Re: [GIT PULL v3] Early boot SLAB for 2.6.31

[Pekka Enberg <penberg@cs.helsinki.fi>]

Hi Ingo,

On Fri, 2009-06-12 at 09:17 +0200, Ingo Molnar wrote:
> Plus i quickly got this crash too:
> 
> [    0.000000] console [tty0] enabled
> [    0.000000] allocation of page_cgroup was failed.
> [    0.000000] please try cgroup_disable=memory boot option
> [    0.000000] Kernel panic - not syncing: Out of memory
> [    0.000000] Rebooting in 1 seconds..<1>BUG: unable to handle kernel NULL pointer dereference at 0000004c
> [    0.000000] IP: [<c16ec708>] klist_next+0x10/0x8f
> [    0.000000] *pdpt = 0000000001a8a001 *pde = 0000000000000000 
> [    0.000000] Thread overran stack, or stack corrupted

Hmm, does this patch fix it? Hiroyuki, Li, does the oops look familiar to you?

			Pekka

From: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>

Now, SLAB is configured in very early stage and it can be used in
init routine now.

But replacing alloc_bootmem() in FLAT/DISCONTIGMEM's page_cgroup()
initialization breaks the allocation, now.
(Works well in SPARSEMEM case...it supports MEMORY_HOTPLUG and
 size of page_cgroup is in reasonable size (< 1 << MAX_ORDER.)

This patch revive FLATMEM+memory cgroup by using alloc_bootmem.

In future,
We stop to support FLATMEM (if no users) or rewrite codes for flatmem
completely.But this will adds more messy codes and overheads.

Changelog: v1->v2
 - fixed typos.

Acked-by: Pekka Enberg <penberg@cs.helsinki.fi>
Tested-by: Li Zefan <lizf@cn.fujitsu.com>
Reported-by: Li Zefan <lizf@cn.fujitsu.com>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
---
 include/linux/page_cgroup.h |   18 +++++++++++++++++-
 init/main.c                 |    5 +++++
 mm/page_cgroup.c            |   29 ++++++++++-------------------
 3 files changed, 32 insertions(+), 20 deletions(-)

Index: linux-2.6.30.org/init/main.c
===================================================================
--- linux-2.6.30.org.orig/init/main.c	2009-06-11 19:02:53.000000000 +0900
+++ linux-2.6.30.org/init/main.c	2009-06-11 20:49:21.000000000 +0900
@@ -539,6 +539,11 @@
  */
 static void __init mm_init(void)
 {
+	/*
+	 * page_cgroup requires countinous pages as memmap
+	 * and it's bigger than MAX_ORDER unless SPARSEMEM.
+	 */
+	page_cgroup_init_flatmem();
 	mem_init();
 	kmem_cache_init();
 	vmalloc_init();
Index: linux-2.6.30.org/mm/page_cgroup.c
===================================================================
--- linux-2.6.30.org.orig/mm/page_cgroup.c	2009-06-11 19:02:53.000000000 +0900
+++ linux-2.6.30.org/mm/page_cgroup.c	2009-06-11 20:49:59.000000000 +0900
@@ -47,8 +47,6 @@
 	struct page_cgroup *base, *pc;
 	unsigned long table_size;
 	unsigned long start_pfn, nr_pages, index;
-	struct page *page;
-	unsigned int order;
 
 	start_pfn = NODE_DATA(nid)->node_start_pfn;
 	nr_pages = NODE_DATA(nid)->node_spanned_pages;
@@ -57,13 +55,11 @@
 		return 0;
 
 	table_size = sizeof(struct page_cgroup) * nr_pages;
-	order = get_order(table_size);
-	page = alloc_pages_node(nid, GFP_NOWAIT | __GFP_ZERO, order);
-	if (!page)
-		page = alloc_pages_node(-1, GFP_NOWAIT | __GFP_ZERO, order);
-	if (!page)
+
+	base = __alloc_bootmem_node_nopanic(NODE_DATA(nid),
+			table_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS));
+	if (!base)
 		return -ENOMEM;
-	base = page_address(page);
 	for (index = 0; index < nr_pages; index++) {
 		pc = base + index;
 		__init_page_cgroup(pc, start_pfn + index);
@@ -73,7 +69,7 @@
 	return 0;
 }
 
-void __init page_cgroup_init(void)
+void __init page_cgroup_init_flatmem(void)
 {
 
 	int nid, fail;
@@ -117,16 +113,11 @@
 	if (!section->page_cgroup) {
 		nid = page_to_nid(pfn_to_page(pfn));
 		table_size = sizeof(struct page_cgroup) * PAGES_PER_SECTION;
-		if (slab_is_available()) {
-			base = kmalloc_node(table_size,
-					GFP_KERNEL | __GFP_NOWARN, 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));
-		}
+		VM_BUG_ON(!slab_is_available());
+		base = kmalloc_node(table_size,
+				GFP_KERNEL | __GFP_NOWARN, nid);
+		if (!base)
+			base = vmalloc_node(table_size, nid);
 	} else {
 		/*
  		 * We don't have to allocate page_cgroup again, but
Index: linux-2.6.30.org/include/linux/page_cgroup.h
===================================================================
--- linux-2.6.30.org.orig/include/linux/page_cgroup.h	2009-06-10 12:05:27.000000000 +0900
+++ linux-2.6.30.org/include/linux/page_cgroup.h	2009-06-11 20:50:32.000000000 +0900
@@ -18,7 +18,19 @@
 };
 
 void __meminit pgdat_page_cgroup_init(struct pglist_data *pgdat);
-void __init page_cgroup_init(void);
+
+#ifdef CONFIG_SPARSEMEM
+static inline void __init page_cgroup_init_flatmem(void)
+{
+}
+extern void __init page_cgroup_init(void);
+#else
+void __init page_cgroup_init_flatmem(void);
+static inline void __init page_cgroup_init(void)
+{
+}
+#endif
+
 struct page_cgroup *lookup_page_cgroup(struct page *page);
 
 enum {
@@ -87,6 +99,10 @@
 {
 }
 
+static inline void __init page_cgroup_init_flatmem(void)
+{
+}
+
 #endif
 
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP