Large store support for ext2fs

This is a revised version of the large store patch for ext2fs, written
by Ognyan Kulev. It provides support for stores larger than 2 GiB.

* ext2fs/balloc.c: Use the new disk_cache_block_ref and disk_cache_block_deref
functions to access blocks from the disk cache.
* ext2fs/ext2fs.c (main): Update initialization call to pokel_init, and
call map_hypermetadata instead of get_hypermetadata.
* ext2fs/ext2fs.h: Include <hurd/store.h> and <hurd/ihash.h>.
(DISK_CACHE_BLOCKS): New macro.
(DC_INCORE): Likewise.
(DC_UNTOUCHED): Likewise.
(DC_FIXED): Likewise.
(DC_DONT_REUSE): Likewise.
(DC_NO_BLOCK): Likewise.
(DISK_CACHE_LAST_READ_XOR) [!NDEBUG]: Likewise.
(struct disk_cache_info): New structure.
(disk_cache): New external variable.
(disk_cache_size): Likewise.
(disk_cache_blocks): Likewise.
(disk_cache_bptr): Likewise.
(disk_cache_info): Likewise.
(disk_cache_lock): Likewise.
(disk_cache_reassociation): Likewise.
(disk_cache_block_ref): New declaration.
(disk_cache_block_ref_ptr): Likewise.
(disk_cache_block_deref): Likewise.
(disk_cache_block_is_ref): Likewise.
(map_hypermetadata): Likewise.
(trunc_block): Cast to off_t.
(round_block): Likewise.
(boffs): Likewise.
(bptr_index): New macro.
(boffs_ptr): Rewrite as an inline function to make it look up a block from
the disk cache.
(bptr_offs): Likewise.
(dino): Remove function, replaced with ...
(dino_ref): ... this one, which adds a reference to the inode block.
(dino_deref): New inline function.
(record_global_poke): Make sure block is referenced.
(record_indir_poke): Likewise.
(sync_global_ptr): Remove block reference, and adjust call to
pager_sync_some.
(sync_global): Add debug call to print wait parameter.
* ext2fs/getblk.c: Use the new disk_cache_block_ref and disk_cache_block_deref
functions to access blocks from the disk cache.
* ext2fs/hyper.c (get_hypermetadata): Read the superblock from the store
now that it's not directly mapped in memory. Move the initialization of
zeroblock here from ...
(map_hypermetadata): ... here. Also, set the superblock pointer.
(diskfs_set_hypermetadata): Add a reference to the superblock.
(diskfs_readonly_changed): Update call to mprotect.
* ext2fs/ialloc.c: Use the new disk_cache_block_ref, disk_cache_block_ref_ptr
and disk_cache_block_deref functions to access blocks from the disk cache.
* ext2fs/inode.c: Update calls that used the disk image to use the disk cache,
and use the new reference handling functions where appropriate.
* ext2fs/pager.c: Include <unistd.h> and "../libpager/priv.h".
(disk_image): Remove global variable.
(disk_pager_read_page): Update cache information.
(disk_pager_write_page): Likewise.
(disk_pager_notify_evict): New function.
(pager_notify_evict): Call disk_pager_notify_evict appropriately.
(disk_cache): New global variable.
(disk_cache_size): Likewise.
(disk_cache_blocks): Likewise.
(disk_cache_bptr): Likewise.
(disk_cache_info): Likewise.
(disk_cache_hint): Likewise.
(disk_cache_lock): Likewise.
(disk_cache_reassociation): Likewise.
(disk_cache_init): New function.
(disk_cache_return_unused): Likewise.
(disk_cache_block_ref): Likewise.
(disk_cache_block_ref_ptr): Likewise.
(disk_cache_block_deref): Likewise.
(disk_cache_block_is_ref): Likewise.
(create_disk_pager): Update initialization of the disk pager.
* ext2fs/pokel.c (pokel_add): Drop block references with disk_cache_block_deref.
(_pokel_exec): Likewise.
* ext2fs/truncate.c (trunc_indirect): Use the new disk_cache_block_ref and
disk_cache_block_deref functions to access blocks from the disk cache.

