memcg: fix page_cgroup allocation
page_cgroup_init() is called from mem_cgroup_init(). But at this
point, we cannot call alloc_bootmem().
(and this caused panic at boot.)
This patch moves page_cgroup_init() to init/main.c.
Time table is following:
==
parse_args(). # we can trust mem_cgroup_subsys.disabled bit after this.
....
cgroup_init_early() # "early" init of cgroup.
....
setup_arch() # memmap is allocated.
...
page_cgroup_init();
mem_init(); # we cannot call alloc_bootmem after this.
....
cgroup_init() # mem_cgroup is initialized.
==
Before page_cgroup_init(), mem_map must be initialized. So,
I added page_cgroup_init() to init/main.c directly.
(*) maybe this is not very clean but
- cgroup_init_early() is too early
- in cgroup_init(), we have to use vmalloc instead of alloc_bootmem().
use of vmalloc area in x86-32 is important and we should avoid very large
vmalloc() in x86-32. So, we want to use alloc_bootmem() and added page_cgroup_init()
directly to init/main.c
[akpm@linux-foundation.org: remove unneeded/bad mem_cgroup_subsys declaration]
[akpm@linux-foundation.org: fix build]
Acked-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Tested-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/include/linux/page_cgroup.h b/include/linux/page_cgroup.h
index 0fd39f2..f546ad6 100644
--- a/include/linux/page_cgroup.h
+++ b/include/linux/page_cgroup.h
@@ -99,5 +99,10 @@
{
return NULL;
}
+
+static inline void page_cgroup_init(void)
+{
+}
+
#endif
#endif
diff --git a/init/main.c b/init/main.c
index 3e17a3b..672ae75 100644
--- a/init/main.c
+++ b/init/main.c
@@ -52,6 +52,7 @@
#include <linux/key.h>
#include <linux/unwind.h>
#include <linux/buffer_head.h>
+#include <linux/page_cgroup.h>
#include <linux/debug_locks.h>
#include <linux/debugobjects.h>
#include <linux/lockdep.h>
@@ -647,6 +648,7 @@
vmalloc_init();
vfs_caches_init_early();
cpuset_init_early();
+ page_cgroup_init();
mem_init();
enable_debug_pagealloc();
cpu_hotplug_init();
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index d4a92b6..866dcc7 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1088,7 +1088,6 @@
int node;
if (unlikely((cont->parent) == NULL)) {
- page_cgroup_init();
mem = &init_mem_cgroup;
} else {
mem = mem_cgroup_alloc();
diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c
index 78242b4..f59d797 100644
--- a/mm/page_cgroup.c
+++ b/mm/page_cgroup.c
@@ -4,8 +4,10 @@
#include <linux/bit_spinlock.h>
#include <linux/page_cgroup.h>
#include <linux/hash.h>
+#include <linux/slab.h>
#include <linux/memory.h>
#include <linux/vmalloc.h>
+#include <linux/cgroup.h>
static void __meminit
__init_page_cgroup(struct page_cgroup *pc, unsigned long pfn)
@@ -67,6 +69,9 @@
int nid, fail;
+ if (mem_cgroup_subsys.disabled)
+ return;
+
for_each_online_node(nid) {
fail = alloc_node_page_cgroup(nid);
if (fail)
@@ -107,9 +112,14 @@
nid = page_to_nid(pfn_to_page(pfn));
table_size = sizeof(struct page_cgroup) * PAGES_PER_SECTION;
- base = kmalloc_node(table_size, GFP_KERNEL, nid);
- if (!base)
- base = vmalloc_node(table_size, nid);
+ if (slab_is_available()) {
+ base = kmalloc_node(table_size, GFP_KERNEL, nid);
+ if (!base)
+ base = vmalloc_node(table_size, nid);
+ } else {
+ base = __alloc_bootmem_node_nopanic(NODE_DATA(nid), table_size,
+ PAGE_SIZE, __pa(MAX_DMA_ADDRESS));
+ }
if (!base) {
printk(KERN_ERR "page cgroup allocation failure\n");
@@ -136,11 +146,16 @@
if (!ms || !ms->page_cgroup)
return;
base = ms->page_cgroup + pfn;
- ms->page_cgroup = NULL;
- if (is_vmalloc_addr(base))
+ if (is_vmalloc_addr(base)) {
vfree(base);
- else
- kfree(base);
+ ms->page_cgroup = NULL;
+ } else {
+ struct page *page = virt_to_page(base);
+ if (!PageReserved(page)) { /* Is bootmem ? */
+ kfree(base);
+ ms->page_cgroup = NULL;
+ }
+ }
}
int online_page_cgroup(unsigned long start_pfn,
@@ -214,6 +229,9 @@
unsigned long pfn;
int fail = 0;
+ if (mem_cgroup_subsys.disabled)
+ return;
+
for (pfn = 0; !fail && pfn < max_pfn; pfn += PAGES_PER_SECTION) {
if (!pfn_present(pfn))
continue;