23 files changed, 1759 insertions, 1359 deletions

diff --git a/fs/xfs/linux-2.6/kmem.c b/fs/xfs/linux-2.6/kmem.c
index 2d3f90afe5f1..bc7405585def 100644
--- a/fs/xfs/linux-2.6/kmem.c
+++ b/fs/xfs/linux-2.6/kmem.c
@@ -16,7 +16,6 @@
  * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
  */
 #include <linux/mm.h>
-#include <linux/vmalloc.h>
 #include <linux/highmem.h>
 #include <linux/swap.h>
 #include <linux/blkdev.h>
@@ -24,8 +23,25 @@
 #include "time.h"
 #include "kmem.h"
 
-#define MAX_VMALLOCS    6
-#define MAX_SLAB_SIZE   0x20000
+/*
+ * Greedy allocation.  May fail and may return vmalloced memory.
+ *
+ * Must be freed using kmem_free_large.
+ */
+void *
+kmem_zalloc_greedy(size_t *size, size_t minsize, size_t maxsize)
+{
+        void            *ptr;
+        size_t          kmsize = maxsize;
+
+        while (!(ptr = kmem_zalloc_large(kmsize))) {
+                if ((kmsize >>= 1) <= minsize)
+                        kmsize = minsize;
+        }
+        if (ptr)
+                *size = kmsize;
+        return ptr;
+}
 
 void *
 kmem_alloc(size_t size, unsigned int __nocast flags)
@@ -34,19 +50,8 @@ kmem_alloc(size_t size, unsigned int __nocast flags)
         gfp_t   lflags = kmem_flags_convert(flags);
         void    *ptr;
 
-#ifdef DEBUG
-        if (unlikely(!(flags & KM_LARGE) && (size > PAGE_SIZE))) {
-                printk(KERN_WARNING "Large %s attempt, size=%ld\n",
-                        __func__, (long)size);
-                dump_stack();
-        }
-#endif
-
         do {
-                if (size < MAX_SLAB_SIZE || retries > MAX_VMALLOCS)
-                        ptr = kmalloc(size, lflags);
-                else
-                        ptr = __vmalloc(size, lflags, PAGE_KERNEL);
+                ptr = kmalloc(size, lflags);
                 if (ptr || (flags & (KM_MAYFAIL|KM_NOSLEEP)))
                         return ptr;
                 if (!(++retries % 100))
@@ -68,27 +73,6 @@ kmem_zalloc(size_t size, unsigned int __nocast flags)
         return ptr;
 }
 
-void *
-kmem_zalloc_greedy(size_t *size, size_t minsize, size_t maxsize,
-                   unsigned int __nocast flags)
-{
-        void            *ptr;
-        size_t          kmsize = maxsize;
-        unsigned int    kmflags = (flags & ~KM_SLEEP) | KM_NOSLEEP;
-
-        while (!(ptr = kmem_zalloc(kmsize, kmflags))) {
-                if ((kmsize <= minsize) && (flags & KM_NOSLEEP))
-                        break;
-                if ((kmsize >>= 1) <= minsize) {
-                        kmsize = minsize;
-                        kmflags = flags;
-                }
-        }
-        if (ptr)
-                *size = kmsize;
-        return ptr;
-}
-
 void
 kmem_free(const void *ptr)
 {
diff --git a/fs/xfs/linux-2.6/kmem.h b/fs/xfs/linux-2.6/kmem.h
index 179cbd630f69..f7c8f7a9ea6d 100644
--- a/fs/xfs/linux-2.6/kmem.h
+++ b/fs/xfs/linux-2.6/kmem.h
@@ -21,6 +21,7 @@
 #include <linux/slab.h>
 #include <linux/sched.h>
 #include <linux/mm.h>
+#include <linux/vmalloc.h>
 
 /*
  * General memory allocation interfaces
@@ -30,7 +31,6 @@
 #define KM_NOSLEEP      0x0002u
 #define KM_NOFS         0x0004u
 #define KM_MAYFAIL      0x0008u
-#define KM_LARGE        0x0010u
 
 /*
  * We use a special process flag to avoid recursive callbacks into
@@ -42,7 +42,7 @@ kmem_flags_convert(unsigned int __nocast flags)
 {
         gfp_t   lflags;
 
-        BUG_ON(flags & ~(KM_SLEEP|KM_NOSLEEP|KM_NOFS|KM_MAYFAIL|KM_LARGE));
+        BUG_ON(flags & ~(KM_SLEEP|KM_NOSLEEP|KM_NOFS|KM_MAYFAIL));
 
         if (flags & KM_NOSLEEP) {
                 lflags = GFP_ATOMIC | __GFP_NOWARN;
@@ -56,10 +56,25 @@ kmem_flags_convert(unsigned int __nocast flags)
 
 extern void *kmem_alloc(size_t, unsigned int __nocast);
 extern void *kmem_zalloc(size_t, unsigned int __nocast);
-extern void *kmem_zalloc_greedy(size_t *, size_t, size_t, unsigned int __nocast);
 extern void *kmem_realloc(const void *, size_t, size_t, unsigned int __nocast);
 extern void  kmem_free(const void *);
 
+static inline void *kmem_zalloc_large(size_t size)
+{
+        void *ptr;
+
+        ptr = vmalloc(size);
+        if (ptr)
+                memset(ptr, 0, size);
+        return ptr;
+}
+static inline void kmem_free_large(void *ptr)
+{
+        vfree(ptr);
+}
+
+extern void *kmem_zalloc_greedy(size_t *, size_t, size_t);
+
 /*
  * Zone interfaces
  */
diff --git a/fs/xfs/linux-2.6/xfs_acl.c b/fs/xfs/linux-2.6/xfs_acl.c
index 883ca5ab8af5..bf85bbe4a9ae 100644
--- a/fs/xfs/linux-2.6/xfs_acl.c
+++ b/fs/xfs/linux-2.6/xfs_acl.c
@@ -106,7 +106,7 @@ xfs_get_acl(struct inode *inode, int type)
         struct posix_acl *acl;
         struct xfs_acl *xfs_acl;
         int len = sizeof(struct xfs_acl);
-        char *ea_name;
+        unsigned char *ea_name;
         int error;
 
         acl = get_cached_acl(inode, type);
@@ -133,7 +133,8 @@ xfs_get_acl(struct inode *inode, int type)
         if (!xfs_acl)
                 return ERR_PTR(-ENOMEM);
 
-        error = -xfs_attr_get(ip, ea_name, (char *)xfs_acl, &len, ATTR_ROOT);
+        error = -xfs_attr_get(ip, ea_name, (unsigned char *)xfs_acl,
+                                                        &len, ATTR_ROOT);
         if (error) {
                 /*
                  * If the attribute doesn't exist make sure we have a negative
@@ -162,7 +163,7 @@ STATIC int
 xfs_set_acl(struct inode *inode, int type, struct posix_acl *acl)
 {
         struct xfs_inode *ip = XFS_I(inode);
-        char *ea_name;
+        unsigned char *ea_name;
         int error;
 
         if (S_ISLNK(inode->i_mode))
@@ -194,7 +195,7 @@ xfs_set_acl(struct inode *inode, int type, struct posix_acl *acl)
                         (sizeof(struct xfs_acl_entry) *
                          (XFS_ACL_MAX_ENTRIES - acl->a_count));
 
-                error = -xfs_attr_set(ip, ea_name, (char *)xfs_acl,
+                error = -xfs_attr_set(ip, ea_name, (unsigned char *)xfs_acl,
                                 len, ATTR_ROOT);
 
                 kfree(xfs_acl);
@@ -262,7 +263,7 @@ xfs_set_mode(struct inode *inode, mode_t mode)
 }
 
 static int
-xfs_acl_exists(struct inode *inode, char *name)
+xfs_acl_exists(struct inode *inode, unsigned char *name)
 {
         int len = sizeof(struct xfs_acl);
 
diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c
index 66abe36c1213..99628508cb11 100644
--- a/fs/xfs/linux-2.6/xfs_aops.c
+++ b/fs/xfs/linux-2.6/xfs_aops.c
@@ -39,6 +39,7 @@
 #include "xfs_iomap.h"
 #include "xfs_vnodeops.h"
 #include "xfs_trace.h"
+#include "xfs_bmap.h"
 #include <linux/mpage.h>
 #include <linux/pagevec.h>
 #include <linux/writeback.h>
@@ -163,14 +164,17 @@ xfs_ioend_new_eof(
 }
 
 /*
- * Update on-disk file size now that data has been written to disk.
- * The current in-memory file size is i_size.  If a write is beyond
- * eof i_new_size will be the intended file size until i_size is
- * updated.  If this write does not extend all the way to the valid
- * file size then restrict this update to the end of the write.
+ * Update on-disk file size now that data has been written to disk.  The
+ * current in-memory file size is i_size.  If a write is beyond eof i_new_size
+ * will be the intended file size until i_size is updated.  If this write does
+ * not extend all the way to the valid file size then restrict this update to
+ * the end of the write.
+ *
+ * This function does not block as blocking on the inode lock in IO completion
+ * can lead to IO completion order dependency deadlocks.. If it can't get the
+ * inode ilock it will return EAGAIN. Callers must handle this.
  */
-
-STATIC void
+STATIC int
 xfs_setfilesize(
         xfs_ioend_t             *ioend)
 {
@@ -181,16 +185,40 @@ xfs_setfilesize(
         ASSERT(ioend->io_type != IOMAP_READ);
 
         if (unlikely(ioend->io_error))
-                return;
+                return 0;
+
+        if (!xfs_ilock_nowait(ip, XFS_ILOCK_EXCL))
+                return EAGAIN;
 
-        xfs_ilock(ip, XFS_ILOCK_EXCL);
         isize = xfs_ioend_new_eof(ioend);
         if (isize) {
                 ip->i_d.di_size = isize;
-                xfs_mark_inode_dirty_sync(ip);
+                xfs_mark_inode_dirty(ip);
         }
 
         xfs_iunlock(ip, XFS_ILOCK_EXCL);
+        return 0;
+}
+
+/*
+ * Schedule IO completion handling on a xfsdatad if this was
+ * the final hold on this ioend. If we are asked to wait,
+ * flush the workqueue.
+ */
+STATIC void
+xfs_finish_ioend(
+        xfs_ioend_t     *ioend,
+        int             wait)
+{
+        if (atomic_dec_and_test(&ioend->io_remaining)) {
+                struct workqueue_struct *wq;
+
+                wq = (ioend->io_type == IOMAP_UNWRITTEN) ?
+                        xfsconvertd_workqueue : xfsdatad_workqueue;
+                queue_work(wq, &ioend->io_work);
+                if (wait)
+                        flush_workqueue(wq);
+        }
 }
 
 /*
@@ -198,11 +226,11 @@ xfs_setfilesize(
  */
 STATIC void
 xfs_end_io(
-        struct work_struct      *work)
+        struct work_struct *work)
 {
-        xfs_ioend_t             *ioend =
-                container_of(work, xfs_ioend_t, io_work);
-        struct xfs_inode        *ip = XFS_I(ioend->io_inode);
+        xfs_ioend_t     *ioend = container_of(work, xfs_ioend_t, io_work);
+        struct xfs_inode *ip = XFS_I(ioend->io_inode);
+        int             error = 0;
 
         /*
          * For unwritten extents we need to issue transactions to convert a
@@ -210,7 +238,6 @@ xfs_end_io(
          */
         if (ioend->io_type == IOMAP_UNWRITTEN &&
             likely(!ioend->io_error && !XFS_FORCED_SHUTDOWN(ip->i_mount))) {
-                int error;
 
                 error = xfs_iomap_write_unwritten(ip, ioend->io_offset,
                                                  ioend->io_size);
@@ -222,30 +249,23 @@ xfs_end_io(
          * We might have to update the on-disk file size after extending
          * writes.
          */
-        if (ioend->io_type != IOMAP_READ)
-                xfs_setfilesize(ioend);
-        xfs_destroy_ioend(ioend);
-}
-
-/*
- * Schedule IO completion handling on a xfsdatad if this was
- * the final hold on this ioend. If we are asked to wait,
- * flush the workqueue.
- */
-STATIC void
-xfs_finish_ioend(
-        xfs_ioend_t     *ioend,
-        int             wait)
-{
-        if (atomic_dec_and_test(&ioend->io_remaining)) {
-                struct workqueue_struct *wq;
-
-                wq = (ioend->io_type == IOMAP_UNWRITTEN) ?
-                        xfsconvertd_workqueue : xfsdatad_workqueue;
-                queue_work(wq, &ioend->io_work);
-                if (wait)
-                        flush_workqueue(wq);
+        if (ioend->io_type != IOMAP_READ) {
+                error = xfs_setfilesize(ioend);
+                ASSERT(!error || error == EAGAIN);
         }
+
+        /*
+         * If we didn't complete processing of the ioend, requeue it to the
+         * tail of the workqueue for another attempt later. Otherwise destroy
+         * it.
+         */
+        if (error == EAGAIN) {
+                atomic_inc(&ioend->io_remaining);
+                xfs_finish_ioend(ioend, 0);
+                /* ensure we don't spin on blocked ioends */
+                delay(1);
+        } else
+                xfs_destroy_ioend(ioend);
 }
 
 /*
@@ -341,7 +361,7 @@ xfs_submit_ioend_bio(
          * but don't update the inode size until I/O completion.
          */
         if (xfs_ioend_new_eof(ioend))
-                xfs_mark_inode_dirty_sync(XFS_I(ioend->io_inode));
+                xfs_mark_inode_dirty(XFS_I(ioend->io_inode));
 
         submit_bio(wbc->sync_mode == WB_SYNC_ALL ?
                    WRITE_SYNC_PLUG : WRITE, bio);
@@ -874,6 +894,125 @@ xfs_cluster_write(
         }
 }
 
+STATIC void
+xfs_vm_invalidatepage(
+        struct page             *page,
+        unsigned long           offset)
+{
+        trace_xfs_invalidatepage(page->mapping->host, page, offset);
+        block_invalidatepage(page, offset);
+}
+
+/*
+ * If the page has delalloc buffers on it, we need to punch them out before we
+ * invalidate the page. If we don't, we leave a stale delalloc mapping on the
+ * inode that can trip a BUG() in xfs_get_blocks() later on if a direct IO read
+ * is done on that same region - the delalloc extent is returned when none is
+ * supposed to be there.
+ *
+ * We prevent this by truncating away the delalloc regions on the page before
+ * invalidating it. Because they are delalloc, we can do this without needing a
+ * transaction. Indeed - if we get ENOSPC errors, we have to be able to do this
+ * truncation without a transaction as there is no space left for block
+ * reservation (typically why we see a ENOSPC in writeback).
+ *
+ * This is not a performance critical path, so for now just do the punching a
+ * buffer head at a time.
+ */
+STATIC void
+xfs_aops_discard_page(
+        struct page             *page)
+{
+        struct inode            *inode = page->mapping->host;
+        struct xfs_inode        *ip = XFS_I(inode);
+        struct buffer_head      *bh, *head;
+        loff_t                  offset = page_offset(page);
+        ssize_t                 len = 1 << inode->i_blkbits;
+
+        if (!xfs_is_delayed_page(page, IOMAP_DELAY))
+                goto out_invalidate;
+
+        if (XFS_FORCED_SHUTDOWN(ip->i_mount))
+                goto out_invalidate;
+
+        xfs_fs_cmn_err(CE_ALERT, ip->i_mount,
+                "page discard on page %p, inode 0x%llx, offset %llu.",
+                        page, ip->i_ino, offset);
+
+        xfs_ilock(ip, XFS_ILOCK_EXCL);
+        bh = head = page_buffers(page);
+        do {
+                int             done;
+                xfs_fileoff_t   offset_fsb;
+                xfs_bmbt_irec_t imap;
+                int             nimaps = 1;
+                int             error;
+                xfs_fsblock_t   firstblock;
+                xfs_bmap_free_t flist;
+
+                if (!buffer_delay(bh))
+                        goto next_buffer;
+
+                offset_fsb = XFS_B_TO_FSBT(ip->i_mount, offset);
+
+                /*
+                 * Map the range first and check that it is a delalloc extent
+                 * before trying to unmap the range. Otherwise we will be
+                 * trying to remove a real extent (which requires a
+                 * transaction) or a hole, which is probably a bad idea...
+                 */
+                error = xfs_bmapi(NULL, ip, offset_fsb, 1,
+                                XFS_BMAPI_ENTIRE,  NULL, 0, &imap,
+                                &nimaps, NULL, NULL);
+
+                if (error) {
+                        /* something screwed, just bail */
+                        if (!XFS_FORCED_SHUTDOWN(ip->i_mount)) {
+                                xfs_fs_cmn_err(CE_ALERT, ip->i_mount,
+                                "page discard failed delalloc mapping lookup.");
+                        }
+                        break;
+                }
+                if (!nimaps) {
+                        /* nothing there */
+                        goto next_buffer;
+                }
+                if (imap.br_startblock != DELAYSTARTBLOCK) {
+                        /* been converted, ignore */
+                        goto next_buffer;
+                }
+                WARN_ON(imap.br_blockcount == 0);
+
+                /*
+                 * Note: while we initialise the firstblock/flist pair, they
+                 * should never be used because blocks should never be
+                 * allocated or freed for a delalloc extent and hence we need
+                 * don't cancel or finish them after the xfs_bunmapi() call.
+                 */
+                xfs_bmap_init(&flist, &firstblock);
+                error = xfs_bunmapi(NULL, ip, offset_fsb, 1, 0, 1, &firstblock,
+                                        &flist, NULL, &done);
+
+                ASSERT(!flist.xbf_count && !flist.xbf_first);
+                if (error) {
+                        /* something screwed, just bail */
+                        if (!XFS_FORCED_SHUTDOWN(ip->i_mount)) {
+                                xfs_fs_cmn_err(CE_ALERT, ip->i_mount,
+                        "page discard unable to remove delalloc mapping.");
+                        }
+                        break;
+                }
+next_buffer:
+                offset += len;
+
+        } while ((bh = bh->b_this_page) != head);
+
+        xfs_iunlock(ip, XFS_ILOCK_EXCL);
+out_invalidate:
+        xfs_vm_invalidatepage(page, 0);
+        return;
+}
+
 /*
  * Calling this without startio set means we are being asked to make a dirty
  * page ready for freeing it's buffers.  When called with startio set then
@@ -1125,7 +1264,7 @@ error:
          */
         if (err != -EAGAIN) {
                 if (!unmapped)
-                        block_invalidatepage(page, 0);
+                        xfs_aops_discard_page(page);
                 ClearPageUptodate(page);
         }
         return err;
@@ -1535,15 +1674,6 @@ xfs_vm_readpages(
         return mpage_readpages(mapping, pages, nr_pages, xfs_get_blocks);
 }
 
-STATIC void
-xfs_vm_invalidatepage(
-        struct page             *page,
-        unsigned long           offset)
-{
-        trace_xfs_invalidatepage(page->mapping->host, page, offset);
-        block_invalidatepage(page, offset);
-}
-
 const struct address_space_operations xfs_address_space_operations = {
         .readpage               = xfs_vm_readpage,
         .readpages              = xfs_vm_readpages,
diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c
index 77b8be81c769..bd111b7e1daa 100644
--- a/fs/xfs/linux-2.6/xfs_buf.c
+++ b/fs/xfs/linux-2.6/xfs_buf.c
@@ -33,6 +33,7 @@
 #include <linux/migrate.h>
 #include <linux/backing-dev.h>
 #include <linux/freezer.h>
+#include <linux/list_sort.h>
 
 #include "xfs_sb.h"
 #include "xfs_inum.h"
@@ -76,6 +77,27 @@ struct workqueue_struct *xfsconvertd_workqueue;
 #define xfs_buf_deallocate(bp) \
         kmem_zone_free(xfs_buf_zone, (bp));
 
