[PATCH] x86_64: mark x86_cpu_to_node_map_init to __initdata like other xx_init

[PATCH] x86_64: mark x86_cpu_to_node_map_init to __initdata like other xx_init

[Yinghai Lu]

[PATCH] x86_64: mark x86_cpu_to_node_map_init to __initdata like other xx_init

Signed-off-by: Yinghai Lu <yinghai.lu@sun.com>

diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index f0e5cab..d7af3fd 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -31,7 +31,7 @@ bootmem_data_t plat_node_bdata[MAX_NUMNODES];
 
 struct memnode memnode;
 
-int x86_cpu_to_node_map_init[NR_CPUS] = {
+int x86_cpu_to_node_map_init[NR_CPUS] __initdata = {
 	[0 ... NR_CPUS-1] = NUMA_NO_NODE
 };
 void *x86_cpu_to_node_map_early_ptr;
diff --git a/include/asm-x86/topology.h b/include/asm-x86/topology.h
index 8af05a9..d3340de 100644
--- a/include/asm-x86/topology.h
+++ b/include/asm-x86/topology.h
@@ -35,7 +35,7 @@ extern int cpu_to_node_map[];
 
 #else
 DECLARE_PER_CPU(int, x86_cpu_to_node_map);
-extern int x86_cpu_to_node_map_init[];
+extern int __initdata x86_cpu_to_node_map_init[];
 extern void *x86_cpu_to_node_map_early_ptr;
 /* Returns the number of the current Node. */
 #define numa_node_id()		(early_cpu_to_node(raw_smp_processor_id()))

Re: [PATCH] x86_64: mark x86_cpu_to_node_map_init to __initdata like other xx_init

[Ingo Molnar]

* Yinghai Lu <Yinghai.Lu@Sun.COM> wrote:

> -int x86_cpu_to_node_map_init[NR_CPUS] = {
> +int x86_cpu_to_node_map_init[NR_CPUS] __initdata = {
>  	[0 ... NR_CPUS-1] = NUMA_NO_NODE
>  };

i remember some linker warning here. While this array should indeed only 
be used in early init, that decision is dynamic and our linker warnings 
do not notice it. There's a special marker for such cases: 
__initdata_refok. But ... i'm slightly nervous about turning off a vital 
warning like that.

Sam, it would be nice to have a DEBUG_INITDATA mode of operation: in 
this case free_initmem() would not truly free those pages but would 
unmap them via:

   kernel_map_pages(page, nrpages, 0);

could be made dependent on DEBUG_PAGEALLOC.

If this debugging is enabled then if any code references it, we get a 
hard page fault. If we had a debug mode like that then bugs in this area 
would not go unnoticed.

Or perhaps just make this part of normal DEBUG_PAGEALLOC. Like the patch 
below on top of latest x86.git. Hm?

	Ingo

------------------->
Subject: x86: init memory debugging
From: Ingo Molnar <mingo@elte.hu>

debug incorrect/late access to init memory, by permanently unmapping
the init memory ranges. Depends on CONFIG_DEBUG_PAGEALLOC=y.

Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/mm/init_32.c |   12 ++++++++++++
 arch/x86/mm/init_64.c |   11 +++++++++++
 2 files changed, 23 insertions(+)

Index: linux-x86.q/arch/x86/mm/init_32.c
===================================================================
--- linux-x86.q.orig/arch/x86/mm/init_32.c
+++ linux-x86.q/arch/x86/mm/init_32.c
@@ -794,6 +794,18 @@ void free_init_pages(char *what, unsigne
 	unsigned long addr;
 
 	/*
+	 * If debugging page accesses then do not free this memory but
+	 * mark them not present - any buggy init-section access will
+	 * create a kernel page fault:
+	 */
+#ifdef CONFIG_DEBUG_PAGEALLOC
+	printk(KERN_INFO "debug: unmapping init memory %08lx..%08lx\n",
+		begin, PAGE_ALIGN(end));
+	set_memory_np(begin, (end - begin) >> PAGE_SHIFT);
+	return;
+#endif
+	set_memory_rw(begin, (end - begin) >> PAGE_SHIFT);
+	/*
 	 * We just marked the kernel text read only above, now that
 	 * we are going to free part of that, we need to make that
 	 * writeable first.
Index: linux-x86.q/arch/x86/mm/init_64.c
===================================================================
--- linux-x86.q.orig/arch/x86/mm/init_64.c
+++ linux-x86.q/arch/x86/mm/init_64.c
@@ -580,6 +580,17 @@ void free_init_pages(char *what, unsigne
 	if (begin >= end)
 		return;
 
