After we mark the blocks in the buddy cache as allocated,
we should ensure that we don't reinit the buddy cache untill
the block bitmap is updated. The patch achieve this by holding
the group_info alloc_semaphore till ext4_mb_release_context
v3 changes:
drop page refence and alloc_sem if we are retrying allocation
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@xxxxxxxxxxxxxxxxxx>
---
fs/ext4/mballoc.c | 21 ++++++++++++++++++---
fs/ext4/mballoc.h | 5 +++++
2 files changed, 23 insertions(+), 3 deletions(-)
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 24fc3ab..3270204 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -1055,7 +1055,8 @@ __releases(e4b->alloc_semp)
if (e4b->bd_buddy_page)
page_cache_release(e4b->bd_buddy_page);
/* Done with the buddy cache */
- up_read(e4b->alloc_semp);
+ if (e4b->alloc_semp)
+ up_read(e4b->alloc_semp);
__release(e4b->alloc_semp);
}
@@ -1375,7 +1376,9 @@ static void ext4_mb_use_best_found(struct ext4_allocation_context *ac,
get_page(ac->ac_bitmap_page);
ac->ac_buddy_page = e4b->bd_buddy_page;
get_page(ac->ac_buddy_page);
-
+ /* on allocation we use ac to track the held semaphore */
+ ac->alloc_semp = e4b->alloc_semp;
+ e4b->alloc_semp = NULL;
/* store last allocated for subsequent stream allocation */
if ((ac->ac_flags & EXT4_MB_HINT_DATA)) {
spin_lock(&sbi->s_md_lock);
@@ -4297,6 +4300,7 @@ ext4_mb_initialize_context(struct ext4_allocation_context *ac,
ac->ac_pa = NULL;
ac->ac_bitmap_page = NULL;
ac->ac_buddy_page = NULL;
+ ac->alloc_semp = NULL;
ac->ac_lg = NULL;
/* we have to define context: we'll we work with a file or
@@ -4478,6 +4482,8 @@ static int ext4_mb_release_context(struct ext4_allocation_context *ac)
}
ext4_mb_put_pa(ac, ac->ac_sb, pa);
}
+ if (ac->alloc_semp)
+ up_read(ac->alloc_semp);
if (ac->ac_bitmap_page)
page_cache_release(ac->ac_bitmap_page);
if (ac->ac_buddy_page)
@@ -4578,7 +4584,6 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle,
ac->ac_o_ex.fe_len < ac->ac_b_ex.fe_len)
ext4_mb_new_preallocation(ac);
}
-
if (likely(ac->ac_status == AC_STATUS_FOUND)) {
*errp = ext4_mb_mark_diskspace_used(ac, handle, reserv_blks);
if (*errp == -EAGAIN) {
@@ -4586,6 +4591,16 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle,
ac->ac_b_ex.fe_start = 0;
ac->ac_b_ex.fe_len = 0;
ac->ac_status = AC_STATUS_CONTINUE;
+ /*
+ * drop the reference that we took
+ * in ext4_mb_use_best_found
+ */
+ if (ac->alloc_semp)
+ up_read(ac->alloc_semp);
+ if (ac->ac_bitmap_page)
+ page_cache_release(ac->ac_bitmap_page);
+ if (ac->ac_buddy_page)
+ page_cache_release(ac->ac_buddy_page);
goto repeat;
} else if (*errp) {
ac->ac_b_ex.fe_len = 0;
diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h
index 95d4c7f..3b598c7 100644
--- a/fs/ext4/mballoc.h
+++ b/fs/ext4/mballoc.h
@@ -195,6 +195,11 @@ struct ext4_allocation_context {
__u8 ac_op; /* operation, for history only */
struct page *ac_bitmap_page;
struct page *ac_buddy_page;
+ /*
+ * pointer to the held semaphore upon successfull
+ * block allocation
+ */
+ struct rw_semaphore *alloc_semp;
struct ext4_prealloc_space *ac_pa;
struct ext4_locality_group *ac_lg;
};
--
1.6.1.rc1
--
To unsubscribe from this list: send the line "unsubscribe linux-ext4" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