+static inline int
+xfs_buf_is_vmapped(
+        struct xfs_buf  *bp)
+{
+        /*
+         * Return true if the buffer is vmapped.
+         *
+         * The XBF_MAPPED flag is set if the buffer should be mapped, but the
+         * code is clever enough to know it doesn't have to map a single page,
+         * so the check has to be both for XBF_MAPPED and bp->b_page_count > 1.
+         */
+        return (bp->b_flags & XBF_MAPPED) && bp->b_page_count > 1;
+}
+
+static inline int
+xfs_buf_vmap_len(
+        struct xfs_buf  *bp)
+{
+        return (bp->b_page_count * PAGE_SIZE) - bp->b_offset;
+}
+
 /*
  *      Page Region interfaces.
  *
@@ -146,75 +168,6 @@ test_page_region(
 }
 
 /*
- *      Mapping of multi-page buffers into contiguous virtual space
- */
-
-typedef struct a_list {
-        void            *vm_addr;
-        struct a_list   *next;
-} a_list_t;
-
-static a_list_t         *as_free_head;
-static int              as_list_len;
-static DEFINE_SPINLOCK(as_lock);
-
-/*
- *      Try to batch vunmaps because they are costly.
- */
-STATIC void
-free_address(
-        void            *addr)
-{
-        a_list_t        *aentry;
-
-#ifdef CONFIG_XEN
-        /*
-         * Xen needs to be able to make sure it can get an exclusive
-         * RO mapping of pages it wants to turn into a pagetable.  If
-         * a newly allocated page is also still being vmap()ed by xfs,
-         * it will cause pagetable construction to fail.  This is a
-         * quick workaround to always eagerly unmap pages so that Xen
-         * is happy.
-         */
-        vunmap(addr);
-        return;
-#endif
-
-        aentry = kmalloc(sizeof(a_list_t), GFP_NOWAIT);
-        if (likely(aentry)) {
-                spin_lock(&as_lock);
-                aentry->next = as_free_head;
-                aentry->vm_addr = addr;
-                as_free_head = aentry;
-                as_list_len++;
-                spin_unlock(&as_lock);
-        } else {
-                vunmap(addr);
-        }
-}
-
-STATIC void
-purge_addresses(void)
-{
-        a_list_t        *aentry, *old;
-
-        if (as_free_head == NULL)
-                return;
-
-        spin_lock(&as_lock);
-        aentry = as_free_head;
-        as_free_head = NULL;
-        as_list_len = 0;
-        spin_unlock(&as_lock);
-
-        while ((old = aentry) != NULL) {
-                vunmap(aentry->vm_addr);
-                aentry = aentry->next;
-                kfree(old);
-        }
-}
-
-/*
  *      Internal xfs_buf_t object manipulation
  */
 
@@ -314,8 +267,9 @@ xfs_buf_free(
         if (bp->b_flags & (_XBF_PAGE_CACHE|_XBF_PAGES)) {
                 uint            i;
 
-                if ((bp->b_flags & XBF_MAPPED) && (bp->b_page_count > 1))
-                        free_address(bp->b_addr - bp->b_offset);
+                if (xfs_buf_is_vmapped(bp))
+                        vm_unmap_ram(bp->b_addr - bp->b_offset,
+                                        bp->b_page_count);
 
                 for (i = 0; i < bp->b_page_count; i++) {
                         struct page     *page = bp->b_pages[i];
@@ -435,10 +389,8 @@ _xfs_buf_map_pages(
                 bp->b_addr = page_address(bp->b_pages[0]) + bp->b_offset;
                 bp->b_flags |= XBF_MAPPED;
         } else if (flags & XBF_MAPPED) {
-                if (as_list_len > 64)
-                        purge_addresses();
-                bp->b_addr = vmap(bp->b_pages, bp->b_page_count,
-                                        VM_MAP, PAGE_KERNEL);
+                bp->b_addr = vm_map_ram(bp->b_pages, bp->b_page_count,
+                                        -1, PAGE_KERNEL);
                 if (unlikely(bp->b_addr == NULL))
                         return -ENOMEM;
                 bp->b_addr += bp->b_offset;
@@ -1051,22 +1003,30 @@ xfs_buf_ioerror(
 }
 
 int
-xfs_bawrite(
-        void                    *mp,
+xfs_bwrite(
+        struct xfs_mount        *mp,
         struct xfs_buf          *bp)
 {
-        trace_xfs_buf_bawrite(bp, _RET_IP_);
+        int                     iowait = (bp->b_flags & XBF_ASYNC) == 0;
+        int                     error = 0;
 
-        ASSERT(bp->b_bn != XFS_BUF_DADDR_NULL);
+        bp->b_strat = xfs_bdstrat_cb;
+        bp->b_mount = mp;
+        bp->b_flags |= XBF_WRITE;
+        if (!iowait)
+                bp->b_flags |= _XBF_RUN_QUEUES;
 
         xfs_buf_delwri_dequeue(bp);
+        xfs_buf_iostrategy(bp);
 
-        bp->b_flags &= ~(XBF_READ | XBF_DELWRI | XBF_READ_AHEAD);
-        bp->b_flags |= (XBF_WRITE | XBF_ASYNC | _XBF_RUN_QUEUES);
+        if (iowait) {
+                error = xfs_buf_iowait(bp);
+                if (error)
+                        xfs_force_shutdown(mp, SHUTDOWN_META_IO_ERROR);
+                xfs_buf_relse(bp);
+        }
 
-        bp->b_mount = mp;
-        bp->b_strat = xfs_bdstrat_cb;
-        return xfs_bdstrat_cb(bp);
+        return error;
 }
 
 void
@@ -1085,6 +1045,126 @@ xfs_bdwrite(
         xfs_buf_delwri_queue(bp, 1);
 }
 
+/*
+ * Called when we want to stop a buffer from getting written or read.
+ * We attach the EIO error, muck with its flags, and call biodone
+ * so that the proper iodone callbacks get called.
+ */
+STATIC int
+xfs_bioerror(
+        xfs_buf_t *bp)
+{
+#ifdef XFSERRORDEBUG
+        ASSERT(XFS_BUF_ISREAD(bp) || bp->b_iodone);
+#endif
+
+        /*
+         * No need to wait until the buffer is unpinned, we aren't flushing it.
+         */
+        XFS_BUF_ERROR(bp, EIO);
+
+        /*
+         * We're calling biodone, so delete XBF_DONE flag.
+         */
+        XFS_BUF_UNREAD(bp);
+        XFS_BUF_UNDELAYWRITE(bp);
+        XFS_BUF_UNDONE(bp);
+        XFS_BUF_STALE(bp);
+
+        XFS_BUF_CLR_BDSTRAT_FUNC(bp);
+        xfs_biodone(bp);
+
+        return EIO;
+}
+
+/*
+ * Same as xfs_bioerror, except that we are releasing the buffer
+ * here ourselves, and avoiding the biodone call.
+ * This is meant for userdata errors; metadata bufs come with
+ * iodone functions attached, so that we can track down errors.
+ */
+STATIC int
+xfs_bioerror_relse(
+        struct xfs_buf  *bp)
+{
+        int64_t         fl = XFS_BUF_BFLAGS(bp);
+        /*
+         * No need to wait until the buffer is unpinned.
+         * We aren't flushing it.
+         *
+         * chunkhold expects B_DONE to be set, whether
+         * we actually finish the I/O or not. We don't want to
+         * change that interface.
+         */
+        XFS_BUF_UNREAD(bp);
+        XFS_BUF_UNDELAYWRITE(bp);
+        XFS_BUF_DONE(bp);
+        XFS_BUF_STALE(bp);
+        XFS_BUF_CLR_IODONE_FUNC(bp);
+        XFS_BUF_CLR_BDSTRAT_FUNC(bp);
+        if (!(fl & XBF_ASYNC)) {
+                /*
+                 * Mark b_error and B_ERROR _both_.
+                 * Lot's of chunkcache code assumes that.
+                 * There's no reason to mark error for
+                 * ASYNC buffers.
+                 */
+                XFS_BUF_ERROR(bp, EIO);
+                XFS_BUF_FINISH_IOWAIT(bp);
+        } else {
+                xfs_buf_relse(bp);
+        }
+
+        return EIO;
+}
+
+
+/*
+ * All xfs metadata buffers except log state machine buffers
+ * get this attached as their b_bdstrat callback function.
+ * This is so that we can catch a buffer
+ * after prematurely unpinning it to forcibly shutdown the filesystem.
+ */
+int
+xfs_bdstrat_cb(
+        struct xfs_buf  *bp)
+{
+        if (XFS_FORCED_SHUTDOWN(bp->b_mount)) {
+                trace_xfs_bdstrat_shut(bp, _RET_IP_);
+                /*
+                 * Metadata write that didn't get logged but
+                 * written delayed anyway. These aren't associated
+                 * with a transaction, and can be ignored.
+                 */
+                if (!bp->b_iodone && !XFS_BUF_ISREAD(bp))
+                        return xfs_bioerror_relse(bp);
+                else
+                        return xfs_bioerror(bp);
+        }
+
+        xfs_buf_iorequest(bp);
+        return 0;
+}
+
+/*
+ * 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.
+ */
+void
+xfsbdstrat(
+        struct xfs_mount        *mp,
+        struct xfs_buf          *bp)
+{
+        if (XFS_FORCED_SHUTDOWN(mp)) {
+                trace_xfs_bdstrat_shut(bp, _RET_IP_);
+                xfs_bioerror_relse(bp);
+                return;
+        }
+
+        xfs_buf_iorequest(bp);
+}
+
 STATIC void
 _xfs_buf_ioend(
         xfs_buf_t               *bp,
@@ -1107,6 +1187,9 @@ xfs_buf_bio_end_io(
 
         xfs_buf_ioerror(bp, -error);
 
+        if (!error && xfs_buf_is_vmapped(bp) && (bp->b_flags & XBF_READ))
+                invalidate_kernel_vmap_range(bp->b_addr, xfs_buf_vmap_len(bp));
+
         do {
                 struct page     *page = bvec->bv_page;
 
@@ -1216,6 +1299,10 @@ next_chunk:
 
 submit_io:
         if (likely(bio->bi_size)) {
+                if (xfs_buf_is_vmapped(bp)) {
+                        flush_kernel_vmap_range(bp->b_addr,
+                                                xfs_buf_vmap_len(bp));
+                }
                 submit_bio(rw, bio);
                 if (size)
                         goto next_chunk;
@@ -1296,7 +1383,7 @@ xfs_buf_iomove(
         xfs_buf_t               *bp,    /* buffer to process            */
         size_t                  boff,   /* starting buffer offset       */
         size_t                  bsize,  /* length to copy               */
-        caddr_t                 data,   /* data address                 */
+        void                    *data,  /* data address                 */
         xfs_buf_rw_t            mode)   /* read/write/zero flag         */
 {
         size_t                  bend, cpoff, csize;
@@ -1378,8 +1465,8 @@ xfs_alloc_bufhash(
 
         btp->bt_hashshift = external ? 3 : 8;   /* 8 or 256 buckets */
         btp->bt_hashmask = (1 << btp->bt_hashshift) - 1;
-        btp->bt_hash = kmem_zalloc((1 << btp->bt_hashshift) *
-                                        sizeof(xfs_bufhash_t), KM_SLEEP | KM_LARGE);
+        btp->bt_hash = kmem_zalloc_large((1 << btp->bt_hashshift) *
+                                         sizeof(xfs_bufhash_t));
         for (i = 0; i < (1 << btp->bt_hashshift); i++) {
                 spin_lock_init(&btp->bt_hash[i].bh_lock);
                 INIT_LIST_HEAD(&btp->bt_hash[i].bh_list);
@@ -1390,7 +1477,7 @@ STATIC void
 xfs_free_bufhash(
         xfs_buftarg_t           *btp)
 {
-        kmem_free(btp->bt_hash);
+        kmem_free_large(btp->bt_hash);
         btp->bt_hash = NULL;
 }
 
@@ -1595,6 +1682,11 @@ xfs_buf_delwri_queue(
                 list_del(&bp->b_list);
         }
 
+        if (list_empty(dwq)) {
+                /* start xfsbufd as it is about to have something to do */
+                wake_up_process(bp->b_target->bt_task);
+        }
+
         bp->b_flags |= _XBF_DELWRI_Q;
         list_add_tail(&bp->b_list, dwq);
         bp->b_queuetime = jiffies;
@@ -1626,6 +1718,35 @@ xfs_buf_delwri_dequeue(
         trace_xfs_buf_delwri_dequeue(bp, _RET_IP_);
 }
 
+/*
+ * If a delwri buffer needs to be pushed before it has aged out, then promote
+ * it to the head of the delwri queue so that it will be flushed on the next
+ * xfsbufd run. We do this by resetting the queuetime of the buffer to be older
+ * than the age currently needed to flush the buffer. Hence the next time the
+ * xfsbufd sees it is guaranteed to be considered old enough to flush.
+ */
+void
+xfs_buf_delwri_promote(
+        struct xfs_buf  *bp)
+{
+        struct xfs_buftarg *btp = bp->b_target;
+        long            age = xfs_buf_age_centisecs * msecs_to_jiffies(10) + 1;
+
+        ASSERT(bp->b_flags & XBF_DELWRI);
+        ASSERT(bp->b_flags & _XBF_DELWRI_Q);
+
+        /*
+         * Check the buffer age before locking the delayed write queue as we
+         * don't need to promote buffers that are already past the flush age.
+         */
+        if (bp->b_queuetime < jiffies - age)
+                return;
+        bp->b_queuetime = jiffies - age;
+        spin_lock(&btp->bt_delwrite_lock);
+        list_move(&bp->b_list, &btp->bt_delwrite_queue);
+        spin_unlock(&btp->bt_delwrite_lock);
+}
+
 STATIC void
 xfs_buf_runall_queues(
         struct workqueue_struct *queue)
@@ -1644,6 +1765,8 @@ xfsbufd_wakeup(
         list_for_each_entry(btp, &xfs_buftarg_list, bt_list) {
                 if (test_bit(XBT_FORCE_SLEEP, &btp->bt_flags))
                         continue;
+                if (list_empty(&btp->bt_delwrite_queue))
+                        continue;
                 set_bit(XBT_FORCE_FLUSH, &btp->bt_flags);
                 wake_up_process(btp->bt_task);
         }
@@ -1694,20 +1817,53 @@ xfs_buf_delwri_split(
 
 }
 
+/*
+ * Compare function is more complex than it needs to be because
+ * the return value is only 32 bits and we are doing comparisons
+ * on 64 bit values
+ */
+static int
+xfs_buf_cmp(
+        void            *priv,
+        struct list_head *a,
+        struct list_head *b)
+{
+        struct xfs_buf  *ap = container_of(a, struct xfs_buf, b_list);
+        struct xfs_buf  *bp = container_of(b, struct xfs_buf, b_list);
+        xfs_daddr_t             diff;
+
+        diff = ap->b_bn - bp->b_bn;
+        if (diff < 0)
+                return -1;
+        if (diff > 0)
+                return 1;
+        return 0;
+}
+
+void
+xfs_buf_delwri_sort(
+        xfs_buftarg_t   *target,
+        struct list_head *list)
+{
+        list_sort(NULL, list, xfs_buf_cmp);
+}
+
 STATIC int
 xfsbufd(
         void            *data)
 {
-        struct list_head tmp;
-        xfs_buftarg_t   *target = (xfs_buftarg_t *)data;
-        int             count;
-        xfs_buf_t       *bp;
+        xfs_buftarg_t   *target = (xfs_buftarg_t *)data;
 
         current->flags |= PF_MEMALLOC;
 
         set_freezable();
 
         do {
+                long    age = xfs_buf_age_centisecs * msecs_to_jiffies(10);
+                long    tout = xfs_buf_timer_centisecs * msecs_to_jiffies(10);
+                int     count = 0;
+                struct list_head tmp;
+
                 if (unlikely(freezing(current))) {
                         set_bit(XBT_FORCE_SLEEP, &target->bt_flags);
                         refrigerator();
@@ -1715,24 +1871,20 @@ xfsbufd(
                         clear_bit(XBT_FORCE_SLEEP, &target->bt_flags);
                 }
 
-                schedule_timeout_interruptible(
-                        xfs_buf_timer_centisecs * msecs_to_jiffies(10));
+                /* sleep for a long time if there is nothing to do. */
+                if (list_empty(&target->bt_delwrite_queue))
+                        tout = MAX_SCHEDULE_TIMEOUT;
+                schedule_timeout_interruptible(tout);
 
-                xfs_buf_delwri_split(target, &tmp,
-                                xfs_buf_age_centisecs * msecs_to_jiffies(10));
-
-                count = 0;
+                xfs_buf_delwri_split(target, &tmp, age);
+                list_sort(NULL, &tmp, xfs_buf_cmp);
                 while (!list_empty(&tmp)) {
-                        bp = list_entry(tmp.next, xfs_buf_t, b_list);
-                        ASSERT(target == bp->b_target);
-
+                        struct xfs_buf *bp;
+                        bp = list_first_entry(&tmp, struct xfs_buf, b_list);
                         list_del_init(&bp->b_list);
                         xfs_buf_iostrategy(bp);
                         count++;
                 }
-
-                if (as_list_len > 0)
-                        purge_addresses();
                 if (count)
                         blk_run_address_space(target->bt_mapping);
 
@@ -1751,42 +1903,45 @@ xfs_flush_buftarg(
         xfs_buftarg_t   *target,
         int             wait)
 {
-        struct list_head tmp;
-        xfs_buf_t       *bp, *n;
+        xfs_buf_t       *bp;
         int             pincount = 0;
+        LIST_HEAD(tmp_list);
+        LIST_HEAD(wait_list);
 
         xfs_buf_runall_queues(xfsconvertd_workqueue);
         xfs_buf_runall_queues(xfsdatad_workqueue);
         xfs_buf_runall_queues(xfslogd_workqueue);
 
         set_bit(XBT_FORCE_FLUSH, &target->bt_flags);
-        pincount = xfs_buf_delwri_split(target, &tmp, 0);
+        pincount = xfs_buf_delwri_split(target, &tmp_list, 0);
 
         /*
-         * Dropped the delayed write list lock, now walk the temporary list
+         * Dropped the delayed write list lock, now walk the temporary list.
+         * All I/O is issued async and then if we need to wait for completion
+         * we do that after issuing all the IO.
          */
-        list_for_each_entry_safe(bp, n, &tmp, b_list) {
+        list_sort(NULL, &tmp_list, xfs_buf_cmp);
+        while (!list_empty(&tmp_list)) {
+                bp = list_first_entry(&tmp_list, struct xfs_buf, b_list);
                 ASSERT(target == bp->b_target);
-                if (wait)
+                list_del_init(&bp->b_list);
+                if (wait) {
                         bp->b_flags &= ~XBF_ASYNC;
-                else
-                        list_del_init(&bp->b_list);
-
+                        list_add(&bp->b_list, &wait_list);
+                }
                 xfs_buf_iostrategy(bp);
         }
 
-        if (wait)
+        if (wait) {
+                /* Expedite and wait for IO to complete. */
                 blk_run_address_space(target->bt_mapping);
+                while (!list_empty(&wait_list)) {
+                        bp = list_first_entry(&wait_list, struct xfs_buf, b_list);
 
-        /*
-         * Remaining list items must be flushed before returning
-         */
-        while (!list_empty(&tmp)) {
-                bp = list_entry(tmp.next, xfs_buf_t, b_list);
-
-                list_del_init(&bp->b_list);
-                xfs_iowait(bp);
-                xfs_buf_relse(bp);
+                        list_del_init(&bp->b_list);
+                        xfs_iowait(bp);
+                        xfs_buf_relse(bp);
+                }
         }
 
         return pincount;
diff --git a/fs/xfs/linux-2.6/xfs_buf.h b/fs/xfs/linux-2.6/xfs_buf.h
index a34c7b54822d..386e7361e50e 100644
--- a/fs/xfs/linux-2.6/xfs_buf.h
+++ b/fs/xfs/linux-2.6/xfs_buf.h
@@ -232,13 +232,17 @@ extern void xfs_buf_lock(xfs_buf_t *);
 extern void xfs_buf_unlock(xfs_buf_t *);
 
