From c04fc586c1a480ba198f03ae7b6cbd7b57380b91 Mon Sep 17 00:00:00 2001 From: Gary Hade Date: Tue, 6 Jan 2009 14:39:14 -0800 Subject: [PATCH] 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 Signed-off-by: Badari Pulavarty Acked-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- .../ABI/testing/sysfs-devices-memory | 51 ++++++++- Documentation/memory-hotplug.txt | 16 ++- arch/ia64/mm/init.c | 2 +- arch/powerpc/mm/mem.c | 2 +- arch/s390/mm/init.c | 2 +- arch/sh/mm/init.c | 3 +- arch/x86/mm/init_32.c | 2 +- arch/x86/mm/init_64.c | 2 +- drivers/base/memory.c | 19 +++- drivers/base/node.c | 103 ++++++++++++++++++ include/linux/memory.h | 6 +- include/linux/memory_hotplug.h | 2 +- include/linux/node.h | 13 +++ mm/memory_hotplug.c | 11 +- 14 files changed, 209 insertions(+), 25 deletions(-) diff --git a/Documentation/ABI/testing/sysfs-devices-memory b/Documentation/ABI/testing/sysfs-devices-memory index 7a16fe1e2270d8..9fe91c02ee40e4 100644 --- a/Documentation/ABI/testing/sysfs-devices-memory +++ b/Documentation/ABI/testing/sysfs-devices-memory @@ -6,7 +6,6 @@ Description: internal state of the kernel memory blocks. Files could be added or removed dynamically to represent hot-add/remove operations. - Users: hotplug memory add/remove tools https://w3.opensource.ibm.com/projects/powerpc-utils/ @@ -19,6 +18,56 @@ Description: This is useful for a user-level agent to determine identify removable sections of the memory before attempting potentially expensive hot-remove memory operation +Users: hotplug memory remove tools + https://w3.opensource.ibm.com/projects/powerpc-utils/ + +What: /sys/devices/system/memory/memoryX/phys_device +Date: September 2008 +Contact: Badari Pulavarty +Description: + The file /sys/devices/system/memory/memoryX/phys_device + is read-only and is designed to show the name of physical + memory device. Implementation is currently incomplete. +What: /sys/devices/system/memory/memoryX/phys_index +Date: September 2008 +Contact: Badari Pulavarty +Description: + The file /sys/devices/system/memory/memoryX/phys_index + is read-only and contains the section ID in hexadecimal + which is equivalent to decimal X contained in the + memory section directory name. + +What: /sys/devices/system/memory/memoryX/state +Date: September 2008 +Contact: Badari Pulavarty +Description: + The file /sys/devices/system/memory/memoryX/state + is read-write. When read, it's contents show the + online/offline state of the memory section. When written, + root can toggle the the online/offline state of a removable + memory section (see removable file description above) + using the following commands. + # echo online > /sys/devices/system/memory/memoryX/state + # echo offline > /sys/devices/system/memory/memoryX/state + + For example, if /sys/devices/system/memory/memory22/removable + contains a value of 1 and + /sys/devices/system/memory/memory22/state contains the + string "online" the following command can be executed by + by root to offline that section. + # echo offline > /sys/devices/system/memory/memory22/state Users: hotplug memory remove tools https://w3.opensource.ibm.com/projects/powerpc-utils/ + +What: /sys/devices/system/node/nodeX/memoryY +Date: September 2008 +Contact: Gary Hade +Description: + When CONFIG_NUMA is enabled + /sys/devices/system/node/nodeX/memoryY is a symbolic link that + points to the corresponding /sys/devices/system/memory/memoryY + memory section directory. For example, the following symbolic + link is created for memory section 9 on node0. + /sys/devices/system/node/node0/memory9 -> ../../memory/memory9 + diff --git a/Documentation/memory-hotplug.txt b/Documentation/memory-hotplug.txt index 168117bd6ee8b8..4c2ecf537a4ad5 100644 --- a/Documentation/memory-hotplug.txt +++ b/Documentation/memory-hotplug.txt @@ -124,7 +124,7 @@ config options. This option can be kernel module too. -------------------------------- -3 sysfs files for memory hotplug +4 sysfs files for memory hotplug -------------------------------- All sections have their device information under /sys/devices/system/memory as @@ -138,11 +138,12 @@ For example, assume 1GiB section size. A device for a memory starting at (0x100000000 / 1Gib = 4) This device covers address range [0x100000000 ... 0x140000000) -Under each section, you can see 3 files. +Under each section, you can see 4 files. /sys/devices/system/memory/memoryXXX/phys_index /sys/devices/system/memory/memoryXXX/phys_device /sys/devices/system/memory/memoryXXX/state +/sys/devices/system/memory/memoryXXX/removable 'phys_index' : read-only and contains section id, same as XXX. 