16 files changed, 127 insertions, 111 deletions

diff --git a/fs/xfs/linux-2.6/kmem.c b/fs/xfs/linux-2.6/kmem.c
index 1cd3b55ee3d2..2d3f90afe5f1 100644
--- a/fs/xfs/linux-2.6/kmem.c
+++ b/fs/xfs/linux-2.6/kmem.c
@@ -53,7 +53,7 @@ kmem_alloc(size_t size, unsigned int __nocast flags)
                         printk(KERN_ERR "XFS: possible memory allocation "
                                         "deadlock in %s (mode:0x%x)\n",
                                         __func__, lflags);
-                congestion_wait(WRITE, HZ/50);
+                congestion_wait(BLK_RW_ASYNC, HZ/50);
         } while (1);
 }
 
@@ -130,7 +130,7 @@ kmem_zone_alloc(kmem_zone_t *zone, unsigned int __nocast flags)
                         printk(KERN_ERR "XFS: possible memory allocation "
                                         "deadlock in %s (mode:0x%x)\n",
                                         __func__, lflags);
-                congestion_wait(WRITE, HZ/50);
+                congestion_wait(BLK_RW_ASYNC, HZ/50);
         } while (1);
 }
 
diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c
index 7ec89fc05b2b..aecf2519db76 100644
--- a/fs/xfs/linux-2.6/xfs_aops.c
+++ b/fs/xfs/linux-2.6/xfs_aops.c
@@ -1268,6 +1268,14 @@ xfs_vm_writepage(
         if (!page_has_buffers(page))
                 create_empty_buffers(page, 1 << inode->i_blkbits, 0);
 
+
+        /*
+         *  VM calculation for nr_to_write seems off.  Bump it way
+         *  up, this gets simple streaming writes zippy again.
+         *  To be reviewed again after Jens' writeback changes.
+         */
+        wbc->nr_to_write *= 4;
+
         /*
          * Convert delayed allocate, unwritten or unmapped space
          * to real space and flush out to disk.
diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c
index 1418b916fc27..965df1227d64 100644
--- a/fs/xfs/linux-2.6/xfs_buf.c
+++ b/fs/xfs/linux-2.6/xfs_buf.c
@@ -412,7 +412,7 @@ _xfs_buf_lookup_pages(
 
                         XFS_STATS_INC(xb_page_retries);
                         xfsbufd_wakeup(0, gfp_mask);
-                        congestion_wait(WRITE, HZ/50);
+                        congestion_wait(BLK_RW_ASYNC, HZ/50);
                         goto retry;
                 }
 
@@ -770,7 +770,7 @@ xfs_buf_associate_memory(
         bp->b_pages = NULL;
         bp->b_addr = mem;
 
-        rval = _xfs_buf_get_pages(bp, page_count, 0);
+        rval = _xfs_buf_get_pages(bp, page_count, XBF_DONT_BLOCK);
         if (rval)
                 return rval;
 
diff --git a/fs/xfs/linux-2.6/xfs_file.c b/fs/xfs/linux-2.6/xfs_file.c
index f4e255441574..0542fd507649 100644
--- a/fs/xfs/linux-2.6/xfs_file.c
+++ b/fs/xfs/linux-2.6/xfs_file.c
@@ -41,7 +41,6 @@
 #include "xfs_ioctl.h"
 
 #include <linux/dcache.h>
-#include <linux/smp_lock.h>
 
 static struct vm_operations_struct xfs_file_vm_ops;
 
diff --git a/fs/xfs/linux-2.6/xfs_iops.c b/fs/xfs/linux-2.6/xfs_iops.c
index 58973bb46038..8070b34cc287 100644
--- a/fs/xfs/linux-2.6/xfs_iops.c
+++ b/fs/xfs/linux-2.6/xfs_iops.c
@@ -680,8 +680,8 @@ xfs_vn_fiemap(
         else
                 bm.bmv_length = BTOBB(length);
 