 /* Buffer Read and Write Routines */
-extern int xfs_bawrite(void *mp, xfs_buf_t *bp);
+extern int xfs_bwrite(struct xfs_mount *mp, struct xfs_buf *bp);
 extern void xfs_bdwrite(void *mp, xfs_buf_t *bp);
+
+extern void xfsbdstrat(struct xfs_mount *, struct xfs_buf *);
+extern int xfs_bdstrat_cb(struct xfs_buf *);
+
 extern void xfs_buf_ioend(xfs_buf_t *,  int);
 extern void xfs_buf_ioerror(xfs_buf_t *, int);
 extern int xfs_buf_iorequest(xfs_buf_t *);
 extern int xfs_buf_iowait(xfs_buf_t *);
-extern void xfs_buf_iomove(xfs_buf_t *, size_t, size_t, xfs_caddr_t,
+extern void xfs_buf_iomove(xfs_buf_t *, size_t, size_t, void *,
                                 xfs_buf_rw_t);
 
 static inline int xfs_buf_iostrategy(xfs_buf_t *bp)
@@ -261,6 +265,7 @@ extern int xfs_buf_ispin(xfs_buf_t *);
 
 /* Delayed Write Buffer Routines */
 extern void xfs_buf_delwri_dequeue(xfs_buf_t *);
+extern void xfs_buf_delwri_promote(xfs_buf_t *);
 
 /* Buffer Daemon Setup Routines */
 extern int xfs_buf_init(void);
@@ -270,33 +275,19 @@ extern void xfs_buf_terminate(void);
         ({ char __b[BDEVNAME_SIZE]; bdevname((target)->bt_bdev, __b); __b; })
 
 
-#define XFS_B_ASYNC             XBF_ASYNC
-#define XFS_B_DELWRI            XBF_DELWRI
-#define XFS_B_READ              XBF_READ
-#define XFS_B_WRITE             XBF_WRITE
-#define XFS_B_STALE             XBF_STALE
-
-#define XFS_BUF_TRYLOCK         XBF_TRYLOCK
-#define XFS_INCORE_TRYLOCK      XBF_TRYLOCK
-#define XFS_BUF_LOCK            XBF_LOCK
-#define XFS_BUF_MAPPED          XBF_MAPPED
-
-#define BUF_BUSY                XBF_DONT_BLOCK
-
 #define XFS_BUF_BFLAGS(bp)      ((bp)->b_flags)
 #define XFS_BUF_ZEROFLAGS(bp)   ((bp)->b_flags &= \
                 ~(XBF_READ|XBF_WRITE|XBF_ASYNC|XBF_DELWRI|XBF_ORDERED))
 
-#define XFS_BUF_STALE(bp)       ((bp)->b_flags |= XFS_B_STALE)
-#define XFS_BUF_UNSTALE(bp)     ((bp)->b_flags &= ~XFS_B_STALE)
-#define XFS_BUF_ISSTALE(bp)     ((bp)->b_flags & XFS_B_STALE)
+#define XFS_BUF_STALE(bp)       ((bp)->b_flags |= XBF_STALE)
+#define XFS_BUF_UNSTALE(bp)     ((bp)->b_flags &= ~XBF_STALE)
+#define XFS_BUF_ISSTALE(bp)     ((bp)->b_flags & XBF_STALE)
 #define XFS_BUF_SUPER_STALE(bp) do {                            \
                                         XFS_BUF_STALE(bp);      \
                                         xfs_buf_delwri_dequeue(bp);     \
                                         XFS_BUF_DONE(bp);       \
                                 } while (0)
 
-#define XFS_BUF_MANAGE          XBF_FS_MANAGED
 #define XFS_BUF_UNMANAGE(bp)    ((bp)->b_flags &= ~XBF_FS_MANAGED)
 
 #define XFS_BUF_DELAYWRITE(bp)          ((bp)->b_flags |= XBF_DELWRI)
@@ -385,31 +376,11 @@ static inline void xfs_buf_relse(xfs_buf_t *bp)
 
 #define xfs_biomove(bp, off, len, data, rw) \
             xfs_buf_iomove((bp), (off), (len), (data), \
-                ((rw) == XFS_B_WRITE) ? XBRW_WRITE : XBRW_READ)
+                ((rw) == XBF_WRITE) ? XBRW_WRITE : XBRW_READ)
 
 #define xfs_biozero(bp, off, len) \
             xfs_buf_iomove((bp), (off), (len), NULL, XBRW_ZERO)
 
-
-static inline int XFS_bwrite(xfs_buf_t *bp)
-{
-        int     iowait = (bp->b_flags & XBF_ASYNC) == 0;
-        int     error = 0;
-
-        if (!iowait)
-                bp->b_flags |= _XBF_RUN_QUEUES;
-
-        xfs_buf_delwri_dequeue(bp);
-        xfs_buf_iostrategy(bp);
-        if (iowait) {
-                error = xfs_buf_iowait(bp);
-                xfs_buf_relse(bp);
-        }
-        return error;
-}
-
-#define XFS_bdstrat(bp) xfs_buf_iorequest(bp)
-
 #define xfs_iowait(bp)  xfs_buf_iowait(bp)
 
 #define xfs_baread(target, rablkno, ralen)  \
@@ -424,6 +395,7 @@ extern void xfs_free_buftarg(struct xfs_mount *, struct xfs_buftarg *);
 extern void xfs_wait_buftarg(xfs_buftarg_t *);
 extern int xfs_setsize_buftarg(xfs_buftarg_t *, unsigned int, unsigned int);
 extern int xfs_flush_buftarg(xfs_buftarg_t *, int);
+
 #ifdef CONFIG_KDB_MODULES
 extern struct list_head *xfs_get_buftarg_list(void);
 #endif
diff --git a/fs/xfs/linux-2.6/xfs_export.c b/fs/xfs/linux-2.6/xfs_export.c
index 87b8cbd23d4b..846b75aeb2ab 100644
--- a/fs/xfs/linux-2.6/xfs_export.c
+++ b/fs/xfs/linux-2.6/xfs_export.c
@@ -29,6 +29,7 @@
 #include "xfs_vnodeops.h"
 #include "xfs_bmap_btree.h"
 #include "xfs_inode.h"
+#include "xfs_inode_item.h"
 
 /*
  * Note that we only accept fileids which are long enough rather than allow
@@ -215,9 +216,28 @@ xfs_fs_get_parent(
         return d_obtain_alias(VFS_I(cip));
 }
 
+STATIC int
+xfs_fs_nfs_commit_metadata(
+        struct inode            *inode)
+{
+        struct xfs_inode        *ip = XFS_I(inode);
+        struct xfs_mount        *mp = ip->i_mount;
+        int                     error = 0;
+
+        xfs_ilock(ip, XFS_ILOCK_SHARED);
+        if (xfs_ipincount(ip)) {
+                error = _xfs_log_force_lsn(mp, ip->i_itemp->ili_last_lsn,
+                                XFS_LOG_SYNC, NULL);
+        }
+        xfs_iunlock(ip, XFS_ILOCK_SHARED);
+
+        return error;
+}
+
 const struct export_operations xfs_export_operations = {
         .encode_fh              = xfs_fs_encode_fh,
         .fh_to_dentry           = xfs_fs_fh_to_dentry,
         .fh_to_parent           = xfs_fs_fh_to_parent,
         .get_parent             = xfs_fs_get_parent,
+        .commit_metadata        = xfs_fs_nfs_commit_metadata,
 };
diff --git a/fs/xfs/linux-2.6/xfs_file.c b/fs/xfs/linux-2.6/xfs_file.c
index e4caeb28ce2e..42dd3bcfba6b 100644
--- a/fs/xfs/linux-2.6/xfs_file.c
+++ b/fs/xfs/linux-2.6/xfs_file.c
@@ -16,6 +16,7 @@
  * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
  */
 #include "xfs.h"
+#include "xfs_fs.h"
 #include "xfs_bit.h"
 #include "xfs_log.h"
 #include "xfs_inum.h"
@@ -34,52 +35,279 @@
 #include "xfs_dir2_sf.h"
 #include "xfs_dinode.h"
 #include "xfs_inode.h"
+#include "xfs_inode_item.h"
+#include "xfs_bmap.h"
 #include "xfs_error.h"
 #include "xfs_rw.h"
 #include "xfs_vnodeops.h"
 #include "xfs_da_btree.h"
 #include "xfs_ioctl.h"
+#include "xfs_trace.h"
 
 #include <linux/dcache.h>
 
 static const struct vm_operations_struct xfs_file_vm_ops;
 
-STATIC ssize_t
-xfs_file_aio_read(
-        struct kiocb            *iocb,
-        const struct iovec      *iov,
-        unsigned long           nr_segs,
-        loff_t                  pos)
+/*
+ *      xfs_iozero
+ *
+ *      xfs_iozero clears the specified range of buffer supplied,
+ *      and marks all the affected blocks as valid and modified.  If
+ *      an affected block is not allocated, it will be allocated.  If
+ *      an affected block is not completely overwritten, and is not
+ *      valid before the operation, it will be read from disk before
+ *      being partially zeroed.
+ */
+STATIC int
+xfs_iozero(
+        struct xfs_inode        *ip,    /* inode                        */
+        loff_t                  pos,    /* offset in file               */
+        size_t                  count)  /* size of data to zero         */
 {
-        struct file             *file = iocb->ki_filp;
-        int                     ioflags = 0;
+        struct page             *page;
+        struct address_space    *mapping;
+        int                     status;
 
-        BUG_ON(iocb->ki_pos != pos);
-        if (unlikely(file->f_flags & O_DIRECT))
-                ioflags |= IO_ISDIRECT;
-        if (file->f_mode & FMODE_NOCMTIME)
-                ioflags |= IO_INVIS;
-        return xfs_read(XFS_I(file->f_path.dentry->d_inode), iocb, iov,
-                                nr_segs, &iocb->ki_pos, ioflags);
+        mapping = VFS_I(ip)->i_mapping;
+        do {
+                unsigned offset, bytes;
+                void *fsdata;
+
+                offset = (pos & (PAGE_CACHE_SIZE -1)); /* Within page */
+                bytes = PAGE_CACHE_SIZE - offset;
+                if (bytes > count)
+                        bytes = count;
+
+                status = pagecache_write_begin(NULL, mapping, pos, bytes,
+                                        AOP_FLAG_UNINTERRUPTIBLE,
+                                        &page, &fsdata);
+                if (status)
+                        break;
+
+                zero_user(page, offset, bytes);
+
+                status = pagecache_write_end(NULL, mapping, pos, bytes, bytes,
+                                        page, fsdata);
+                WARN_ON(status <= 0); /* can't return less than zero! */
+                pos += bytes;
+                count -= bytes;
+                status = 0;
+        } while (count);
+
+        return (-status);
+}
+
+STATIC int
+xfs_file_fsync(
+        struct file             *file,
+        struct dentry           *dentry,
+        int                     datasync)
+{
+        struct xfs_inode        *ip = XFS_I(dentry->d_inode);
+        struct xfs_trans        *tp;
+        int                     error = 0;
+        int                     log_flushed = 0;
+
+        xfs_itrace_entry(ip);
+
+        if (XFS_FORCED_SHUTDOWN(ip->i_mount))
+                return -XFS_ERROR(EIO);
+
+        xfs_iflags_clear(ip, XFS_ITRUNCATED);
+
+        /*
+         * We always need to make sure that the required inode state is safe on
+         * disk.  The inode might be clean but we still might need to force the
+         * log because of committed transactions that haven't hit the disk yet.
+         * Likewise, there could be unflushed non-transactional changes to the
+         * inode core that have to go to disk and this requires us to issue
+         * a synchronous transaction to capture these changes correctly.
+         *
+         * This code relies on the assumption that if the i_update_core field
+         * of the inode is clear and the inode is unpinned then it is clean
+         * and no action is required.
+         */
+        xfs_ilock(ip, XFS_ILOCK_SHARED);
+
+        /*
+         * First check if the VFS inode is marked dirty.  All the dirtying
+         * of non-transactional updates no goes through mark_inode_dirty*,
+         * which allows us to distinguish beteeen pure timestamp updates
+         * and i_size updates which need to be caught for fdatasync.
+         * After that also theck for the dirty state in the XFS inode, which
+         * might gets cleared when the inode gets written out via the AIL
+         * or xfs_iflush_cluster.
+         */
+        if (((dentry->d_inode->i_state & I_DIRTY_DATASYNC) ||
+            ((dentry->d_inode->i_state & I_DIRTY_SYNC) && !datasync)) &&
+            ip->i_update_core) {
+                /*
+                 * Kick off a transaction to log the inode core to get the
+                 * updates.  The sync transaction will also force the log.
+                 */
+                xfs_iunlock(ip, XFS_ILOCK_SHARED);
+                tp = xfs_trans_alloc(ip->i_mount, XFS_TRANS_FSYNC_TS);
+                error = xfs_trans_reserve(tp, 0,
+                                XFS_FSYNC_TS_LOG_RES(ip->i_mount), 0, 0, 0);
+                if (error) {
+                        xfs_trans_cancel(tp, 0);
+                        return -error;
+                }
+                xfs_ilock(ip, XFS_ILOCK_EXCL);
+
+                /*
+                 * Note - it's possible that we might have pushed ourselves out
+                 * of the way during trans_reserve which would flush the inode.
+                 * But there's no guarantee that the inode buffer has actually
+                 * gone out yet (it's delwri).  Plus the buffer could be pinned
+                 * anyway if it's part of an inode in another recent
+                 * transaction.  So we play it safe and fire off the
+                 * transaction anyway.
+                 */
+                xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
+                xfs_trans_ihold(tp, ip);
+                xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+                xfs_trans_set_sync(tp);
+                error = _xfs_trans_commit(tp, 0, &log_flushed);
+
+                xfs_iunlock(ip, XFS_ILOCK_EXCL);
+        } else {
+                /*
+                 * Timestamps/size haven't changed since last inode flush or
+                 * inode transaction commit.  That means either nothing got
+                 * written or a transaction committed which caught the updates.
+                 * If the latter happened and the transaction hasn't hit the
+                 * disk yet, the inode will be still be pinned.  If it is,
+                 * force the log.
+                 */
+                if (xfs_ipincount(ip)) {
+                        error = _xfs_log_force_lsn(ip->i_mount,
+                                        ip->i_itemp->ili_last_lsn,
+                                        XFS_LOG_SYNC, &log_flushed);
+                }
+                xfs_iunlock(ip, XFS_ILOCK_SHARED);
+        }
+
+        if (ip->i_mount->m_flags & XFS_MOUNT_BARRIER) {
+                /*
+                 * If the log write didn't issue an ordered tag we need
+                 * to flush the disk cache for the data device now.
+                 */
+                if (!log_flushed)
+                        xfs_blkdev_issue_flush(ip->i_mount->m_ddev_targp);
+
+                /*
+                 * If this inode is on the RT dev we need to flush that
+                 * cache as well.
+                 */
+                if (XFS_IS_REALTIME_INODE(ip))
+                        xfs_blkdev_issue_flush(ip->i_mount->m_rtdev_targp);
+        }
+
+        return -error;
 }
 
 STATIC ssize_t
-xfs_file_aio_write(
+xfs_file_aio_read(
         struct kiocb            *iocb,
-        const struct iovec      *iov,
+        const struct iovec      *iovp,
         unsigned long           nr_segs,
         loff_t                  pos)
 {
         struct file             *file = iocb->ki_filp;
+        struct inode            *inode = file->f_mapping->host;
+        struct xfs_inode        *ip = XFS_I(inode);
+        struct xfs_mount        *mp = ip->i_mount;
+        size_t                  size = 0;
+        ssize_t                 ret = 0;
         int                     ioflags = 0;
+        xfs_fsize_t             n;
+        unsigned long           seg;
+
+        XFS_STATS_INC(xs_read_calls);
 
         BUG_ON(iocb->ki_pos != pos);
+
         if (unlikely(file->f_flags & O_DIRECT))
                 ioflags |= IO_ISDIRECT;
         if (file->f_mode & FMODE_NOCMTIME)
                 ioflags |= IO_INVIS;
-        return xfs_write(XFS_I(file->f_mapping->host), iocb, iov, nr_segs,
-                                &iocb->ki_pos, ioflags);
+
+        /* START copy & waste from filemap.c */
+        for (seg = 0; seg < nr_segs; seg++) {
+                const struct iovec *iv = &iovp[seg];
+
+                /*
+                 * If any segment has a negative length, or the cumulative
+                 * length ever wraps negative then return -EINVAL.
+                 */
+                size += iv->iov_len;
+                if (unlikely((ssize_t)(size|iv->iov_len) < 0))
+                        return XFS_ERROR(-EINVAL);
+        }
+        /* END copy & waste from filemap.c */
+
+        if (unlikely(ioflags & IO_ISDIRECT)) {
+                xfs_buftarg_t   *target =
+                        XFS_IS_REALTIME_INODE(ip) ?
+                                mp->m_rtdev_targp : mp->m_ddev_targp;
+                if ((iocb->ki_pos & target->bt_smask) ||
+                    (size & target->bt_smask)) {
+                        if (iocb->ki_pos == ip->i_size)
+                                return 0;
+                        return -XFS_ERROR(EINVAL);
+                }
+        }
+
+        n = XFS_MAXIOFFSET(mp) - iocb->ki_pos;
+        if (n <= 0 || size == 0)
+                return 0;
+
+        if (n < size)
+                size = n;
+
+        if (XFS_FORCED_SHUTDOWN(mp))
+                return -EIO;
+
+        if (unlikely(ioflags & IO_ISDIRECT))
+                mutex_lock(&inode->i_mutex);
+        xfs_ilock(ip, XFS_IOLOCK_SHARED);
+
+        if (DM_EVENT_ENABLED(ip, DM_EVENT_READ) && !(ioflags & IO_INVIS)) {
+                int dmflags = FILP_DELAY_FLAG(file) | DM_SEM_FLAG_RD(ioflags);
+                int iolock = XFS_IOLOCK_SHARED;
+
+                ret = -XFS_SEND_DATA(mp, DM_EVENT_READ, ip, iocb->ki_pos, size,
+                                        dmflags, &iolock);
+                if (ret) {
+                        xfs_iunlock(ip, XFS_IOLOCK_SHARED);
+                        if (unlikely(ioflags & IO_ISDIRECT))
+                                mutex_unlock(&inode->i_mutex);
+                        return ret;
+                }
+        }
+
+        if (unlikely(ioflags & IO_ISDIRECT)) {
+                if (inode->i_mapping->nrpages) {
+                        ret = -xfs_flushinval_pages(ip,
+                                        (iocb->ki_pos & PAGE_CACHE_MASK),
+                                        -1, FI_REMAPF_LOCKED);
+                }
+                mutex_unlock(&inode->i_mutex);
+                if (ret) {
+                        xfs_iunlock(ip, XFS_IOLOCK_SHARED);
+                        return ret;
+                }
+        }
+
+        trace_xfs_file_read(ip, size, iocb->ki_pos, ioflags);
+
+        ret = generic_file_aio_read(iocb, iovp, nr_segs, iocb->ki_pos);
+        if (ret > 0)
+                XFS_STATS_ADD(xs_read_bytes, ret);
+
+        xfs_iunlock(ip, XFS_IOLOCK_SHARED);
+        return ret;
 }
 
 STATIC ssize_t
@@ -87,16 +315,44 @@ xfs_file_splice_read(
         struct file             *infilp,
         loff_t                  *ppos,
         struct pipe_inode_info  *pipe,
-        size_t                  len,
+        size_t                  count,
         unsigned int            flags)
 {
+        struct xfs_inode        *ip = XFS_I(infilp->f_mapping->host);
+        struct xfs_mount        *mp = ip->i_mount;
         int                     ioflags = 0;
+        ssize_t                 ret;
+
+        XFS_STATS_INC(xs_read_calls);
 
         if (infilp->f_mode & FMODE_NOCMTIME)
                 ioflags |= IO_INVIS;
 
