Merge branch 'upstream-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jlbec/ocfs2

* 'upstream-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jlbec/ocfs2: (47 commits)
  ocfs2: Silence a gcc warning.
  ocfs2: Don't retry xattr set in case value extension fails.
  ocfs2:dlm: avoid dlm->ast_lock lockres->spinlock dependency break
  ocfs2: Reset xattr value size after xa_cleanup_value_truncate().
  fs/ocfs2/dlm: Use kstrdup
  fs/ocfs2/dlm: Drop memory allocation cast
  Ocfs2: Optimize punching-hole code.
  Ocfs2: Make ocfs2_find_cpos_for_left_leaf() public.
  Ocfs2: Fix hole punching to correctly do CoW during cluster zeroing.
  Ocfs2: Optimize ocfs2 truncate to use ocfs2_remove_btree_range() instead.
  ocfs2: Block signals for mkdir/link/symlink/O_CREAT.
  ocfs2: Wrap signal blocking in void functions.
  ocfs2/dlm: Increase o2dlm lockres hash size
  ocfs2: Make ocfs2_extend_trans() really extend.
  ocfs2/trivial: Code cleanup for allocation reservation.
  ocfs2: make ocfs2_adjust_resv_from_alloc simple.
  ocfs2: Make nointr a default mount option
  ocfs2/dlm: Make o2dlm domain join/leave messages KERN_NOTICE
  o2net: log socket state changes
  ocfs2: print node # when tcp fails
  ...

1 files changed, 170 insertions, 45 deletions

diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index a5fbd9cea968..f74f1400eccd 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -278,10 +278,7 @@ int ocfs2_update_inode_atime(struct inode *inode,
         inode->i_atime = CURRENT_TIME;
         di->i_atime = cpu_to_le64(inode->i_atime.tv_sec);
         di->i_atime_nsec = cpu_to_le32(inode->i_atime.tv_nsec);
-
-        ret = ocfs2_journal_dirty(handle, bh);
-        if (ret < 0)
-                mlog_errno(ret);
+        ocfs2_journal_dirty(handle, bh);
 
 out_commit:
         ocfs2_commit_trans(OCFS2_SB(inode->i_sb), handle);
@@ -430,9 +427,7 @@ static int ocfs2_orphan_for_truncate(struct ocfs2_super *osb,
         di->i_ctime = di->i_mtime = cpu_to_le64(inode->i_ctime.tv_sec);
         di->i_ctime_nsec = di->i_mtime_nsec = cpu_to_le32(inode->i_ctime.tv_nsec);
 
-        status = ocfs2_journal_dirty(handle, fe_bh);
-        if (status < 0)
-                mlog_errno(status);
+        ocfs2_journal_dirty(handle, fe_bh);
 
 out_commit:
         ocfs2_commit_trans(osb, handle);
@@ -449,7 +444,6 @@ static int ocfs2_truncate_file(struct inode *inode,
         int status = 0;
         struct ocfs2_dinode *fe = NULL;
         struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
-        struct ocfs2_truncate_context *tc = NULL;
 
         mlog_entry("(inode = %llu, new_i_size = %llu\n",
                    (unsigned long long)OCFS2_I(inode)->ip_blkno,
@@ -488,6 +482,9 @@ static int ocfs2_truncate_file(struct inode *inode,
 
         down_write(&OCFS2_I(inode)->ip_alloc_sem);
 
+        ocfs2_resv_discard(&osb->osb_la_resmap,
+                           &OCFS2_I(inode)->ip_la_data_resv);
+
         /*
          * The inode lock forced other nodes to sync and drop their
          * pages, which (correctly) happens even if we have a truncate
@@ -517,13 +514,7 @@ static int ocfs2_truncate_file(struct inode *inode,
                 goto bail_unlock_sem;
         }
 
-        status = ocfs2_prepare_truncate(osb, inode, di_bh, &tc);
-        if (status < 0) {
-                mlog_errno(status);
-                goto bail_unlock_sem;
-        }
-
-        status = ocfs2_commit_truncate(osb, inode, di_bh, tc);
+        status = ocfs2_commit_truncate(osb, inode, di_bh);
         if (status < 0) {
                 mlog_errno(status);
                 goto bail_unlock_sem;
@@ -666,11 +657,7 @@ restarted_transaction:
                 goto leave;
         }
 