-        /* our formatter will tell xfs_getbmap when to stop. */
-        bm.bmv_count = MAXEXTNUM;
+        /* We add one because in getbmap world count includes the header */
+        bm.bmv_count = fieinfo->fi_extents_max + 1;
         bm.bmv_iflags = BMV_IF_PREALLOC;
         if (fieinfo->fi_flags & FIEMAP_FLAG_XATTR)
                 bm.bmv_iflags |= BMV_IF_ATTRFORK;
diff --git a/fs/xfs/xfs_attr.c b/fs/xfs/xfs_attr.c
index db15feb906ff..4ece1906bd41 100644
--- a/fs/xfs/xfs_attr.c
+++ b/fs/xfs/xfs_attr.c
@@ -2010,7 +2010,9 @@ xfs_attr_rmtval_get(xfs_da_args_t *args)
                         dblkno = XFS_FSB_TO_DADDR(mp, map[i].br_startblock);
                         blkcnt = XFS_FSB_TO_BB(mp, map[i].br_blockcount);
                         error = xfs_read_buf(mp, mp->m_ddev_targp, dblkno,
-                                             blkcnt, XFS_BUF_LOCK, &bp);
+                                             blkcnt,
+                                             XFS_BUF_LOCK | XBF_DONT_BLOCK,
+                                             &bp);
                         if (error)
                                 return(error);
 
@@ -2141,8 +2143,8 @@ xfs_attr_rmtval_set(xfs_da_args_t *args)
                 dblkno = XFS_FSB_TO_DADDR(mp, map.br_startblock),
                 blkcnt = XFS_FSB_TO_BB(mp, map.br_blockcount);
 
-                bp = xfs_buf_get_flags(mp->m_ddev_targp, dblkno,
-                                                        blkcnt, XFS_BUF_LOCK);
+                bp = xfs_buf_get_flags(mp->m_ddev_targp, dblkno, blkcnt,
+                                       XFS_BUF_LOCK | XBF_DONT_BLOCK);
                 ASSERT(bp);
                 ASSERT(!XFS_BUF_GETERROR(bp));
 
diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c
index 7928b9983c1d..8ee5b5a76a2a 100644
--- a/fs/xfs/xfs_bmap.c
+++ b/fs/xfs/xfs_bmap.c
@@ -6009,7 +6009,7 @@ xfs_getbmap(
          */
         error = ENOMEM;
         subnex = 16;
-        map = kmem_alloc(subnex * sizeof(*map), KM_MAYFAIL);
+        map = kmem_alloc(subnex * sizeof(*map), KM_MAYFAIL | KM_NOFS);
         if (!map)
                 goto out_unlock_ilock;
 
diff --git a/fs/xfs/xfs_btree.c b/fs/xfs/xfs_btree.c
index e9df99574829..26717388acf5 100644
--- a/fs/xfs/xfs_btree.c
+++ b/fs/xfs/xfs_btree.c
@@ -120,8 +120,8 @@ xfs_btree_check_sblock(
                         XFS_RANDOM_BTREE_CHECK_SBLOCK))) {
                 if (bp)
                         xfs_buftrace("SBTREE ERROR", bp);
-                XFS_ERROR_REPORT("xfs_btree_check_sblock", XFS_ERRLEVEL_LOW,
-                                 cur->bc_mp);
+                XFS_CORRUPTION_ERROR("xfs_btree_check_sblock",
+                        XFS_ERRLEVEL_LOW, cur->bc_mp, block);
                 return XFS_ERROR(EFSCORRUPTED);
         }
         return 0;
diff --git a/fs/xfs/xfs_da_btree.c b/fs/xfs/xfs_da_btree.c
index 9ff6e57a5075..2847bbc1c534 100644
--- a/fs/xfs/xfs_da_btree.c
+++ b/fs/xfs/xfs_da_btree.c
@@ -2201,7 +2201,7 @@ kmem_zone_t *xfs_dabuf_zone;		/* dabuf zone */
 xfs_da_state_t *
 xfs_da_state_alloc(void)
 {
-        return kmem_zone_zalloc(xfs_da_state_zone, KM_SLEEP);
+        return kmem_zone_zalloc(xfs_da_state_zone, KM_NOFS);
 }
 
 /*
@@ -2261,9 +2261,9 @@ xfs_da_buf_make(int nbuf, xfs_buf_t **bps, inst_t *ra)
         int             off;
 
         if (nbuf == 1)
-                dabuf = kmem_zone_alloc(xfs_dabuf_zone, KM_SLEEP);
+                dabuf = kmem_zone_alloc(xfs_dabuf_zone, KM_NOFS);
         else
-                dabuf = kmem_alloc(XFS_DA_BUF_SIZE(nbuf), KM_SLEEP);
+                dabuf = kmem_alloc(XFS_DA_BUF_SIZE(nbuf), KM_NOFS);
         dabuf->dirty = 0;
 #ifdef XFS_DABUF_DEBUG
         dabuf->ra = ra;
diff --git a/fs/xfs/xfs_dir2.c b/fs/xfs/xfs_dir2.c
index c657bec6d951..bb1d58eb3982 100644
--- a/fs/xfs/xfs_dir2.c
+++ b/fs/xfs/xfs_dir2.c
@@ -256,7 +256,7 @@ xfs_dir_cilookup_result(
                                         !(args->op_flags & XFS_DA_OP_CILOOKUP))
                 return EEXIST;
 