-        return xfs_splice_read(XFS_I(infilp->f_path.dentry->d_inode),
-                                   infilp, ppos, pipe, len, flags, ioflags);
+        if (XFS_FORCED_SHUTDOWN(ip->i_mount))
+                return -EIO;
+
+        xfs_ilock(ip, XFS_IOLOCK_SHARED);
+
+        if (DM_EVENT_ENABLED(ip, DM_EVENT_READ) && !(ioflags & IO_INVIS)) {
+                int iolock = XFS_IOLOCK_SHARED;
+                int error;
+
+                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;
+                }
+        }
+
+        trace_xfs_file_splice_read(ip, count, *ppos, ioflags);
+
+        ret = generic_file_splice_read(infilp, ppos, pipe, count, flags);
+        if (ret > 0)
+                XFS_STATS_ADD(xs_read_bytes, ret);
+
+        xfs_iunlock(ip, XFS_IOLOCK_SHARED);
+        return ret;
 }
 
 STATIC ssize_t
@@ -104,16 +360,538 @@ xfs_file_splice_write(
         struct pipe_inode_info  *pipe,
         struct file             *outfilp,
         loff_t                  *ppos,
-        size_t                  len,
+        size_t                  count,
         unsigned int            flags)
 {
+        struct inode            *inode = outfilp->f_mapping->host;
+        struct xfs_inode        *ip = XFS_I(inode);
+        struct xfs_mount        *mp = ip->i_mount;
+        xfs_fsize_t             isize, new_size;
         int                     ioflags = 0;
+        ssize_t                 ret;
+
+        XFS_STATS_INC(xs_write_calls);
 
         if (outfilp->f_mode & FMODE_NOCMTIME)
                 ioflags |= IO_INVIS;
 
-        return xfs_splice_write(XFS_I(outfilp->f_path.dentry->d_inode),
-                                    pipe, outfilp, ppos, len, flags, ioflags);
+        if (XFS_FORCED_SHUTDOWN(ip->i_mount))
+                return -EIO;
+
+        xfs_ilock(ip, XFS_IOLOCK_EXCL);
+
+        if (DM_EVENT_ENABLED(ip, DM_EVENT_WRITE) && !(ioflags & IO_INVIS)) {
+                int iolock = XFS_IOLOCK_EXCL;
+                int error;
+
+                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;
+                }
+        }
+
+        new_size = *ppos + count;
+
+        xfs_ilock(ip, XFS_ILOCK_EXCL);
+        if (new_size > ip->i_size)
+                ip->i_new_size = new_size;
+        xfs_iunlock(ip, XFS_ILOCK_EXCL);
+
+        trace_xfs_file_splice_write(ip, count, *ppos, ioflags);
+
+        ret = generic_file_splice_write(pipe, outfilp, ppos, count, flags);
+        if (ret > 0)
+                XFS_STATS_ADD(xs_write_bytes, ret);
+
+        isize = i_size_read(inode);
+        if (unlikely(ret < 0 && ret != -EFAULT && *ppos > isize))
+                *ppos = isize;
+
+        if (*ppos > ip->i_size) {
+                xfs_ilock(ip, XFS_ILOCK_EXCL);
+                if (*ppos > ip->i_size)
+                        ip->i_size = *ppos;
+                xfs_iunlock(ip, XFS_ILOCK_EXCL);
+        }
+
+        if (ip->i_new_size) {
+                xfs_ilock(ip, XFS_ILOCK_EXCL);
+                ip->i_new_size = 0;
+                if (ip->i_d.di_size > ip->i_size)
+                        ip->i_d.di_size = ip->i_size;
+                xfs_iunlock(ip, XFS_ILOCK_EXCL);
+        }
+        xfs_iunlock(ip, XFS_IOLOCK_EXCL);
+        return ret;
+}
+
+/*
+ * This routine is called to handle zeroing any space in the last
+ * block of the file that is beyond the EOF.  We do this since the
+ * size is being increased without writing anything to that block
+ * and we don't want anyone to read the garbage on the disk.
+ */
+STATIC int                              /* error (positive) */
+xfs_zero_last_block(
+        xfs_inode_t     *ip,
+        xfs_fsize_t     offset,
+        xfs_fsize_t     isize)
+{
+        xfs_fileoff_t   last_fsb;
+        xfs_mount_t     *mp = ip->i_mount;
+        int             nimaps;
+        int             zero_offset;
+        int             zero_len;
+        int             error = 0;
+        xfs_bmbt_irec_t imap;
+
+        ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
+
+        zero_offset = XFS_B_FSB_OFFSET(mp, isize);
+        if (zero_offset == 0) {
+                /*
+                 * There are no extra bytes in the last block on disk to
+                 * zero, so return.
+                 */
+                return 0;
+        }
+
+        last_fsb = XFS_B_TO_FSBT(mp, isize);
+        nimaps = 1;
+        error = xfs_bmapi(NULL, ip, last_fsb, 1, 0, NULL, 0, &imap,
+                          &nimaps, NULL, NULL);
+        if (error) {
+                return error;
+        }
+        ASSERT(nimaps > 0);
+        /*
+         * If the block underlying isize is just a hole, then there
+         * is nothing to zero.
+         */
+        if (imap.br_startblock == HOLESTARTBLOCK) {
+                return 0;
+        }
+        /*
+         * Zero the part of the last block beyond the EOF, and write it
+         * out sync.  We need to drop the ilock while we do this so we
+         * don't deadlock when the buffer cache calls back to us.
+         */
+        xfs_iunlock(ip, XFS_ILOCK_EXCL);
+
+        zero_len = mp->m_sb.sb_blocksize - zero_offset;
+        if (isize + zero_len > offset)
+                zero_len = offset - isize;
+        error = xfs_iozero(ip, isize, zero_len);
+
+        xfs_ilock(ip, XFS_ILOCK_EXCL);
+        ASSERT(error >= 0);
+        return error;
+}
+
+/*
+ * Zero any on disk space between the current EOF and the new,
+ * larger EOF.  This handles the normal case of zeroing the remainder
+ * of the last block in the file and the unusual case of zeroing blocks
+ * out beyond the size of the file.  This second case only happens
+ * with fixed size extents and when the system crashes before the inode
+ * size was updated but after blocks were allocated.  If fill is set,
+ * then any holes in the range are filled and zeroed.  If not, the holes
+ * are left alone as holes.
+ */
+
+int                                     /* error (positive) */
+xfs_zero_eof(
+        xfs_inode_t     *ip,
+        xfs_off_t       offset,         /* starting I/O offset */
+        xfs_fsize_t     isize)          /* current inode size */
+{
+        xfs_mount_t     *mp = ip->i_mount;
+        xfs_fileoff_t   start_zero_fsb;
+        xfs_fileoff_t   end_zero_fsb;
+        xfs_fileoff_t   zero_count_fsb;
+        xfs_fileoff_t   last_fsb;
+        xfs_fileoff_t   zero_off;
+        xfs_fsize_t     zero_len;
+        int             nimaps;
+        int             error = 0;
+        xfs_bmbt_irec_t imap;
+
+        ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_IOLOCK_EXCL));
+        ASSERT(offset > isize);
+
+        /*
+         * First handle zeroing the block on which isize resides.
+         * We only zero a part of that block so it is handled specially.
+         */
+        error = xfs_zero_last_block(ip, offset, isize);
+        if (error) {
+                ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_IOLOCK_EXCL));
+                return error;
+        }
+
+        /*
+         * Calculate the range between the new size and the old
+         * where blocks needing to be zeroed may exist.  To get the
+         * block where the last byte in the file currently resides,
+         * we need to subtract one from the size and truncate back
+         * to a block boundary.  We subtract 1 in case the size is
+         * exactly on a block boundary.
+         */
+        last_fsb = isize ? XFS_B_TO_FSBT(mp, isize - 1) : (xfs_fileoff_t)-1;
+        start_zero_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)isize);
+        end_zero_fsb = XFS_B_TO_FSBT(mp, offset - 1);
+        ASSERT((xfs_sfiloff_t)last_fsb < (xfs_sfiloff_t)start_zero_fsb);
+        if (last_fsb == end_zero_fsb) {
+                /*
+                 * The size was only incremented on its last block.
+                 * We took care of that above, so just return.
+                 */
+                return 0;
+        }
+
+        ASSERT(start_zero_fsb <= end_zero_fsb);
+        while (start_zero_fsb <= end_zero_fsb) {
+                nimaps = 1;
+                zero_count_fsb = end_zero_fsb - start_zero_fsb + 1;
+                error = xfs_bmapi(NULL, ip, start_zero_fsb, zero_count_fsb,
+                                  0, NULL, 0, &imap, &nimaps, NULL, NULL);
+                if (error) {
+                        ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_IOLOCK_EXCL));
+                        return error;
+                }
+                ASSERT(nimaps > 0);
+
+                if (imap.br_state == XFS_EXT_UNWRITTEN ||
+                    imap.br_startblock == HOLESTARTBLOCK) {
+                        /*
+                         * This loop handles initializing pages that were
+                         * partially initialized by the code below this
+                         * loop. It basically zeroes the part of the page
+                         * that sits on a hole and sets the page as P_HOLE
+                         * and calls remapf if it is a mapped file.
+                         */
+                        start_zero_fsb = imap.br_startoff + imap.br_blockcount;
+                        ASSERT(start_zero_fsb <= (end_zero_fsb + 1));
+                        continue;
+                }
+
+                /*
+                 * There are blocks we need to zero.
+                 * Drop the inode lock while we're doing the I/O.
+                 * We'll still have the iolock to protect us.
+                 */
+                xfs_iunlock(ip, XFS_ILOCK_EXCL);
+
+                zero_off = XFS_FSB_TO_B(mp, start_zero_fsb);
+                zero_len = XFS_FSB_TO_B(mp, imap.br_blockcount);
+
+                if ((zero_off + zero_len) > offset)
+                        zero_len = offset - zero_off;
+
+                error = xfs_iozero(ip, zero_off, zero_len);
+                if (error) {
+                        goto out_lock;
+                }
+
+                start_zero_fsb = imap.br_startoff + imap.br_blockcount;
+                ASSERT(start_zero_fsb <= (end_zero_fsb + 1));
+
+                xfs_ilock(ip, XFS_ILOCK_EXCL);
+        }
+
+        return 0;
+
+out_lock:
+        xfs_ilock(ip, XFS_ILOCK_EXCL);
+        ASSERT(error >= 0);
+        return error;
+}
+
+STATIC ssize_t
+xfs_file_aio_write(
+        struct kiocb            *iocb,
+        const struct iovec      *iovp,
+        unsigned long           nr_segs,
+        loff_t                  pos)
+{
+        struct file             *file = iocb->ki_filp;
+        struct address_space    *mapping = file->f_mapping;
+        struct inode            *inode = mapping->host;
+        struct xfs_inode        *ip = XFS_I(inode);
+        struct xfs_mount        *mp = ip->i_mount;
+        ssize_t                 ret = 0, error = 0;
+        int                     ioflags = 0;
+        xfs_fsize_t             isize, new_size;
+        int                     iolock;
+        int                     eventsent = 0;
+        size_t                  ocount = 0, count;
+        int                     need_i_mutex;
+
+        XFS_STATS_INC(xs_write_calls);
+
+        BUG_ON(iocb->ki_pos != pos);
+
+        if (unlikely(file->f_flags & O_DIRECT))
+                ioflags |= IO_ISDIRECT;
+        if (file->f_mode & FMODE_NOCMTIME)
+                ioflags |= IO_INVIS;
+
+        error = generic_segment_checks(iovp, &nr_segs, &ocount, VERIFY_READ);
+        if (error)
+                return error;
+
+        count = ocount;
+        if (count == 0)
+                return 0;
+
+        xfs_wait_for_freeze(mp, SB_FREEZE_WRITE);
+
+        if (XFS_FORCED_SHUTDOWN(mp))
+                return -EIO;
+
+relock:
+        if (ioflags & IO_ISDIRECT) {
+                iolock = XFS_IOLOCK_SHARED;
+                need_i_mutex = 0;
+        } else {
+                iolock = XFS_IOLOCK_EXCL;
+                need_i_mutex = 1;
+                mutex_lock(&inode->i_mutex);
+        }
+
+        xfs_ilock(ip, XFS_ILOCK_EXCL|iolock);
+
+start:
+        error = -generic_write_checks(file, &pos, &count,
+                                        S_ISBLK(inode->i_mode));
+        if (error) {
+                xfs_iunlock(ip, XFS_ILOCK_EXCL|iolock);
+                goto out_unlock_mutex;
+        }
+
+        if ((DM_EVENT_ENABLED(ip, DM_EVENT_WRITE) &&
+            !(ioflags & IO_INVIS) && !eventsent)) {
+                int             dmflags = FILP_DELAY_FLAG(file);
+
+                if (need_i_mutex)
+                        dmflags |= DM_FLAGS_IMUX;
+
+                xfs_iunlock(ip, XFS_ILOCK_EXCL);
+                error = XFS_SEND_DATA(ip->i_mount, DM_EVENT_WRITE, ip,
+                                      pos, count, dmflags, &iolock);
+                if (error) {
+                        goto out_unlock_internal;
+                }
+                xfs_ilock(ip, XFS_ILOCK_EXCL);
+                eventsent = 1;
+
+                /*
+                 * The iolock was dropped and reacquired in XFS_SEND_DATA
+                 * so we have to recheck the size when appending.
+                 * We will only "goto start;" once, since having sent the
+                 * event prevents another call to XFS_SEND_DATA, which is
+                 * what allows the size to change in the first place.
+                 */
+                if ((file->f_flags & O_APPEND) && pos != ip->i_size)
+                        goto start;
+        }
+
+        if (ioflags & IO_ISDIRECT) {
+                xfs_buftarg_t   *target =
+                        XFS_IS_REALTIME_INODE(ip) ?
+                                mp->m_rtdev_targp : mp->m_ddev_targp;
+
+                if ((pos & target->bt_smask) || (count & target->bt_smask)) {
+                        xfs_iunlock(ip, XFS_ILOCK_EXCL|iolock);
+                        return XFS_ERROR(-EINVAL);
+                }
+
+                if (!need_i_mutex && (mapping->nrpages || pos > ip->i_size)) {
+                        xfs_iunlock(ip, XFS_ILOCK_EXCL|iolock);
+                        iolock = XFS_IOLOCK_EXCL;
+                        need_i_mutex = 1;
+                        mutex_lock(&inode->i_mutex);
+                        xfs_ilock(ip, XFS_ILOCK_EXCL|iolock);
+                        goto start;
+                }
+        }
+
+        new_size = pos + count;
+        if (new_size > ip->i_size)
+                ip->i_new_size = new_size;
+
+        if (likely(!(ioflags & IO_INVIS)))
+                file_update_time(file);
+
+        /*
+         * If the offset is beyond the size of the file, we have a couple
+         * of things to do. First, if there is already space allocated
+         * we need to either create holes or zero the disk or ...
+         *
+         * If there is a page where the previous size lands, we need
+         * to zero it out up to the new size.
+         */
+
+        if (pos > ip->i_size) {
+                error = xfs_zero_eof(ip, pos, ip->i_size);
+                if (error) {
+                        xfs_iunlock(ip, XFS_ILOCK_EXCL);
+                        goto out_unlock_internal;
+                }
+        }
+        xfs_iunlock(ip, XFS_ILOCK_EXCL);
+
+        /*
+         * If we're writing the file then make sure to clear the
+         * setuid and setgid bits if the process is not being run
+         * by root.  This keeps people from modifying setuid and
+         * setgid binaries.
+         */
+        error = -file_remove_suid(file);
+        if (unlikely(error))
+                goto out_unlock_internal;
+
+        /* We can write back this queue in page reclaim */
+        current->backing_dev_info = mapping->backing_dev_info;
+
+        if ((ioflags & IO_ISDIRECT)) {
+                if (mapping->nrpages) {
+                        WARN_ON(need_i_mutex == 0);
+                        error = xfs_flushinval_pages(ip,
+                                        (pos & PAGE_CACHE_MASK),
+                                        -1, FI_REMAPF_LOCKED);
+                        if (error)
+                                goto out_unlock_internal;
+                }
+
+                if (need_i_mutex) {
+                        /* demote the lock now the cached pages are gone */
+                        xfs_ilock_demote(ip, XFS_IOLOCK_EXCL);
+                        mutex_unlock(&inode->i_mutex);
+
+                        iolock = XFS_IOLOCK_SHARED;
+                        need_i_mutex = 0;
+                }
+
+                trace_xfs_file_direct_write(ip, count, iocb->ki_pos, ioflags);
+                ret = generic_file_direct_write(iocb, iovp,
+                                &nr_segs, pos, &iocb->ki_pos, count, ocount);
+
+                /*
+                 * direct-io write to a hole: fall through to buffered I/O
+                 * for completing the rest of the request.
+                 */
+                if (ret >= 0 && ret != count) {
+                        XFS_STATS_ADD(xs_write_bytes, ret);
+
+                        pos += ret;
+                        count -= ret;
+
+                        ioflags &= ~IO_ISDIRECT;
+                        xfs_iunlock(ip, iolock);
+                        goto relock;
+                }
+        } else {
+                int enospc = 0;
+                ssize_t ret2 = 0;
+
+write_retry:
+                trace_xfs_file_buffered_write(ip, count, iocb->ki_pos, ioflags);
+                ret2 = generic_file_buffered_write(iocb, iovp, nr_segs,
+                                pos, &iocb->ki_pos, count, ret);
+                /*
+                 * if we just got an ENOSPC, flush the inode now we
+                 * aren't holding any page locks and retry *once*
+                 */
+                if (ret2 == -ENOSPC && !enospc) {
+                        error = xfs_flush_pages(ip, 0, -1, 0, FI_NONE);
+                        if (error)
+                                goto out_unlock_internal;
+                        enospc = 1;
+                        goto write_retry;
+                }
+                ret = ret2;
+        }
+
+        current->backing_dev_info = NULL;
+
+        isize = i_size_read(inode);
+        if (unlikely(ret < 0 && ret != -EFAULT && iocb->ki_pos > isize))
+                iocb->ki_pos = isize;
+
+        if (iocb->ki_pos > ip->i_size) {
+                xfs_ilock(ip, XFS_ILOCK_EXCL);
+                if (iocb->ki_pos > ip->i_size)
+                        ip->i_size = iocb->ki_pos;
+                xfs_iunlock(ip, XFS_ILOCK_EXCL);
+        }
+
+        if (ret == -ENOSPC &&
+            DM_EVENT_ENABLED(ip, DM_EVENT_NOSPACE) && !(ioflags & IO_INVIS)) {
+                xfs_iunlock(ip, iolock);
+                if (need_i_mutex)
+                        mutex_unlock(&inode->i_mutex);
+                error = XFS_SEND_NAMESP(ip->i_mount, DM_EVENT_NOSPACE, ip,
+                                DM_RIGHT_NULL, ip, DM_RIGHT_NULL, NULL, NULL,
+                                0, 0, 0); /* Delay flag intentionally  unused */
+                if (need_i_mutex)
+                        mutex_lock(&inode->i_mutex);
+                xfs_ilock(ip, iolock);
+                if (error)
+                        goto out_unlock_internal;
+                goto start;
+        }
+
+        error = -ret;
+        if (ret <= 0)
+                goto out_unlock_internal;
+
+        XFS_STATS_ADD(xs_write_bytes, ret);
+
+        /* Handle various SYNC-type writes */
+        if ((file->f_flags & O_DSYNC) || IS_SYNC(inode)) {
+                loff_t end = pos + ret - 1;
+                int error2;
+
+                xfs_iunlock(ip, iolock);
+                if (need_i_mutex)
+                        mutex_unlock(&inode->i_mutex);
+
+                error2 = filemap_write_and_wait_range(mapping, pos, end);
+                if (!error)
+                        error = error2;
+                if (need_i_mutex)
+                        mutex_lock(&inode->i_mutex);
+                xfs_ilock(ip, iolock);
+
+                error2 = -xfs_file_fsync(file, file->f_path.dentry,
+                                         (file->f_flags & __O_SYNC) ? 0 : 1);
+                if (!error)
+                        error = error2;
+        }
+
+ out_unlock_internal:
+        if (ip->i_new_size) {
+                xfs_ilock(ip, XFS_ILOCK_EXCL);
+                ip->i_new_size = 0;
+                /*
+                 * If this was a direct or synchronous I/O that failed (such
+                 * as ENOSPC) then part of the I/O may have been written to
+                 * disk before the error occured.  In this case the on-disk
+                 * file size may have been adjusted beyond the in-memory file
+                 * size and now needs to be truncated back.
+                 */
+                if (ip->i_d.di_size > ip->i_size)
+                        ip->i_d.di_size = ip->i_size;
+                xfs_iunlock(ip, XFS_ILOCK_EXCL);
+        }
+        xfs_iunlock(ip, iolock);
+ out_unlock_mutex:
+        if (need_i_mutex)
+                mutex_unlock(&inode->i_mutex);
+        return -error;
 }
 
