ocfs2: Allow smaller allocations during large writes

The ocfs2 write code loops through a page much like the block code, except
that ocfs2 allocation units can be any size, including larger than page
size. Typically it's equal to or larger than page size - most kernels run 4k
pages, the minimum ocfs2 allocation (cluster) size.

Some changes introduced during 2.6.23 changed the way writes to pages are
handled, and inadvertantly broke support for > 4k page size. Instead of just
writing one cluster at a time, we now handle the whole page in one pass.

This means that multiple (small) seperate allocations might happen in the
same pass. The allocation code howver typically optimizes by getting the
maximum which was reserved. This triggered a BUG_ON in the extend code where
it'd ask for a single bit (for one part of a > 4k page) and get back more
than it asked for.

Fix this by providing a variant of the high level allocation function which
allows the caller to specify a maximum. The traditional function remains and
just calls the new one with a maximum determined from the initial
reservation.

Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>

5 files changed, 36 insertions, 14 deletions

diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 7e34e66159c6..f3bc3658e7a5 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -491,8 +491,8 @@ int ocfs2_do_extend_allocation(struct ocfs2_super *osb,
                 goto leave;
         }
 
-        status = ocfs2_claim_clusters(osb, handle, data_ac, 1,
-                                      &bit_off, &num_bits);
+        status = __ocfs2_claim_clusters(osb, handle, data_ac, 1,
+                                        clusters_to_add, &bit_off, &num_bits);
         if (status < 0) {
                 if (status != -ENOSPC)
                         mlog_errno(status);
diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c
index 545f7892cdf3..de984d272576 100644
--- a/fs/ocfs2/localalloc.c
+++ b/fs/ocfs2/localalloc.c
@@ -524,13 +524,12 @@ bail:
 int ocfs2_claim_local_alloc_bits(struct ocfs2_super *osb,
                                  handle_t *handle,
                                  struct ocfs2_alloc_context *ac,
-                                 u32 min_bits,
+                                 u32 bits_wanted,
                                  u32 *bit_off,
                                  u32 *num_bits)
 {
         int status, start;
         struct inode *local_alloc_inode;
-        u32 bits_wanted;
         void *bitmap;
         struct ocfs2_dinode *alloc;
         struct ocfs2_local_alloc *la;
@@ -538,7 +537,6 @@ int ocfs2_claim_local_alloc_bits(struct ocfs2_super *osb,
         mlog_entry_void();
         BUG_ON(ac->ac_which != OCFS2_AC_USE_LOCAL);
 
-        bits_wanted = ac->ac_bits_wanted - ac->ac_bits_given;
         local_alloc_inode = ac->ac_inode;
         alloc = (struct ocfs2_dinode *) osb->local_alloc_bh->b_data;
         la = OCFS2_LOCAL_ALLOC(alloc);
diff --git a/fs/ocfs2/localalloc.h b/fs/ocfs2/localalloc.h
index 385a10152f9c..3f76631e110c 100644
--- a/fs/ocfs2/localalloc.h
+++ b/fs/ocfs2/localalloc.h
@@ -48,7 +48,7 @@ int ocfs2_reserve_local_alloc_bits(struct ocfs2_super *osb,
 int ocfs2_claim_local_alloc_bits(struct ocfs2_super *osb,
                                  handle_t *handle,
                                  struct ocfs2_alloc_context *ac,
-                                 u32 min_bits,
+                                 u32 bits_wanted,
                                  u32 *bit_off,
                                  u32 *num_bits);
 
diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c
index d9c5c9fcb30f..8f09f5235e3a 100644
--- a/fs/ocfs2/suballoc.c
+++ b/fs/ocfs2/suballoc.c
@@ -1486,21 +1486,21 @@ static inline void ocfs2_block_to_cluster_group(struct inode *inode,
  * contig. allocation, set to '1' to indicate we can deal with extents
  * of any size.
  */
-int ocfs2_claim_clusters(struct ocfs2_super *osb,
-                         handle_t *handle,
-                         struct ocfs2_alloc_context *ac,
-                         u32 min_clusters,
-                         u32 *cluster_start,
-                         u32 *num_clusters)
+int __ocfs2_claim_clusters(struct ocfs2_super *osb,
+                           handle_t *handle,
+                           struct ocfs2_alloc_context *ac,
+                           u32 min_clusters,
+                           u32 max_clusters,
+                           u32 *cluster_start,
+                           u32 *num_clusters)
 {
         int status;
-        unsigned int bits_wanted = ac->ac_bits_wanted - ac->ac_bits_given;
+        unsigned int bits_wanted = max_clusters;
         u64 bg_blkno = 0;
         u16 bg_bit_off;
 
         mlog_entry_void();
 
-        BUG_ON(!ac);
         BUG_ON(ac->ac_bits_given >= ac->ac_bits_wanted);
 
         BUG_ON(ac->ac_which != OCFS2_AC_USE_LOCAL
@@ -1557,6 +1557,19 @@ bail:
         return status;
 }
 
+int ocfs2_claim_clusters(struct ocfs2_super *osb,
+                         handle_t *handle,
+                         struct ocfs2_alloc_context *ac,
+                         u32 min_clusters,
+                         u32 *cluster_start,
+                         u32 *num_clusters)
+{
+        unsigned int bits_wanted = ac->ac_bits_wanted - ac->ac_bits_given;
+
+        return __ocfs2_claim_clusters(osb, handle, ac, min_clusters,
+                                      bits_wanted, cluster_start, num_clusters);
+}
+
 static inline int ocfs2_block_group_clear_bits(handle_t *handle,
                                                struct inode *alloc_inode,
                                                struct ocfs2_group_desc *bg,
diff --git a/fs/ocfs2/suballoc.h b/fs/ocfs2/suballoc.h
index f212dc01a84b..cafe93703095 100644
--- a/fs/ocfs2/suballoc.h
+++ b/fs/ocfs2/suballoc.h
@@ -85,6 +85,17 @@ int ocfs2_claim_clusters(struct ocfs2_super *osb,
                          u32 min_clusters,
                          u32 *cluster_start,
                          u32 *num_clusters);
+/*
+ * Use this variant of ocfs2_claim_clusters to specify a maxiumum
+ * number of clusters smaller than the allocation reserved.
+ */
+int __ocfs2_claim_clusters(struct ocfs2_super *osb,
+                           handle_t *handle,
+                           struct ocfs2_alloc_context *ac,
+                           u32 min_clusters,
+                           u32 max_clusters,
+                           u32 *cluster_start,
+                           u32 *num_clusters);
 
 int ocfs2_free_suballoc_bits(handle_t *handle,
                              struct inode *alloc_inode,