-        args->value = kmem_alloc(len, KM_MAYFAIL);
+        args->value = kmem_alloc(len, KM_NOFS | KM_MAYFAIL);
         if (!args->value)
                 return ENOMEM;
 
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index cbd451bb4848..2d0b3e1da9e6 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -167,17 +167,25 @@ xfs_growfs_data_private(
         new = nb - mp->m_sb.sb_dblocks;
         oagcount = mp->m_sb.sb_agcount;
         if (nagcount > oagcount) {
+                void *new_perag, *old_perag;
+
                 xfs_filestream_flush(mp);
+
+                new_perag = kmem_zalloc(sizeof(xfs_perag_t) * nagcount,
+                                        KM_MAYFAIL);
+                if (!new_perag)
+                        return XFS_ERROR(ENOMEM);
+
                 down_write(&mp->m_peraglock);
-                mp->m_perag = kmem_realloc(mp->m_perag,
-                        sizeof(xfs_perag_t) * nagcount,
-                        sizeof(xfs_perag_t) * oagcount,
-                        KM_SLEEP);
-                memset(&mp->m_perag[oagcount], 0,
-                        (nagcount - oagcount) * sizeof(xfs_perag_t));
+                memcpy(new_perag, mp->m_perag, sizeof(xfs_perag_t) * oagcount);
+                old_perag = mp->m_perag;
+                mp->m_perag = new_perag;
+
                 mp->m_flags |= XFS_MOUNT_32BITINODES;
                 nagimax = xfs_initialize_perag(mp, nagcount);
                 up_write(&mp->m_peraglock);
+
+                kmem_free(old_perag);
         }
         tp = xfs_trans_alloc(mp, XFS_TRANS_GROWFS);
         tp->t_flags |= XFS_TRANS_RESERVE;
diff --git a/fs/xfs/xfs_iget.c b/fs/xfs/xfs_iget.c
index 5fcec6f020a7..34ec86923f7e 100644
--- a/fs/xfs/xfs_iget.c
+++ b/fs/xfs/xfs_iget.c
@@ -64,6 +64,10 @@ xfs_inode_alloc(
         ip = kmem_zone_alloc(xfs_inode_zone, KM_SLEEP);
         if (!ip)
                 return NULL;
+        if (inode_init_always(mp->m_super, VFS_I(ip))) {
+                kmem_zone_free(xfs_inode_zone, ip);
+                return NULL;
+        }
 
         ASSERT(atomic_read(&ip->i_iocount) == 0);
         ASSERT(atomic_read(&ip->i_pincount) == 0);
@@ -105,17 +109,6 @@ xfs_inode_alloc(
 #ifdef XFS_DIR2_TRACE
         ip->i_dir_trace = ktrace_alloc(XFS_DIR2_KTRACE_SIZE, KM_NOFS);
 #endif
-        /*
-        * Now initialise the VFS inode. We do this after the xfs_inode
-        * initialisation as internal failures will result in ->destroy_inode
-        * being called and that will pass down through the reclaim path and
-        * free the XFS inode. This path requires the XFS inode to already be
-        * initialised. Hence if this call fails, the xfs_inode has already
-        * been freed and we should not reference it at all in the error
-        * handling.
-        */
-        if (!inode_init_always(mp->m_super, VFS_I(ip)))
-                return NULL;
 
         /* prevent anyone from using this yet */
         VFS_I(ip)->i_state = I_NEW|I_LOCK;
@@ -123,6 +116,71 @@ xfs_inode_alloc(
         return ip;
 }
 
