10 files changed, 127 insertions, 83 deletions

diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c
index 04e79d57bca6..e9d401ce93bb 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.c
+++ b/fs/xfs/libxfs/xfs_attr_leaf.c
@@ -574,8 +574,8 @@ xfs_attr_shortform_add(xfs_da_args_t *args, int forkoff)
  * After the last attribute is removed revert to original inode format,
  * making all literal area available to the data fork once more.
  */
-STATIC void
-xfs_attr_fork_reset(
+void
+xfs_attr_fork_remove(
         struct xfs_inode        *ip,
         struct xfs_trans        *tp)
 {
@@ -641,7 +641,7 @@ xfs_attr_shortform_remove(xfs_da_args_t *args)
             (mp->m_flags & XFS_MOUNT_ATTR2) &&
             (dp->i_d.di_format != XFS_DINODE_FMT_BTREE) &&
             !(args->op_flags & XFS_DA_OP_ADDNAME)) {
-                xfs_attr_fork_reset(dp, args->trans);
+                xfs_attr_fork_remove(dp, args->trans);
         } else {
                 xfs_idata_realloc(dp, -size, XFS_ATTR_FORK);
                 dp->i_d.di_forkoff = xfs_attr_shortform_bytesfit(dp, totsize);
@@ -905,7 +905,7 @@ xfs_attr3_leaf_to_shortform(
         if (forkoff == -1) {
                 ASSERT(dp->i_mount->m_flags & XFS_MOUNT_ATTR2);
                 ASSERT(dp->i_d.di_format != XFS_DINODE_FMT_BTREE);
-                xfs_attr_fork_reset(dp, args->trans);
+                xfs_attr_fork_remove(dp, args->trans);
                 goto out;
         }
 
diff --git a/fs/xfs/libxfs/xfs_attr_leaf.h b/fs/xfs/libxfs/xfs_attr_leaf.h
index 025c4b820c03..882c8d338891 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.h
+++ b/fs/xfs/libxfs/xfs_attr_leaf.h
@@ -53,7 +53,7 @@ int	xfs_attr_shortform_remove(struct xfs_da_args *args);
 int     xfs_attr_shortform_list(struct xfs_attr_list_context *context);
 int     xfs_attr_shortform_allfit(struct xfs_buf *bp, struct xfs_inode *dp);
 int     xfs_attr_shortform_bytesfit(xfs_inode_t *dp, int bytes);
-
+void    xfs_attr_fork_remove(struct xfs_inode *ip, struct xfs_trans *tp);
 
 /*
  * Internal routines when attribute fork size == XFS_LBSIZE(mp).
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index aeffeaaac0ec..f1026e86dabc 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -3224,12 +3224,24 @@ xfs_bmap_extsize_align(
                 align_alen += temp;
                 align_off -= temp;
         }
+
+        /* Same adjustment for the end of the requested area. */
+        temp = (align_alen % extsz);
+        if (temp)
+                align_alen += extsz - temp;
+
         /*
-         * Same adjustment for the end of the requested area.
+         * For large extent hint sizes, the aligned extent might be larger than
+         * MAXEXTLEN. In that case, reduce the size by an extsz so that it pulls
+         * the length back under MAXEXTLEN. The outer allocation loops handle
+         * short allocation just fine, so it is safe to do this. We only want to
+         * do it when we are forced to, though, because it means more allocation
+         * operations are required.
          */
-        if ((temp = (align_alen % extsz))) {
-                align_alen += extsz - temp;
-        }
+        while (align_alen > MAXEXTLEN)
+                align_alen -= extsz;
+        ASSERT(align_alen <= MAXEXTLEN);
+
         /*
          * If the previous block overlaps with this proposed allocation
          * then move the start forward without adjusting the length.
@@ -3318,7 +3330,9 @@ xfs_bmap_extsize_align(
                         return -EINVAL;
         } else {
                 ASSERT(orig_off >= align_off);
-                ASSERT(orig_end <= align_off + align_alen);
+                /* see MAXEXTLEN handling above */
+                ASSERT(orig_end <= align_off + align_alen ||
+                       align_alen + extsz > MAXEXTLEN);
         }
 
