mirror of
https://github.com/torvalds/linux.git
synced 2024-12-14 23:25:54 +00:00
321bf4ed5f
One system with 2048g ram, reported soft lockup on recent kernel. [ 34.426749] cpu_dev_init done [ 61.166399] BUG: soft lockup - CPU#0 stuck for 22s! [swapper/0:1] [ 61.166733] Modules linked in: [ 61.166904] irq event stamp: 1935610 [ 61.178431] hardirqs last enabled at (1935609): [<ffffffff81ce8c05>] mutex_lock_nested+0x299/0x2b4 [ 61.178923] hardirqs last disabled at (1935610): [<ffffffff81cf2bab>] apic_timer_interrupt+0x6b/0x80 [ 61.198767] softirqs last enabled at (1935476): [<ffffffff8106e59c>] __do_softirq+0x195/0x1ab [ 61.218604] softirqs last disabled at (1935471): [<ffffffff81cf359c>] call_softirq+0x1c/0x30 [ 61.238408] CPU 0 [ 61.238549] Modules linked in: [ 61.238744] [ 61.238825] Pid: 1, comm: swapper/0 Not tainted 3.3.0-rc1-tip-yh-02076-g962f689-dirty #171 [ 61.278212] RIP: 0010:[<ffffffff810b3e3a>] [<ffffffff810b3e3a>] lock_release+0x90/0x9c [ 61.278627] RSP: 0018:ffff883f64dbfd70 EFLAGS: 00000246 [ 61.298287] RAX: ffff883f64dc0000 RBX: 0000000000000000 RCX: 000000000000008b [ 61.298690] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000 [ 61.318383] RBP: ffff883f64dbfda0 R08: 0000000000000001 R09: 000000000000008b [ 61.338215] R10: 0000000000000000 R11: 0000000000000000 R12: ffff883f64dbfd10 [ 61.338610] R13: ffff883f64dc0708 R14: ffff883f64dc0708 R15: ffffffff81095657 [ 61.358299] FS: 0000000000000000(0000) GS:ffff883f7d600000(0000) knlGS:0000000000000000 [ 61.378118] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b [ 61.378450] CR2: 0000000000000000 CR3: 00000000024af000 CR4: 00000000000007f0 [ 61.398144] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 61.417918] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 [ 61.418260] Process swapper/0 (pid: 1, threadinfo ffff883f64dbe000, task ffff883f64dc0000) [ 61.445358] Stack: [ 61.445511] 0000000000000002 ffff897f649ba168 ffff883f64dbfe10 ffff88ff64bb57a8 [ 61.458040] 0000000000000000 0000000000000000 ffff883f64dbfdc0 ffffffff81ceb1b4 [ 61.458491] 000000000011608c ffff88ff64bb58a8 ffff883f64dbfdf0 ffffffff81c57638 [ 61.478215] Call Trace: [ 61.478367] [<ffffffff81ceb1b4>] _raw_spin_unlock+0x21/0x2e [ 61.497994] [<ffffffff81c57638>] klist_next+0x9e/0xbc [ 61.498264] [<ffffffff8148ba99>] next_device+0xe/0x1e [ 61.517867] [<ffffffff8148c0cc>] subsys_find_device_by_id+0xb7/0xd6 [ 61.518197] [<ffffffff81498846>] find_memory_block_hinted+0x3d/0x66 [ 61.537927] [<ffffffff8149887f>] find_memory_block+0x10/0x12 [ 61.538193] [<ffffffff814988b6>] add_memory_section+0x35/0x9e [ 61.557932] [<ffffffff827fecef>] memory_dev_init+0x68/0xda [ 61.558227] [<ffffffff827fec01>] driver_init+0x97/0xa7 [ 61.577853] [<ffffffff827cdf3c>] kernel_init+0xf6/0x1c0 [ 61.578140] [<ffffffff81cf34a4>] kernel_thread_helper+0x4/0x10 [ 61.597850] [<ffffffff81ceb59d>] ? retint_restore_args+0xe/0xe [ 61.598144] [<ffffffff827cde46>] ? start_kernel+0x3ab/0x3ab [ 61.617826] [<ffffffff81cf34a0>] ? gs_change+0xb/0xb [ 61.618060] Code: 10 48 83 3b 00 eb e8 4c 89 f2 44 89 fe 4c 89 ef e8 e1 fe ff ff 65 48 8b 04 25 40 bc 00 00 c7 80 cc 06 00 00 00 00 00 00 41 54 9d <5e> 5b 41 5c 41 5d 41 5e 41 5f 5d c3 55 48 89 e5 41 57 41 89 cf [ 89.285380] memory_dev_init done Finally it takes about 55s to create 16400 memory entries. Root cause: for x86_64, 2048g (with 2g hole at [2g,4g), and TOP2 will be 2050g), will have 16400 memory block. find_memory_block/subsys_find_device_by_id will be expensive with that many entries. Actually, we don't need to find that memory block for BOOT path. Skip that finding make it get back to normal. [ 34.466696] cpu_dev_init done [ 35.290080] memory_dev_init done Also solved the delay with topology_init when sections_per_block is not 1. Signed-off-by: Yinghai Lu <yinghai@kernel.org> Cc: Kay Sievers <kay.sievers@vrfy.org> Cc: Nathan Fontenot <nfont@austin.ibm.com> Cc: Robin Holt <holt@sgi.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
706 lines
17 KiB
C
706 lines
17 KiB
C
/*
|
|
* Memory subsystem support
|
|
*
|
|
* Written by Matt Tolentino <matthew.e.tolentino@intel.com>
|
|
* Dave Hansen <haveblue@us.ibm.com>
|
|
*
|
|
* This file provides the necessary infrastructure to represent
|
|
* a SPARSEMEM-memory-model system's physical memory in /sysfs.
|
|
* All arch-independent code that assumes MEMORY_HOTPLUG requires
|
|
* SPARSEMEM should be contained here, or in mm/memory_hotplug.c.
|
|
*/
|
|
|
|
#include <linux/module.h>
|
|
#include <linux/init.h>
|
|
#include <linux/topology.h>
|
|
#include <linux/capability.h>
|
|
#include <linux/device.h>
|
|
#include <linux/memory.h>
|
|
#include <linux/kobject.h>
|
|
#include <linux/memory_hotplug.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/mutex.h>
|
|
#include <linux/stat.h>
|
|
#include <linux/slab.h>
|
|
|
|
#include <linux/atomic.h>
|
|
#include <asm/uaccess.h>
|
|
|
|
static DEFINE_MUTEX(mem_sysfs_mutex);
|
|
|
|
#define MEMORY_CLASS_NAME "memory"
|
|
|
|
static int sections_per_block;
|
|
|
|
static inline int base_memory_block_id(int section_nr)
|
|
{
|
|
return section_nr / sections_per_block;
|
|
}
|
|
|
|
static struct bus_type memory_subsys = {
|
|
.name = MEMORY_CLASS_NAME,
|
|
.dev_name = MEMORY_CLASS_NAME,
|
|
};
|
|
|
|
static BLOCKING_NOTIFIER_HEAD(memory_chain);
|
|
|
|
int register_memory_notifier(struct notifier_block *nb)
|
|
{
|
|
return blocking_notifier_chain_register(&memory_chain, nb);
|
|
}
|
|
EXPORT_SYMBOL(register_memory_notifier);
|
|
|
|
void unregister_memory_notifier(struct notifier_block *nb)
|
|
{
|
|
blocking_notifier_chain_unregister(&memory_chain, nb);
|
|
}
|
|
EXPORT_SYMBOL(unregister_memory_notifier);
|
|
|
|
static ATOMIC_NOTIFIER_HEAD(memory_isolate_chain);
|
|
|
|
