[PATCH] memory hotplug: sysfs and add/remove functions

This adds generic memory add/remove and supporting functions for memory
hotplug into a new file as well as a memory hotplug kernel config option.

Individual architecture patches will follow.

For now, disable memory hotplug when swsusp is enabled.  There's a lot of
churn there right now.  We'll fix it up properly once it calms down.
Signed-off-by: Matt Tolentino <matthew.e.tolentino@intel.com>
Signed-off-by: Dave Hansen <haveblue@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

drivers/base/Makefile

@@ -7,6 +7,7 @@ obj-y			:= core.o sys.o bus.o dd.o \
 obj-y			+= power/
 obj-$(CONFIG_FW_LOADER)	+= firmware_class.o
 obj-$(CONFIG_NUMA)	+= node.o
+obj-$(CONFIG_MEMORY_HOTPLUG) += memory.o
 
 ifeq ($(CONFIG_DEBUG_DRIVER),y)
 EXTRA_CFLAGS += -DDEBUG

drivers/base/init.c

@@ -9,6 +9,7 @@
 
 #include <linux/device.h>
 #include <linux/init.h>
+#include <linux/memory.h>
 
 #include "base.h"
 
@@ -33,5 +34,6 @@ void __init driver_init(void)
 	platform_bus_init();
 	system_bus_init();
 	cpu_dev_init();
+	memory_dev_init();
 	attribute_container_init();
 }

include/linux/memory.h

+/*
+ * include/linux/memory.h - generic memory definition
+ *
+ * This is mainly for topological representation. We define the
+ * basic "struct memory_block" here, which can be embedded in per-arch
+ * definitions or NUMA information.
+ *
+ * Basic handling of the devices is done in drivers/base/memory.c
+ * and system devices are handled in drivers/base/sys.c.
+ *
+ * Memory block are exported via sysfs in the class/memory/devices/
+ * directory.
+ *
+ */
+#ifndef _LINUX_MEMORY_H_
+#define _LINUX_MEMORY_H_
+
+#include <linux/sysdev.h>
+#include <linux/node.h>
+#include <linux/compiler.h>
+
+#include <asm/semaphore.h>
+
+struct memory_block {
+	unsigned long phys_index;
+	unsigned long state;
+	/*
+	 * This serializes all state change requests.  It isn't
+	 * held during creation because the control files are
+	 * created long after the critical areas during
+	 * initialization.
+	 */
+	struct semaphore state_sem;
+	int phys_device;		/* to which fru does this belong? */
+	void *hw;			/* optional pointer to fw/hw data */
+	int (*phys_callback)(struct memory_block *);
+	struct sys_device sysdev;
+};
+
+/* These states are exposed to userspace as text strings in sysfs */
+#define	MEM_ONLINE		(1<<0) /* exposed to userspace */
+#define	MEM_GOING_OFFLINE	(1<<1) /* exposed to userspace */
+#define	MEM_OFFLINE		(1<<2) /* exposed to userspace */
+
+/*
+ * All of these states are currently kernel-internal for notifying
+ * kernel components and architectures.
+ *
+ * For MEM_MAPPING_INVALID, all notifier chains with priority >0
+ * are called before pfn_to_page() becomes invalid.  The priority=0
+ * entry is reserved for the function that actually makes
+ * pfn_to_page() stop working.  Any notifiers that want to be called
+ * after that should have priority <0.
+ */
+#define	MEM_MAPPING_INVALID	(1<<3)
+
+#ifndef CONFIG_MEMORY_HOTPLUG
+static inline int memory_dev_init(void)
+{
+	return 0;
+}
+static inline int register_memory_notifier(struct notifier_block *nb)
+{
+	return 0;
+}
+static inline void unregister_memory_notifier(struct notifier_block *nb)
+{
+}
+#else
+extern int register_memory(struct memory_block *, struct mem_section *section, struct node *);
+extern int register_new_memory(struct mem_section *);
+extern int unregister_memory_section(struct mem_section *);
+extern int memory_dev_init(void);
+extern int register_memory_notifier(struct notifier_block *nb);
+extern void unregister_memory_notifier(struct notifier_block *nb);
+
+#define CONFIG_MEM_BLOCK_SIZE	(PAGES_PER_SECTION<<PAGE_SHIFT)
+
+extern int invalidate_phys_mapping(unsigned long, unsigned long);
+struct notifier_block;
+
+extern int register_memory_notifier(struct notifier_block *nb);
+extern void unregister_memory_notifier(struct notifier_block *nb);
+
+extern struct sysdev_class memory_sysdev_class;
+#endif /* CONFIG_MEMORY_HOTPLUG */
+
+#define hotplug_memory_notifier(fn, pri) {			\
+	static struct notifier_block fn##_mem_nb =		\
+		{ .notifier_call = fn, .priority = pri };	\
+	register_memory_notifier(&fn##_mem_nb);			\
+}
+
+#endif /* _LINUX_MEMORY_H_ */

include/linux/memory_hotplug.h

@@ -3,6 +3,8 @@
 
 #include <linux/mmzone.h>
 #include <linux/spinlock.h>
+#include <linux/mmzone.h>
+#include <linux/notifier.h>
 
 #ifdef CONFIG_MEMORY_HOTPLUG
 /*
@@ -46,6 +48,19 @@ static inline void zone_seqlock_init(struct zone *zone)
 {
 	seqlock_init(&zone->span_seqlock);
 }
+extern int zone_grow_free_lists(struct zone *zone, unsigned long new_nr_pages);
+extern int zone_grow_waitqueues(struct zone *zone, unsigned long nr_pages);
+extern int add_one_highpage(struct page *page, int pfn, int bad_ppro);
+/* need some defines for these for archs that don't support it */
+extern void online_page(struct page *page);
+/* VM interface that may be used by firmware interface */
+extern int add_memory(u64 start, u64 size);
+extern int remove_memory(u64 start, u64 size);
+extern int online_pages(unsigned long, unsigned long);
+
+/* reasonably generic interface to expand the physical pages in a zone  */
+extern int __add_pages(struct zone *zone, unsigned long start_pfn,
+	unsigned long nr_pages);
 #else /* ! CONFIG_MEMORY_HOTPLUG */
 /*
  * Stub functions for when hotplug is off
@@ -65,5 +80,25 @@ static inline int zone_span_seqretry(struct zone *zone, unsigned iv)
 static inline void zone_span_writelock(struct zone *zone) {}
 static inline void zone_span_writeunlock(struct zone *zone) {}
 static inline void zone_seqlock_init(struct zone *zone) {}
+
+static inline int mhp_notimplemented(const char *func)
+{
+	printk(KERN_WARNING "%s() called, with CONFIG_MEMORY_HOTPLUG disabled\n", func);
+	dump_stack();
+	return -ENOSYS;
+}
+
+static inline int __add_pages(struct zone *zone, unsigned long start_pfn,
+	unsigned long nr_pages)
+{
+	return mhp_notimplemented(__FUNCTION__);
+}
 #endif /* ! CONFIG_MEMORY_HOTPLUG */
+static inline int __remove_pages(struct zone *zone, unsigned long start_pfn,
+	unsigned long nr_pages)
+{
+	printk(KERN_WARNING "%s() called, not yet supported\n", __FUNCTION__);
+	dump_stack();
+	return -ENOSYS;
+}
 #endif /* __LINUX_MEMORY_HOTPLUG_H */

include/linux/mm.h

@@ -840,6 +840,7 @@ extern void free_area_init_node(int nid, pg_data_t *pgdat,
 	unsigned long * zones_size, unsigned long zone_start_pfn, 
 	unsigned long *zholes_size);
 extern void memmap_init_zone(unsigned long, int, unsigned long, unsigned long);
+extern void setup_per_zone_pages_min(void);
 extern void mem_init(void);
 extern void show_mem(void);
 extern void si_meminfo(struct sysinfo * val);

mm/Kconfig

@@ -112,6 +112,14 @@ config SPARSEMEM_EXTREME
 	def_bool y
 	depends on SPARSEMEM && !SPARSEMEM_STATIC
 