+STATIC void
+xfs_inode_free(
+        struct xfs_inode        *ip)
+{
+        switch (ip->i_d.di_mode & S_IFMT) {
+        case S_IFREG:
+        case S_IFDIR:
+        case S_IFLNK:
+                xfs_idestroy_fork(ip, XFS_DATA_FORK);
+                break;
+        }
+
+        if (ip->i_afp)
+                xfs_idestroy_fork(ip, XFS_ATTR_FORK);
+
+#ifdef XFS_INODE_TRACE
+        ktrace_free(ip->i_trace);
+#endif
+#ifdef XFS_BMAP_TRACE
+        ktrace_free(ip->i_xtrace);
+#endif
+#ifdef XFS_BTREE_TRACE
+        ktrace_free(ip->i_btrace);
+#endif
+#ifdef XFS_RW_TRACE
+        ktrace_free(ip->i_rwtrace);
+#endif
+#ifdef XFS_ILOCK_TRACE
+        ktrace_free(ip->i_lock_trace);
+#endif
+#ifdef XFS_DIR2_TRACE
+        ktrace_free(ip->i_dir_trace);
+#endif
+
+        if (ip->i_itemp) {
+                /*
+                 * Only if we are shutting down the fs will we see an
+                 * inode still in the AIL. If it is there, we should remove
+                 * it to prevent a use-after-free from occurring.
+                 */
+                xfs_log_item_t  *lip = &ip->i_itemp->ili_item;
+                struct xfs_ail  *ailp = lip->li_ailp;
+
+                ASSERT(((lip->li_flags & XFS_LI_IN_AIL) == 0) ||
+                                       XFS_FORCED_SHUTDOWN(ip->i_mount));
+                if (lip->li_flags & XFS_LI_IN_AIL) {
+                        spin_lock(&ailp->xa_lock);
+                        if (lip->li_flags & XFS_LI_IN_AIL)
+                                xfs_trans_ail_delete(ailp, lip);
+                        else
+                                spin_unlock(&ailp->xa_lock);
+                }
+                xfs_inode_item_destroy(ip);
+                ip->i_itemp = NULL;
+        }
+
+        /* asserts to verify all state is correct here */
+        ASSERT(atomic_read(&ip->i_iocount) == 0);
+        ASSERT(atomic_read(&ip->i_pincount) == 0);
+        ASSERT(!spin_is_locked(&ip->i_flags_lock));
+        ASSERT(completion_done(&ip->i_flush));
+
+        kmem_zone_free(xfs_inode_zone, ip);
+}
+
 /*
  * Check the validity of the inode we just found it the cache
  */
@@ -167,7 +225,7 @@ xfs_iget_cache_hit(
                  * errors cleanly, then tag it so it can be set up correctly
                  * later.
                  */
-                if (!inode_init_always(mp->m_super, VFS_I(ip))) {
+                if (inode_init_always(mp->m_super, VFS_I(ip))) {
                         error = ENOMEM;
                         goto out_error;
                 }
@@ -299,7 +357,8 @@ out_preload_end:
         if (lock_flags)
                 xfs_iunlock(ip, lock_flags);
 out_destroy:
-        xfs_destroy_inode(ip);
+        __destroy_inode(VFS_I(ip));
+        xfs_inode_free(ip);
         return error;
 }
 
@@ -504,62 +563,7 @@ xfs_ireclaim(
         xfs_qm_dqdetach(ip);
         xfs_iunlock(ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
 
-        switch (ip->i_d.di_mode & S_IFMT) {
-        case S_IFREG:
-        case S_IFDIR:
-        case S_IFLNK:
-                xfs_idestroy_fork(ip, XFS_DATA_FORK);
-                break;
-        }
-
-        if (ip->i_afp)
-                xfs_idestroy_fork(ip, XFS_ATTR_FORK);
-
-#ifdef XFS_INODE_TRACE
-        ktrace_free(ip->i_trace);
-#endif
-#ifdef XFS_BMAP_TRACE
-        ktrace_free(ip->i_xtrace);
-#endif
-#ifdef XFS_BTREE_TRACE
-        ktrace_free(ip->i_btrace);
-#endif
-#ifdef XFS_RW_TRACE
-        ktrace_free(ip->i_rwtrace);
-#endif
-#ifdef XFS_ILOCK_TRACE
-        ktrace_free(ip->i_lock_trace);
-#endif
-#ifdef XFS_DIR2_TRACE
-        ktrace_free(ip->i_dir_trace);
-#endif
-        if (ip->i_itemp) {
-                /*
-                 * Only if we are shutting down the fs will we see an
-                 * inode still in the AIL. If it is there, we should remove
-                 * it to prevent a use-after-free from occurring.
-                 */
-                xfs_log_item_t  *lip = &ip->i_itemp->ili_item;
-                struct xfs_ail  *ailp = lip->li_ailp;
-
-                ASSERT(((lip->li_flags & XFS_LI_IN_AIL) == 0) ||
-                                       XFS_FORCED_SHUTDOWN(ip->i_mount));
-                if (lip->li_flags & XFS_LI_IN_AIL) {
-                        spin_lock(&ailp->xa_lock);
-                        if (lip->li_flags & XFS_LI_IN_AIL)
-                                xfs_trans_ail_delete(ailp, lip);
-                        else
-                                spin_unlock(&ailp->xa_lock);
-                }
-                xfs_inode_item_destroy(ip);
-                ip->i_itemp = NULL;
-        }
-        /* asserts to verify all state is correct here */
-        ASSERT(atomic_read(&ip->i_iocount) == 0);
-        ASSERT(atomic_read(&ip->i_pincount) == 0);
-        ASSERT(!spin_is_locked(&ip->i_flags_lock));
-        ASSERT(completion_done(&ip->i_flush));
-        kmem_zone_free(xfs_inode_zone, ip);
+        xfs_inode_free(ip);
 }
 