 STATIC int
@@ -160,28 +938,6 @@ xfs_file_release(
         return -xfs_release(XFS_I(inode));
 }
 
-/*
- * We ignore the datasync flag here because a datasync is effectively
- * identical to an fsync. That is, datasync implies that we need to write
- * only the metadata needed to be able to access the data that is written
- * if we crash after the call completes. Hence if we are writing beyond
- * EOF we have to log the inode size change as well, which makes it a
- * full fsync. If we don't write beyond EOF, the inode core will be
- * clean in memory and so we don't need to log the inode, just like
- * fsync.
- */
-STATIC int
-xfs_file_fsync(
-        struct file             *file,
-        struct dentry           *dentry,
-        int                     datasync)
-{
-        struct xfs_inode        *ip = XFS_I(dentry->d_inode);
-
-        xfs_iflags_clear(ip, XFS_ITRUNCATED);
-        return -xfs_fsync(ip);
-}
-
 STATIC int
 xfs_file_readdir(
         struct file     *filp,
@@ -203,9 +959,9 @@ xfs_file_readdir(
          *
          * Try to give it an estimate that's good enough, maybe at some
          * point we can change the ->readdir prototype to include the
-         * buffer size.
+         * buffer size.  For now we use the current glibc buffer size.
          */
-        bufsize = (size_t)min_t(loff_t, PAGE_SIZE, ip->i_d.di_size);
+        bufsize = (size_t)min_t(loff_t, 32768, ip->i_d.di_size);
 
         error = xfs_readdir(ip, dirent, bufsize,
                                 (xfs_off_t *)&filp->f_pos, filldir);
diff --git a/fs/xfs/linux-2.6/xfs_fs_subr.c b/fs/xfs/linux-2.6/xfs_fs_subr.c
index 7501b85fd860..b6918d76bc7b 100644
--- a/fs/xfs/linux-2.6/xfs_fs_subr.c
+++ b/fs/xfs/linux-2.6/xfs_fs_subr.c
@@ -79,7 +79,7 @@ xfs_flush_pages(
                 xfs_iflags_clear(ip, XFS_ITRUNCATED);
                 ret = -filemap_fdatawrite(mapping);
         }
-        if (flags & XFS_B_ASYNC)
+        if (flags & XBF_ASYNC)
                 return ret;
         ret2 = xfs_wait_on_pages(ip, first, last);
         if (!ret)
diff --git a/fs/xfs/linux-2.6/xfs_ioctl.c b/fs/xfs/linux-2.6/xfs_ioctl.c
index a034cf624437..4ea1ee18aded 100644
--- a/fs/xfs/linux-2.6/xfs_ioctl.c
+++ b/fs/xfs/linux-2.6/xfs_ioctl.c
@@ -447,12 +447,12 @@ xfs_attrlist_by_handle(
 int
 xfs_attrmulti_attr_get(
         struct inode            *inode,
-        char                    *name,
-        char                    __user *ubuf,
+        unsigned char           *name,
+        unsigned char           __user *ubuf,
         __uint32_t              *len,
         __uint32_t              flags)
 {
-        char                    *kbuf;
+        unsigned char           *kbuf;
         int                     error = EFAULT;
 
         if (*len > XATTR_SIZE_MAX)
@@ -476,12 +476,12 @@ xfs_attrmulti_attr_get(
 int
 xfs_attrmulti_attr_set(
         struct inode            *inode,
-        char                    *name,
-        const char              __user *ubuf,
+        unsigned char           *name,
+        const unsigned char     __user *ubuf,
         __uint32_t              len,
         __uint32_t              flags)
 {
-        char                    *kbuf;
+        unsigned char           *kbuf;
         int                     error = EFAULT;
 
         if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
@@ -501,7 +501,7 @@ xfs_attrmulti_attr_set(
 int
 xfs_attrmulti_attr_remove(
         struct inode            *inode,
-        char                    *name,
+        unsigned char           *name,
         __uint32_t              flags)
 {
         if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
@@ -519,7 +519,7 @@ xfs_attrmulti_by_handle(
         xfs_fsop_attrmulti_handlereq_t am_hreq;
         struct dentry           *dentry;
         unsigned int            i, size;
-        char                    *attr_name;
+        unsigned char           *attr_name;
 
         if (!capable(CAP_SYS_ADMIN))
                 return -XFS_ERROR(EPERM);
@@ -547,7 +547,7 @@ xfs_attrmulti_by_handle(
 
         error = 0;
         for (i = 0; i < am_hreq.opcount; i++) {
-                ops[i].am_error = strncpy_from_user(attr_name,
+                ops[i].am_error = strncpy_from_user((char *)attr_name,
                                 ops[i].am_attrname, MAXNAMELEN);
                 if (ops[i].am_error == 0 || ops[i].am_error == MAXNAMELEN)
                         error = -ERANGE;
@@ -1431,6 +1431,9 @@ xfs_file_ioctl(
                 if (!capable(CAP_SYS_ADMIN))
                         return -EPERM;
 
+                if (mp->m_flags & XFS_MOUNT_RDONLY)
+                        return -XFS_ERROR(EROFS);
+
                 if (copy_from_user(&inout, arg, sizeof(inout)))
                         return -XFS_ERROR(EFAULT);
 
diff --git a/fs/xfs/linux-2.6/xfs_ioctl.h b/fs/xfs/linux-2.6/xfs_ioctl.h
index 7bd7c6afc1eb..d56173b34a2a 100644
--- a/fs/xfs/linux-2.6/xfs_ioctl.h
+++ b/fs/xfs/linux-2.6/xfs_ioctl.h
@@ -45,23 +45,23 @@ xfs_readlink_by_handle(
 extern int
 xfs_attrmulti_attr_get(
         struct inode            *inode,
-        char                    *name,
-        char                    __user *ubuf,
+        unsigned char           *name,
+        unsigned char           __user *ubuf,
         __uint32_t              *len,
         __uint32_t              flags);
 
 extern int
-        xfs_attrmulti_attr_set(
+xfs_attrmulti_attr_set(
         struct inode            *inode,
-        char                    *name,
-        const char              __user *ubuf,
+        unsigned char           *name,
+        const unsigned char     __user *ubuf,
         __uint32_t              len,
         __uint32_t              flags);
 
 extern int
 xfs_attrmulti_attr_remove(
         struct inode            *inode,
-        char                    *name,
+        unsigned char           *name,
         __uint32_t              flags);
 
 extern struct dentry *
diff --git a/fs/xfs/linux-2.6/xfs_ioctl32.c b/fs/xfs/linux-2.6/xfs_ioctl32.c
index be1527b1670c..0bf6d61f0528 100644
--- a/fs/xfs/linux-2.6/xfs_ioctl32.c
+++ b/fs/xfs/linux-2.6/xfs_ioctl32.c
@@ -411,7 +411,7 @@ xfs_compat_attrmulti_by_handle(
         compat_xfs_fsop_attrmulti_handlereq_t   am_hreq;
         struct dentry                           *dentry;
         unsigned int                            i, size;
-        char                                    *attr_name;
+        unsigned char                           *attr_name;
 
         if (!capable(CAP_SYS_ADMIN))
                 return -XFS_ERROR(EPERM);
@@ -440,7 +440,7 @@ xfs_compat_attrmulti_by_handle(
 
         error = 0;
         for (i = 0; i < am_hreq.opcount; i++) {
-                ops[i].am_error = strncpy_from_user(attr_name,
+                ops[i].am_error = strncpy_from_user((char *)attr_name,
                                 compat_ptr(ops[i].am_attrname),
                                 MAXNAMELEN);
                 if (ops[i].am_error == 0 || ops[i].am_error == MAXNAMELEN)
diff --git a/fs/xfs/linux-2.6/xfs_iops.c b/fs/xfs/linux-2.6/xfs_iops.c
index 225946012d0b..61a99608731e 100644
--- a/fs/xfs/linux-2.6/xfs_iops.c
+++ b/fs/xfs/linux-2.6/xfs_iops.c
@@ -91,6 +91,16 @@ xfs_mark_inode_dirty_sync(
                 mark_inode_dirty_sync(inode);
 }
 
+void
+xfs_mark_inode_dirty(
+        xfs_inode_t     *ip)
+{
+        struct inode    *inode = VFS_I(ip);
+
+        if (!(inode->i_state & (I_WILL_FREE|I_FREEING|I_CLEAR)))
+                mark_inode_dirty(inode);
+}
+
 /*
  * Change the requested timestamp in the given inode.
  * We don't lock across timestamp updates, and we don't log them but
@@ -140,10 +150,10 @@ xfs_init_security(
         struct xfs_inode *ip = XFS_I(inode);
         size_t          length;
         void            *value;
-        char            *name;
+        unsigned char   *name;
         int             error;
 
-        error = security_inode_init_security(inode, dir, &name,
+        error = security_inode_init_security(inode, dir, (char **)&name,
                                              &value, &length);
         if (error) {
                 if (error == -EOPNOTSUPP)
diff --git a/fs/xfs/linux-2.6/xfs_linux.h b/fs/xfs/linux-2.6/xfs_linux.h
index 5af0c81ca1ae..facfb323a706 100644
--- a/fs/xfs/linux-2.6/xfs_linux.h
+++ b/fs/xfs/linux-2.6/xfs_linux.h
@@ -88,7 +88,6 @@
 #include <xfs_super.h>
 #include <xfs_globals.h>
 #include <xfs_fs_subr.h>
-#include <xfs_lrw.h>
 #include <xfs_buf.h>
 
