[PATCH] blk: fix tag shrinking (revive real_max_size)
My patch in commit fa72b903f75e4f0f0b2c2feed093005167da4023 incorrectly
removed blk_queue_tag->real_max_depth.
The original resize implementation was incorrect in the following
points.
* actual allocation size of tag_index was shorter than real_max_size,
but assumed to be of the same size, possibly causing memory access
beyond the allocated area.
* bits in tag_map between max_deptn and real_max_depth were
initialized to 1's, making the tags permanently reserved.
In an attempt to fix above two bugs, I had removed allocation optimization
in init_tag_map and real_max_size. Tag map/index were allocated and freed
immediately during resize.
Unfortunately, I wasn't considering that tag map/index can be resized
dynamically with tags beyond new_depth active. This led to accessing
freed area after shrinking tags and led to the following bug reporting
thread on linux-scsi.
http://marc.theaimsgroup.com/?l=linux-scsi&m=112319898111885&w=2
To fix the problem, I've revived real_max_depth without allocation
optimization in init_tag_map, and Andrew Vasquez confirmed that the
problem was fixed. As Jens is not going to be available for a week, he
asked me to make sure that this patch reaches you.
http://marc.theaimsgroup.com/?l=linux-scsi&m=112325778530886&w=2
Also, a comment was added to make sure that real_max_size is needed for
dynamic shrinking.
Signed-off-by: Tejun Heo <htejun@gmail.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
diff --git a/drivers/block/ll_rw_blk.c b/drivers/block/ll_rw_blk.c
index 692a5fc..3c81854 100644
--- a/drivers/block/ll_rw_blk.c
+++ b/drivers/block/ll_rw_blk.c
@@ -719,7 +719,7 @@
{
struct blk_queue_tag *bqt = q->queue_tags;
- if (unlikely(bqt == NULL || tag >= bqt->max_depth))
+ if (unlikely(bqt == NULL || tag >= bqt->real_max_depth))
return NULL;
return bqt->tag_index[tag];
@@ -798,6 +798,7 @@
memset(tag_index, 0, depth * sizeof(struct request *));
memset(tag_map, 0, nr_ulongs * sizeof(unsigned long));
+ tags->real_max_depth = depth;
tags->max_depth = depth;
tags->tag_index = tag_index;
tags->tag_map = tag_map;
@@ -872,11 +873,22 @@
return -ENXIO;
/*
+ * if we already have large enough real_max_depth. just
+ * adjust max_depth. *NOTE* as requests with tag value
+ * between new_depth and real_max_depth can be in-flight, tag
+ * map can not be shrunk blindly here.
+ */
+ if (new_depth <= bqt->real_max_depth) {
+ bqt->max_depth = new_depth;
+ return 0;
+ }
+
+ /*
* save the old state info, so we can copy it back
*/
tag_index = bqt->tag_index;
tag_map = bqt->tag_map;
- max_depth = bqt->max_depth;
+ max_depth = bqt->real_max_depth;
if (init_tag_map(q, bqt, new_depth))
return -ENOMEM;
@@ -913,7 +925,7 @@
BUG_ON(tag == -1);
- if (unlikely(tag >= bqt->max_depth))
+ if (unlikely(tag >= bqt->real_max_depth))
/*
* This can happen after tag depth has been reduced.
* FIXME: how about a warning or info message here?
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 0881b5c..19bd8e7 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -301,6 +301,7 @@
struct list_head busy_list; /* fifo list of busy tags */
int busy; /* current depth */
int max_depth; /* what we will send to device */
+ int real_max_depth; /* what the array can hold */
atomic_t refcnt; /* map can be shared */
};
