f98..97fc056130e 100644
--- a/fs/xfs/linux-2.6/xfs_aops.c
+++ b/fs/xfs/linux-2.6/xfs_aops.c
@@ -43,7 +43,29 @@
 #include <linux/pagevec.h>
 #include <linux/writeback.h>
 
-STATIC void xfs_count_page_state(struct page *, int *, int *, int *);
+STATIC void
+xfs_count_page_state(
+	struct page		*page,
+	int			*delalloc,
+	int			*unmapped,
+	int			*unwritten)
+{
+	struct buffer_head	*bh, *head;
+
+	*delalloc = *unmapped = *unwritten = 0;
+
+	bh = head = page_buffers(page);
+	do {
+		if (buffer_uptodate(bh) && !buffer_mapped(bh))
+			(*unmapped) = 1;
+		else if (buffer_unwritten(bh) && !buffer_delay(bh))
+			clear_buffer_unwritten(bh);
+		else if (buffer_unwritten(bh))
+			(*unwritten) = 1;
+		else if (buffer_delay(bh))
+			(*delalloc) = 1;
+	} while ((bh = bh->b_this_page) != head);
+}
 
 #if defined(XFS_RW_TRACE)
 void
@@ -54,7 +76,7 @@ xfs_page_trace(
 	int		mask)
 {
 	xfs_inode_t	*ip;
-	vnode_t		*vp = LINVFS_GET_VP(inode);
+	vnode_t		*vp = vn_from_inode(inode);
 	loff_t		isize = i_size_read(inode);
 	loff_t		offset = page_offset(page);
 	int		delalloc = -1, unmapped = -1, unwritten = -1;
@@ -81,7 +103,7 @@ xfs_page_trace(
 		(void *)((unsigned long)delalloc),
 		(void *)((unsigned long)unmapped),
 		(void *)((unsigned long)unwritten),
-		(void *)NULL,
+		(void *)((unsigned long)current_pid()),
 		(void *)NULL);
 }
 #else
@@ -192,7 +214,7 @@ xfs_alloc_ioend(
 	ioend->io_uptodate = 1; /* cleared if any I/O fails */
 	ioend->io_list = NULL;
 	ioend->io_type = type;
-	ioend->io_vnode = LINVFS_GET_VP(inode);
+	ioend->io_vnode = vn_from_inode(inode);
 	ioend->io_buffer_head = NULL;
 	ioend->io_buffer_tail = NULL;
 	atomic_inc(&ioend->io_vnode->v_iocount);
@@ -217,7 +239,7 @@ xfs_map_blocks(
 	xfs_iomap_t		*mapp,
 	int			flags)
 {
-	vnode_t			*vp = LINVFS_GET_VP(inode);
+	vnode_t			*vp = vn_from_inode(inode);
 	int			error, nmaps = 1;
 
 	VOP_BMAP(vp, offset, count, flags, mapp, &nmaps, error);
@@ -462,28 +484,37 @@ xfs_add_to_ioend(
 }
 
 STATIC void
+xfs_map_buffer(
+	struct buffer_head	*bh,
+	xfs_iomap_t		*mp,
+	xfs_off_t		offset,
+	uint			block_bits)
+{
+	sector_t		bn;
+
+	ASSERT(mp->iomap_bn != IOMAP_DADDR_NULL);
+
+	bn = (mp->iomap_bn >> (block_bits - BBSHIFT)) +
+	      ((offset - mp->iomap_offset) >> block_bits);
+
+	ASSERT(bn || (mp->iomap_flags & IOMAP_REALTIME));
+
+	bh->b_blocknr = bn;
+	set_buffer_mapped(bh);
+}
+
+STATIC void
 xfs_map_at_offset(
 	struct buffer_head	*bh,
 	loff_t			offset,
 	int			block_bits,
 	xfs_iomap_t		*iomapp)
 {
-	xfs_daddr_t		bn;
-	int			sector_shift;
-
 	ASSERT(!(iomapp->iomap_flags & IOMAP_HOLE));
 	ASSERT(!(iomapp->iomap_flags & IOMAP_DELAY));
-	ASSERT(iomapp->iomap_bn != IOMAP_DADDR_NULL);
-
-	sector_shift = block_bits - BBSHIFT;
-	bn = (iomapp->iomap_bn >> sector_shift) +
-	      ((offset - iomapp->iomap_offset) >> block_bits);
-
-	ASSERT(bn || (iomapp->iomap_flags & IOMAP_REALTIME));
-	ASSERT((bn << sector_shift) >= iomapp->iomap_bn);
 