+# eventually, we can have this option just 'select SPARSEMEM'
+config MEMORY_HOTPLUG
+	bool "Allow for memory hot-add"
+	depends on SPARSEMEM && HOTPLUG && !SOFTWARE_SUSPEND
+
+comment "Memory hotplug is currently incompatible with Software Suspend"
+	depends on SPARSEMEM && HOTPLUG && SOFTWARE_SUSPEND
+
 # Heavily threaded applications may benefit from splitting the mm-wide
 # page_table_lock, so that faults on different parts of the user address
 # space can be handled with less contention: split it at this NR_CPUS.

mm/Makefile

@@ -18,5 +18,5 @@ obj-$(CONFIG_NUMA) 	+= mempolicy.o
 obj-$(CONFIG_SPARSEMEM)	+= sparse.o
 obj-$(CONFIG_SHMEM) += shmem.o
 obj-$(CONFIG_TINY_SHMEM) += tiny-shmem.o
-
+obj-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o
 obj-$(CONFIG_FS_XIP) += filemap_xip.o

mm/memory_hotplug.c

+/*
+ *  linux/mm/memory_hotplug.c
+ *
+ *  Copyright (C)
+ */
+
+#include <linux/config.h>
+#include <linux/stddef.h>
+#include <linux/mm.h>
+#include <linux/swap.h>
+#include <linux/interrupt.h>
+#include <linux/pagemap.h>
+#include <linux/bootmem.h>
+#include <linux/compiler.h>
+#include <linux/module.h>
+#include <linux/pagevec.h>
+#include <linux/slab.h>
+#include <linux/sysctl.h>
+#include <linux/cpu.h>
+#include <linux/memory.h>
+#include <linux/memory_hotplug.h>
+#include <linux/highmem.h>
+#include <linux/vmalloc.h>
+
+#include <asm/tlbflush.h>
+
+static struct page *__kmalloc_section_memmap(unsigned long nr_pages)
+{
+	struct page *page, *ret;
+	unsigned long memmap_size = sizeof(struct page) * nr_pages;
+
+	page = alloc_pages(GFP_KERNEL, get_order(memmap_size));
+	if (page)
+		goto got_map_page;
+
+	ret = vmalloc(memmap_size);
+	if (ret)
+		goto got_map_ptr;
+
+	return NULL;
+got_map_page:
+	ret = (struct page *)pfn_to_kaddr(page_to_pfn(page));
+got_map_ptr:
+	memset(ret, 0, memmap_size);
+
+	return ret;
+}
+
+extern void zonetable_add(struct zone *zone, int nid, int zid, unsigned long pfn,
+			  unsigned long size);
+static void __add_zone(struct zone *zone, unsigned long phys_start_pfn)
+{
+	struct pglist_data *pgdat = zone->zone_pgdat;
+	int nr_pages = PAGES_PER_SECTION;
+	int nid = pgdat->node_id;
+	int zone_type;
+
+	zone_type = zone - pgdat->node_zones;
+	memmap_init_zone(nr_pages, nid, zone_type, phys_start_pfn);
+	zonetable_add(zone, nid, zone_type, phys_start_pfn, nr_pages);
+}
+
+extern int sparse_add_one_section(struct zone *, unsigned long,
+				  struct page *mem_map);
+static int __add_section(struct zone *zone, unsigned long phys_start_pfn)
+{
+	struct pglist_data *pgdat = zone->zone_pgdat;
+	int nr_pages = PAGES_PER_SECTION;
+	struct page *memmap;
+	int ret;
+
+	/*
+	 * This can potentially allocate memory, and does its own
+	 * internal locking.
+	 */
+	sparse_index_init(pfn_to_section_nr(phys_start_pfn), pgdat->node_id);
+
+	pgdat_resize_lock(pgdat, &flags);
+	memmap = __kmalloc_section_memmap(nr_pages);
+	ret = sparse_add_one_section(zone, phys_start_pfn, memmap);
+	pgdat_resize_unlock(pgdat, &flags);
+
+	if (ret <= 0) {
+		/* the mem_map didn't get used */
+		if (memmap >= (struct page *)VMALLOC_START &&
+		    memmap < (struct page *)VMALLOC_END)