'state' : read-write @@ -150,10 +151,20 @@ Under each section, you can see 3 files. at write: user can specify "online", "offline" command 'phys_device': read-only: designed to show the name of physical memory device. This is not well implemented now. +'removable' : read-only: contains an integer value indicating + whether the memory section is removable or not + removable. A value of 1 indicates that the memory + section is removable and a value of 0 indicates that + it is not removable. NOTE: These directories/files appear after physical memory hotplug phase. +If CONFIG_NUMA is enabled the +/sys/devices/system/memory/memoryXXX memory section +directories can also be accessed via symbolic links located in +the /sys/devices/system/node/node* directories. For example: +/sys/devices/system/node/node0/memory9 -> ../../memory/memory9 -------------------------------- 4. Physical memory hot-add phase @@ -365,7 +376,6 @@ node if necessary. - allowing memory hot-add to ZONE_MOVABLE. maybe we need some switch like sysctl or new control file. - showing memory section and physical device relationship. - - showing memory section and node relationship (maybe good for NUMA) - showing memory section is under ZONE_MOVABLE or not - test and make it better memory offlining. - support HugeTLB page migration and offlining. diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index 054bcd9439aa88..56e12903973cc6 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -692,7 +692,7 @@ int arch_add_memory(int nid, u64 start, u64 size) pgdat = NODE_DATA(nid); zone = pgdat->node_zones + ZONE_NORMAL; - ret = __add_pages(zone, start_pfn, nr_pages); + ret = __add_pages(nid, zone, start_pfn, nr_pages); if (ret) printk("%s: Problem encountered in __add_pages() as ret=%d\n", diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 53b06ebb3f2f7c..f00f09a77f12f3 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -132,7 +132,7 @@ int arch_add_memory(int nid, u64 start, u64 size) /* this should work for most non-highmem platforms */ zone = pgdata->node_zones; - return __add_pages(zone, start_pfn, nr_pages); + return __add_pages(nid, zone, start_pfn, nr_pages); } #endif /* CONFIG_MEMORY_HOTPLUG */ diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index 158b0d6d704629..f0258ca3b17ed0 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -183,7 +183,7 @@ int arch_add_memory(int nid, u64 start, u64 size) rc = vmem_add_mapping(start, size); if (rc) return rc; - rc = __add_pages(zone, PFN_DOWN(start), PFN_DOWN(size)); + rc = __add_pages(nid, zone, PFN_DOWN(start), PFN_DOWN(size)); if (rc) vmem_remove_mapping(start, size); return rc; diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c index 6cbef8caeb560e..3edf297c829bd1 100644 --- a/arch/sh/mm/init.c +++ b/arch/sh/mm/init.c @@ -311,7 +311,8 @@ int arch_add_memory(int nid, u64 start, u64 size) pgdat = NODE_DATA(nid); /* We only have ZONE_NORMAL, so this is easy.. */ - ret = __add_pages(pgdat->node_zones + ZONE_NORMAL, start_pfn, nr_pages); + ret = __add_pages(nid, pgdat->node_zones + ZONE_NORMAL, + start_pfn, nr_pages); if (unlikely(ret)) printk("%s: Failed, __add_pages() == %d\n", __func__, ret); diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index f99a6c6c432ebc..544d724caeee01 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -1079,7 +1079,7 @@ int arch_add_memory(int nid, u64 start, u64 size) unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; - return __add_pages(zone, start_pfn, nr_pages); + return __add_pages(nid, zone, start_pfn, nr_pages); } #endif diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 9f7a0d24d42a93..54c437e96541f2 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -857,7 +857,7 @@ int arch_add_memory(int nid, u64 start, u64 size) if (last_mapped_pfn > max_pfn_mapped) max_pfn_mapped = last_mapped_pfn; - ret = __add_pages(zone, start_pfn, nr_pages); + ret = __add_pages(nid, zone, start_pfn, nr_pages); WARN_ON_ONCE(ret); return ret; diff --git a/drivers/base/memory.c b/drivers/base/memory.c index 5260e9e0df48a3..989429cfed88a7 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 91636cd8b6c9ad..43fa90b837eec4 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -6,6 +6,7 @@ #include #include #include +#include #include #include #include @@ -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; diff --git a/include/linux/memory.h b/include/linux/memory.h index 36c82c9e6ea709..3fdc10806d31b9 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -79,14 +79,14 @@ static inline int memory_notify(unsigned long val, void *v) #else extern int register_memory_notifier(struct notifier_block *nb); extern void unregister_memory_notifier(struct notifier_block *nb); -extern int register_new_memory(struct mem_section *); +extern int register_new_memory(int, struct mem_section *); extern int unregister_memory_section(struct mem_section *); extern int memory_dev_init(void); extern int remove_memory_block(unsigned long, struct mem_section *, int); extern int memory_notify(unsigned long val, void *v); +extern struct memory_block *find_memory_block(struct mem_section *); #define CONFIG_MEM_BLOCK_SIZE (PAGES_PER_SECTION<