+	/*
+	 * If debugging page accesses then do not free this memory but
+	 * mark them not present - any buggy init-section access will
+	 * create a kernel page fault:
+	 */
+#ifdef CONFIG_DEBUG_PAGEALLOC
+	printk(KERN_INFO "debug: unmapping init memory %08lx..%08lx\n",
+		begin, PAGE_ALIGN(end));
+	set_memory_np(begin, (end - begin) >> PAGE_SHIFT);
+	return;
+#endif
 	printk(KERN_INFO "Freeing %s: %luk freed\n", what, (end - begin) >> 10);
 
 	for (addr = begin; addr < end; addr += PAGE_SIZE) {

[PATCH 1/2] print out node_data addr and bootmap_start addr

[Yinghai Lu]

[PATCH 1/2] print out node_data addr and bootmap_start addr

Signed-off-by: Yinghai Lu <yinghai.lu@sun.com>

Index: linux-2.6/arch/x86/mm/numa_64.c
===================================================================
--- linux-2.6.orig/arch/x86/mm/numa_64.c
+++ linux-2.6/arch/x86/mm/numa_64.c
@@ -202,6 +202,8 @@ void __init setup_node_bootmem(int nodei
 	if (node_data[nodeid] == NULL)
 		return;
 	nodedata_phys = __pa(node_data[nodeid]);
+	printk(KERN_INFO "  NODE_DATA [%016lx - %016lx]\n", nodedata_phys,
+		nodedata_phys + pgdat_size - 1);
 
 	memset(NODE_DATA(nodeid), 0, sizeof(pg_data_t));
 	NODE_DATA(nodeid)->bdata = &plat_node_bdata[nodeid];
@@ -221,12 +223,15 @@ void __init setup_node_bootmem(int nodei
 		return;
 	}
 	bootmap_start = __pa(bootmap);
-	Dprintk("bootmap start %lu pages %lu\n", bootmap_start, bootmap_pages);
 
 	bootmap_size = init_bootmem_node(NODE_DATA(nodeid),
 					 bootmap_start >> PAGE_SHIFT,
 					 start_pfn, end_pfn);
 
+	printk(KERN_INFO "  bootmap [%016lx -  %016lx] pages %lx\n",
+		 bootmap_start, bootmap_start + bootmap_size - 1,
+		 bootmap_pages);
+
 	free_bootmem_with_active_regions(nodeid, end);
 
 	reserve_bootmem_node(NODE_DATA(nodeid), nodedata_phys, pgdat_size);

[PATCH] x86_64: mark x86_cpu_to_node_map_init to __initdata like other xx_init

[Yinghai Lu]

[PATCH] x86_64: mark x86_cpu_to_node_map_init to __initdata like other xx_init

x86_cpu_to_apicid_init and x86_bios_cpu_apicid_init are defined with __initdata.

Signed-off-by: Yinghai Lu <yinghai.lu@sun.com>

diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index f0e5cab..d7af3fd 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -31,7 +31,7 @@ bootmem_data_t plat_node_bdata[MAX_NUMNODES];
 
 struct memnode memnode;
 
-int x86_cpu_to_node_map_init[NR_CPUS] = {
+int x86_cpu_to_node_map_init[NR_CPUS] __initdata = {
 	[0 ... NR_CPUS-1] = NUMA_NO_NODE
 };
 void *x86_cpu_to_node_map_early_ptr;
diff --git a/include/asm-x86/topology.h b/include/asm-x86/topology.h
index 8af05a9..d3340de 100644
--- a/include/asm-x86/topology.h
+++ b/include/asm-x86/topology.h
@@ -35,7 +35,7 @@ extern int cpu_to_node_map[];
 
 #else
 DECLARE_PER_CPU(int, x86_cpu_to_node_map);
-extern int x86_cpu_to_node_map_init[];
+extern int __initdata x86_cpu_to_node_map_init[];
 extern void *x86_cpu_to_node_map_early_ptr;
 /* Returns the number of the current Node. */
 #define numa_node_id()		(early_cpu_to_node(raw_smp_processor_id()))