int register_memory_isolate_notifier(struct notifier_block *nb)
|
|
{
|
|
return atomic_notifier_chain_register(&memory_isolate_chain, nb);
|
|
}
|
|
EXPORT_SYMBOL(register_memory_isolate_notifier);
|
|
|
|
void unregister_memory_isolate_notifier(struct notifier_block *nb)
|
|
{
|
|
atomic_notifier_chain_unregister(&memory_isolate_chain, nb);
|
|
}
|
|
EXPORT_SYMBOL(unregister_memory_isolate_notifier);
|
|
|
|
/*
|
|
* register_memory - Setup a sysfs device for a memory block
|
|
*/
|
|
static
|
|
int register_memory(struct memory_block *memory)
|
|
{
|
|
int error;
|
|
|
|
memory->dev.bus = &memory_subsys;
|
|
memory->dev.id = memory->start_section_nr / sections_per_block;
|
|
|
|
error = device_register(&memory->dev);
|
|
return error;
|
|
}
|
|
|
|
static void
|
|
unregister_memory(struct memory_block *memory)
|
|
{
|
|
BUG_ON(memory->dev.bus != &memory_subsys);
|
|
|
|
/* drop the ref. we got in remove_memory_block() */
|
|
kobject_put(&memory->dev.kobj);
|
|
device_unregister(&memory->dev);
|
|
}
|
|
|
|
unsigned long __weak memory_block_size_bytes(void)
|
|
{
|
|
return MIN_MEMORY_BLOCK_SIZE;
|
|
}
|
|
|
|
static unsigned long get_memory_block_size(void)
|
|
{
|
|
unsigned long block_sz;
|
|
|
|
block_sz = memory_block_size_bytes();
|
|
|
|
/* Validate blk_sz is a power of 2 and not less than section size */
|
|
if ((block_sz & (block_sz - 1)) || (block_sz < MIN_MEMORY_BLOCK_SIZE)) {
|
|
WARN_ON(1);
|
|
block_sz = MIN_MEMORY_BLOCK_SIZE;
|
|
}
|
|
|
|
return block_sz;
|
|
}
|
|
|
|
/*
|
|
* use this as the physical section index that this memsection
|
|
* uses.
|
|
*/
|
|
|
|
static ssize_t show_mem_start_phys_index(struct device *dev,
|
|
struct device_attribute *attr, char *buf)
|
|
{
|
|
struct memory_block *mem =
|
|
container_of(dev, struct memory_block, dev);
|
|
unsigned long phys_index;
|
|
|
|
phys_index = mem->start_section_nr / sections_per_block;
|
|
return sprintf(buf, "%08lx\n", phys_index);
|
|
}
|
|
|
|
static ssize_t show_mem_end_phys_index(struct device *dev,
|
|
struct device_attribute *attr, char *buf)
|
|
{
|
|
struct memory_block *mem =
|
|
container_of(dev, struct memory_block, dev);
|
|
unsigned long phys_index;
|
|
|
|
phys_index = mem->end_section_nr / sections_per_block;
|
|
return sprintf(buf, "%08lx\n", phys_index);
|
|
}
|
|
|
|
/*
|
|
* Show whether the section of memory is likely to be hot-removable
|
|
*/
|
|
static ssize_t show_mem_removable(struct device *dev,
|
|
struct device_attribute *attr, char *buf)
|
|
{
|
|
unsigned long i, pfn;
|
|
int ret = 1;
|
|
struct memory_block *mem =
|
|
container_of(dev, struct memory_block, dev);
|
|
|
|
for (i = 0; i < sections_per_block; i++) {
|
|
pfn = section_nr_to_pfn(mem->start_section_nr + i);
|
|
ret &= is_mem_section_removable(pfn, PAGES_PER_SECTION);
|
|
}
|
|
|
|
return sprintf(buf, "%d\n", ret);
|
|
}
|
|
|
|
/*
|
|
* online, offline, going offline, etc.
