Hi,
On my ARM machine, the total kernel memory is not aligned to the section size SECTION_SIZE_BITS.
I observe kernel crashes in the following 3 scenarios:
i) When we do a "cat /proc/pagetypeinfo": This happens because the pfn_valid() macro is not able to detect invalid PFNs in the loop in
vmstat.c: pagetypeinfo_showblockcount_print().
ii) When we do "echo xxxx > /proc/vm/sys/min_free_kbytes": This happens because the pfn_valid() macro is not able to detect invalid PFNs in
page_alloc.c: setup_zone_migrate_reserve().
iii) When I try to copy a really huge file form one directory to another: This happens because the CONFIG_HOLES_IN_ZONE config option is not set.
So, the code in move_freepages() crashes.
I did find one patch somewhat related to this problem at: https://patchwork.kernel.org/patch/793862/
However, this patch is not suitable for my version of linux-2.6.35.13 because this uses memblock_*() functionality and
CONFIG_HAVE_MEMBLOCK is not enabled for my platform. Also, I am not sure whether this will solve point iii) above, as pfn_valid_within()
will continue to return 1 back to the caller when it should be calling pfn_vald() instead.
I created a solution patch for this and would appreciate it if anyone in these mailing lists could review this patch and tell me whether:
i) There is a better way to do this or,
ii) There is already a more suitable patch for the configuration I am mentioning above.
Patch:
--- linux-2.6.35.11.p29-FR/arch/arm/Kconfig 2011-07-27 10:27:02.243936001 +0530
+++ linux-2.6.35.11.p29-FR.new/arch/arm/Kconfig 2011-07-27 09:54:00.823935866 +0530
@@ -581,6 +581,16 @@ config OABI_COMPAT
config ARCH_HAS_HOLES_MEMORYMODEL
bool
+config ARCH_HAS_PFN_VALID
+ bool
+ depends on SPARSEMEM
+ default y
+
+config HOLES_IN_ZONE
+ bool
+ depends on SPARSEMEM
+ default y
+
# Discontigmem is deprecated
config ARCH_DISCONTIGMEM_ENABLE
bool
--- linux-2.6.35.9/arch/arm/mm/init.c 2011-06-13 15:18:47.921796999 +0530
+++ linux-2.6.35.9.new/arch/arm/mm/init.c 2011-06-13 11:59:47.236796983 +0530
@@ -350,6 +350,27 @@ static void arm_memory_present(struct me
{
}
#else
+#ifdef CONFIG_ARCH_HAS_PFN_VALID
+int arch_pfn_valid(unsigned long pfn)
+{
+ struct meminfo *mi = &meminfo;
+ unsigned int left = 0, right = mi->nr_banks;
+
+ do {
+ unsigned int mid = (right + left) / 2;
+ struct membank *bank = &mi->bank[mid];
+
+ if (pfn < bank_pfn_start(bank))
+ right = mid;
+ else if (pfn >= bank_pfn_end(bank))
+ left = mid + 1;
+ else
+ return 1;
+ } while (left < right);
+ return 0;
+}
+#endif
+
static void arm_memory_present(struct meminfo *mi, int node)
{
int i;
--- linux-2.6.35.9/include/linux/mmzone.h 2010-11-23 00:31:26.000000000 +0530
+++ linux-2.6.35.9.new/include/linux/mmzone.h 2011-06-13 12:32:37.182796701 +0530
@@ -1062,10 +1062,20 @@ static inline struct mem_section *__pfn_
return __nr_to_section(pfn_to_section_nr(pfn));
}
+#ifdef CONFIG_ARCH_HAS_PFN_VALID
+int arch_pfn_valid(unsigned long) ;
+#endif
+
static inline int pfn_valid(unsigned long pfn)
{
if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS)
return 0;
+
+#ifdef CONFIG_ARCH_HAS_PFN_VALID
+ if (!arch_pfn_valid(pfn))
+ return 0 ;
+#endif
+
return valid_section(__nr_to_section(pfn_to_section_nr(pfn)));
}
@@ -1073,6 +1083,12 @@ static inline int pfn_present(unsigned l
{
if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS)
return 0;
+
+#ifdef CONFIG_ARCH_HAS_PFN_VALID
+ if (!arch_pfn_valid(pfn))
+ return 0 ;
+#endif
+
return present_section(__nr_to_section(pfn_to_section_nr(pfn)));
}
Thanks,
Kautuk.