 #ifdef DEBUG
@@ -4099,13 +4113,6 @@ xfs_bmapi_reserve_delalloc(
         /* Figure out the extent size, adjust alen */
         extsz = xfs_get_extsz_hint(ip);
         if (extsz) {
-                /*
-                 * Make sure we don't exceed a single extent length when we
-                 * align the extent by reducing length we are going to
-                 * allocate by the maximum amount extent size aligment may
-                 * require.
-                 */
-                alen = XFS_FILBLKS_MIN(len, MAXEXTLEN - (2 * extsz - 1));
                 error = xfs_bmap_extsize_align(mp, got, prev, extsz, rt, eof,
                                                1, 0, &aoff, &alen);
                 ASSERT(!error);
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index 07349a183a11..1c9e75521250 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -376,7 +376,7 @@ xfs_ialloc_ag_alloc(
          */
         newlen = args.mp->m_ialloc_inos;
         if (args.mp->m_maxicount &&
-            percpu_counter_read(&args.mp->m_icount) + newlen >
+            percpu_counter_read_positive(&args.mp->m_icount) + newlen >
                                                         args.mp->m_maxicount)
                 return -ENOSPC;
         args.minlen = args.maxlen = args.mp->m_ialloc_blks;
@@ -1339,10 +1339,13 @@ xfs_dialloc(
          * If we have already hit the ceiling of inode blocks then clear
          * okalloc so we scan all available agi structures for a free
          * inode.
+         *
+         * Read rough value of mp->m_icount by percpu_counter_read_positive,
+         * which will sacrifice the preciseness but improve the performance.
          */
         if (mp->m_maxicount &&
-            percpu_counter_read(&mp->m_icount) + mp->m_ialloc_inos >
-                                                        mp->m_maxicount) {
+            percpu_counter_read_positive(&mp->m_icount) + mp->m_ialloc_inos
+                                                        > mp->m_maxicount) {
                 noroom = 1;
                 okalloc = 0;
         }
diff --git a/fs/xfs/xfs_attr_inactive.c b/fs/xfs/xfs_attr_inactive.c
index f9c1c64782d3..3fbf167cfb4c 100644
--- a/fs/xfs/xfs_attr_inactive.c
+++ b/fs/xfs/xfs_attr_inactive.c
@@ -380,23 +380,31 @@ xfs_attr3_root_inactive(
         return error;
 }
 
+/*
+ * xfs_attr_inactive kills all traces of an attribute fork on an inode. It
+ * removes both the on-disk and in-memory inode fork. Note that this also has to
+ * handle the condition of inodes without attributes but with an attribute fork
+ * configured, so we can't use xfs_inode_hasattr() here.
+ *
+ * The in-memory attribute fork is removed even on error.
+ */
 int
-xfs_attr_inactive(xfs_inode_t *dp)
+xfs_attr_inactive(
+        struct xfs_inode        *dp)
 {
-        xfs_trans_t *trans;
-        xfs_mount_t *mp;
-        int error;
+        struct xfs_trans        *trans;
+        struct xfs_mount        *mp;
+        int                     cancel_flags = 0;
+        int                     lock_mode = XFS_ILOCK_SHARED;
+        int                     error = 0;
 
         mp = dp->i_mount;
         ASSERT(! XFS_NOT_DQATTACHED(mp, dp));
 
-        xfs_ilock(dp, XFS_ILOCK_SHARED);
-        if (!xfs_inode_hasattr(dp) ||
-            dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) {
-                xfs_iunlock(dp, XFS_ILOCK_SHARED);
-                return 0;
-        }
-        xfs_iunlock(dp, XFS_ILOCK_SHARED);
+        xfs_ilock(dp, lock_mode);
+        if (!XFS_IFORK_Q(dp))
+                goto out_destroy_fork;
+        xfs_iunlock(dp, lock_mode);
 
         /*
          * Start our first transaction of the day.
@@ -408,13 +416,18 @@ xfs_attr_inactive(xfs_inode_t *dp)
          * the inode in every transaction to let it float upward through
          * the log.
          */
+        lock_mode = 0;
         trans = xfs_trans_alloc(mp, XFS_TRANS_ATTRINVAL);
         error = xfs_trans_reserve(trans, &M_RES(mp)->tr_attrinval, 0, 0);
-        if (error) {
-                xfs_trans_cancel(trans, 0);
-                return error;
-        }
-        xfs_ilock(dp, XFS_ILOCK_EXCL);
+        if (error)
+                goto out_cancel;
+
+        lock_mode = XFS_ILOCK_EXCL;
+        cancel_flags = XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT;
+        xfs_ilock(dp, lock_mode);
+
+        if (!XFS_IFORK_Q(dp))
+                goto out_cancel;
 
         /*
          * No need to make quota reservations here. We expect to release some
@@ -422,29 +435,31 @@ xfs_attr_inactive(xfs_inode_t *dp)
          */
         xfs_trans_ijoin(trans, dp, 0);
 