|
|
*/
|
|
static ssize_t show_mem_state(struct device *dev,
|
|
struct device_attribute *attr, char *buf)
|
|
{
|
|
struct memory_block *mem =
|
|
container_of(dev, struct memory_block, dev);
|
|
ssize_t len = 0;
|
|
|
|
/*
|
|
* We can probably put these states in a nice little array
|
|
* so that they're not open-coded
|
|
*/
|
|
switch (mem->state) {
|
|
case MEM_ONLINE:
|
|
len = sprintf(buf, "online\n");
|
|
break;
|
|
case MEM_OFFLINE:
|
|
len = sprintf(buf, "offline\n");
|
|
break;
|
|
case MEM_GOING_OFFLINE:
|
|
len = sprintf(buf, "going-offline\n");
|
|
break;
|
|
default:
|
|
len = sprintf(buf, "ERROR-UNKNOWN-%ld\n",
|
|
mem->state);
|
|
WARN_ON(1);
|
|
break;
|
|
}
|
|
|
|
return len;
|
|
}
|
|
|
|
int memory_notify(unsigned long val, void *v)
|
|
{
|
|
return blocking_notifier_call_chain(&memory_chain, val, v);
|
|
}
|
|
|
|
int memory_isolate_notify(unsigned long val, void *v)
|
|
{
|
|
return atomic_notifier_call_chain(&memory_isolate_chain, val, v);
|
|
}
|
|
|
|
/*
|
|
* The probe routines leave the pages reserved, just as the bootmem code does.
|
|
* Make sure they're still that way.
|
|
*/
|
|
static bool pages_correctly_reserved(unsigned long start_pfn,
|
|
unsigned long nr_pages)
|
|
{
|
|
int i, j;
|
|
struct page *page;
|
|
unsigned long pfn = start_pfn;
|
|
|
|
/*
|
|
* memmap between sections is not contiguous except with
|
|
* SPARSEMEM_VMEMMAP. We lookup the page once per section
|
|
* and assume memmap is contiguous within each section
|
|
*/
|
|
for (i = 0; i < sections_per_block; i++, pfn += PAGES_PER_SECTION) {
|
|
if (WARN_ON_ONCE(!pfn_valid(pfn)))
|
|
return false;
|
|
page = pfn_to_page(pfn);
|
|
|
|
for (j = 0; j < PAGES_PER_SECTION; j++) {
|
|
if (PageReserved(page + j))
|
|
continue;
|
|
|
|
printk(KERN_WARNING "section number %ld page number %d "
|
|
"not reserved, was it already online?\n",
|
|
pfn_to_section_nr(pfn), j);
|
|
|
|
return false;
|
|
}
|
|
}
|
|
|
|
return true;
|
|
}
|
|
|
|
/*
|
|
* MEMORY_HOTPLUG depends on SPARSEMEM in mm/Kconfig, so it is
|
|
* OK to have direct references to sparsemem variables in here.
|
|
*/
|
|
static int
|
|
memory_block_action(unsigned long phys_index, unsigned long action)
|
|
{
|
|
unsigned long start_pfn, start_paddr;
|
|
unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block;
|
|
struct page *first_page;
|
|
int ret;
|
|
|
|
first_page = pfn_to_page(phys_index << PFN_SECTION_SHIFT);
|
|
|
|
switch (action) {
|
|
case MEM_ONLINE:
|
|
start_pfn = page_to_pfn(first_page);
|
|
|
|
if (!pages_correctly_reserved(start_pfn, nr_pages))
|
|
return -EBUSY;
|
|
|
|
ret = online_pages(start_pfn, nr_pages);
|
|
break;
|
|
case MEM_OFFLINE:
|
|
start_paddr = page_to_pfn(first_page) << PAGE_SHIFT;
|
|
ret = remove_memory(start_paddr,
|
|
nr_pages << PAGE_SHIFT);
|
|
break;
|
|
default:
|
|
WARN(1, KERN_WARNING "%s(%ld, %ld) unknown action: "
|
|
"%ld\n", __func__, phys_index, action, action);
|
|
ret = -EINVAL;
|
|
}
|
|
|
|
return ret;
|
|
}
|
|
|
|
static int memory_block_change_state(struct memory_block *mem,
|
|
unsigned long to_state, unsigned long from_state_req)
|
|
{
|
|
int ret = 0;