 	lock_buffer(bh);
-	bh->b_blocknr = bn;
+	xfs_map_buffer(bh, iomapp, offset, block_bits);
 	bh->b_bdev = iomapp->iomap_target->bt_bdev;
 	set_buffer_mapped(bh);
 	clear_buffer_delay(bh);
@@ -616,7 +647,7 @@ xfs_is_delayed_page(
 				acceptable = (type == IOMAP_UNWRITTEN);
 			else if (buffer_delay(bh))
 				acceptable = (type == IOMAP_DELAY);
-			else if (buffer_mapped(bh))
+			else if (buffer_dirty(bh) && buffer_mapped(bh))
 				acceptable = (type == 0);
 			else
 				break;
@@ -1040,8 +1071,159 @@ error:
 	return err;
 }
 
+/*
+ * writepage: Called from one of two places:
+ *
+ * 1. we are flushing a delalloc buffer head.
+ *
+ * 2. we are writing out a dirty page. Typically the page dirty
+ *    state is cleared before we get here. In this case is it
+ *    conceivable we have no buffer heads.
+ *
+ * For delalloc space on the page we need to allocate space and
+ * flush it. For unmapped buffer heads on the page we should
+ * allocate space if the page is uptodate. For any other dirty
+ * buffer heads on the page we should flush them.
+ *
+ * If we detect that a transaction would be required to flush
+ * the page, we have to check the process flags first, if we
+ * are already in a transaction or disk I/O during allocations
+ * is off, we need to fail the writepage and redirty the page.
+ */
+
+STATIC int
+xfs_vm_writepage(
+	struct page		*page,
+	struct writeback_control *wbc)
+{
+	int			error;
+	int			need_trans;
+	int			delalloc, unmapped, unwritten;
+	struct inode		*inode = page->mapping->host;
+
+	xfs_page_trace(XFS_WRITEPAGE_ENTER, inode, page, 0);
+
+	/*
+	 * We need a transaction if:
+	 *  1. There are delalloc buffers on the page
+	 *  2. The page is uptodate and we have unmapped buffers
+	 *  3. The page is uptodate and we have no buffers
+	 *  4. There are unwritten buffers on the page
+	 */
+
+	if (!page_has_buffers(page)) {
+		unmapped = 1;
+		need_trans = 1;
+	} else {
+		xfs_count_page_state(page, &delalloc, &unmapped, &unwritten);
+		if (!PageUptodate(page))
+			unmapped = 0;
+		need_trans = delalloc + unmapped + unwritten;
+	}
+
+	/*
+	 * If we need a transaction and the process flags say
+	 * we are already in a transaction, or no IO is allowed
+	 * then mark the page dirty again and leave the page
+	 * as is.
+	 */
+	if (PFLAGS_TEST_FSTRANS() && need_trans)
+		goto out_fail;
+
+	/*
+	 * Delay hooking up buffer heads until we have
+	 * made our go/no-go decision.
+	 */
+	if (!page_has_buffers(page))
+		create_empty_buffers(page, 1 << inode->i_blkbits, 0);
+
+	/*
+	 * Convert delayed allocate, unwritten or unmapped space
+	 * to real space and flush out to disk.
+	 */
+	error = xfs_page_state_convert(inode, page, wbc, 1, unmapped);
+	if (error == -EAGAIN)
+		goto out_fail;
+	if (unlikely(error < 0))
+		goto out_unlock;
+
+	return 0;
+
+out_fail:
+	redirty_page_for_writepage(wbc, page);
+	unlock_page(page);
+	return 0;
+out_unlock:
+	unlock_page(page);
+	return error;
+}
+
+/*
+ * Called to move a page into cleanable state - and from there
+ * to be released. Possibly the page is already clean. We always
+ * have buffer heads in this call.
+ *
+ * Returns 0 if the page is ok to release, 1 otherwise.
+ *
+ * Possible scenarios are:
+ *
+ * 1. We are being called to release a page which has been written
+ *    to via regular I/O. buffer heads will be dirty and possibly
+ *    delalloc. If no delalloc buffer heads in this case then we
+ *    can just return zero.
+ *
+ * 2. We are called to release a page which has been written via
+ *    mmap, all we need to do is ensure there is no delalloc
+ *    state in the buffer heads, if not we can let the caller
+ *    free them and we should come back later via writepage.
+ */
 STATIC int
-__linvfs_get_block(
+xfs_vm_releasepage(
+	struct page		*page,
+	gfp_t			gfp_mask)
+{
+	struct inode		*inode = page->mapping->host;
+	int			dirty, delalloc, unmapped, unwritten;
+	struct writeback_control wbc = {
+		.sync_mode = WB_SYNC_ALL,
+		.nr_to_write = 1,
+	};
+
+	xfs_page_trace(XFS_RELEASEPAGE_ENTER, inode, page, gfp_mask);
+
+	if (!page_has_buffers(page))
+		return 0;
+
+	xfs_count_page_state(page, &delalloc, &unmapped, &unwritten);
+	if (!delalloc && !unwritten)
+		goto free_buffers;
+
+	if (!(gfp_mask & __GFP_FS))
+		return 0;
+
+	/* If we are already inside a transaction or the thread cannot
+	 * do I/O, we cannot release this page.
+	 */
+	if (PFLAGS_TEST_FSTRANS())
+		return 0;
+
+	/*
+	 * Convert delalloc space to real space, do not flush the
+	 * data out to disk, that will be done by the caller.
+	 * Never need to allocate space here - we will always
+	 * come back to writepage in that case.
+	 */
+	dirty = xfs_page_state_convert(inode, page, &wbc, 0, 0);
+	if (dirty == 0 && !unwritten)
+		goto free_buffers;
+	return 0;
+
+free_buffers:
+	return try_to_free_buffers(page);
+}
+
+STATIC int
+__xfs_get_block(
 	struct inode		*inode,
 	sector_t		iblock,
 	unsigned long		blocks,
@@ -1050,7 +1232,7 @@ __linvfs_get_block(
 	int			direct,
 	bmapi_flags_t		flags)
 {
-	vnode_t			*vp = LINVFS_GET_VP(inode);
+	vnode_t			*vp = vn_from_inode(inode);
 	xfs_iomap_t		iomap;
 	xfs_off_t		offset;
 	ssize_t			size;
@@ -1073,21 +1255,13 @@ __linvfs_get_block(
 		return 0;
 
