17 files changed, 727 insertions, 305 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_buf.c b/fs/xfs/linux-2.6/xfs_buf.c
index 77b8be81c769..6f76ba85f193 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.
  *
@@ -314,7 +336,7 @@ 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))
+                if (xfs_buf_is_vmapped(bp))
                         free_address(bp->b_addr - bp->b_offset);
 
                 for (i = 0; i < bp->b_page_count; i++) {
@@ -1051,22 +1073,30 @@ 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 +1115,126 @@ 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 +1257,9 @@ 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 +1369,10 @@ 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 +1453,7 @@ 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 +1535,8 @@ 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 +1547,7 @@ 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 +1752,11 @@ 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 +1788,35 @@ 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 +1835,8 @@ 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 +1887,53 @@ 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();
@@ -1715,17 +1941,16 @@ 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++;
@@ -1751,42 +1976,45 @@ 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_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..e8566bbf0f00 100644
--- a/fs/xfs/linux-2.6/xfs_iops.c
+++ b/fs/xfs/linux-2.6/xfs_iops.c
@@ -140,10 +140,10 @@ 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_lrw.c b/fs/xfs/linux-2.6/xfs_lrw.c
index 0d32457abef1..eac6f80d786d 100644
--- a/fs/xfs/linux-2.6/xfs_lrw.c
+++ b/fs/xfs/linux-2.6/xfs_lrw.c
@@ -630,18 +630,9 @@ start:
          * 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;
-                }
-        }
+        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;
@@ -784,53 +775,6 @@ write_retry:
 }
 
 /*
- * 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.
  */
diff --git a/fs/xfs/linux-2.6/xfs_lrw.h b/fs/xfs/linux-2.6/xfs_lrw.h
index d1f7789c7ffb..342ae8c0d011 100644
--- a/fs/xfs/linux-2.6/xfs_lrw.h
+++ b/fs/xfs/linux-2.6/xfs_lrw.h
@@ -22,9 +22,6 @@ 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);
diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c
index 77414db10dc2..25ea2408118f 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();
@@ -1022,12 +1021,45 @@ 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,
@@ -1035,7 +1067,7 @@ xfs_fs_write_inode(
 {
         struct xfs_inode        *ip = XFS_I(inode);
         struct xfs_mount        *mp = ip->i_mount;
-        int                     error = 0;
+        int                     error = EAGAIN;
 
         xfs_itrace_entry(ip);
 
@@ -1046,35 +1078,55 @@ xfs_fs_write_inode(
                 error = xfs_wait_on_pages(ip, 0, -1);
                 if (error)
                         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;
 
-        /*
-         * 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 (sync) {
+                /*
+                 * 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);
-                xfs_iflock(ip);
-
-                error = xfs_iflush(ip, XFS_IFLUSH_SYNC);
+                if (ip->i_update_core) {
+                        error = xfs_log_inode(ip);
+                        if (error)
+                                goto out_unlock;
+                }
         } else {
-                error = EAGAIN;
+                /*
+                 * 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;
-                if (xfs_ipincount(ip) || !xfs_iflock_nowait(ip))
-                        goto out_unlock;
+        }
 
-                error = xfs_iflush(ip, XFS_IFLUSH_ASYNC_NOBLOCK);
+        if (xfs_ipincount(ip) || !xfs_iflock_nowait(ip))
+                goto out_unlock;
+
+        /*
+         * 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 (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 +1309,29 @@ 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 +1411,27 @@ 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 +1450,22 @@ 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 +1687,7 @@ 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..a9f6d20aff41 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);
@@ -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;
 
+        pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino));
         read_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);
+        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.h b/fs/xfs/linux-2.6/xfs_trace.h
index c22a608321a3..a4574dcf5065 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), \
@@ -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);
@@ -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;