|
|
|
|
mutex_lock(&mem->state_mutex);
|
|
|
|
if (mem->state != from_state_req) {
|
|
ret = -EINVAL;
|
|
goto out;
|
|
}
|
|
|
|
if (to_state == MEM_OFFLINE)
|
|
mem->state = MEM_GOING_OFFLINE;
|
|
|
|
ret = memory_block_action(mem->start_section_nr, to_state);
|
|
|
|
if (ret) {
|
|
mem->state = from_state_req;
|
|
goto out;
|
|
}
|
|
|
|
mem->state = to_state;
|
|
switch (mem->state) {
|
|
case MEM_OFFLINE:
|
|
kobject_uevent(&mem->dev.kobj, KOBJ_OFFLINE);
|
|
break;
|
|
case MEM_ONLINE:
|
|
kobject_uevent(&mem->dev.kobj, KOBJ_ONLINE);
|
|
break;
|
|
default:
|
|
break;
|
|
}
|
|
out:
|
|
mutex_unlock(&mem->state_mutex);
|
|
return ret;
|
|
}
|
|
|
|
static ssize_t
|
|
store_mem_state(struct device *dev,
|
|
struct device_attribute *attr, const char *buf, size_t count)
|
|
{
|
|
struct memory_block *mem;
|
|
int ret = -EINVAL;
|
|
|
|
mem = container_of(dev, struct memory_block, dev);
|
|
|
|
if (!strncmp(buf, "online", min((int)count, 6)))
|
|
ret = memory_block_change_state(mem, MEM_ONLINE, MEM_OFFLINE);
|
|
else if(!strncmp(buf, "offline", min((int)count, 7)))
|
|
ret = memory_block_change_state(mem, MEM_OFFLINE, MEM_ONLINE);
|
|
|
|
if (ret)
|
|
return ret;
|
|
return count;
|
|
}
|
|
|
|
/*
|
|
* phys_device is a bad name for this. What I really want
|
|
* is a way to differentiate between memory ranges that
|
|
* are part of physical devices that constitute
|
|
* a complete removable unit or fru.
|
|
* i.e. do these ranges belong to the same physical device,
|
|
* s.t. if I offline all of these sections I can then
|
|
* remove the physical device?
|
|
*/
|
|
static ssize_t show_phys_device(struct device *dev,
|
|
struct device_attribute *attr, char *buf)
|
|
{
|
|
struct memory_block *mem =
|
|
container_of(dev, struct memory_block, dev);
|
|
return sprintf(buf, "%d\n", mem->phys_device);
|
|
}
|
|
|
|
static DEVICE_ATTR(phys_index, 0444, show_mem_start_phys_index, NULL);
|
|
static DEVICE_ATTR(end_phys_index, 0444, show_mem_end_phys_index, NULL);
|
|
static DEVICE_ATTR(state, 0644, show_mem_state, store_mem_state);
|
|
static DEVICE_ATTR(phys_device, 0444, show_phys_device, NULL);
|
|
static DEVICE_ATTR(removable, 0444, show_mem_removable, NULL);
|
|
|
|
#define mem_create_simple_file(mem, attr_name) \
|
|
device_create_file(&mem->dev, &dev_attr_##attr_name)
|
|
#define mem_remove_simple_file(mem, attr_name) \
|
|
device_remove_file(&mem->dev, &dev_attr_##attr_name)
|
|
|
|
/*
|
|
* Block size attribute stuff
|
|
*/
|
|
static ssize_t
|
|
print_block_size(struct device *dev, struct device_attribute *attr,
|
|
char *buf)
|
|
{
|
|
return sprintf(buf, "%lx\n", get_memory_block_size());
|
|
}
|
|
|
|
static DEVICE_ATTR(block_size_bytes, 0444, print_block_size, NULL);
|
|
|
|
static int block_size_init(void)
|
|
{
|
|
return device_create_file(memory_subsys.dev_root,
|
|
&dev_attr_block_size_bytes);
|
|
}
|
|
|
|
/*
|
|
* Some architectures will have custom drivers to do this, and
|
|
* will not need to do it from userspace. The fake hot-add code
|
|
* as well as ppc64 will do all of their discovery in userspace
|
|
* and will require this interface.
