Memory hot remove uses get_nid_for_pfn() while tearing down linked sysfs
entries between memory block and node. It first checks pfn validity with
pfn_valid_within() before fetching nid. With CONFIG_HOLES_IN_ZONE config
(arm64 has this enabled) pfn_valid_within() calls pfn_valid().
pfn_valid() is an arch implementation on arm64 (CONFIG_HAVE_ARCH_PFN_VALID)
which scans all mapped memblock regions with memblock_is_map_memory(). This
creates a problem in memory hot remove path which has already removed given
memory range from memory block with memblock_[remove|free] before arriving
at unregister_mem_sect_under_nodes().
During runtime memory hot remove get_nid_for_pfn() needs to validate that
given pfn has a struct page mapping so that it can fetch required nid. This
can be achieved just by looking into it's section mapping information. This
adds a new helper pfn_section_valid() for this purpose. Its same as generic
pfn_valid().
This maintains existing behaviour for deferred struct page init case.
Signed-off-by: Anshuman Khandual <anshuman.khandual@xxxxxxx>
---
This is a preparatory patch for memory hot-remove enablement on arm64. I
will appreciate some early feedback on this approach.
drivers/base/node.c | 15 ++++++++++++---
include/linux/mmzone.h | 9 +++++++--
2 files changed, 19 insertions(+), 5 deletions(-)
diff --git a/drivers/base/node.c b/drivers/base/node.c
index 86d6cd92ce3d..9e944b71e352 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -394,11 +394,20 @@ int unregister_cpu_under_node(unsigned int cpu, unsigned int nid)
#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
static int __ref get_nid_for_pfn(unsigned long pfn)
{
- if (!pfn_valid_within(pfn))
- return -1;
#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
- if (system_state < SYSTEM_RUNNING)
+ if (system_state < SYSTEM_RUNNING) {
+ if (!pfn_valid_within(pfn))
+ return -1;
return early_pfn_to_nid(pfn);
+ }
+#endif
+
+#if defined(CONFIG_HAVE_ARCH_PFN_VALID) && defined(CONFIG_HOLES_IN_ZONE)
+ if (!pfn_section_valid(pfn))
+ return -1;
+#else
+ if (!pfn_valid_within(pfn))
+ return -1;
#endif
return pfn_to_nid(pfn);
}
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 842f9189537b..9cf4c1111b95 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -1242,13 +1242,18 @@ static inline struct mem_section *__pfn_to_section(unsigned long pfn)
extern int __highest_present_section_nr;
-#ifndef CONFIG_HAVE_ARCH_PFN_VALID
-static inline int pfn_valid(unsigned long pfn)
+static inline int pfn_section_valid(unsigned long pfn)
{
if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS)
return 0;
return valid_section(__nr_to_section(pfn_to_section_nr(pfn)));
}
+
+#ifndef CONFIG_HAVE_ARCH_PFN_VALID
+static inline int pfn_valid(unsigned long pfn)
+{
+ return pfn_section_valid(pfn);
+}
#endif
static inline int pfn_present(unsigned long pfn)
--
2.20.1