-        /*
-         * Decide on what work routines to call based on the inode size.
-         */
-        if (!xfs_inode_hasattr(dp) ||
-            dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) {
-                error = 0;
-                goto out;
+        /* invalidate and truncate the attribute fork extents */
+        if (dp->i_d.di_aformat != XFS_DINODE_FMT_LOCAL) {
+                error = xfs_attr3_root_inactive(&trans, dp);
+                if (error)
+                        goto out_cancel;
+
+                error = xfs_itruncate_extents(&trans, dp, XFS_ATTR_FORK, 0);
+                if (error)
+                        goto out_cancel;
         }
-        error = xfs_attr3_root_inactive(&trans, dp);
-        if (error)
-                goto out;
 
-        error = xfs_itruncate_extents(&trans, dp, XFS_ATTR_FORK, 0);
-        if (error)
-                goto out;
+        /* Reset the attribute fork - this also destroys the in-core fork */
+        xfs_attr_fork_remove(dp, trans);
 
         error = xfs_trans_commit(trans, XFS_TRANS_RELEASE_LOG_RES);
-        xfs_iunlock(dp, XFS_ILOCK_EXCL);
-
+        xfs_iunlock(dp, lock_mode);
         return error;
 
-out:
-        xfs_trans_cancel(trans, XFS_TRANS_RELEASE_LOG_RES|XFS_TRANS_ABORT);
-        xfs_iunlock(dp, XFS_ILOCK_EXCL);
+out_cancel:
+        xfs_trans_cancel(trans, cancel_flags);
+out_destroy_fork:
+        /* kill the in-core attr fork before we drop the inode lock */
+        if (dp->i_afp)
+                xfs_idestroy_fork(dp, XFS_ATTR_FORK);
+        if (lock_mode)
+                xfs_iunlock(dp, lock_mode);
         return error;
 }
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 8121e75352ee..3b7591224f4a 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -124,7 +124,7 @@ xfs_iozero(
                 status = 0;
         } while (count);
 
-        return (-status);
+        return status;
 }
 
 int
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index d6ebc85192b7..539a85fddbc2 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1946,21 +1946,17 @@ xfs_inactive(
         /*
          * If there are attributes associated with the file then blow them away
          * now.  The code calls a routine that recursively deconstructs the
-         * attribute fork.  We need to just commit the current transaction
-         * because we can't use it for xfs_attr_inactive().
+         * attribute fork. If also blows away the in-core attribute fork.
          */
-        if (ip->i_d.di_anextents > 0) {
-                ASSERT(ip->i_d.di_forkoff != 0);
-
+        if (XFS_IFORK_Q(ip)) {
                 error = xfs_attr_inactive(ip);
                 if (error)
                         return;
         }
 
-        if (ip->i_afp)
-                xfs_idestroy_fork(ip, XFS_ATTR_FORK);
-
+        ASSERT(!ip->i_afp);
         ASSERT(ip->i_d.di_anextents == 0);
+        ASSERT(ip->i_d.di_forkoff == 0);
 
         /*
          * Free the inode.
@@ -2883,7 +2879,13 @@ xfs_rename_alloc_whiteout(
         if (error)
                 return error;
 
-        /* Satisfy xfs_bumplink that this is a real tmpfile */
+        /*
+         * Prepare the tmpfile inode as if it were created through the VFS.
+         * Otherwise, the link increment paths will complain about nlink 0->1.
+         * Drop the link count as done by d_tmpfile(), complete the inode setup
+         * and flag it as linkable.
+         */
+        drop_nlink(VFS_I(tmpfile));
         xfs_finish_inode_setup(tmpfile);
         VFS_I(tmpfile)->i_state |= I_LINKABLE;
 
@@ -3151,7 +3153,7 @@ xfs_rename(
          * intermediate state on disk.
          */
         if (wip) {
-                ASSERT(wip->i_d.di_nlink == 0);
+                ASSERT(VFS_I(wip)->i_nlink == 0 && wip->i_d.di_nlink == 0);
                 error = xfs_bumplink(tp, wip);
                 if (error)
                         goto out_trans_abort;
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 2ce7ee3b4ec1..6f23fbdfb365 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -1084,14 +1084,18 @@ xfs_log_sbcount(xfs_mount_t *mp)
         return xfs_sync_sb(mp, true);
 }
 
