ext4: let ext4 maintain extent status tree

This patch lets ext4 maintain extent status tree.

Currently it only tracks delay extent status in extent status tree.  When a
delay allocation is issued, the related delay extent will be inserted into
extent status tree.  When a delay extent is written out or invalidated, it will
be removed from this tree.

Signed-off-by: Yongqiang Yang <xiaoqiangnk@gmail.com>
Signed-off-by: Allison Henderson <achender@linux.vnet.ibm.com>
Signed-off-by: Zheng Liu <wenqing.lz@taobao.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>

4 files changed, 51 insertions, 4 deletions

diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index dce97de6a409..67660fa2a7e6 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -4344,6 +4344,8 @@ void ext4_ext_truncate(struct inode *inode)
 
         last_block = (inode->i_size + sb->s_blocksize - 1)
                         >> EXT4_BLOCK_SIZE_BITS(sb);
+        err = ext4_es_remove_extent(inode, last_block,
+                                    EXT_MAX_BLOCKS - last_block);
         err = ext4_ext_remove_space(inode, last_block, EXT_MAX_BLOCKS - 1);
 
         /* In a multi-transaction truncate, we only make the final
@@ -4971,6 +4973,8 @@ int ext4_ext_punch_hole(struct file *file, loff_t offset, loff_t length)
         ext4_ext_invalidate_cache(inode);
         ext4_discard_preallocations(inode);
 
+        err = ext4_es_remove_extent(inode, first_block,
+                                    stop_block - first_block);
         err = ext4_ext_remove_space(inode, first_block, stop_block - 1);
 
         ext4_ext_invalidate_cache(inode);
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index 292337f27c9c..f6663c3a946d 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -1411,6 +1411,7 @@ void ext4_ind_truncate(struct inode *inode)
         down_write(&ei->i_data_sem);
 
         ext4_discard_preallocations(inode);
+        ext4_es_remove_extent(inode, last_block, EXT_MAX_BLOCKS - last_block);
 
         /*
          * The orphan list entry will now protect us from any crash which
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index f84bfd6d1867..1e92349272e0 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -574,7 +574,16 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
                 up_read((&EXT4_I(inode)->i_data_sem));
 
         if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) {
-                int ret = check_block_validity(inode, map);
+                int ret;
+                if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) {
+                        /* delayed alloc may be allocated by fallocate and
+                         * coverted to initialized by directIO.
+                         * we need to handle delayed extent here.
+                         */
+                        down_write((&EXT4_I(inode)->i_data_sem));
+                        goto delayed_mapped;
+                }
+                ret = check_block_validity(inode, map);
                 if (ret != 0)
                         return ret;
         }
@@ -656,8 +665,16 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
                  * set the BH_Da_Mapped bit on them. Its important to do this
                  * under the protection of i_data_sem.
                  */
-                if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED)
+                if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) {
+                        int ret;
                         set_buffers_da_mapped(inode, map);
+delayed_mapped:
+                        /* delayed allocation blocks has been allocated */
+                        ret = ext4_es_remove_extent(inode, map->m_lblk,
+                                                    map->m_len);
+                        if (ret < 0)
+                                retval = ret;
+                }
         }
 
         up_write((&EXT4_I(inode)->i_data_sem));
@@ -1303,6 +1320,7 @@ static void ext4_da_page_release_reservation(struct page *page,
         struct inode *inode = page->mapping->host;
         struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
         int num_clusters;
+        ext4_fsblk_t lblk;
 
         head = page_buffers(page);
         bh = head;
@@ -1317,11 +1335,15 @@ static void ext4_da_page_release_reservation(struct page *page,
                 curr_off = next_off;
         } while ((bh = bh->b_this_page) != head);
 
+        if (to_release) {
+                lblk = page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits);
+                ext4_es_remove_extent(inode, lblk, to_release);
+        }
+
         /* If we have released all the blocks belonging to a cluster, then we
          * need to release the reserved space for that cluster. */
         num_clusters = EXT4_NUM_B2C(sbi, to_release);
         while (num_clusters > 0) {
-                ext4_fsblk_t lblk;
                 lblk = (page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits)) +
                         ((num_clusters - 1) << sbi->s_cluster_bits);
                 if (sbi->s_cluster_ratio == 1 ||
@@ -1502,9 +1524,15 @@ static void ext4_da_block_invalidatepages(struct mpage_da_data *mpd)
         struct pagevec pvec;
         struct inode *inode = mpd->inode;
         struct address_space *mapping = inode->i_mapping;
+        ext4_lblk_t start, last;
 
         index = mpd->first_page;
         end   = mpd->next_page - 1;
+
+        start = index << (PAGE_CACHE_SHIFT - inode->i_blkbits);
+        last = end << (PAGE_CACHE_SHIFT - inode->i_blkbits);
+        ext4_es_remove_extent(inode, start, last - start + 1);
+
         while (index <= end) {
                 nr_pages = pagevec_lookup(&pvec, mapping, index, PAGEVEC_SIZE);
                 if (nr_pages == 0)
@@ -1816,6 +1844,10 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock,
                                 goto out_unlock;
                 }
 
+                retval = ext4_es_insert_extent(inode, map->m_lblk, map->m_len);
+                if (retval)
+                        goto out_unlock;
+
                 /* Clear EXT4_MAP_FROM_CLUSTER flag since its purpose is served
                  * and it should not appear on the bh->b_state.
                  */
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 6791d091fbc7..ad6cd8aeb946 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -50,6 +50,7 @@
 #include "xattr.h"
 #include "acl.h"
 #include "mballoc.h"
+#include "ext4_extents.h"
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/ext4.h>
@@ -1033,6 +1034,7 @@ void ext4_clear_inode(struct inode *inode)
         clear_inode(inode);
         dquot_drop(inode);
         ext4_discard_preallocations(inode);
+        ext4_es_remove_extent(inode, 0, EXT_MAX_BLOCKS);
         if (EXT4_I(inode)->jinode) {
                 jbd2_journal_release_jbd_inode(EXT4_JOURNAL(inode),
                                                EXT4_I(inode)->jinode);
@@ -5296,9 +5298,14 @@ static int __init ext4_init_fs(void)
                 init_waitqueue_head(&ext4__ioend_wq[i]);
         }
 
-        err = ext4_init_pageio();
+        err = ext4_init_es();
         if (err)
                 return err;
+
+        err = ext4_init_pageio();
+        if (err)
+                goto out7;
+
         err = ext4_init_system_zone();
         if (err)
                 goto out6;
@@ -5348,6 +5355,9 @@ out5:
         ext4_exit_system_zone();
 out6:
         ext4_exit_pageio();
+out7:
+        ext4_exit_es();
+
         return err;
 }