[PATCH 4.9 021/138] dm: allocate struct mapped_device with kvzalloc

[Greg Kroah-Hartman]

4.9-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Mikulas Patocka <mpatocka@xxxxxxxxxx>

commit 856eb0916d181da6d043cc33e03f54d5c5bbe54a upstream.

The structure srcu_struct can be very big, its size is proportional to the
value CONFIG_NR_CPUS. The Fedora kernel has CONFIG_NR_CPUS 8192, the field
io_barrier in the struct mapped_device has 84kB in the debugging kernel
and 50kB in the non-debugging kernel. The large size may result in failure
of the function kzalloc_node.

In order to avoid the allocation failure, we use the function
kvzalloc_node, this function falls back to vmalloc if a large contiguous
chunk of memory is not available. This patch also moves the field
io_barrier to the last position of struct mapped_device - the reason is
that on many processor architectures, short memory offsets result in
smaller code than long memory offsets - on x86-64 it reduces code size by
320 bytes.

Note to stable kernel maintainers - the kernels 4.11 and older don't have
the function kvzalloc_node, you can use the function vzalloc_node instead.

Signed-off-by: Mikulas Patocka <mpatocka@xxxxxxxxxx>
Signed-off-by: Mike Snitzer <snitzer@xxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>

---
 drivers/md/dm-core.h |    3 ++-
 drivers/md/dm.c      |    7 ++++---
 2 files changed, 6 insertions(+), 4 deletions(-)

--- a/drivers/md/dm-core.h
+++ b/drivers/md/dm-core.h
@@ -29,7 +29,6 @@ struct dm_kobject_holder {
  * DM targets must _not_ deference a mapped_device to directly access its members!
  */
 struct mapped_device {
-	struct srcu_struct io_barrier;
 	struct mutex suspend_lock;
 
 	/*
@@ -127,6 +126,8 @@ struct mapped_device {
 	struct blk_mq_tag_set *tag_set;
 	bool use_blk_mq:1;
 	bool init_tio_pdu:1;
+
+	struct srcu_struct io_barrier;
 };
 
 void dm_init_md_queue(struct mapped_device *md);
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -21,6 +21,7 @@
 #include <linux/delay.h>
 #include <linux/wait.h>
 #include <linux/pr.h>
+#include <linux/vmalloc.h>
 
 #define DM_MSG_PREFIX "core"
 
@@ -1511,7 +1512,7 @@ static struct mapped_device *alloc_dev(i
 	struct mapped_device *md;
 	void *old_md;
 
-	md = kzalloc_node(sizeof(*md), GFP_KERNEL, numa_node_id);
+	md = vzalloc_node(sizeof(*md), numa_node_id);
 	if (!md) {
 		DMWARN("unable to allocate device, out of memory.");
 		return NULL;
@@ -1605,7 +1606,7 @@ bad_io_barrier:
 bad_minor:
 	module_put(THIS_MODULE);
 bad_module_get:
-	kfree(md);
+	kvfree(md);
 	return NULL;
 }
 
@@ -1624,7 +1625,7 @@ static void free_dev(struct mapped_devic
 	free_minor(minor);
 
 	module_put(THIS_MODULE);
-	kfree(md);
+	kvfree(md);
 }
 
 static void __bind_mempools(struct mapped_device *md, struct dm_table *t)