 /*
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 1f22d65fed0a..da428b3fe0f5 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -343,6 +343,16 @@ xfs_iformat(
                 return XFS_ERROR(EFSCORRUPTED);
         }
 
+        if (unlikely((ip->i_d.di_flags & XFS_DIFLAG_REALTIME) &&
+                     !ip->i_mount->m_rtdev_targp)) {
+                xfs_fs_repair_cmn_err(CE_WARN, ip->i_mount,
+                        "corrupt dinode %Lu, has realtime flag set.",
+                        ip->i_ino);
+                XFS_CORRUPTION_ERROR("xfs_iformat(realtime)",
+                                     XFS_ERRLEVEL_LOW, ip->i_mount, dip);
+                return XFS_ERROR(EFSCORRUPTED);
+        }
+
         switch (ip->i_d.di_mode & S_IFMT) {
         case S_IFIFO:
         case S_IFCHR:
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 1804f866a71d..65f24a3cc992 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -310,23 +310,6 @@ static inline struct inode *VFS_I(struct xfs_inode *ip)
 }
 
 /*
- * Get rid of a partially initialized inode.
- *
- * We have to go through destroy_inode to make sure allocations
- * from init_inode_always like the security data are undone.
- *
- * We mark the inode bad so that it takes the short cut in
- * the reclaim path instead of going through the flush path
- * which doesn't make sense for an inode that has never seen the
- * light of day.
- */
-static inline void xfs_destroy_inode(struct xfs_inode *ip)
-{
-        make_bad_inode(VFS_I(ip));
-        return destroy_inode(VFS_I(ip));
-}
-
-/*
  * i_flags helper functions
  */
 static inline void
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index 3750f04ede0b..9dbdff3ea484 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -3180,7 +3180,7 @@ try_again:
 STATIC void
 xlog_state_want_sync(xlog_t *log, xlog_in_core_t *iclog)
 {
-        ASSERT(spin_is_locked(&log->l_icloglock));
+        assert_spin_locked(&log->l_icloglock);
 
         if (iclog->ic_state == XLOG_STATE_ACTIVE) {
                 xlog_state_switch_iclogs(log, iclog, 0);
diff --git a/fs/xfs/xfs_vnodeops.c b/fs/xfs/xfs_vnodeops.c
index c4eca5ed5dab..492d75bae2bf 100644
--- a/fs/xfs/xfs_vnodeops.c
+++ b/fs/xfs/xfs_vnodeops.c
@@ -538,7 +538,9 @@ xfs_readlink_bmap(
                 d = XFS_FSB_TO_DADDR(mp, mval[n].br_startblock);
                 byte_cnt = XFS_FSB_TO_B(mp, mval[n].br_blockcount);
 
-                bp = xfs_buf_read(mp->m_ddev_targp, d, BTOBB(byte_cnt), 0);
+                bp = xfs_buf_read_flags(mp->m_ddev_targp, d, BTOBB(byte_cnt),
+                                        XBF_LOCK | XBF_MAPPED |
+                                        XBF_DONT_BLOCK);
                 error = XFS_BUF_GETERROR(bp);
                 if (error) {
                         xfs_ioerror_alert("xfs_readlink",