-        status = ocfs2_journal_dirty(handle, bh);
-        if (status < 0) {
-                mlog_errno(status);
-                goto leave;
-        }
+        ocfs2_journal_dirty(handle, bh);
 
         spin_lock(&OCFS2_I(inode)->ip_lock);
         clusters_to_add -= (OCFS2_I(inode)->ip_clusters - prev_clusters);
@@ -1195,9 +1182,7 @@ static int __ocfs2_write_remove_suid(struct inode *inode,
         di = (struct ocfs2_dinode *) bh->b_data;
         di->i_mode = cpu_to_le16(inode->i_mode);
 
-        ret = ocfs2_journal_dirty(handle, bh);
-        if (ret < 0)
-                mlog_errno(ret);
+        ocfs2_journal_dirty(handle, bh);
 
 out_trans:
         ocfs2_commit_trans(osb, handle);
@@ -1434,16 +1419,90 @@ out:
         return ret;
 }
 
+static int ocfs2_find_rec(struct ocfs2_extent_list *el, u32 pos)
+{
+        int i;
+        struct ocfs2_extent_rec *rec = NULL;
+
+        for (i = le16_to_cpu(el->l_next_free_rec) - 1; i >= 0; i--) {
+
+                rec = &el->l_recs[i];
+
+                if (le32_to_cpu(rec->e_cpos) < pos)
+                        break;
+        }
+
+        return i;
+}
+
+/*
+ * Helper to calculate the punching pos and length in one run, we handle the
+ * following three cases in order:
+ *
+ * - remove the entire record
+ * - remove a partial record
+ * - no record needs to be removed (hole-punching completed)
+*/
+static void ocfs2_calc_trunc_pos(struct inode *inode,
+                                 struct ocfs2_extent_list *el,
+                                 struct ocfs2_extent_rec *rec,
+                                 u32 trunc_start, u32 *trunc_cpos,
+                                 u32 *trunc_len, u32 *trunc_end,
+                                 u64 *blkno, int *done)
+{
+        int ret = 0;
+        u32 coff, range;
+
+        range = le32_to_cpu(rec->e_cpos) + ocfs2_rec_clusters(el, rec);
+
+        if (le32_to_cpu(rec->e_cpos) >= trunc_start) {
+                *trunc_cpos = le32_to_cpu(rec->e_cpos);
+                /*
+                 * Skip holes if any.
+                 */
+                if (range < *trunc_end)
+                        *trunc_end = range;
+                *trunc_len = *trunc_end - le32_to_cpu(rec->e_cpos);
+                *blkno = le64_to_cpu(rec->e_blkno);
+                *trunc_end = le32_to_cpu(rec->e_cpos);
+        } else if (range > trunc_start) {
+                *trunc_cpos = trunc_start;
+                *trunc_len = *trunc_end - trunc_start;
+                coff = trunc_start - le32_to_cpu(rec->e_cpos);
+                *blkno = le64_to_cpu(rec->e_blkno) +
+                                ocfs2_clusters_to_blocks(inode->i_sb, coff);
+                *trunc_end = trunc_start;
+        } else {
+                /*
+                 * It may have two following possibilities:
+                 *
+                 * - last record has been removed
+                 * - trunc_start was within a hole
+                 *
+                 * both two cases mean the completion of hole punching.
+                 */
+                ret = 1;
+        }
+
+        *done = ret;
+}
+
 static int ocfs2_remove_inode_range(struct inode *inode,
                                     struct buffer_head *di_bh, u64 byte_start,
                                     u64 byte_len)
 {
-        int ret = 0;
-        u32 trunc_start, trunc_len, cpos, phys_cpos, alloc_size;
+        int ret = 0, flags = 0, done = 0, i;
+        u32 trunc_start, trunc_len, trunc_end, trunc_cpos, phys_cpos;
+        u32 cluster_in_el;
         struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
         struct ocfs2_cached_dealloc_ctxt dealloc;
         struct address_space *mapping = inode->i_mapping;
         struct ocfs2_extent_tree et;
+        struct ocfs2_path *path = NULL;
+        struct ocfs2_extent_list *el = NULL;
+        struct ocfs2_extent_rec *rec = NULL;
+        struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;
+        u64 blkno, refcount_loc = le64_to_cpu(di->i_refcount_loc);
 
         ocfs2_init_dinode_extent_tree(&et, INODE_CACHE(inode), di_bh);
         ocfs2_init_dealloc_ctxt(&dealloc);
@@ -1469,17 +1528,35 @@ static int ocfs2_remove_inode_range(struct inode *inode,
                 goto out;
         }
 