 /*
diff --git a/fs/xfs/linux-2.6/xfs_lrw.c b/fs/xfs/linux-2.6/xfs_lrw.c
deleted file mode 100644
index 0d32457abef1..000000000000
--- a/fs/xfs/linux-2.6/xfs_lrw.c
+++ /dev/null
@@ -1,852 +0,0 @@
-/*
- * Copyright (c) 2000-2003,2005 Silicon Graphics, Inc.
- * All Rights Reserved.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it would be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write the Free Software Foundation,
- * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
- */
-#include "xfs.h"
-#include "xfs_fs.h"
-#include "xfs_bit.h"
-#include "xfs_log.h"
-#include "xfs_inum.h"
-#include "xfs_trans.h"
-#include "xfs_sb.h"
-#include "xfs_ag.h"
-#include "xfs_dir2.h"
-#include "xfs_alloc.h"
-#include "xfs_dmapi.h"
-#include "xfs_quota.h"
-#include "xfs_mount.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_alloc_btree.h"
-#include "xfs_ialloc_btree.h"
-#include "xfs_dir2_sf.h"
-#include "xfs_attr_sf.h"
-#include "xfs_dinode.h"
-#include "xfs_inode.h"
-#include "xfs_bmap.h"
-#include "xfs_btree.h"
-#include "xfs_ialloc.h"
-#include "xfs_rtalloc.h"
-#include "xfs_error.h"
-#include "xfs_itable.h"
-#include "xfs_rw.h"
-#include "xfs_attr.h"
-#include "xfs_inode_item.h"
-#include "xfs_buf_item.h"
-#include "xfs_utils.h"
-#include "xfs_iomap.h"
-#include "xfs_vnodeops.h"
-#include "xfs_trace.h"
-
-#include <linux/capability.h>
-#include <linux/writeback.h>
-
-
-/*
- *      xfs_iozero
- *
- *      xfs_iozero clears the specified range of buffer supplied,
- *      and marks all the affected blocks as valid and modified.  If
- *      an affected block is not allocated, it will be allocated.  If
- *      an affected block is not completely overwritten, and is not
- *      valid before the operation, it will be read from disk before
- *      being partially zeroed.
- */
-STATIC int
-xfs_iozero(
-        struct xfs_inode        *ip,    /* inode                        */
-        loff_t                  pos,    /* offset in file               */
-        size_t                  count)  /* size of data to zero         */
-{
-        struct page             *page;
-        struct address_space    *mapping;
-        int                     status;
-
-        mapping = VFS_I(ip)->i_mapping;
-        do {
-                unsigned offset, bytes;
-                void *fsdata;
-
-                offset = (pos & (PAGE_CACHE_SIZE -1)); /* Within page */
-                bytes = PAGE_CACHE_SIZE - offset;
-                if (bytes > count)
-                        bytes = count;
-
-                status = pagecache_write_begin(NULL, mapping, pos, bytes,
-                                        AOP_FLAG_UNINTERRUPTIBLE,
-                                        &page, &fsdata);
-                if (status)
-                        break;
-
-                zero_user(page, offset, bytes);
-
-                status = pagecache_write_end(NULL, mapping, pos, bytes, bytes,
-                                        page, fsdata);
-                WARN_ON(status <= 0); /* can't return less than zero! */
-                pos += bytes;
-                count -= bytes;
-                status = 0;
-        } while (count);
-
-        return (-status);
-}
-
-ssize_t                 /* bytes read, or (-)  error */
-xfs_read(
-        xfs_inode_t             *ip,
-        struct kiocb            *iocb,
-        const struct iovec      *iovp,
-        unsigned int            segs,
-        loff_t                  *offset,
-        int                     ioflags)
-{
-        struct file             *file = iocb->ki_filp;
-        struct inode            *inode = file->f_mapping->host;
-        xfs_mount_t             *mp = ip->i_mount;
-        size_t                  size = 0;
-        ssize_t                 ret = 0;
-        xfs_fsize_t             n;
-        unsigned long           seg;
-
-
-        XFS_STATS_INC(xs_read_calls);
-
-        /* START copy & waste from filemap.c */
-        for (seg = 0; seg < segs; seg++) {
-                const struct iovec *iv = &iovp[seg];
-
-                /*
-                 * If any segment has a negative length, or the cumulative
-                 * length ever wraps negative then return -EINVAL.
-                 */
-                size += iv->iov_len;
-                if (unlikely((ssize_t)(size|iv->iov_len) < 0))
-                        return XFS_ERROR(-EINVAL);
-        }
-        /* END copy & waste from filemap.c */
-
-        if (unlikely(ioflags & IO_ISDIRECT)) {
-                xfs_buftarg_t   *target =
-                        XFS_IS_REALTIME_INODE(ip) ?
-                                mp->m_rtdev_targp : mp->m_ddev_targp;
-                if ((*offset & target->bt_smask) ||
-                    (size & target->bt_smask)) {
-                        if (*offset == ip->i_size) {
-                                return (0);
-                        }
-                        return -XFS_ERROR(EINVAL);
-                }
-        }
-
-        n = XFS_MAXIOFFSET(mp) - *offset;
-        if ((n <= 0) || (size == 0))
-                return 0;
-
-        if (n < size)
-                size = n;
-
-        if (XFS_FORCED_SHUTDOWN(mp))
-                return -EIO;
-
-        if (unlikely(ioflags & IO_ISDIRECT))
-                mutex_lock(&inode->i_mutex);
-        xfs_ilock(ip, XFS_IOLOCK_SHARED);
-
-        if (DM_EVENT_ENABLED(ip, DM_EVENT_READ) && !(ioflags & IO_INVIS)) {
-                int dmflags = FILP_DELAY_FLAG(file) | DM_SEM_FLAG_RD(ioflags);
-                int iolock = XFS_IOLOCK_SHARED;
-
-                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))
-                                mutex_unlock(&inode->i_mutex);
-                        return ret;
-                }
-        }
-
-        if (unlikely(ioflags & IO_ISDIRECT)) {
-                if (inode->i_mapping->nrpages)
-                        ret = -xfs_flushinval_pages(ip, (*offset & PAGE_CACHE_MASK),
-                                                    -1, FI_REMAPF_LOCKED);
-                mutex_unlock(&inode->i_mutex);
-                if (ret) {
-                        xfs_iunlock(ip, XFS_IOLOCK_SHARED);
-                        return ret;
-                }
-        }
-
-        trace_xfs_file_read(ip, size, *offset, ioflags);
-
-        iocb->ki_pos = *offset;
-        ret = generic_file_aio_read(iocb, iovp, segs, *offset);
-        if (ret > 0)
-                XFS_STATS_ADD(xs_read_bytes, ret);
-
-        xfs_iunlock(ip, XFS_IOLOCK_SHARED);
-        return ret;
-}
-
-ssize_t
-xfs_splice_read(
-        xfs_inode_t             *ip,
-        struct file             *infilp,
-        loff_t                  *ppos,
-        struct pipe_inode_info  *pipe,
-        size_t                  count,
-        int                     flags,
-        int                     ioflags)
-{
-        xfs_mount_t             *mp = ip->i_mount;
-        ssize_t                 ret;
-
-        XFS_STATS_INC(xs_read_calls);
-        if (XFS_FORCED_SHUTDOWN(ip->i_mount))
-                return -EIO;
-
-        xfs_ilock(ip, XFS_IOLOCK_SHARED);
-
-        if (DM_EVENT_ENABLED(ip, DM_EVENT_READ) && !(ioflags & IO_INVIS)) {
-                int iolock = XFS_IOLOCK_SHARED;
-                int error;
-
-                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;
-                }
-        }
-
-        trace_xfs_file_splice_read(ip, count, *ppos, ioflags);
-
-        ret = generic_file_splice_read(infilp, ppos, pipe, count, flags);
-        if (ret > 0)
-                XFS_STATS_ADD(xs_read_bytes, ret);
-
-        xfs_iunlock(ip, XFS_IOLOCK_SHARED);
-        return ret;
-}
-
-ssize_t
-xfs_splice_write(
-        xfs_inode_t             *ip,
-        struct pipe_inode_info  *pipe,
-        struct file             *outfilp,
-        loff_t                  *ppos,
-        size_t                  count,
-        int                     flags,
-        int                     ioflags)
-{
-        xfs_mount_t             *mp = ip->i_mount;
-        ssize_t                 ret;
-        struct inode            *inode = outfilp->f_mapping->host;
-        xfs_fsize_t             isize, new_size;
-
-        XFS_STATS_INC(xs_write_calls);
-        if (XFS_FORCED_SHUTDOWN(ip->i_mount))
-                return -EIO;
-
-        xfs_ilock(ip, XFS_IOLOCK_EXCL);
-
-        if (DM_EVENT_ENABLED(ip, DM_EVENT_WRITE) && !(ioflags & IO_INVIS)) {
-                int iolock = XFS_IOLOCK_EXCL;
-                int error;
-
-                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;
-                }
-        }
-
-        new_size = *ppos + count;
-
-        xfs_ilock(ip, XFS_ILOCK_EXCL);
-        if (new_size > ip->i_size)
-                ip->i_new_size = new_size;
-        xfs_iunlock(ip, XFS_ILOCK_EXCL);
-
-        trace_xfs_file_splice_write(ip, count, *ppos, ioflags);
-
-        ret = generic_file_splice_write(pipe, outfilp, ppos, count, flags);
-        if (ret > 0)
-                XFS_STATS_ADD(xs_write_bytes, ret);
-
-        isize = i_size_read(inode);
-        if (unlikely(ret < 0 && ret != -EFAULT && *ppos > isize))
-                *ppos = isize;
-
-        if (*ppos > ip->i_size) {
-                xfs_ilock(ip, XFS_ILOCK_EXCL);
-                if (*ppos > ip->i_size)
-                        ip->i_size = *ppos;
-                xfs_iunlock(ip, XFS_ILOCK_EXCL);
-        }
-
-        if (ip->i_new_size) {
-                xfs_ilock(ip, XFS_ILOCK_EXCL);
-                ip->i_new_size = 0;
-                if (ip->i_d.di_size > ip->i_size)
-                        ip->i_d.di_size = ip->i_size;
-                xfs_iunlock(ip, XFS_ILOCK_EXCL);
-        }
-        xfs_iunlock(ip, XFS_IOLOCK_EXCL);
-        return ret;
-}
-
-/*
- * This routine is called to handle zeroing any space in the last
- * block of the file that is beyond the EOF.  We do this since the
- * size is being increased without writing anything to that block
- * and we don't want anyone to read the garbage on the disk.
- */
-STATIC int                              /* error (positive) */
-xfs_zero_last_block(
-        xfs_inode_t     *ip,
-        xfs_fsize_t     offset,
-        xfs_fsize_t     isize)
-{
-        xfs_fileoff_t   last_fsb;
-        xfs_mount_t     *mp = ip->i_mount;
-        int             nimaps;
-        int             zero_offset;
-        int             zero_len;
-        int             error = 0;
-        xfs_bmbt_irec_t imap;
-
-        ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
-
-        zero_offset = XFS_B_FSB_OFFSET(mp, isize);
-        if (zero_offset == 0) {
-                /*
-                 * There are no extra bytes in the last block on disk to
-                 * zero, so return.
-                 */
-                return 0;
-        }
-
-        last_fsb = XFS_B_TO_FSBT(mp, isize);
-        nimaps = 1;
-        error = xfs_bmapi(NULL, ip, last_fsb, 1, 0, NULL, 0, &imap,
-                          &nimaps, NULL, NULL);
-        if (error) {
-                return error;
-        }
-        ASSERT(nimaps > 0);
-        /*
-         * If the block underlying isize is just a hole, then there
-         * is nothing to zero.
-         */
-        if (imap.br_startblock == HOLESTARTBLOCK) {
-                return 0;
-        }
-        /*
-         * Zero the part of the last block beyond the EOF, and write it
-         * out sync.  We need to drop the ilock while we do this so we
-         * don't deadlock when the buffer cache calls back to us.
-         */
-        xfs_iunlock(ip, XFS_ILOCK_EXCL);
-
-        zero_len = mp->m_sb.sb_blocksize - zero_offset;
-        if (isize + zero_len > offset)
-                zero_len = offset - isize;
-        error = xfs_iozero(ip, isize, zero_len);
-
-        xfs_ilock(ip, XFS_ILOCK_EXCL);
-        ASSERT(error >= 0);
-        return error;
-}
-
-/*
- * Zero any on disk space between the current EOF and the new,
- * larger EOF.  This handles the normal case of zeroing the remainder
- * of the last block in the file and the unusual case of zeroing blocks
- * out beyond the size of the file.  This second case only happens
- * with fixed size extents and when the system crashes before the inode
- * size was updated but after blocks were allocated.  If fill is set,
- * then any holes in the range are filled and zeroed.  If not, the holes
- * are left alone as holes.
- */
-
-int                                     /* error (positive) */
-xfs_zero_eof(
-        xfs_inode_t     *ip,
-        xfs_off_t       offset,         /* starting I/O offset */
-        xfs_fsize_t     isize)          /* current inode size */
-{
-        xfs_mount_t     *mp = ip->i_mount;
-        xfs_fileoff_t   start_zero_fsb;
-        xfs_fileoff_t   end_zero_fsb;
-        xfs_fileoff_t   zero_count_fsb;
-        xfs_fileoff_t   last_fsb;
-        xfs_fileoff_t   zero_off;
-        xfs_fsize_t     zero_len;
-        int             nimaps;
-        int             error = 0;
-        xfs_bmbt_irec_t imap;
-
-        ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_IOLOCK_EXCL));
-        ASSERT(offset > isize);
-
-        /*
-         * First handle zeroing the block on which isize resides.
-         * We only zero a part of that block so it is handled specially.
-         */
-        error = xfs_zero_last_block(ip, offset, isize);
-        if (error) {
-                ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_IOLOCK_EXCL));
-                return error;
-        }
-
-        /*
-         * Calculate the range between the new size and the old
-         * where blocks needing to be zeroed may exist.  To get the
-         * block where the last byte in the file currently resides,
-         * we need to subtract one from the size and truncate back
-         * to a block boundary.  We subtract 1 in case the size is
-         * exactly on a block boundary.
-         */
-        last_fsb = isize ? XFS_B_TO_FSBT(mp, isize - 1) : (xfs_fileoff_t)-1;
-        start_zero_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)isize);
-        end_zero_fsb = XFS_B_TO_FSBT(mp, offset - 1);
-        ASSERT((xfs_sfiloff_t)last_fsb < (xfs_sfiloff_t)start_zero_fsb);
-        if (last_fsb == end_zero_fsb) {
-                /*
-                 * The size was only incremented on its last block.
-                 * We took care of that above, so just return.
-                 */
-                return 0;
-        }
-
-        ASSERT(start_zero_fsb <= end_zero_fsb);
-        while (start_zero_fsb <= end_zero_fsb) {
-                nimaps = 1;
-                zero_count_fsb = end_zero_fsb - start_zero_fsb + 1;
-                error = xfs_bmapi(NULL, ip, start_zero_fsb, zero_count_fsb,
-                                  0, NULL, 0, &imap, &nimaps, NULL, NULL);
-                if (error) {
-                        ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_IOLOCK_EXCL));
-                        return error;
-                }
-                ASSERT(nimaps > 0);
-
-                if (imap.br_state == XFS_EXT_UNWRITTEN ||
-                    imap.br_startblock == HOLESTARTBLOCK) {
-                        /*
-                         * This loop handles initializing pages that were
-                         * partially initialized by the code below this
-                         * loop. It basically zeroes the part of the page
-                         * that sits on a hole and sets the page as P_HOLE
-                         * and calls remapf if it is a mapped file.
-                         */
-                        start_zero_fsb = imap.br_startoff + imap.br_blockcount;
-                        ASSERT(start_zero_fsb <= (end_zero_fsb + 1));
-                        continue;
-                }
-
-                /*
-                 * There are blocks we need to zero.
-                 * Drop the inode lock while we're doing the I/O.
-                 * We'll still have the iolock to protect us.
-                 */
-                xfs_iunlock(ip, XFS_ILOCK_EXCL);
-
-                zero_off = XFS_FSB_TO_B(mp, start_zero_fsb);
-                zero_len = XFS_FSB_TO_B(mp, imap.br_blockcount);
-
-                if ((zero_off + zero_len) > offset)
-                        zero_len = offset - zero_off;
-
-                error = xfs_iozero(ip, zero_off, zero_len);
-                if (error) {
-                        goto out_lock;
-                }
-
-                start_zero_fsb = imap.br_startoff + imap.br_blockcount;
-                ASSERT(start_zero_fsb <= (end_zero_fsb + 1));
-
-                xfs_ilock(ip, XFS_ILOCK_EXCL);
-        }
-
-        return 0;
-
-out_lock:
-        xfs_ilock(ip, XFS_ILOCK_EXCL);
-        ASSERT(error >= 0);
-        return error;
-}
-
-ssize_t                         /* bytes written, or (-) error */
-xfs_write(
-        struct xfs_inode        *xip,
-        struct kiocb            *iocb,
-        const struct iovec      *iovp,
-        unsigned int            nsegs,
-        loff_t                  *offset,
-        int                     ioflags)
-{
-        struct file             *file = iocb->ki_filp;
-        struct address_space    *mapping = file->f_mapping;
-        struct inode            *inode = mapping->host;
-        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;
-        size_t                  ocount = 0, count;
-        loff_t                  pos;
-        int                     need_i_mutex;
-
-        XFS_STATS_INC(xs_write_calls);
-
-        error = generic_segment_checks(iovp, &segs, &ocount, VERIFY_READ);
-        if (error)
-                return error;
-
-        count = ocount;
-        pos = *offset;
-
-        if (count == 0)
-                return 0;
-
-        mp = xip->i_mount;
-
-        xfs_wait_for_freeze(mp, SB_FREEZE_WRITE);
-
-        if (XFS_FORCED_SHUTDOWN(mp))
-                return -EIO;
-
-relock:
-        if (ioflags & IO_ISDIRECT) {
-                iolock = XFS_IOLOCK_SHARED;
-                need_i_mutex = 0;
-        } else {
-                iolock = XFS_IOLOCK_EXCL;
-                need_i_mutex = 1;
-                mutex_lock(&inode->i_mutex);
-        }
-
-        xfs_ilock(xip, XFS_ILOCK_EXCL|iolock);
-
-start:
-        error = -generic_write_checks(file, &pos, &count,
-                                        S_ISBLK(inode->i_mode));
-        if (error) {
-                xfs_iunlock(xip, XFS_ILOCK_EXCL|iolock);
-                goto out_unlock_mutex;
-        }
-
-        if ((DM_EVENT_ENABLED(xip, DM_EVENT_WRITE) &&
-            !(ioflags & IO_INVIS) && !eventsent)) {
-                int             dmflags = FILP_DELAY_FLAG(file);
-
-                if (need_i_mutex)
-                        dmflags |= DM_FLAGS_IMUX;
-
-                xfs_iunlock(xip, XFS_ILOCK_EXCL);
-                error = XFS_SEND_DATA(xip->i_mount, DM_EVENT_WRITE, xip,
-                                      pos, count, dmflags, &iolock);
-                if (error) {
-                        goto out_unlock_internal;
-                }
-                xfs_ilock(xip, XFS_ILOCK_EXCL);
-                eventsent = 1;
-
-                /*
-                 * The iolock was dropped and reacquired in XFS_SEND_DATA
-                 * so we have to recheck the size when appending.
-                 * We will only "goto start;" once, since having sent the
-                 * event prevents another call to XFS_SEND_DATA, which is
-                 * what allows the size to change in the first place.
-                 */
-                if ((file->f_flags & O_APPEND) && pos != xip->i_size)
-                        goto start;
-        }
-
-        if (ioflags & IO_ISDIRECT) {
-                xfs_buftarg_t   *target =
-                        XFS_IS_REALTIME_INODE(xip) ?
-                                mp->m_rtdev_targp : mp->m_ddev_targp;
-
-                if ((pos & target->bt_smask) || (count & target->bt_smask)) {
-                        xfs_iunlock(xip, XFS_ILOCK_EXCL|iolock);
-                        return XFS_ERROR(-EINVAL);
-                }
-
-                if (!need_i_mutex && (mapping->nrpages || pos > xip->i_size)) {
-                        xfs_iunlock(xip, XFS_ILOCK_EXCL|iolock);
-                        iolock = XFS_IOLOCK_EXCL;
-                        need_i_mutex = 1;
-                        mutex_lock(&inode->i_mutex);
-                        xfs_ilock(xip, XFS_ILOCK_EXCL|iolock);
-                        goto start;
-                }
-        }
-
-        new_size = pos + count;
-        if (new_size > xip->i_size)
-                xip->i_new_size = new_size;
-
-        if (likely(!(ioflags & IO_INVIS)))
-                file_update_time(file);
-
-        /*
-         * If the offset is beyond the size of the file, we have a couple
-         * of things to do. First, if there is already space allocated
-         * we need to either create holes or zero the disk or ...
-         *
-         * If there is a page where the previous size lands, we need
-         * to zero it out up to the new size.
-         */
-
-        if (pos > xip->i_size) {
-                error = xfs_zero_eof(xip, pos, xip->i_size);
-                if (error) {
-                        xfs_iunlock(xip, XFS_ILOCK_EXCL);
-                        goto out_unlock_internal;
-                }
-        }
-        xfs_iunlock(xip, XFS_ILOCK_EXCL);
-
-        /*
-         * If we're writing the file then make sure to clear the
-         * setuid and setgid bits if the process is not being run
-         * by root.  This keeps people from modifying setuid and
-         * setgid binaries.
-         */
-
-        if (((xip->i_d.di_mode & S_ISUID) ||
-            ((xip->i_d.di_mode & (S_ISGID | S_IXGRP)) ==
-                (S_ISGID | S_IXGRP))) &&
-             !capable(CAP_FSETID)) {
-                error = xfs_write_clear_setuid(xip);
-                if (likely(!error))
-                        error = -file_remove_suid(file);
-                if (unlikely(error)) {
-                        goto out_unlock_internal;
-                }
-        }
-
-        /* We can write back this queue in page reclaim */
-        current->backing_dev_info = mapping->backing_dev_info;
-
-        if ((ioflags & IO_ISDIRECT)) {
-                if (mapping->nrpages) {
-                        WARN_ON(need_i_mutex == 0);
-                        error = xfs_flushinval_pages(xip,
-                                        (pos & PAGE_CACHE_MASK),
-                                        -1, FI_REMAPF_LOCKED);
-                        if (error)
-                                goto out_unlock_internal;
-                }
-
-                if (need_i_mutex) {
-                        /* demote the lock now the cached pages are gone */
-                        xfs_ilock_demote(xip, XFS_IOLOCK_EXCL);
-                        mutex_unlock(&inode->i_mutex);
-
-                        iolock = XFS_IOLOCK_SHARED;
-                        need_i_mutex = 0;
-                }
-
-                trace_xfs_file_direct_write(xip, count, *offset, ioflags);
-                ret = generic_file_direct_write(iocb, iovp,
-                                &segs, pos, offset, count, ocount);
-
-                /*
-                 * direct-io write to a hole: fall through to buffered I/O
-                 * for completing the rest of the request.
-                 */
-                if (ret >= 0 && ret != count) {
-                        XFS_STATS_ADD(xs_write_bytes, ret);
-
-                        pos += ret;
-                        count -= ret;
-
-                        ioflags &= ~IO_ISDIRECT;
-                        xfs_iunlock(xip, iolock);
-                        goto relock;
-                }
-        } else {
-                int enospc = 0;
-                ssize_t ret2 = 0;
-
-write_retry:
-                trace_xfs_file_buffered_write(xip, count, *offset, ioflags);
-                ret2 = generic_file_buffered_write(iocb, iovp, segs,
-                                pos, offset, count, ret);
-                /*
-                 * if we just got an ENOSPC, flush the inode now we
-                 * aren't holding any page locks and retry *once*
-                 */
-                if (ret2 == -ENOSPC && !enospc) {
-                        error = xfs_flush_pages(xip, 0, -1, 0, FI_NONE);
-                        if (error)
-                                goto out_unlock_internal;
-                        enospc = 1;
-                        goto write_retry;
-                }
-                ret = ret2;
-        }
-
-        current->backing_dev_info = NULL;
-
-        isize = i_size_read(inode);
-        if (unlikely(ret < 0 && ret != -EFAULT && *offset > isize))
-                *offset = isize;
-
-        if (*offset > xip->i_size) {
-                xfs_ilock(xip, XFS_ILOCK_EXCL);
-                if (*offset > xip->i_size)
-                        xip->i_size = *offset;
-                xfs_iunlock(xip, XFS_ILOCK_EXCL);
-        }
-
-        if (ret == -ENOSPC &&
-            DM_EVENT_ENABLED(xip, DM_EVENT_NOSPACE) && !(ioflags & IO_INVIS)) {
-                xfs_iunlock(xip, iolock);
-                if (need_i_mutex)
-                        mutex_unlock(&inode->i_mutex);
-                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_ilock(xip, iolock);
-                if (error)
-                        goto out_unlock_internal;
-                goto start;
-        }
-
-        error = -ret;
-        if (ret <= 0)
-                goto out_unlock_internal;
-
-        XFS_STATS_ADD(xs_write_bytes, ret);
-
-        /* Handle various SYNC-type writes */
-        if ((file->f_flags & O_DSYNC) || IS_SYNC(inode)) {
-                loff_t end = pos + ret - 1;
-                int error2;
-
-                xfs_iunlock(xip, iolock);
-                if (need_i_mutex)
-                        mutex_unlock(&inode->i_mutex);
-
-                error2 = filemap_write_and_wait_range(mapping, pos, end);
-                if (!error)
-                        error = error2;
-                if (need_i_mutex)
-                        mutex_lock(&inode->i_mutex);
-                xfs_ilock(xip, iolock);
-
-                error2 = xfs_fsync(xip);
-                if (!error)
-                        error = error2;
-        }
-
- out_unlock_internal:
-        if (xip->i_new_size) {
-                xfs_ilock(xip, XFS_ILOCK_EXCL);
-                xip->i_new_size = 0;
-                /*
-                 * If this was a direct or synchronous I/O that failed (such
-                 * as ENOSPC) then part of the I/O may have been written to
-                 * disk before the error occured.  In this case the on-disk
-                 * file size may have been adjusted beyond the in-memory file
-                 * size and now needs to be truncated back.
-                 */
-                if (xip->i_d.di_size > xip->i_size)
-                        xip->i_d.di_size = xip->i_size;
-                xfs_iunlock(xip, XFS_ILOCK_EXCL);
-        }
-        xfs_iunlock(xip, iolock);
- out_unlock_mutex:
-        if (need_i_mutex)
-                mutex_unlock(&inode->i_mutex);
-        return -error;
-}
-
-/*
- * All xfs metadata buffers except log state machine buffers
- * get this attached as their b_bdstrat callback function.
- * This is so that we can catch a buffer
- * after prematurely unpinning it to forcibly shutdown the filesystem.
- */
-int
-xfs_bdstrat_cb(struct xfs_buf *bp)
-{
-        if (XFS_FORCED_SHUTDOWN(bp->b_mount)) {
-                trace_xfs_bdstrat_shut(bp, _RET_IP_);
-                /*
-                 * Metadata write that didn't get logged but
-                 * written delayed anyway. These aren't associated
-                 * with a transaction, and can be ignored.
-                 */
-                if (XFS_BUF_IODONE_FUNC(bp) == NULL &&
-                    (XFS_BUF_ISREAD(bp)) == 0)
-                        return (xfs_bioerror_relse(bp));
-                else
-                        return (xfs_bioerror(bp));
-        }
-
-        xfs_buf_iorequest(bp);
-        return 0;
-}
-
-/*
- * 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.
- */
-void
-xfsbdstrat(
-        struct xfs_mount        *mp,
-        struct xfs_buf          *bp)
-{
-        ASSERT(mp);
-        if (!XFS_FORCED_SHUTDOWN(mp)) {
-                xfs_buf_iorequest(bp);
-                return;
-        }
-
-        trace_xfs_bdstrat_shut(bp, _RET_IP_);
-        xfs_bioerror_relse(bp);
-}
-
-/*
- * If the underlying (data/log/rt) device is readonly, there are some
- * operations that cannot proceed.
- */
-int
-xfs_dev_is_read_only(
-        xfs_mount_t             *mp,
-        char                    *message)
-{
-        if (xfs_readonly_buftarg(mp->m_ddev_targp) ||
-            xfs_readonly_buftarg(mp->m_logdev_targp) ||
-            (mp->m_rtdev_targp && xfs_readonly_buftarg(mp->m_rtdev_targp))) {
-                cmn_err(CE_NOTE,
-                        "XFS: %s required on read-only device.", message);
-                cmn_err(CE_NOTE,
-                        "XFS: write access unavailable, cannot proceed.");
-                return EROFS;
-        }
-        return 0;
-}
diff --git a/fs/xfs/linux-2.6/xfs_lrw.h b/fs/xfs/linux-2.6/xfs_lrw.h
deleted file mode 100644
index d1f7789c7ffb..000000000000
--- a/fs/xfs/linux-2.6/xfs_lrw.h
+++ /dev/null
@@ -1,32 +0,0 @@
-/*
- * Copyright (c) 2000-2003,2005 Silicon Graphics, Inc.
- * All Rights Reserved.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it would be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write the Free Software Foundation,
- * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
- */
-#ifndef __XFS_LRW_H__
-#define __XFS_LRW_H__
-
-struct xfs_mount;
-struct xfs_inode;
-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 *);
-
-extern int xfs_zero_eof(struct xfs_inode *, xfs_off_t, xfs_fsize_t);
-
-#endif  /* __XFS_LRW_H__ */
diff --git a/fs/xfs/linux-2.6/xfs_quotaops.c b/fs/xfs/linux-2.6/xfs_quotaops.c
index 3d4a0c84d634..1947514ce1ad 100644
--- a/fs/xfs/linux-2.6/xfs_quotaops.c
+++ b/fs/xfs/linux-2.6/xfs_quotaops.c
@@ -44,20 +44,6 @@ xfs_quota_type(int type)
 }
 