+			vfree(memmap);
+		else
+			free_pages((unsigned long)memmap,
+				   get_order(sizeof(struct page) * nr_pages));
+	}
+
+	if (ret < 0)
+		return ret;
+
+	__add_zone(zone, phys_start_pfn);
+	return register_new_memory(__pfn_to_section(phys_start_pfn));
+}
+
+/*
+ * Reasonably generic function for adding memory.  It is
+ * expected that archs that support memory hotplug will
+ * call this function after deciding the zone to which to
+ * add the new pages.
+ */
+int __add_pages(struct zone *zone, unsigned long phys_start_pfn,
+		 unsigned long nr_pages)
+{
+	unsigned long i;
+	int err = 0;
+
+	for (i = 0; i < nr_pages; i += PAGES_PER_SECTION) {
+		err = __add_section(zone, phys_start_pfn + i);
+
+		if (err)
+			break;
+	}
+
+	return err;
+}
+
+static void grow_zone_span(struct zone *zone,
+		unsigned long start_pfn, unsigned long end_pfn)
+{
+	unsigned long old_zone_end_pfn;
+
+	zone_span_writelock(zone);
+
+	old_zone_end_pfn = zone->zone_start_pfn + zone->spanned_pages;
+	if (start_pfn < zone->zone_start_pfn)
+		zone->zone_start_pfn = start_pfn;
+
+	if (end_pfn > old_zone_end_pfn)
+		zone->spanned_pages = end_pfn - zone->zone_start_pfn;
+
+	zone_span_writeunlock(zone);
+}
+
+static void grow_pgdat_span(struct pglist_data *pgdat,
+		unsigned long start_pfn, unsigned long end_pfn)
+{
+	unsigned long old_pgdat_end_pfn =
+		pgdat->node_start_pfn + pgdat->node_spanned_pages;
+
+	if (start_pfn < pgdat->node_start_pfn)
+		pgdat->node_start_pfn = start_pfn;
+
+	if (end_pfn > old_pgdat_end_pfn)
+		pgdat->node_spanned_pages = end_pfn - pgdat->node_spanned_pages;
+}
+
+int online_pages(unsigned long pfn, unsigned long nr_pages)
+{
+	unsigned long i;
+	unsigned long flags;
+	unsigned long onlined_pages = 0;
+	struct zone *zone;
+
+	/*
+	 * This doesn't need a lock to do pfn_to_page().
+	 * The section can't be removed here because of the
+	 * memory_block->state_sem.
+	 */
+	zone = page_zone(pfn_to_page(pfn));
+	pgdat_resize_lock(zone->zone_pgdat, &flags);
+	grow_zone_span(zone, pfn, pfn + nr_pages);
+	grow_pgdat_span(zone->zone_pgdat, pfn, pfn + nr_pages);
+	pgdat_resize_unlock(zone->zone_pgdat, &flags);
+
+	for (i = 0; i < nr_pages; i++) {
+		struct page *page = pfn_to_page(pfn + i);
+		online_page(page);
+		onlined_pages++;
+	}
+	zone->present_pages += onlined_pages;
+
+	return 0;
+}

mm/page_alloc.c

@@ -1686,7 +1686,7 @@ static void __init calculate_zone_totalpages(struct pglist_data *pgdat,
  * up by free_all_bootmem() once the early boot process is
  * done. Non-atomic initialization, single-pass.
  */
-void __init memmap_init_zone(unsigned long size, int nid, unsigned long zone,
+void __devinit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
 		unsigned long start_pfn)
 {
 	struct page *page;
@@ -2407,7 +2407,7 @@ static void setup_per_zone_lowmem_reserve(void)
  *	that the pages_{min,low,high} values for each zone are set correctly 
  *	with respect to min_free_kbytes.
  */
-static void setup_per_zone_pages_min(void)
+void setup_per_zone_pages_min(void)
 {
 	unsigned long pages_min = min_free_kbytes >> (PAGE_SHIFT - 10);
 	unsigned long lowmem_pages = 0;