mm: show node to memory section relationship with symlinks in sysfs

Show node to memory section relationship with symlinks in sysfs

Add /sys/devices/system/node/nodeX/memoryY symlinks for all
the memory sections located on nodeX.  For example:
/sys/devices/system/node/node1/memory135 -> ../../memory/memory135
indicates that memory section 135 resides on node1.

Also revises documentation to cover this change as well as updating
Documentation/ABI/testing/sysfs-devices-memory to include descriptions
of memory hotremove files 'phys_device', 'phys_index', and 'state'
that were previously not described there.

In addition to it always being a good policy to provide users with
the maximum possible amount of physical location information for
resources that can be hot-added and/or hot-removed, the following
are some (but likely not all) of the user benefits provided by
this change.
Immediate:
  - Provides information needed to determine the specific node
    on which a defective DIMM is located.  This will reduce system
    downtime when the node or defective DIMM is swapped out.
  - Prevents unintended onlining of a memory section that was
    previously offlined due to a defective DIMM.  This could happen
    during node hot-add when the user or node hot-add assist script
    onlines _all_ offlined sections due to user or script inability
    to identify the specific memory sections located on the hot-added
    node.  The consequences of reintroducing the defective memory
    could be ugly.
  - Provides information needed to vary the amount and distribution
    of memory on specific nodes for testing or debugging purposes.
Future:
  - Will provide information needed to identify the memory
    sections that need to be offlined prior to physical removal
    of a specific node.

Symlink creation during boot was tested on 2-node x86_64, 2-node
ppc64, and 2-node ia64 systems.  Symlink creation during physical
memory hot-add tested on a 2-node x86_64 system.

Signed-off-by: Gary Hade <garyhade@us.ibm.com>
Signed-off-by: Badari Pulavarty <pbadari@us.ibm.com>
Acked-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 116 insertions, 6 deletions

diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index 5260e9e0df4..989429cfed8 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -347,8 +347,9 @@ static inline int memory_probe_init(void)
  * section belongs to...
  */
 
-static int add_memory_block(unsigned long node_id, struct mem_section *section,
-		     unsigned long state, int phys_device)
+static int add_memory_block(int nid, struct mem_section *section,
+			unsigned long state, int phys_device,
+			enum mem_add_context context)
 {
 	struct memory_block *mem = kzalloc(sizeof(*mem), GFP_KERNEL);
 	int ret = 0;
@@ -370,6 +371,10 @@ static int add_memory_block(unsigned long node_id, struct mem_section *section,
 		ret = mem_create_simple_file(mem, phys_device);
 	if (!ret)
 		ret = mem_create_simple_file(mem, removable);
+	if (!ret) {
+		if (context == HOTPLUG)
+			ret = register_mem_sect_under_node(mem, nid);
+	}
 
 	return ret;
 }
@@ -382,7 +387,7 @@ static int add_memory_block(unsigned long node_id, struct mem_section *section,
  *
  * This could be made generic for all sysdev classes.
  */
-static struct memory_block *find_memory_block(struct mem_section *section)
+struct memory_block *find_memory_block(struct mem_section *section)
 {
 	struct kobject *kobj;
 	struct sys_device *sysdev;
@@ -411,6 +416,7 @@ int remove_memory_block(unsigned long node_id, struct mem_section *section,
 	struct memory_block *mem;
 
 	mem = find_memory_block(section);
+	unregister_mem_sect_under_nodes(mem);
 	mem_remove_simple_file(mem, phys_index);
 	mem_remove_simple_file(mem, state);
 	mem_remove_simple_file(mem, phys_device);
@@ -424,9 +430,9 @@ int remove_memory_block(unsigned long node_id, struct mem_section *section,
  * need an interface for the VM to add new memory regions,
  * but without onlining it.
  */
-int register_new_memory(struct mem_section *section)
+int register_new_memory(int nid, struct mem_section *section)
 {
-	return add_memory_block(0, section, MEM_OFFLINE, 0);
+	return add_memory_block(nid, section, MEM_OFFLINE, 0, HOTPLUG);
 }
 
 int unregister_memory_section(struct mem_section *section)
@@ -458,7 +464,8 @@ int __init memory_dev_init(void)
 	for (i = 0; i < NR_MEM_SECTIONS; i++) {
 		if (!present_section_nr(i))
 			continue;
-		err = add_memory_block(0, __nr_to_section(i), MEM_ONLINE, 0);
+		err = add_memory_block(0, __nr_to_section(i), MEM_ONLINE,
+					0, BOOT);
 		if (!ret)
 			ret = err;
 	}
diff --git a/drivers/base/node.c b/drivers/base/node.c
index 91636cd8b6c..43fa90b837e 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -6,6 +6,7 @@
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/mm.h>
+#include <linux/memory.h>
 #include <linux/node.h>
 #include <linux/hugetlb.h>
 #include <linux/cpumask.h>
@@ -248,6 +249,105 @@ int unregister_cpu_under_node(unsigned int cpu, unsigned int nid)
 	return 0;
 }
 