 STATIC int
-xfs_fs_quota_sync(
-        struct super_block      *sb,
-        int                     type)
-{
-        struct xfs_mount        *mp = XFS_M(sb);
-
-        if (sb->s_flags & MS_RDONLY)
-                return -EROFS;
-        if (!XFS_IS_QUOTA_RUNNING(mp))
-                return -ENOSYS;
-        return -xfs_sync_data(mp, 0);
-}
-
-STATIC int
 xfs_fs_get_xstate(
         struct super_block      *sb,
         struct fs_quota_stat    *fqs)
@@ -82,8 +68,6 @@ xfs_fs_set_xstate(
                 return -EROFS;
         if (op != Q_XQUOTARM && !XFS_IS_QUOTA_RUNNING(mp))
                 return -ENOSYS;
-        if (!capable(CAP_SYS_ADMIN))
-                return -EPERM;
 
         if (uflags & XFS_QUOTA_UDQ_ACCT)
                 flags |= XFS_UQUOTA_ACCT;
@@ -144,14 +128,11 @@ xfs_fs_set_xquota(
                 return -ENOSYS;
         if (!XFS_IS_QUOTA_ON(mp))
                 return -ESRCH;
-        if (!capable(CAP_SYS_ADMIN))
-                return -EPERM;
 
         return -xfs_qm_scall_setqlim(mp, id, xfs_quota_type(type), fdq);
 }
 
 const struct quotactl_ops xfs_quotactl_operations = {
-        .quota_sync             = xfs_fs_quota_sync,
         .get_xstate             = xfs_fs_get_xstate,
         .set_xstate             = xfs_fs_set_xstate,
         .get_xquota             = xfs_fs_get_xquota,
diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c
index 77414db10dc2..71345a370d9f 100644
--- a/fs/xfs/linux-2.6/xfs_super.c
+++ b/fs/xfs/linux-2.6/xfs_super.c
@@ -877,12 +877,11 @@ xfsaild(
 {
         struct xfs_ail  *ailp = data;
         xfs_lsn_t       last_pushed_lsn = 0;
-        long            tout = 0;
+        long            tout = 0; /* milliseconds */
 
         while (!kthread_should_stop()) {
-                if (tout)
-                        schedule_timeout_interruptible(msecs_to_jiffies(tout));
-                tout = 1000;
+                schedule_timeout_interruptible(tout ?
+                                msecs_to_jiffies(tout) : MAX_SCHEDULE_TIMEOUT);
 
                 /* swsusp */
                 try_to_freeze();
@@ -1022,59 +1021,108 @@ xfs_fs_dirty_inode(
         XFS_I(inode)->i_update_core = 1;
 }
 
-/*
- * Attempt to flush the inode, this will actually fail
- * if the inode is pinned, but we dirty the inode again
- * at the point when it is unpinned after a log write,
- * since this is when the inode itself becomes flushable.
- */
+STATIC int
+xfs_log_inode(
+        struct xfs_inode        *ip)
+{
+        struct xfs_mount        *mp = ip->i_mount;
+        struct xfs_trans        *tp;
+        int                     error;
+
+        xfs_iunlock(ip, XFS_ILOCK_SHARED);
+        tp = xfs_trans_alloc(mp, XFS_TRANS_FSYNC_TS);
+        error = xfs_trans_reserve(tp, 0, XFS_FSYNC_TS_LOG_RES(mp), 0, 0, 0);
+
+        if (error) {
+                xfs_trans_cancel(tp, 0);
+                /* we need to return with the lock hold shared */
+                xfs_ilock(ip, XFS_ILOCK_SHARED);
+                return error;
+        }
+
+        xfs_ilock(ip, XFS_ILOCK_EXCL);
+
+        /*
+         * Note - it's possible that we might have pushed ourselves out of the
+         * way during trans_reserve which would flush the inode.  But there's
+         * no guarantee that the inode buffer has actually gone out yet (it's
+         * delwri).  Plus the buffer could be pinned anyway if it's part of
+         * an inode in another recent transaction.  So we play it safe and
+         * fire off the transaction anyway.
+         */
+        xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
+        xfs_trans_ihold(tp, ip);
+        xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+        xfs_trans_set_sync(tp);
+        error = xfs_trans_commit(tp, 0);
+        xfs_ilock_demote(ip, XFS_ILOCK_EXCL);
+
+        return error;
+}
+
 STATIC int
 xfs_fs_write_inode(
         struct inode            *inode,
-        int                     sync)
+        struct writeback_control *wbc)
 {
         struct xfs_inode        *ip = XFS_I(inode);
         struct xfs_mount        *mp = ip->i_mount;
-        int                     error = 0;
+        int                     error = EAGAIN;
 
         xfs_itrace_entry(ip);
 
         if (XFS_FORCED_SHUTDOWN(mp))
                 return XFS_ERROR(EIO);
 
-        if (sync) {
-                error = xfs_wait_on_pages(ip, 0, -1);
-                if (error)
+        if (wbc->sync_mode == WB_SYNC_ALL) {
+                /*
+                 * Make sure the inode has hit stable storage.  By using the
+                 * log and the fsync transactions we reduce the IOs we have
+                 * to do here from two (log and inode) to just the log.
+                 *
+                 * Note: We still need to do a delwri write of the inode after
+                 * this to flush it to the backing buffer so that bulkstat
+                 * works properly if this is the first time the inode has been
+                 * written.  Because we hold the ilock atomically over the
+                 * transaction commit and the inode flush we are guaranteed
+                 * that the inode is not pinned when it returns. If the flush
+                 * lock is already held, then the inode has already been
+                 * flushed once and we don't need to flush it again.  Hence
+                 * the code will only flush the inode if it isn't already
+                 * being flushed.
+                 */
+                xfs_ilock(ip, XFS_ILOCK_SHARED);
+                if (ip->i_update_core) {
+                        error = xfs_log_inode(ip);
+                        if (error)
+                                goto out_unlock;
+                }
+        } else {
+                /*
+                 * We make this non-blocking if the inode is contended, return
+                 * EAGAIN to indicate to the caller that they did not succeed.
+                 * This prevents the flush path from blocking on inodes inside
+                 * another operation right now, they get caught later by xfs_sync.
+                 */
+                if (!xfs_ilock_nowait(ip, XFS_ILOCK_SHARED))
                         goto out;
         }
 
-        /*
-         * Bypass inodes which have already been cleaned by
-         * the inode flush clustering code inside xfs_iflush
-         */
-        if (xfs_inode_clean(ip))
-                goto out;
+        if (xfs_ipincount(ip) || !xfs_iflock_nowait(ip))
+                goto out_unlock;
 
         /*
-         * We make this non-blocking if the inode is contended, return
-         * EAGAIN to indicate to the caller that they did not succeed.
-         * This prevents the flush path from blocking on inodes inside
-         * another operation right now, they get caught later by xfs_sync.
+         * Now we have the flush lock and the inode is not pinned, we can check
+         * if the inode is really clean as we know that there are no pending
+         * transaction completions, it is not waiting on the delayed write
+         * queue and there is no IO in progress.
          */
-        if (sync) {
-                xfs_ilock(ip, XFS_ILOCK_SHARED);
-                xfs_iflock(ip);
-
-                error = xfs_iflush(ip, XFS_IFLUSH_SYNC);
-        } else {
-                error = EAGAIN;
-                if (!xfs_ilock_nowait(ip, XFS_ILOCK_SHARED))
-                        goto out;
-                if (xfs_ipincount(ip) || !xfs_iflock_nowait(ip))
-                        goto out_unlock;
-
-                error = xfs_iflush(ip, XFS_IFLUSH_ASYNC_NOBLOCK);
+        if (xfs_inode_clean(ip)) {
+                xfs_ifunlock(ip);
+                error = 0;
+                goto out_unlock;
         }
+        error = xfs_iflush(ip, 0);
 
  out_unlock:
         xfs_iunlock(ip, XFS_ILOCK_SHARED);
@@ -1257,6 +1305,29 @@ xfs_fs_statfs(
         return 0;
 }
 
+STATIC void
+xfs_save_resvblks(struct xfs_mount *mp)
+{
+        __uint64_t resblks = 0;
+
+        mp->m_resblks_save = mp->m_resblks;
+        xfs_reserve_blocks(mp, &resblks, NULL);
+}
+
+STATIC void
+xfs_restore_resvblks(struct xfs_mount *mp)
+{
+        __uint64_t resblks;
+
+        if (mp->m_resblks_save) {
+                resblks = mp->m_resblks_save;
+                mp->m_resblks_save = 0;
+        } else
+                resblks = xfs_default_resblks(mp);
+
+        xfs_reserve_blocks(mp, &resblks, NULL);
+}
+
 STATIC int
 xfs_fs_remount(
         struct super_block      *sb,
@@ -1336,11 +1407,27 @@ xfs_fs_remount(
                         }
                         mp->m_update_flags = 0;
                 }
+
+                /*
+                 * Fill out the reserve pool if it is empty. Use the stashed
+                 * value if it is non-zero, otherwise go with the default.
+                 */
+                xfs_restore_resvblks(mp);
         }
 
         /* rw -> ro */
         if (!(mp->m_flags & XFS_MOUNT_RDONLY) && (*flags & MS_RDONLY)) {
+                /*
+                 * After we have synced the data but before we sync the
+                 * metadata, we need to free up the reserve block pool so that
+                 * the used block count in the superblock on disk is correct at
+                 * the end of the remount. Stash the current reserve pool size
+                 * so that if we get remounted rw, we can return it to the same
+                 * size.
+                 */
+
                 xfs_quiesce_data(mp);
+                xfs_save_resvblks(mp);
                 xfs_quiesce_attr(mp);
                 mp->m_flags |= XFS_MOUNT_RDONLY;
         }
@@ -1359,11 +1446,22 @@ xfs_fs_freeze(
 {
         struct xfs_mount        *mp = XFS_M(sb);
 
+        xfs_save_resvblks(mp);
         xfs_quiesce_attr(mp);
         return -xfs_fs_log_dummy(mp);
 }
 
 STATIC int
+xfs_fs_unfreeze(
+        struct super_block      *sb)
+{
+        struct xfs_mount        *mp = XFS_M(sb);
+
+        xfs_restore_resvblks(mp);
+        return 0;
+}
+
+STATIC int
 xfs_fs_show_options(
         struct seq_file         *m,
         struct vfsmount         *mnt)
@@ -1585,6 +1683,7 @@ static const struct super_operations xfs_super_operations = {
         .put_super              = xfs_fs_put_super,
         .sync_fs                = xfs_fs_sync_fs,
         .freeze_fs              = xfs_fs_freeze,
+        .unfreeze_fs            = xfs_fs_unfreeze,
         .statfs                 = xfs_fs_statfs,
         .remount_fs             = xfs_fs_remount,
         .show_options           = xfs_fs_show_options,
diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c
index 1f5e4bb5e970..05cd85317f6f 100644
--- a/fs/xfs/linux-2.6/xfs_sync.c
+++ b/fs/xfs/linux-2.6/xfs_sync.c
@@ -90,14 +90,13 @@ xfs_inode_ag_lookup(
 STATIC int
 xfs_inode_ag_walk(
         struct xfs_mount        *mp,
-        xfs_agnumber_t          ag,
+        struct xfs_perag        *pag,
         int                     (*execute)(struct xfs_inode *ip,
                                            struct xfs_perag *pag, int flags),
         int                     flags,
         int                     tag,
         int                     exclusive)
 {
-        struct xfs_perag        *pag = &mp->m_perag[ag];
         uint32_t                first_index;
         int                     last_error = 0;
         int                     skipped;
@@ -141,8 +140,6 @@ restart:
                 delay(1);
                 goto restart;
         }
-
-        xfs_put_perag(mp, pag);
         return last_error;
 }
 
@@ -160,10 +157,16 @@ xfs_inode_ag_iterator(
         xfs_agnumber_t          ag;
 
         for (ag = 0; ag < mp->m_sb.sb_agcount; ag++) {
-                if (!mp->m_perag[ag].pag_ici_init)
+                struct xfs_perag        *pag;
+
+                pag = xfs_perag_get(mp, ag);
+                if (!pag->pag_ici_init) {
+                        xfs_perag_put(pag);
                         continue;
-                error = xfs_inode_ag_walk(mp, ag, execute, flags, tag,
+                }
+                error = xfs_inode_ag_walk(mp, pag, execute, flags, tag,
                                                 exclusive);
+                xfs_perag_put(pag);
                 if (error) {
                         last_error = error;
                         if (error == EFSCORRUPTED)
@@ -231,7 +234,7 @@ xfs_sync_inode_data(
         }
 
         error = xfs_flush_pages(ip, 0, -1, (flags & SYNC_WAIT) ?
-                                0 : XFS_B_ASYNC, FI_NONE);
+                                0 : XBF_ASYNC, FI_NONE);
         xfs_iunlock(ip, XFS_IOLOCK_SHARED);
 
  out_wait:
@@ -267,8 +270,7 @@ xfs_sync_inode_attr(
                 goto out_unlock;
         }
 
-        error = xfs_iflush(ip, (flags & SYNC_WAIT) ?
-                           XFS_IFLUSH_SYNC : XFS_IFLUSH_DELWRI);
+        error = xfs_iflush(ip, flags);
 
  out_unlock:
         xfs_iunlock(ip, XFS_ILOCK_SHARED);
@@ -293,10 +295,7 @@ xfs_sync_data(
         if (error)
                 return XFS_ERROR(error);
 
-        xfs_log_force(mp, 0,
-                      (flags & SYNC_WAIT) ?
-                       XFS_LOG_FORCE | XFS_LOG_SYNC :
-                       XFS_LOG_FORCE);
+        xfs_log_force(mp, (flags & SYNC_WAIT) ? XFS_LOG_SYNC : 0);
         return 0;
 }
 
@@ -322,10 +321,6 @@ xfs_commit_dummy_trans(
         struct xfs_inode        *ip = mp->m_rootip;
         struct xfs_trans        *tp;
         int                     error;
-        int                     log_flags = XFS_LOG_FORCE;
-
-        if (flags & SYNC_WAIT)
-                log_flags |= XFS_LOG_SYNC;
 
         /*
          * Put a dummy transaction in the log to tell recovery
@@ -347,11 +342,11 @@ xfs_commit_dummy_trans(
         xfs_iunlock(ip, XFS_ILOCK_EXCL);
 
         /* the log force ensures this transaction is pushed to disk */
-        xfs_log_force(mp, 0, log_flags);
+        xfs_log_force(mp, (flags & SYNC_WAIT) ? XFS_LOG_SYNC : 0);
         return error;
 }
 
-int
+STATIC int
 xfs_sync_fsdata(
         struct xfs_mount        *mp,
         int                     flags)
@@ -367,7 +362,7 @@ xfs_sync_fsdata(
         if (flags & SYNC_TRYLOCK) {
                 ASSERT(!(flags & SYNC_WAIT));
 
-                bp = xfs_getsb(mp, XFS_BUF_TRYLOCK);
+                bp = xfs_getsb(mp, XBF_TRYLOCK);
                 if (!bp)
                         goto out;
 
@@ -387,7 +382,7 @@ xfs_sync_fsdata(
                  * become pinned in between there and here.
                  */
                 if (XFS_BUF_ISPINNED(bp))
-                        xfs_log_force(mp, 0, XFS_LOG_FORCE);
+                        xfs_log_force(mp, 0);
         }
 
 
@@ -448,9 +443,6 @@ xfs_quiesce_data(
         xfs_sync_data(mp, SYNC_WAIT);
         xfs_qm_sync(mp, SYNC_WAIT);
 
-        /* drop inode references pinned by filestreams */
-        xfs_filestream_flush(mp);
-
         /* write superblock and hoover up shutdown errors */
         error = xfs_sync_fsdata(mp, SYNC_WAIT);
 
@@ -467,16 +459,18 @@ xfs_quiesce_fs(
 {
         int     count = 0, pincount;
 
+        xfs_reclaim_inodes(mp, 0);
         xfs_flush_buftarg(mp->m_ddev_targp, 0);
-        xfs_reclaim_inodes(mp, XFS_IFLUSH_DELWRI_ELSE_ASYNC);
 
         /*
          * This loop must run at least twice.  The first instance of the loop
          * will flush most meta data but that will generate more meta data
          * (typically directory updates).  Which then must be flushed and
-         * logged before we can write the unmount record.
+         * logged before we can write the unmount record. We also so sync
+         * reclaim of inodes to catch any that the above delwri flush skipped.
          */
         do {
+                xfs_reclaim_inodes(mp, SYNC_WAIT);
                 xfs_sync_attr(mp, SYNC_WAIT);
                 pincount = xfs_flush_buftarg(mp->m_ddev_targp, 1);
                 if (!pincount) {
@@ -575,7 +569,7 @@ xfs_flush_inodes(
         igrab(inode);
         xfs_syncd_queue_work(ip->i_mount, inode, xfs_flush_inodes_work, &completion);
         wait_for_completion(&completion);
-        xfs_log_force(ip->i_mount, (xfs_lsn_t)0, XFS_LOG_FORCE|XFS_LOG_SYNC);
+        xfs_log_force(ip->i_mount, XFS_LOG_SYNC);
 }
 
 /*
@@ -591,8 +585,8 @@ xfs_sync_worker(
         int             error;
 
         if (!(mp->m_flags & XFS_MOUNT_RDONLY)) {
-                xfs_log_force(mp, (xfs_lsn_t)0, XFS_LOG_FORCE);
-                xfs_reclaim_inodes(mp, XFS_IFLUSH_DELWRI_ELSE_ASYNC);
+                xfs_log_force(mp, 0);
+                xfs_reclaim_inodes(mp, 0);
                 /* dgc: errors ignored here */
                 error = xfs_qm_sync(mp, SYNC_TRYLOCK);
                 error = xfs_sync_fsdata(mp, SYNC_TRYLOCK);
@@ -613,7 +607,8 @@ xfssyncd(
         set_freezable();
         timeleft = xfs_syncd_centisecs * msecs_to_jiffies(10);
         for (;;) {
-                timeleft = schedule_timeout_interruptible(timeleft);
+                if (list_empty(&mp->m_sync_list))
+                        timeleft = schedule_timeout_interruptible(timeleft);
                 /* swsusp */
                 try_to_freeze();
                 if (kthread_should_stop() && list_empty(&mp->m_sync_list))
@@ -633,8 +628,7 @@ xfssyncd(
                         list_add_tail(&mp->m_sync_work.w_list,
                                         &mp->m_sync_list);
                 }
-                list_for_each_entry_safe(work, n, &mp->m_sync_list, w_list)
-                        list_move(&work->w_list, &tmp);
+                list_splice_init(&mp->m_sync_list, &tmp);
                 spin_unlock(&mp->m_sync_lock);
 
                 list_for_each_entry_safe(work, n, &tmp, w_list) {
@@ -690,16 +684,17 @@ void
 xfs_inode_set_reclaim_tag(
         xfs_inode_t     *ip)
 {
-        xfs_mount_t     *mp = ip->i_mount;
-        xfs_perag_t     *pag = xfs_get_perag(mp, ip->i_ino);
+        struct xfs_mount *mp = ip->i_mount;
+        struct xfs_perag *pag;
 
-        read_lock(&pag->pag_ici_lock);
+        pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino));
+        write_lock(&pag->pag_ici_lock);
         spin_lock(&ip->i_flags_lock);
         __xfs_inode_set_reclaim_tag(pag, ip);
         __xfs_iflags_set(ip, XFS_IRECLAIMABLE);
         spin_unlock(&ip->i_flags_lock);
-        read_unlock(&pag->pag_ici_lock);
-        xfs_put_perag(mp, pag);
+        write_unlock(&pag->pag_ici_lock);
+        xfs_perag_put(pag);
 }
 
 void
@@ -712,12 +707,64 @@ __xfs_inode_clear_reclaim_tag(
                         XFS_INO_TO_AGINO(mp, ip->i_ino), XFS_ICI_RECLAIM_TAG);
 }
 
