[BUGFIX][PATCH] Aditional fix for memmap initalization

From: KAMEZAWA Hiroyuki
Date: Fri Feb 06 2009 - 04:56:39 EST

On Fri, 6 Feb 2009 17:17:24 +0900
KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx> wrote:

> On Thu, 05 Feb 2009 09:29:54 -0800
> akpm@xxxxxxxxxxxxxxxxxxxx wrote:
>
> >
> > The patch titled
> > mm: fix memmap init to initialize valid memmap for memory hole
> > has been added to the -mm tree. Its filename is
> > mm-fix-memmap-init-to-initialize-valid-memmap-for-memory-hole.patch
<snip>
> > The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/
> >
> Sorry, Kosaki reported me that this patch breaks ia64 compile/boot.
> So, I'm fixing the bug in cooperation with him, now.
> I think I can send a fix soon. But I hope this patch set for BOOT will be
> tested under various arch/configs before going up to.
>

This is an add-on fix. Tested on ia64 DISCONTIGMEM/SPARSEMEM, x86-64 fake-numa.

The patch mm-fix-memmap-init-to-initialize-valid-memmap-for-memory-hole.patch
breaks ia64's compile and boot.

After investigation, changing return value of early_pfn_to_nid() doesn't seem
to be very good. This patch adds early_pfn_to_nid_solid() for our purpose
(init memmap) and fixes all breakage.

Tested-by: KOSAKI Motohiro <kosaki.motohiro@xxxxxxxxxxxxxx>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
---
arch/ia64/mm/numa.c | 12 ++++++++++--
arch/x86/mm/numa_64.c | 6 +++++-
include/linux/mm.h | 1 +
mm/page_alloc.c | 39 +++++++++++++++++++++++++++++----------
4 files changed, 45 insertions(+), 13 deletions(-)

Index: mmotm-2.6.29-Feb05/include/linux/mm.h
===================================================================
--- mmotm-2.6.29-Feb05.orig/include/linux/mm.h
+++ mmotm-2.6.29-Feb05/include/linux/mm.h
@@ -1049,6 +1049,7 @@ extern void work_with_active_regions(int
extern void sparse_memory_present_with_active_regions(int nid);
#ifndef CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID
extern int early_pfn_to_nid(unsigned long pfn);
+extern int early_pfn_to_solid(unsigned long pfn);
#endif /* CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID */
#endif /* CONFIG_ARCH_POPULATES_NODE_MAP */
extern void set_dma_reserve(unsigned long new_dma_reserve);
Index: mmotm-2.6.29-Feb05/arch/ia64/mm/numa.c
===================================================================
--- mmotm-2.6.29-Feb05.orig/arch/ia64/mm/numa.c
+++ mmotm-2.6.29-Feb05/arch/ia64/mm/numa.c
@@ -58,7 +58,7 @@ paddr_to_nid(unsigned long paddr)
* SPARSEMEM to allocate the SPARSEMEM sectionmap on the NUMA node where
* the section resides.
*/
-int early_pfn_to_nid(unsigned long pfn)
+int early_pfn_to_nid_solid(unsigned long pfn)
{
int i, section = pfn >> PFN_SECTION_SHIFT, ssec, esec;

@@ -70,9 +70,17 @@ int early_pfn_to_nid(unsigned long pfn)
return node_memblk[i].nid;
}

- return 0;
+ return -1;
}

+int early_pfn_to_nid(unsigned long pfn)
+{
+ int nid = early_pfn_to_nid_solid(pfn);
+
+ if (nid < 0) /* see page_alloc.c */
+ return 0;
+ return nid;
+}
#ifdef CONFIG_MEMORY_HOTPLUG
/*
* SRAT information is stored in node_memblk[], then we can use SRAT
Index: mmotm-2.6.29-Feb05/arch/x86/mm/numa_64.c
===================================================================
--- mmotm-2.6.29-Feb05.orig/arch/x86/mm/numa_64.c
+++ mmotm-2.6.29-Feb05/arch/x86/mm/numa_64.c
@@ -166,10 +166,14 @@ int __init compute_hash_shift(struct boo
return shift;
}

-int early_pfn_to_nid(unsigned long pfn)
+int early_pfn_to_nid_solid(unsigned long pfn)
{
return phys_to_nid(pfn << PAGE_SHIFT);
}
+int early_pfn_to_nid(unsigned long pfn)
+{
+ return early_pfn_to_nid_solid(pfn);
+}

static void * __init early_node_mem(int nodeid, unsigned long start,
unsigned long end, unsigned long size,
Index: mmotm-2.6.29-Feb05/mm/page_alloc.c
===================================================================
--- mmotm-2.6.29-Feb05.orig/mm/page_alloc.c
+++ mmotm-2.6.29-Feb05/mm/page_alloc.c
@@ -2554,6 +2554,21 @@ static inline unsigned long wait_table_b
* higher will lead to a bigger reserve which will get freed as contiguous
* blocks as reclaim kicks in
*/
+#ifdef CONFIG_NODE_SPAN_OTHER_NODE
+static inline bool init_pfn_under_nid(unsigned long pfn, int nid)
+{
+ int nid_in_map = early_pfn_to_nid_solid(pfn);
+
+ if (nid_in_map == -1)
+ return true;
+ return (nid_in_map == nid);
+}
+#else
+static inline bool init_pfn_under_nid(unsigned long pfn, int nid)
+{
+ return true;
+}
+#endif
static void setup_zone_migrate_reserve(struct zone *zone)
{
unsigned long start_pfn, pfn, end_pfn;
@@ -2630,18 +2645,13 @@ void __meminit memmap_init_zone(unsigned
* exist on hotplugged memory.
*/
if (context == MEMMAP_EARLY) {
- int nid_from_node_memory_map;
-
if (!early_pfn_valid(pfn))
continue;
/*
- * early_pfn_to_nid() returns -1 if the page doesn't
- * exist in early_node_map[]. Initialize it in force
- * and set PG_reserved at el.
+ * This returns false if the page exists and it's
+ * not under this node.
*/
- nid_from_node_memory_map = early_pfn_to_nid(pfn);
- if (nid_from_node_memory_map > -1 &&
- nid_from_node_memory_map != nid)
+ if (!init_pfn_under_nid(pfn, nid))
continue;
}
page = pfn_to_page(pfn);
@@ -2996,7 +3006,7 @@ static int __meminit next_active_region_
* was used and there are no special requirements, this is a convenient
* alternative
*/
-int __meminit early_pfn_to_nid(unsigned long pfn)
+int __meminit early_pfn_to_nid_solid(unsigned long pfn)
{
int i;

@@ -3007,9 +3017,18 @@ int __meminit early_pfn_to_nid(unsigned
if (start_pfn <= pfn && pfn < end_pfn)
return early_node_map[i].nid;
}
-
return -1;
}
+/* Allow fallback to 0 */
+int __meminit early_pfn_to_nid(unsigned long pfn)
+{
+ int nid;
+
+ nid = early_pfn_to_nid_solid(pfn);
+ if (nid < 0)
+ return 0;
+ return nid;
+}
#endif /* CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID */

/* Basic iterator support to walk early_node_map[] */

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/