+#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
+#define page_initialized(page)  (page->lru.next)
+
+static int get_nid_for_pfn(unsigned long pfn)
+{
+	struct page *page;
+
+	if (!pfn_valid_within(pfn))
+		return -1;
+	page = pfn_to_page(pfn);
+	if (!page_initialized(page))
+		return -1;
+	return pfn_to_nid(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)
+{
+	unsigned long pfn, sect_start_pfn, sect_end_pfn;
+
+	if (!mem_blk)
+		return -EFAULT;
+	if (!node_online(nid))
+		return 0;
+	sect_start_pfn = section_nr_to_pfn(mem_blk->phys_index);
+	sect_end_pfn = sect_start_pfn + PAGES_PER_SECTION - 1;
+	for (pfn = sect_start_pfn; pfn <= sect_end_pfn; pfn++) {
+		int page_nid;
+
+		page_nid = get_nid_for_pfn(pfn);
+		if (page_nid < 0)
+			continue;
+		if (page_nid != nid)
+			continue;
+		return sysfs_create_link_nowarn(&node_devices[nid].sysdev.kobj,
+					&mem_blk->sysdev.kobj,
+					kobject_name(&mem_blk->sysdev.kobj));
+	}
+	/* mem section does not span the specified node */
+	return 0;
+}
+
+/* unregister memory section under all nodes that it spans */
+int unregister_mem_sect_under_nodes(struct memory_block *mem_blk)
+{
+	nodemask_t unlinked_nodes;
+	unsigned long pfn, sect_start_pfn, sect_end_pfn;
+
+	if (!mem_blk)
+		return -EFAULT;
+	nodes_clear(unlinked_nodes);
+	sect_start_pfn = section_nr_to_pfn(mem_blk->phys_index);
+	sect_end_pfn = sect_start_pfn + PAGES_PER_SECTION - 1;
+	for (pfn = sect_start_pfn; pfn <= sect_end_pfn; pfn++) {
+		unsigned int nid;
+
+		nid = get_nid_for_pfn(pfn);
+		if (nid < 0)
+			continue;
+		if (!node_online(nid))
+			continue;
+		if (node_test_and_set(nid, unlinked_nodes))
+			continue;
+		sysfs_remove_link(&node_devices[nid].sysdev.kobj,
+			 kobject_name(&mem_blk->sysdev.kobj));
+	}
+	return 0;
+}
+
+static int link_mem_sections(int nid)
+{
+	unsigned long start_pfn = NODE_DATA(nid)->node_start_pfn;
+	unsigned long end_pfn = start_pfn + NODE_DATA(nid)->node_spanned_pages;
+	unsigned long pfn;
+	int err = 0;
+
+	for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
+		unsigned long section_nr = pfn_to_section_nr(pfn);
+		struct mem_section *mem_sect;
+		struct memory_block *mem_blk;
+		int ret;
+
+		if (!present_section_nr(section_nr))
+			continue;
+		mem_sect = __nr_to_section(section_nr);
+		mem_blk = find_memory_block(mem_sect);
+		ret = register_mem_sect_under_node(mem_blk, nid);
+		if (!err)
+			err = ret;
+
+		/* discard ref obtained in find_memory_block() */
+		kobject_put(&mem_blk->sysdev.kobj);
+	}
+	return err;
+}
+#else
+static int link_mem_sections(int nid) { return 0; }
+#endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */
+
 int register_one_node(int nid)
 {
 	int error = 0;
@@ -267,6 +367,9 @@ int register_one_node(int nid)
 			if (cpu_to_node(cpu) == nid)
 				register_cpu_under_node(cpu, nid);
 		}
+
+		/* link memory sections under this node */
+		error = link_mem_sections(nid);
 	}
 
 	return error;