+/*
+ * Inodes in different states need to be treated differently, and the return
+ * value of xfs_iflush is not sufficient to get this right. The following table
+ * lists the inode states and the reclaim actions necessary for non-blocking
+ * reclaim:
+ *
+ *
+ *      inode state          iflush ret         required action
+ *      ---------------      ----------         ---------------
+ *      bad                     -               reclaim
+ *      shutdown                EIO             unpin and reclaim
+ *      clean, unpinned         0               reclaim
+ *      stale, unpinned         0               reclaim
+ *      clean, pinned(*)        0               requeue
+ *      stale, pinned           EAGAIN          requeue
+ *      dirty, delwri ok        0               requeue
+ *      dirty, delwri blocked   EAGAIN          requeue
+ *      dirty, sync flush       0               reclaim
+ *
+ * (*) dgc: I don't think the clean, pinned state is possible but it gets
+ * handled anyway given the order of checks implemented.
+ *
+ * As can be seen from the table, the return value of xfs_iflush() is not
+ * sufficient to correctly decide the reclaim action here. The checks in
+ * xfs_iflush() might look like duplicates, but they are not.
+ *
+ * Also, because we get the flush lock first, we know that any inode that has
+ * been flushed delwri has had the flush completed by the time we check that
+ * the inode is clean. The clean inode check needs to be done before flushing
+ * the inode delwri otherwise we would loop forever requeuing clean inodes as
+ * we cannot tell apart a successful delwri flush and a clean inode from the
+ * return value of xfs_iflush().
+ *
+ * Note that because the inode is flushed delayed write by background
+ * writeback, the flush lock may already be held here and waiting on it can
+ * result in very long latencies. Hence for sync reclaims, where we wait on the
+ * flush lock, the caller should push out delayed write inodes first before
+ * trying to reclaim them to minimise the amount of time spent waiting. For
+ * background relaim, we just requeue the inode for the next pass.
+ *
+ * Hence the order of actions after gaining the locks should be:
+ *      bad             => reclaim
+ *      shutdown        => unpin and reclaim
+ *      pinned, delwri  => requeue
+ *      pinned, sync    => unpin
+ *      stale           => reclaim
+ *      clean           => reclaim
+ *      dirty, delwri   => flush and requeue
+ *      dirty, sync     => flush, wait and reclaim
+ */
 STATIC int
 xfs_reclaim_inode(
         struct xfs_inode        *ip,
         struct xfs_perag        *pag,
         int                     sync_mode)
 {
+        int     error = 0;
+
         /*
          * The radix tree lock here protects a thread in xfs_iget from racing
          * with us starting reclaim on the inode.  Once we have the
@@ -735,33 +782,70 @@ xfs_reclaim_inode(
         spin_unlock(&ip->i_flags_lock);
         write_unlock(&pag->pag_ici_lock);
 
-        /*
-         * If the inode is still dirty, then flush it out.  If the inode
-         * is not in the AIL, then it will be OK to flush it delwri as
-         * long as xfs_iflush() does not keep any references to the inode.
-         * We leave that decision up to xfs_iflush() since it has the
-         * knowledge of whether it's OK to simply do a delwri flush of
-         * the inode or whether we need to wait until the inode is
-         * pulled from the AIL.
-         * We get the flush lock regardless, though, just to make sure
-         * we don't free it while it is being flushed.
-         */
         xfs_ilock(ip, XFS_ILOCK_EXCL);
-        xfs_iflock(ip);
+        if (!xfs_iflock_nowait(ip)) {
+                if (!(sync_mode & SYNC_WAIT))
+                        goto out;
+                xfs_iflock(ip);
+        }
+
+        if (is_bad_inode(VFS_I(ip)))
+                goto reclaim;
+        if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
+                xfs_iunpin_wait(ip);
+                goto reclaim;
+        }
+        if (xfs_ipincount(ip)) {
+                if (!(sync_mode & SYNC_WAIT)) {
+                        xfs_ifunlock(ip);
+                        goto out;
+                }
+                xfs_iunpin_wait(ip);
+        }
+        if (xfs_iflags_test(ip, XFS_ISTALE))
+                goto reclaim;
+        if (xfs_inode_clean(ip))
+                goto reclaim;
+
+        /* Now we have an inode that needs flushing */
+        error = xfs_iflush(ip, sync_mode);
+        if (sync_mode & SYNC_WAIT) {
+                xfs_iflock(ip);
+                goto reclaim;
+        }
 
         /*
-         * In the case of a forced shutdown we rely on xfs_iflush() to
-         * wait for the inode to be unpinned before returning an error.
+         * When we have to flush an inode but don't have SYNC_WAIT set, we
+         * flush the inode out using a delwri buffer and wait for the next
+         * call into reclaim to find it in a clean state instead of waiting for
+         * it now. We also don't return errors here - if the error is transient
+         * then the next reclaim pass will flush the inode, and if the error
+         * is permanent then the next sync reclaim will relcaim the inode and
+         * pass on the error.
          */
-        if (!is_bad_inode(VFS_I(ip)) && xfs_iflush(ip, sync_mode) == 0) {
-                /* synchronize with xfs_iflush_done */
-                xfs_iflock(ip);
-                xfs_ifunlock(ip);
+        if (error && !XFS_FORCED_SHUTDOWN(ip->i_mount)) {
+                xfs_fs_cmn_err(CE_WARN, ip->i_mount,
+                        "inode 0x%llx background reclaim flush failed with %d",
+                        (long long)ip->i_ino, error);
         }
+out:
+        xfs_iflags_clear(ip, XFS_IRECLAIM);
+        xfs_iunlock(ip, XFS_ILOCK_EXCL);
+        /*
+         * We could return EAGAIN here to make reclaim rescan the inode tree in
+         * a short while. However, this just burns CPU time scanning the tree
+         * waiting for IO to complete and xfssyncd never goes back to the idle
+         * state. Instead, return 0 to let the next scheduled background reclaim
+         * attempt to reclaim the inode again.
+         */
+        return 0;
 
+reclaim:
+        xfs_ifunlock(ip);
         xfs_iunlock(ip, XFS_ILOCK_EXCL);
         xfs_ireclaim(ip);
-        return 0;
+        return error;
+
 }
 
 int
diff --git a/fs/xfs/linux-2.6/xfs_sync.h b/fs/xfs/linux-2.6/xfs_sync.h
index ea932b43335d..d480c346cabb 100644
--- a/fs/xfs/linux-2.6/xfs_sync.h
+++ b/fs/xfs/linux-2.6/xfs_sync.h
@@ -37,7 +37,6 @@ void xfs_syncd_stop(struct xfs_mount *mp);
 
 int xfs_sync_attr(struct xfs_mount *mp, int flags);
 int xfs_sync_data(struct xfs_mount *mp, int flags);
-int xfs_sync_fsdata(struct xfs_mount *mp, int flags);
 
 int xfs_quiesce_data(struct xfs_mount *mp);
 void xfs_quiesce_attr(struct xfs_mount *mp);
diff --git a/fs/xfs/linux-2.6/xfs_trace.c b/fs/xfs/linux-2.6/xfs_trace.c
index 856eb3c8d605..5a107601e969 100644
--- a/fs/xfs/linux-2.6/xfs_trace.c
+++ b/fs/xfs/linux-2.6/xfs_trace.c
@@ -52,22 +52,6 @@
 #include "quota/xfs_dquot.h"
 
 /*
- * Format fsblock number into a static buffer & return it.
- */
-STATIC char *xfs_fmtfsblock(xfs_fsblock_t bno)
-{
-        static char rval[50];
-
-        if (bno == NULLFSBLOCK)
-                sprintf(rval, "NULLFSBLOCK");
-        else if (isnullstartblock(bno))
-                sprintf(rval, "NULLSTARTBLOCK(%lld)", startblockval(bno));
-        else
-                sprintf(rval, "%lld", (xfs_dfsbno_t)bno);
-        return rval;
-}
-
-/*
  * We include this last to have the helpers above available for the trace
  * event implementations.
  */
diff --git a/fs/xfs/linux-2.6/xfs_trace.h b/fs/xfs/linux-2.6/xfs_trace.h
index c22a608321a3..fcaa62f0799e 100644
--- a/fs/xfs/linux-2.6/xfs_trace.h
+++ b/fs/xfs/linux-2.6/xfs_trace.h
@@ -78,6 +78,33 @@ DECLARE_EVENT_CLASS(xfs_attr_list_class,
         )
 )
 
+#define DEFINE_PERAG_REF_EVENT(name) \
+TRACE_EVENT(name, \
+        TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, int refcount, \
+                 unsigned long caller_ip), \
+        TP_ARGS(mp, agno, refcount, caller_ip), \
+        TP_STRUCT__entry( \
+                __field(dev_t, dev) \
+                __field(xfs_agnumber_t, agno) \
+                __field(int, refcount) \
+                __field(unsigned long, caller_ip) \
+        ), \
+        TP_fast_assign( \
+                __entry->dev = mp->m_super->s_dev; \
+                __entry->agno = agno; \
+                __entry->refcount = refcount; \
+                __entry->caller_ip = caller_ip; \
+        ), \
+        TP_printk("dev %d:%d agno %u refcount %d caller %pf", \
+                  MAJOR(__entry->dev), MINOR(__entry->dev), \
+                  __entry->agno, \
+                  __entry->refcount, \
+                  (char *)__entry->caller_ip) \
+);
+
+DEFINE_PERAG_REF_EVENT(xfs_perag_get)
+DEFINE_PERAG_REF_EVENT(xfs_perag_put)
+
 #define DEFINE_ATTR_LIST_EVENT(name) \
 DEFINE_EVENT(xfs_attr_list_class, name, \
         TP_PROTO(struct xfs_attr_list_context *ctx), \
@@ -170,13 +197,13 @@ TRACE_EVENT(xfs_iext_insert,
                 __entry->caller_ip = caller_ip;
         ),
         TP_printk("dev %d:%d ino 0x%llx state %s idx %ld "
-                  "offset %lld block %s count %lld flag %d caller %pf",
+                  "offset %lld block %lld count %lld flag %d caller %pf",
                   MAJOR(__entry->dev), MINOR(__entry->dev),
                   __entry->ino,
                   __print_flags(__entry->bmap_state, "|", XFS_BMAP_EXT_FLAGS),
                   (long)__entry->idx,
                   __entry->startoff,
-                  xfs_fmtfsblock(__entry->startblock),
+                  (__int64_t)__entry->startblock,
                   __entry->blockcount,
                   __entry->state,
                   (char *)__entry->caller_ip)
@@ -214,13 +241,13 @@ DECLARE_EVENT_CLASS(xfs_bmap_class,
                 __entry->caller_ip = caller_ip;
         ),
         TP_printk("dev %d:%d ino 0x%llx state %s idx %ld "
-                  "offset %lld block %s count %lld flag %d caller %pf",
+                  "offset %lld block %lld count %lld flag %d caller %pf",
                   MAJOR(__entry->dev), MINOR(__entry->dev),
                   __entry->ino,
                   __print_flags(__entry->bmap_state, "|", XFS_BMAP_EXT_FLAGS),
                   (long)__entry->idx,
                   __entry->startoff,
-                  xfs_fmtfsblock(__entry->startblock),
+                  (__int64_t)__entry->startblock,
                   __entry->blockcount,
                   __entry->state,
                   (char *)__entry->caller_ip)
@@ -456,6 +483,7 @@ DEFINE_BUF_ITEM_EVENT(xfs_buf_item_unlock);
 DEFINE_BUF_ITEM_EVENT(xfs_buf_item_unlock_stale);
 DEFINE_BUF_ITEM_EVENT(xfs_buf_item_committed);
 DEFINE_BUF_ITEM_EVENT(xfs_buf_item_push);
+DEFINE_BUF_ITEM_EVENT(xfs_buf_item_pushbuf);
 DEFINE_BUF_ITEM_EVENT(xfs_trans_get_buf);
 DEFINE_BUF_ITEM_EVENT(xfs_trans_get_buf_recur);
 DEFINE_BUF_ITEM_EVENT(xfs_trans_getsb);
@@ -565,7 +593,7 @@ DECLARE_EVENT_CLASS(xfs_dquot_class,
         TP_ARGS(dqp),
         TP_STRUCT__entry(
                 __field(dev_t, dev)
-                __field(__be32, id)
+                __field(u32, id)
                 __field(unsigned, flags)
                 __field(unsigned, nrefs)
                 __field(unsigned long long, res_bcount)
@@ -578,7 +606,7 @@ DECLARE_EVENT_CLASS(xfs_dquot_class,
         ), \
         TP_fast_assign(
                 __entry->dev = dqp->q_mount->m_super->s_dev;
-                __entry->id = dqp->q_core.d_id;
+                __entry->id = be32_to_cpu(dqp->q_core.d_id);
                 __entry->flags = dqp->dq_flags;
                 __entry->nrefs = dqp->q_nrefs;
                 __entry->res_bcount = dqp->q_res_bcount;
@@ -594,10 +622,10 @@ DECLARE_EVENT_CLASS(xfs_dquot_class,
                         be64_to_cpu(dqp->q_core.d_ino_softlimit);
         ),
         TP_printk("dev %d:%d id 0x%x flags %s nrefs %u res_bc 0x%llx "
-                  "bcnt 0x%llx [hard 0x%llx | soft 0x%llx] "
-                  "icnt 0x%llx [hard 0x%llx | soft 0x%llx]",
+                  "bcnt 0x%llx bhardlimit 0x%llx bsoftlimit 0x%llx "
+                  "icnt 0x%llx ihardlimit 0x%llx isoftlimit 0x%llx]",
                   MAJOR(__entry->dev), MINOR(__entry->dev),
-                  be32_to_cpu(__entry->id),
+                  __entry->id,
                   __print_flags(__entry->flags, "|", XFS_DQ_FLAGS),
                   __entry->nrefs,
                   __entry->res_bcount,
@@ -853,7 +881,7 @@ TRACE_EVENT(name, \
         ), \
         TP_printk("dev %d:%d ino 0x%llx size 0x%llx new_size 0x%llx " \
                   "offset 0x%llx count %zd flags %s " \
-                  "startoff 0x%llx startblock %s blockcount 0x%llx", \
+                  "startoff 0x%llx startblock %lld blockcount 0x%llx", \
                   MAJOR(__entry->dev), MINOR(__entry->dev), \
                   __entry->ino, \
                   __entry->size, \
@@ -862,7 +890,7 @@ TRACE_EVENT(name, \
                   __entry->count, \
                   __print_flags(__entry->flags, "|", BMAPI_FLAGS), \
                   __entry->startoff, \
-                  xfs_fmtfsblock(__entry->startblock), \
+                  (__int64_t)__entry->startblock, \
                   __entry->blockcount) \
 )
 DEFINE_IOMAP_EVENT(xfs_iomap_enter);
@@ -1414,6 +1442,59 @@ TRACE_EVENT(xfs_dir2_leafn_moveents,
                   __entry->count)
 );
 
+#define XFS_SWAPEXT_INODES \
+        { 0,    "target" }, \
+        { 1,    "temp" }
+
+#define XFS_INODE_FORMAT_STR \
+        { 0,    "invalid" }, \
+        { 1,    "local" }, \
+        { 2,    "extent" }, \
+        { 3,    "btree" }
+
+DECLARE_EVENT_CLASS(xfs_swap_extent_class,
+        TP_PROTO(struct xfs_inode *ip, int which),
+        TP_ARGS(ip, which),
+        TP_STRUCT__entry(
+                __field(dev_t, dev)
+                __field(int, which)
+                __field(xfs_ino_t, ino)
+                __field(int, format)
+                __field(int, nex)
+                __field(int, max_nex)
+                __field(int, broot_size)
+                __field(int, fork_off)
+        ),
+        TP_fast_assign(
+                __entry->dev = VFS_I(ip)->i_sb->s_dev;
+                __entry->which = which;
+                __entry->ino = ip->i_ino;
+                __entry->format = ip->i_d.di_format;
+                __entry->nex = ip->i_d.di_nextents;
+                __entry->max_nex = ip->i_df.if_ext_max;
+                __entry->broot_size = ip->i_df.if_broot_bytes;
+                __entry->fork_off = XFS_IFORK_BOFF(ip);
+        ),
+        TP_printk("dev %d:%d ino 0x%llx (%s), %s format, num_extents %d, "
+                  "Max in-fork extents %d, broot size %d, fork offset %d",
+                  MAJOR(__entry->dev), MINOR(__entry->dev),
+                  __entry->ino,
+                  __print_symbolic(__entry->which, XFS_SWAPEXT_INODES),
+                  __print_symbolic(__entry->format, XFS_INODE_FORMAT_STR),
+                  __entry->nex,
+                  __entry->max_nex,
+                  __entry->broot_size,
+                  __entry->fork_off)
+)
+
+#define DEFINE_SWAPEXT_EVENT(name) \
+DEFINE_EVENT(xfs_swap_extent_class, name, \
+        TP_PROTO(struct xfs_inode *ip, int which), \
+        TP_ARGS(ip, which))
+
+DEFINE_SWAPEXT_EVENT(xfs_swap_extent_before);
+DEFINE_SWAPEXT_EVENT(xfs_swap_extent_after);
+
 #endif /* _TRACE_XFS_H */
 
 #undef TRACE_INCLUDE_PATH
diff --git a/fs/xfs/linux-2.6/xfs_xattr.c b/fs/xfs/linux-2.6/xfs_xattr.c
index 0b1878857fc3..fa01b9daba6b 100644
--- a/fs/xfs/linux-2.6/xfs_xattr.c
+++ b/fs/xfs/linux-2.6/xfs_xattr.c
@@ -45,7 +45,7 @@ xfs_xattr_get(struct dentry *dentry, const char *name,
                 value = NULL;
         }
 
-        error = -xfs_attr_get(ip, name, value, &asize, xflags);
+        error = -xfs_attr_get(ip, (unsigned char *)name, value, &asize, xflags);
         if (error)
                 return error;
         return asize;
@@ -67,8 +67,9 @@ xfs_xattr_set(struct dentry *dentry, const char *name, const void *value,
                 xflags |= ATTR_REPLACE;
 
         if (!value)
-                return -xfs_attr_remove(ip, name, xflags);
-        return -xfs_attr_set(ip, name, (void *)value, size, xflags);
+                return -xfs_attr_remove(ip, (unsigned char *)name, xflags);
+        return -xfs_attr_set(ip, (unsigned char *)name,
+                                (void *)value, size, xflags);
 }
 
 static struct xattr_handler xfs_xattr_user_handler = {
@@ -124,8 +125,13 @@ static const char *xfs_xattr_prefix(int flags)
 }
 
 static int
-xfs_xattr_put_listent(struct xfs_attr_list_context *context, int flags,
-                char *name, int namelen, int valuelen, char *value)
+xfs_xattr_put_listent(
+        struct xfs_attr_list_context *context,
+        int             flags,
+        unsigned char   *name,
+        int             namelen,
+        int             valuelen,
+        unsigned char   *value)
 {
         unsigned int prefix_len = xfs_xattr_prefix_len(flags);
         char *offset;
@@ -148,7 +154,7 @@ xfs_xattr_put_listent(struct xfs_attr_list_context *context, int flags,
         offset = (char *)context->alist + context->count;
         strncpy(offset, xfs_xattr_prefix(flags), prefix_len);
         offset += prefix_len;
-        strncpy(offset, name, namelen);                 /* real name */
+        strncpy(offset, (char *)name, namelen);                 /* real name */
         offset += namelen;
         *offset = '\0';
         context->count += prefix_len + namelen + 1;
@@ -156,8 +162,13 @@ xfs_xattr_put_listent(struct xfs_attr_list_context *context, int flags,
 }
 
 static int
-xfs_xattr_put_listent_sizes(struct xfs_attr_list_context *context, int flags,
-                char *name, int namelen, int valuelen, char *value)
+xfs_xattr_put_listent_sizes(
+        struct xfs_attr_list_context *context,
+        int             flags,
+        unsigned char   *name,
+        int             namelen,
+        int             valuelen,
+        unsigned char   *value)
 {
         context->count += xfs_xattr_prefix_len(flags) + namelen + 1;
         return 0;