|
|
*/
|
|
#ifdef CONFIG_ARCH_MEMORY_PROBE
|
|
static ssize_t
|
|
memory_probe_store(struct device *dev, struct device_attribute *attr,
|
|
const char *buf, size_t count)
|
|
{
|
|
u64 phys_addr;
|
|
int nid;
|
|
int i, ret;
|
|
unsigned long pages_per_block = PAGES_PER_SECTION * sections_per_block;
|
|
|
|
phys_addr = simple_strtoull(buf, NULL, 0);
|
|
|
|
if (phys_addr & ((pages_per_block << PAGE_SHIFT) - 1))
|
|
return -EINVAL;
|
|
|
|
for (i = 0; i < sections_per_block; i++) {
|
|
nid = memory_add_physaddr_to_nid(phys_addr);
|
|
ret = add_memory(nid, phys_addr,
|
|
PAGES_PER_SECTION << PAGE_SHIFT);
|
|
if (ret)
|
|
goto out;
|
|
|
|
phys_addr += MIN_MEMORY_BLOCK_SIZE;
|
|
}
|
|
|
|
ret = count;
|
|
out:
|
|
return ret;
|
|
}
|
|
static DEVICE_ATTR(probe, S_IWUSR, NULL, memory_probe_store);
|
|
|
|
static int memory_probe_init(void)
|
|
{
|
|
return device_create_file(memory_subsys.dev_root, &dev_attr_probe);
|
|
}
|
|
#else
|
|
static inline int memory_probe_init(void)
|
|
{
|
|
return 0;
|
|
}
|
|
#endif
|
|
|
|
#ifdef CONFIG_MEMORY_FAILURE
|
|
/*
|
|
* Support for offlining pages of memory
|
|
*/
|
|
|
|
/* Soft offline a page */
|
|
static ssize_t
|
|
store_soft_offline_page(struct device *dev,
|
|
struct device_attribute *attr,
|
|
const char *buf, size_t count)
|
|
{
|
|
int ret;
|
|
u64 pfn;
|
|
if (!capable(CAP_SYS_ADMIN))
|
|
return -EPERM;
|
|
if (strict_strtoull(buf, 0, &pfn) < 0)
|
|
return -EINVAL;
|
|
pfn >>= PAGE_SHIFT;
|
|
if (!pfn_valid(pfn))
|
|
return -ENXIO;
|
|
ret = soft_offline_page(pfn_to_page(pfn), 0);
|
|
return ret == 0 ? count : ret;
|
|
}
|
|
|
|
/* Forcibly offline a page, including killing processes. */
|
|
static ssize_t
|
|
store_hard_offline_page(struct device *dev,
|
|
struct device_attribute *attr,
|
|
const char *buf, size_t count)
|
|
{
|
|
int ret;
|
|
u64 pfn;
|
|
if (!capable(CAP_SYS_ADMIN))
|
|
return -EPERM;
|
|
if (strict_strtoull(buf, 0, &pfn) < 0)
|
|
return -EINVAL;
|
|
pfn >>= PAGE_SHIFT;
|
|
ret = __memory_failure(pfn, 0, 0);
|
|
return ret ? ret : count;
|
|
}
|
|
|
|
static DEVICE_ATTR(soft_offline_page, 0644, NULL, store_soft_offline_page);
|
|
static DEVICE_ATTR(hard_offline_page, 0644, NULL, store_hard_offline_page);
|
|
|
|
static __init int memory_fail_init(void)
|
|
{
|
|
int err;
|
|
|
|
err = device_create_file(memory_subsys.dev_root,
|
|
&dev_attr_soft_offline_page);
|
|
if (!err)
|
|
err = device_create_file(memory_subsys.dev_root,
|
|
&dev_attr_hard_offline_page);
|
|
return err;
|
|
}
|
|
#else
|
|
static inline int memory_fail_init(void)
|
|
{
|
|
return 0;
|
|
}
|
|
#endif
|
|
|
|
/*
|
|
* Note that phys_device is optional. It is here to allow for
|
|
* differentiation between which *physical* devices each
|
|
* section belongs to...