+        /*
+         * For reflinks, we may need to CoW 2 clusters which might be
+         * partially zero'd later, if hole's start and end offset were
+         * within one cluster(means is not exactly aligned to clustersize).
+         */
+
+        if (OCFS2_I(inode)->ip_dyn_features & OCFS2_HAS_REFCOUNT_FL) {
+
+                ret = ocfs2_cow_file_pos(inode, di_bh, byte_start);
+                if (ret) {
+                        mlog_errno(ret);
+                        goto out;
+                }
+
+                ret = ocfs2_cow_file_pos(inode, di_bh, byte_start + byte_len);
+                if (ret) {
+                        mlog_errno(ret);
+                        goto out;
+                }
+        }
+
         trunc_start = ocfs2_clusters_for_bytes(osb->sb, byte_start);
-        trunc_len = (byte_start + byte_len) >> osb->s_clustersize_bits;
-        if (trunc_len >= trunc_start)
-                trunc_len -= trunc_start;
-        else
-                trunc_len = 0;
+        trunc_end = (byte_start + byte_len) >> osb->s_clustersize_bits;
+        cluster_in_el = trunc_end;
 
-        mlog(0, "Inode: %llu, start: %llu, len: %llu, cstart: %u, clen: %u\n",
+        mlog(0, "Inode: %llu, start: %llu, len: %llu, cstart: %u, cend: %u\n",
              (unsigned long long)OCFS2_I(inode)->ip_blkno,
              (unsigned long long)byte_start,
-             (unsigned long long)byte_len, trunc_start, trunc_len);
+             (unsigned long long)byte_len, trunc_start, trunc_end);
 
         ret = ocfs2_zero_partial_clusters(inode, byte_start, byte_len);
         if (ret) {
@@ -1487,31 +1564,79 @@ static int ocfs2_remove_inode_range(struct inode *inode,
                 goto out;
         }
 
-        cpos = trunc_start;
-        while (trunc_len) {
-                ret = ocfs2_get_clusters(inode, cpos, &phys_cpos,
-                                         &alloc_size, NULL);
+        path = ocfs2_new_path_from_et(&et);
+        if (!path) {
+                ret = -ENOMEM;
+                mlog_errno(ret);
+                goto out;
+        }
+
+        while (trunc_end > trunc_start) {
+
+                ret = ocfs2_find_path(INODE_CACHE(inode), path,
+                                      cluster_in_el);
                 if (ret) {
                         mlog_errno(ret);
                         goto out;
                 }
 
-                if (alloc_size > trunc_len)
-                        alloc_size = trunc_len;
+                el = path_leaf_el(path);
 
-                /* Only do work for non-holes */
-                if (phys_cpos != 0) {
-                        ret = ocfs2_remove_btree_range(inode, &et, cpos,
-                                                       phys_cpos, alloc_size,
-                                                       &dealloc);
+                i = ocfs2_find_rec(el, trunc_end);
+                /*
+                 * Need to go to previous extent block.
+                 */
+                if (i < 0) {
+                        if (path->p_tree_depth == 0)
+                                break;
+
+                        ret = ocfs2_find_cpos_for_left_leaf(inode->i_sb,
+                                                            path,
+                                                            &cluster_in_el);
                         if (ret) {
                                 mlog_errno(ret);
                                 goto out;
                         }
+
+                        /*
+                         * We've reached the leftmost extent block,
+                         * it's safe to leave.
+                         */
+                        if (cluster_in_el == 0)
+                                break;
+
+                        /*
+                         * The 'pos' searched for previous extent block is
+                         * always one cluster less than actual trunc_end.
+                         */
+                        trunc_end = cluster_in_el + 1;
+
+                        ocfs2_reinit_path(path, 1);
+
+                        continue;
+
+                } else
+                        rec = &el->l_recs[i];
+
+                ocfs2_calc_trunc_pos(inode, el, rec, trunc_start, &trunc_cpos,
+                                     &trunc_len, &trunc_end, &blkno, &done);
+                if (done)
+                        break;
+
+                flags = rec->e_flags;
+                phys_cpos = ocfs2_blocks_to_clusters(inode->i_sb, blkno);
+
+                ret = ocfs2_remove_btree_range(inode, &et, trunc_cpos,
+                                               phys_cpos, trunc_len, flags,
+                                               &dealloc, refcount_loc);
+                if (ret < 0) {
+                        mlog_errno(ret);
+                        goto out;
                 }
 
-                cpos += alloc_size;
-                trunc_len -= alloc_size;
+                cluster_in_el = trunc_end;
+
+                ocfs2_reinit_path(path, 1);
         }
 
         ocfs2_truncate_cluster_pages(inode, byte_start, byte_len);