+/*
+ * Deltas for the inode count are +/-64, hence we use a large batch size
+ * of 128 so we don't need to take the counter lock on every update.
+ */
+#define XFS_ICOUNT_BATCH        128
 int
 xfs_mod_icount(
         struct xfs_mount        *mp,
         int64_t                 delta)
 {
-        /* deltas are +/-64, hence the large batch size of 128. */
-        __percpu_counter_add(&mp->m_icount, delta, 128);
-        if (percpu_counter_compare(&mp->m_icount, 0) < 0) {
+        __percpu_counter_add(&mp->m_icount, delta, XFS_ICOUNT_BATCH);
+        if (__percpu_counter_compare(&mp->m_icount, 0, XFS_ICOUNT_BATCH) < 0) {
                 ASSERT(0);
                 percpu_counter_add(&mp->m_icount, -delta);
                 return -EINVAL;
@@ -1113,6 +1117,14 @@ xfs_mod_ifree(
         return 0;
 }
 
+/*
+ * Deltas for the block count can vary from 1 to very large, but lock contention
+ * only occurs on frequent small block count updates such as in the delayed
+ * allocation path for buffered writes (page a time updates). Hence we set
+ * a large batch count (1024) to minimise global counter updates except when
+ * we get near to ENOSPC and we have to be very accurate with our updates.
+ */
+#define XFS_FDBLOCKS_BATCH      1024
 int
 xfs_mod_fdblocks(
         struct xfs_mount        *mp,
@@ -1151,25 +1163,19 @@ xfs_mod_fdblocks(
          * Taking blocks away, need to be more accurate the closer we
          * are to zero.
          *
-         * batch size is set to a maximum of 1024 blocks - if we are
-         * allocating of freeing extents larger than this then we aren't
-         * going to be hammering the counter lock so a lock per update
-         * is not a problem.
-         *
          * If the counter has a value of less than 2 * max batch size,
          * then make everything serialise as we are real close to
          * ENOSPC.
          */
-#define __BATCH 1024
-        if (percpu_counter_compare(&mp->m_fdblocks, 2 * __BATCH) < 0)
+        if (__percpu_counter_compare(&mp->m_fdblocks, 2 * XFS_FDBLOCKS_BATCH,
+                                     XFS_FDBLOCKS_BATCH) < 0)
                 batch = 1;
         else
-                batch = __BATCH;
-#undef __BATCH
+                batch = XFS_FDBLOCKS_BATCH;
 
         __percpu_counter_add(&mp->m_fdblocks, delta, batch);
-        if (percpu_counter_compare(&mp->m_fdblocks,
-                                   XFS_ALLOC_SET_ASIDE(mp)) >= 0) {
+        if (__percpu_counter_compare(&mp->m_fdblocks, XFS_ALLOC_SET_ASIDE(mp),
+                                     XFS_FDBLOCKS_BATCH) >= 0) {
                 /* we had space! */
                 return 0;
         }
diff --git a/include/linux/percpu_counter.h b/include/linux/percpu_counter.h
index 50e50095c8d1..84a109449610 100644
--- a/include/linux/percpu_counter.h
+++ b/include/linux/percpu_counter.h
@@ -41,7 +41,12 @@ void percpu_counter_destroy(struct percpu_counter *fbc);
 void percpu_counter_set(struct percpu_counter *fbc, s64 amount);
 void __percpu_counter_add(struct percpu_counter *fbc, s64 amount, s32 batch);
 s64 __percpu_counter_sum(struct percpu_counter *fbc);
-int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs);
+int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch);
+
+static inline int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs)
+{
+        return __percpu_counter_compare(fbc, rhs, percpu_counter_batch);
+}
 
 static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount)
 {
@@ -116,6 +121,12 @@ static inline int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs)
                 return 0;
 }
 
+static inline int
+__percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch)
+{
+        return percpu_counter_compare(fbc, rhs);
+}
+
 static inline void
 percpu_counter_add(struct percpu_counter *fbc, s64 amount)
 {
diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c
index 48144cdae819..f051d69f0910 100644
--- a/lib/percpu_counter.c
+++ b/lib/percpu_counter.c
@@ -197,13 +197,13 @@ static int percpu_counter_hotcpu_callback(struct notifier_block *nb,
  * Compare counter against given value.
  * Return 1 if greater, 0 if equal and -1 if less
  */
-int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs)
+int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch)
 {
         s64     count;
 
         count = percpu_counter_read(fbc);
         /* Check to see if rough count will be sufficient for comparison */
-        if (abs(count - rhs) > (percpu_counter_batch*num_online_cpus())) {
+        if (abs(count - rhs) > (batch * num_online_cpus())) {
                 if (count > rhs)
                         return 1;
                 else
@@ -218,7 +218,7 @@ int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs)
         else
                 return 0;
 }
-EXPORT_SYMBOL(percpu_counter_compare);
+EXPORT_SYMBOL(__percpu_counter_compare);
 
 static int __init percpu_counter_startup(void)
 {