|
|
*/
|
|
int __weak arch_get_memory_phys_device(unsigned long start_pfn)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* A reference for the returned object is held and the reference for the
|
|
* hinted object is released.
|
|
*/
|
|
struct memory_block *find_memory_block_hinted(struct mem_section *section,
|
|
struct memory_block *hint)
|
|
{
|
|
int block_id = base_memory_block_id(__section_nr(section));
|
|
struct device *hintdev = hint ? &hint->dev : NULL;
|
|
struct device *dev;
|
|
|
|
dev = subsys_find_device_by_id(&memory_subsys, block_id, hintdev);
|
|
if (hint)
|
|
put_device(&hint->dev);
|
|
if (!dev)
|
|
return NULL;
|
|
return container_of(dev, struct memory_block, dev);
|
|
}
|
|
|
|
/*
|
|
* For now, we have a linear search to go find the appropriate
|
|
* memory_block corresponding to a particular phys_index. If
|
|
* this gets to be a real problem, we can always use a radix
|
|
* tree or something here.
|
|
*
|
|
* This could be made generic for all device subsystems.
|
|
*/
|
|
struct memory_block *find_memory_block(struct mem_section *section)
|
|
{
|
|
return find_memory_block_hinted(section, NULL);
|
|
}
|
|
|
|
static int init_memory_block(struct memory_block **memory,
|
|
struct mem_section *section, unsigned long state)
|
|
{
|
|
struct memory_block *mem;
|
|
unsigned long start_pfn;
|
|
int scn_nr;
|
|
int ret = 0;
|
|
|
|
mem = kzalloc(sizeof(*mem), GFP_KERNEL);
|
|
if (!mem)
|
|
return -ENOMEM;
|
|
|
|
scn_nr = __section_nr(section);
|
|
mem->start_section_nr =
|
|
base_memory_block_id(scn_nr) * sections_per_block;
|
|
mem->end_section_nr = mem->start_section_nr + sections_per_block - 1;
|
|
mem->state = state;
|
|
mem->section_count++;
|
|
mutex_init(&mem->state_mutex);
|
|
start_pfn = section_nr_to_pfn(mem->start_section_nr);
|
|
mem->phys_device = arch_get_memory_phys_device(start_pfn);
|
|
|
|
ret = register_memory(mem);
|
|
if (!ret)
|
|
ret = mem_create_simple_file(mem, phys_index);
|
|
if (!ret)
|
|
ret = mem_create_simple_file(mem, end_phys_index);
|
|
if (!ret)
|
|
ret = mem_create_simple_file(mem, state);
|
|
if (!ret)
|
|
ret = mem_create_simple_file(mem, phys_device);
|
|
if (!ret)
|
|
ret = mem_create_simple_file(mem, removable);
|
|
|
|
*memory = mem;
|
|
return ret;
|
|
}
|
|
|
|
static int add_memory_section(int nid, struct mem_section *section,
|
|
struct memory_block **mem_p,
|
|
unsigned long state, enum mem_add_context context)
|
|
{
|
|
struct memory_block *mem = NULL;
|
|
int scn_nr = __section_nr(section);
|
|
int ret = 0;
|
|
|
|
mutex_lock(&mem_sysfs_mutex);
|
|
|
|
if (context == BOOT) {
|
|
/* same memory block ? */
|
|
if (mem_p && *mem_p)
|
|
if (scn_nr >= (*mem_p)->start_section_nr &&
|
|
scn_nr <= (*mem_p)->end_section_nr) {
|
|
mem = *mem_p;
|
|
