From fc44f7f9231a73821fc858f5bc48883a9e78f6de Mon Sep 17 00:00:00 2001
From: Pavel Tatashin <pasha.tatashin@oracle.com>
Date: Thu, 5 Apr 2018 16:22:56 -0700
Subject: [PATCH] mm/memory_hotplug: don't read nid from struct page during
hotplug
Git-commit: fc44f7f9231a73821fc858f5bc48883a9e78f6de
Patch-mainline: v4.17-rc1
References: bnc#1114830, fate#326764
During memory hotplugging the probe routine will leave struct pages
uninitialized, the same as it is currently done during boot. Therefore,
we do not want to access the inside of struct pages before
__init_single_page() is called during onlining.
Because during hotplug we know that pages in one memory block belong to
the same numa node, we can skip the checking. We should keep checking
for the boot case.
[pasha.tatashin@oracle.com: s/register_new_memory()/hotplug_memory_register()]
Link: http://lkml.kernel.org/r/20180228030308.1116-6-pasha.tatashin@oracle.com
Link: http://lkml.kernel.org/r/20180215165920.8570-6-pasha.tatashin@oracle.com
Signed-off-by: Pavel Tatashin <pasha.tatashin@oracle.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Cc: Baoquan He <bhe@redhat.com>
Cc: Bharata B Rao <bharata@linux.vnet.ibm.com>
Cc: Daniel Jordan <daniel.m.jordan@oracle.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Steven Sistare <steven.sistare@oracle.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
drivers/base/memory.c | 4 ++--
drivers/base/node.c | 22 +++++++++++++++-------
include/linux/memory.h | 2 +-
include/linux/node.h | 4 ++--
mm/memory_hotplug.c | 2 +-
5 files changed, 21 insertions(+), 13 deletions(-)
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index deb3f029b451..79fcd2bae96b 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -712,7 +712,7 @@ static int add_memory_block(int base_section_nr)
* need an interface for the VM to add new memory regions,
* but without onlining it.
*/
-int register_new_memory(int nid, struct mem_section *section)
+int hotplug_memory_register(int nid, struct mem_section *section)
{
int ret = 0;
struct memory_block *mem;
@@ -731,7 +731,7 @@ int register_new_memory(int nid, struct mem_section *section)
}
if (mem->section_count == sections_per_block)
- ret = register_mem_sect_under_node(mem, nid);
+ ret = register_mem_sect_under_node(mem, nid, false);
out:
mutex_unlock(&mem_sysfs_mutex);
return ret;
diff --git a/drivers/base/node.c b/drivers/base/node.c
index c5f81fc621ac..92b00a7e6a02 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -399,7 +399,8 @@ static int __ref get_nid_for_pfn(unsigned long pfn)
}
/* register memory section under specified node if it spans that node */
-int register_mem_sect_under_node(struct memory_block *mem_blk, int nid)
+int register_mem_sect_under_node(struct memory_block *mem_blk, int nid,
+ bool check_nid)
{
int ret;
unsigned long pfn, sect_start_pfn, sect_end_pfn;
@@ -425,11 +426,18 @@ int register_mem_sect_under_node(struct memory_block *mem_blk, int nid)
continue;
}
- page_nid = get_nid_for_pfn(pfn);
- if (page_nid < 0)
- continue;
- if (page_nid != nid)
- continue;
+ /*
+ * We need to check if page belongs to nid only for the boot
+ * case, during hotplug we know that all pages in the memory
+ * block belong to the same node.
+ */
+ if (check_nid) {
+ page_nid = get_nid_for_pfn(pfn);
+ if (page_nid < 0)
+ continue;
+ if (page_nid != nid)
+ continue;
+ }
ret = sysfs_create_link_nowarn(&node_devices[nid]->dev.kobj,
&mem_blk->dev.kobj,
kobject_name(&mem_blk->dev.kobj));
@@ -504,7 +512,7 @@ int link_mem_sections(int nid, unsigned long start_pfn, unsigned long nr_pages)
mem_blk = find_memory_block_hinted(mem_sect, mem_blk);
- ret = register_mem_sect_under_node(mem_blk, nid);
+ ret = register_mem_sect_under_node(mem_blk, nid, true);
if (!err)
err = ret;
diff --git a/include/linux/memory.h b/include/linux/memory.h
index f71e732c77b2..9f8cd856ca1e 100644
--- a/include/linux/memory.h
+++ b/include/linux/memory.h
@@ -109,7 +109,7 @@ static inline int memory_isolate_notify(unsigned long val, void *v)
extern void unregister_memory_notifier(struct notifier_block *nb);
extern int register_memory_isolate_notifier(struct notifier_block *nb);
extern void unregister_memory_isolate_notifier(struct notifier_block *nb);
-extern int register_new_memory(int, struct mem_section *);
+int hotplug_memory_register(int nid, struct mem_section *section);
#ifdef CONFIG_MEMORY_HOTREMOVE
extern int unregister_memory_section(struct mem_section *);
#endif
diff --git a/include/linux/node.h b/include/linux/node.h
index 4ece0fee0ffc..41f171861dcc 100644
--- a/include/linux/node.h
+++ b/include/linux/node.h
@@ -67,7 +67,7 @@ static inline int register_one_node(int nid)
extern int register_cpu_under_node(unsigned int cpu, unsigned int nid);
extern int unregister_cpu_under_node(unsigned int cpu, unsigned int nid);
extern int register_mem_sect_under_node(struct memory_block *mem_blk,
- int nid);
+ int nid, bool check_nid);
extern int unregister_mem_sect_under_nodes(struct memory_block *mem_blk,
unsigned long phys_index);
@@ -97,7 +97,7 @@ static inline int unregister_cpu_under_node(unsigned int cpu, unsigned int nid)
return 0;
}
static inline int register_mem_sect_under_node(struct memory_block *mem_blk,
- int nid)
+ int nid, bool check_nid)
{
return 0;
}
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 565048f496f7..477e183a4ac7 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -279,7 +279,7 @@ static int __meminit __add_section(int nid, unsigned long phys_start_pfn,
if (!want_memblock)
return 0;
- return register_new_memory(nid, __pfn_to_section(phys_start_pfn));
+ return hotplug_memory_register(nid, __pfn_to_section(phys_start_pfn));
}
/*
--
1.8.5.6