1 files changed, 30 insertions, 7 deletions

diff --git a/ext2fs/ialloc.c b/ext2fs/ialloc.c
index aa018d94..2d8e51e0 100644
--- a/ext2fs/ialloc.c
+++ b/ext2fs/ialloc.c
@@ -75,22 +75,25 @@ diskfs_free_node (struct node *np, mode_t old_mode)
   bit = (inum - 1) % sblock->s_inodes_per_group;
 
   gdp = group_desc (block_group);
-  bh = bptr (gdp->bg_inode_bitmap);
+  bh = disk_cache_block_ref (gdp->bg_inode_bitmap);
 
   if (!clear_bit (bit, bh))
     ext2_warning ("bit already cleared for inode %Ld", inum);
   else
     {
+      disk_cache_block_ref_ptr (bh);
       record_global_poke (bh);
 
       gdp->bg_free_inodes_count++;
       if (S_ISDIR (old_mode))
 	gdp->bg_used_dirs_count--;
+      disk_cache_block_ref_ptr (gdp);
       record_global_poke (gdp);
 
       sblock->s_free_inodes_count++;
     }
 
+  disk_cache_block_deref (bh);
   sblock_dirty = 1;
   pthread_spin_unlock (&global_lock);
   alloc_sync(0);
@@ -111,7 +114,7 @@ diskfs_free_node (struct node *np, mode_t old_mode)
 ino_t
 ext2_alloc_inode (ino_t dir_inum, mode_t mode)
 {
-  char *bh;
+  char *bh = NULL;
   int i, j, inum, avefreei;
   struct ext2_group_desc *gdp;
   struct ext2_group_desc *tmp;
@@ -119,6 +122,7 @@ ext2_alloc_inode (ino_t dir_inum, mode_t mode)
   pthread_spin_lock (&global_lock);
 
 repeat:
+  assert (bh == NULL);
   gdp = NULL;
   i = 0;
 
@@ -213,7 +217,7 @@ repeat:
       return 0;
     }
 
-  bh = bptr (gdp->bg_inode_bitmap);
+  bh = disk_cache_block_ref (gdp->bg_inode_bitmap);
   if ((inum =
        find_first_zero_bit ((unsigned long *) bh, sblock->s_inodes_per_group))
       < sblock->s_inodes_per_group)
@@ -221,12 +225,17 @@ repeat:
       if (set_bit (inum, bh))
 	{
 	  ext2_warning ("bit already set for inode %d", inum);
+	  disk_cache_block_deref (bh);
+	  bh = NULL;
 	  goto repeat;
 	}
       record_global_poke (bh);
+      bh = NULL;
     }
   else
     {
+      disk_cache_block_deref (bh);
+      bh = NULL;
       if (gdp->bg_free_inodes_count != 0)
 	{
 	  ext2_error ("free inodes count corrupted in group %d", i);
@@ -248,15 +257,25 @@ repeat:
   gdp->bg_free_inodes_count--;
   if (S_ISDIR (mode))
     gdp->bg_used_dirs_count++;
+  disk_cache_block_ref_ptr (gdp);
   record_global_poke (gdp);
 
   sblock->s_free_inodes_count--;
   sblock_dirty = 1;
 
  sync_out:
+  assert (bh == NULL);
   pthread_spin_unlock (&global_lock);
   alloc_sync (0);
 
+  /* Make sure the coming read_node won't complain about bad
+     fields.  */
+  {
+    struct ext2_inode *di = dino_ref (inum);
+    memset (di, 0, sizeof *di);
+    dino_deref (di);
+  }
+
   return inum;
 }
 
@@ -353,10 +372,12 @@ ext2_count_free_inodes ()
   gdp = NULL;
   for (i = 0; i < groups_count; i++)
     {
+      void *bh;
       gdp = group_desc (i);
       desc_count += gdp->bg_free_inodes_count;
-      x = count_free (bptr (gdp->bg_inode_bitmap),
-		      sblock->s_inodes_per_group / 8);
+      bh = disk_cache_block_ref (gdp->bg_inode_bitmap);
+      x = count_free (bh, sblock->s_inodes_per_group / 8);
+      disk_cache_block_deref (bh);
       ext2_debug ("group %d: stored = %d, counted = %lu",
 		  i, gdp->bg_free_inodes_count, x);
       bitmap_count += x;
@@ -386,10 +407,12 @@ ext2_check_inodes_bitmap ()
   gdp = NULL;
   for (i = 0; i < groups_count; i++)
     {
+      void *bh;
       gdp = group_desc (i);
       desc_count += gdp->bg_free_inodes_count;
-      x = count_free (bptr (gdp->bg_inode_bitmap),
-		      sblock->s_inodes_per_group / 8);
+      bh = disk_cache_block_ref (gdp->bg_inode_bitmap);
+      x = count_free (bh, sblock->s_inodes_per_group / 8);
+      disk_cache_block_deref (bh);
       if (gdp->bg_free_inodes_count != x)
 	ext2_error ("wrong free inodes count in group %d, "
 		    "stored = %d, counted = %lu",