kobject_get(&mem->dev.kobj);
|
|
}
|
|
} else
|
|
mem = find_memory_block(section);
|
|
|
|
if (mem) {
|
|
mem->section_count++;
|
|
kobject_put(&mem->dev.kobj);
|
|
} else {
|
|
ret = init_memory_block(&mem, section, state);
|
|
/* store memory_block pointer for next loop */
|
|
if (!ret && context == BOOT)
|
|
if (mem_p)
|
|
*mem_p = mem;
|
|
}
|
|
|
|
if (!ret) {
|
|
if (context == HOTPLUG &&
|
|
mem->section_count == sections_per_block)
|
|
ret = register_mem_sect_under_node(mem, nid);
|
|
}
|
|
|
|
mutex_unlock(&mem_sysfs_mutex);
|
|
return ret;
|
|
}
|
|
|
|
int remove_memory_block(unsigned long node_id, struct mem_section *section,
|
|
int phys_device)
|
|
{
|
|
struct memory_block *mem;
|
|
|
|
mutex_lock(&mem_sysfs_mutex);
|
|
mem = find_memory_block(section);
|
|
unregister_mem_sect_under_nodes(mem, __section_nr(section));
|
|
|
|
mem->section_count--;
|
|
if (mem->section_count == 0) {
|
|
mem_remove_simple_file(mem, phys_index);
|
|
mem_remove_simple_file(mem, end_phys_index);
|
|
mem_remove_simple_file(mem, state);
|
|
mem_remove_simple_file(mem, phys_device);
|
|
mem_remove_simple_file(mem, removable);
|
|
unregister_memory(mem);
|
|
kfree(mem);
|
|
} else
|
|
kobject_put(&mem->dev.kobj);
|
|
|
|
mutex_unlock(&mem_sysfs_mutex);
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* 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)
|
|
{
|
|
return add_memory_section(nid, section, NULL, MEM_OFFLINE, HOTPLUG);
|
|
}
|
|
|
|
int unregister_memory_section(struct mem_section *section)
|
|
{
|
|
if (!present_section(section))
|
|
return -EINVAL;
|
|
|
|
return remove_memory_block(0, section, 0);
|
|
}
|
|
|
|
/*
|
|
* Initialize the sysfs support for memory devices...
|
|
*/
|
|
int __init memory_dev_init(void)
|
|
{
|
|
unsigned int i;
|
|
int ret;
|
|
int err;
|
|
unsigned long block_sz;
|
|
struct memory_block *mem = NULL;
|
|
|
|
ret = subsys_system_register(&memory_subsys, NULL);
|
|
if (ret)
|
|
goto out;
|
|
|
|
block_sz = get_memory_block_size();
|
|
sections_per_block = block_sz / MIN_MEMORY_BLOCK_SIZE;
|
|
|
|
/*
|
|
* Create entries for memory sections that were found
|
|
* during boot and have been initialized
|
|
*/
|
|
for (i = 0; i < NR_MEM_SECTIONS; i++) {
|
|
if (!present_section_nr(i))
|
|
continue;
|
|
/* don't need to reuse memory_block if only one per block */
|
|
err = add_memory_section(0, __nr_to_section(i),
|
|
(sections_per_block == 1) ? NULL : &mem,
|
|
MEM_ONLINE,
|
|
BOOT);
|
|
if (!ret)
|
|
ret = err;
|
|
}
|
|
|
|
err = memory_probe_init();
|
|
if (!ret)
|
|
ret = err;
|
|
err = memory_fail_init();
|
|
if (!ret)
|
|
ret = err;
|
|
err = block_size_init();
|
|
if (!ret)
|
|
ret = err;
|
|
out:
|
|
if (ret)
|
|
printk(KERN_ERR "%s() failed: %d\n", __func__, ret);
|
|
return ret;
|
|
}
|