 	if (iomap.iomap_bn != IOMAP_DADDR_NULL) {
-		xfs_daddr_t	bn;
-		xfs_off_t	delta;
-
-		/* For unwritten extents do not report a disk address on
+		/*
+		 * For unwritten extents do not report a disk address on
 		 * the read case (treat as if we're reading into a hole).
 		 */
 		if (create || !(iomap.iomap_flags & IOMAP_UNWRITTEN)) {
-			delta = offset - iomap.iomap_offset;
-			delta >>= inode->i_blkbits;
-
-			bn = iomap.iomap_bn >> (inode->i_blkbits - BBSHIFT);
-			bn += delta;
-			BUG_ON(!bn && !(iomap.iomap_flags & IOMAP_REALTIME));
-			bh_result->b_blocknr = bn;
-			set_buffer_mapped(bh_result);
+			xfs_map_buffer(bh_result, &iomap, offset,
+				       inode->i_blkbits);
 		}
 		if (create && (iomap.iomap_flags & IOMAP_UNWRITTEN)) {
 			if (direct)
@@ -1130,30 +1304,30 @@ __linvfs_get_block(
 }
 
 int
-linvfs_get_block(
+xfs_get_block(
 	struct inode		*inode,
 	sector_t		iblock,
 	struct buffer_head	*bh_result,
 	int			create)
 {
-	return __linvfs_get_block(inode, iblock, 0, bh_result,
+	return __xfs_get_block(inode, iblock, 0, bh_result,
 					create, 0, BMAPI_WRITE);
 }
 
 STATIC int
-linvfs_get_blocks_direct(
+xfs_get_blocks_direct(
 	struct inode		*inode,
 	sector_t		iblock,
 	unsigned long		max_blocks,
 	struct buffer_head	*bh_result,
 	int			create)
 {
-	retu