mm: allow memory hotplug and hibernation in the same kernel

Allow memory hotplug and hibernation in the same kernel

Memory hotplug and hibernation were exclusive in Kconfig.  This is
obviously a problem for distribution kernels who want to support both in
the same image.

After some discussions with Rafael and others the only problem is with
parallel memory hotadd or removal while a hibernation operation is in
process.  It was also working for s390 before.

This patch removes the Kconfig level exclusion, and simply makes the
memory add / remove functions grab the pm_mutex to exclude against
hibernation.

Fixes a regression - old kernels didn't exclude memory hotadd and
hibernation.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Cc: Gerald Schaefer <gerald.schaefer@de.ibm.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Acked-by: Rafael J. Wysocki <rjw@sisk.pl>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 37 insertions, 10 deletions

diff --git a/include/linux/suspend.h b/include/linux/suspend.h
index cd15df6c63c..5e781d824e6 100644
--- a/include/linux/suspend.h
+++ b/include/linux/suspend.h
@@ -301,6 +301,8 @@ static inline int unregister_pm_notifier(struct notifier_block *nb)
 #define pm_notifier(fn, pri)	do { (void)(fn); } while (0)
 #endif /* !CONFIG_PM_SLEEP */
 
+extern struct mutex pm_mutex;
+
 #ifndef CONFIG_HIBERNATION
 static inline void register_nosave_region(unsigned long b, unsigned long e)
 {
@@ -308,8 +310,23 @@ static inline void register_nosave_region(unsigned long b, unsigned long e)
 static inline void register_nosave_region_late(unsigned long b, unsigned long e)
 {
 }
-#endif
 
-extern struct mutex pm_mutex;
+static inline void lock_system_sleep(void) {}
+static inline void unlock_system_sleep(void) {}
+
+#else
+
+/* Let some subsystems like memory hotadd exclude hibernation */
+
+static inline void lock_system_sleep(void)
+{
+	mutex_lock(&pm_mutex);
+}
+
+static inline void unlock_system_sleep(void)
+{
+	mutex_unlock(&pm_mutex);
+}
+#endif
 
 #endif /* _LINUX_SUSPEND_H */
diff --git a/mm/Kconfig b/mm/Kconfig
index fd3386242cf..44cf6f0a3a6 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -128,12 +128,9 @@ config SPARSEMEM_VMEMMAP
 config MEMORY_HOTPLUG
 	bool "Allow for memory hot-add"
 	depends on SPARSEMEM || X86_64_ACPI_NUMA
-	depends on HOTPLUG && !(HIBERNATION && !S390) && ARCH_ENABLE_MEMORY_HOTPLUG
+	depends on HOTPLUG && ARCH_ENABLE_MEMORY_HOTPLUG
 	depends on (IA64 || X86 || PPC_BOOK3S_64 || SUPERH || S390)
 
-comment "Memory hotplug is currently incompatible with Software Suspend"
-	depends on SPARSEMEM && HOTPLUG && HIBERNATION && !S390
-
 config MEMORY_HOTPLUG_SPARSE
 	def_bool y
 	depends on SPARSEMEM && MEMORY_HOTPLUG
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 380aef45c2c..2047465cd27 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -26,6 +26,7 @@
 #include <linux/migrate.h>
 #include <linux/page-isolation.h>
 #include <linux/pfn.h>
+#include <linux/suspend.h>
 
 #include <asm/tlbflush.h>
 
@@ -485,14 +486,18 @@ int __ref add_memory(int nid, u64 start, u64 size)
 	struct resource *res;
 	int ret;
 
+	lock_system_sleep();
+
 	res = register_memory_resource(start, size);
+	ret = -EEXIST;
 	if (!res)
-		return -EEXIST;
+		goto out;
 
 	if (!node_online(nid)) {
 		pgdat = hotadd_new_pgdat(nid, start);
+		ret = -ENOMEM;
 		if (!pgdat)
-			return -ENOMEM;
+			goto out;
 		new_pgdat = 1;
 	}
 
@@ -515,7 +520,8 @@ int __ref add_memory(int nid, u64 start, u64 size)
 		BUG_ON(ret);
 	}
 
-	return ret;
+	goto out;
+
 error:
 	/* rollback pgdat allocation and others */
 	if (new_pgdat)
@@ -523,6 +529,8 @@ error:
 	if (res)
 		release_memory_resource(res);
 
+out:
+	unlock_system_sleep();
 	return ret;
 }
 EXPORT_SYMBOL_GPL(add_memory);
@@ -759,6 +767,8 @@ int offline_pages(unsigned long start_pfn,
 	if (!test_pages_in_a_zone(start_pfn, end_pfn))
 		return -EINVAL;
 
+	lock_system_sleep();
+
 	zone = page_zone(pfn_to_page(start_pfn));
 	node = zone_to_nid(zone);
 	nr_pages = end_pfn - start_pfn;
@@ -766,7 +776,7 @@ int offline_pages(unsigned long start_pfn,
 	/* set above range as isolated */
 	ret = start_isolate_page_range(start_pfn, end_pfn);
 	if (ret)
-		return ret;
+		goto out;
 
 	arg.start_pfn = start_pfn;
 	arg.nr_pages = nr_pages;
@@ -844,6 +854,7 @@ repeat:
 	writeback_set_ratelimit();
 
 	memory_notify(MEM_OFFLINE, &arg);
+	unlock_system_sleep();
 	return 0;
 
 failed_removal:
@@ -853,6 +864,8 @@ failed_removal:
 	/* pushback to free area */
 	undo_isolate_page_range(start_pfn, end_pfn);
 
+out:
+	unlock_system_sleep();
 	return ret;
 }