![Linus Torvalds](/assets/img/avatar_default.png)
1) ACPI-based PCI hotplug (ACPIPHP) subsystem rework and introduction of Intel Thunderbolt support on systems that use ACPI for signalling Thunderbolt hotplug events. This also should make ACPIPHP work in some cases in which it was known to have problems. From Rafael J Wysocki, Mika Westerberg and Kirill A Shutemov. 2) ACPI core code cleanups and dock station support cleanups from Jiang Liu and Rafael J Wysocki. 3) Fixes for locking problems related to ACPI device hotplug from Rafael J Wysocki. 4) ACPICA update to version 20130725 includig fixes, cleanups, support for more than 256 GPEs per GPE block and a change to make the ACPI PM Timer optional (we've seen systems without the PM Timer in the field already). One of the fixes, related to the DeRefOf operator, is necessary to prevent some Windows 8 oriented AML from causing problems to happen. From Bob Moore, Lv Zheng, and Jung-uk Kim. 5) Removal of the old and long deprecated /proc/acpi/event interface and related driver changes from Thomas Renninger. 6) ACPI and Xen changes to make the reduced hardware sleep work with the latter from Ben Guthro. 7) ACPI video driver cleanups and a blacklist of systems that should not tell the BIOS that they are compatible with Windows 8 (or ACPI backlight and possibly other things will not work on them). From Felipe Contreras. 8) Assorted ACPI fixes and cleanups from Aaron Lu, Hanjun Guo, Kuppuswamy Sathyanarayanan, Lan Tianyu, Sachin Kamat, Tang Chen, Toshi Kani, and Wei Yongjun. 9) cpufreq ondemand governor target frequency selection change to reduce oscillations between min and max frequencies (essentially, it causes the governor to choose target frequencies proportional to load) from Stratos Karafotis. 10) cpufreq fixes allowing sysfs attributes file permissions to be preserved over suspend/resume cycles Srivatsa S Bhat. 11) Removal of Device Tree parsing for CPU device nodes from multiple cpufreq drivers that required some changes related to of_get_cpu_node() to be made in a few architectures and in the driver core. From Sudeep KarkadaNagesha. 12) cpufreq core fixes and cleanups related to mutual exclusion and driver module references from Viresh Kumar, Lukasz Majewski and Rafael J Wysocki. 13) Assorted cpufreq fixes and cleanups from Amit Daniel Kachhap, Bartlomiej Zolnierkiewicz, Hanjun Guo, Jingoo Han, Joseph Lo, Julia Lawall, Li Zhong, Mark Brown, Sascha Hauer, Stephen Boyd, Stratos Karafotis, and Viresh Kumar. 14) Fixes to prevent race conditions in coupled cpuidle from happening from Colin Cross. 15) cpuidle core fixes and cleanups from Daniel Lezcano and Tuukka Tikkanen. 16) Assorted cpuidle fixes and cleanups from Daniel Lezcano, Geert Uytterhoeven, Jingoo Han, Julia Lawall, Linus Walleij, and Sahara. 17) System sleep tracing changes from Todd E Brandt and Shuah Khan. 18) PNP subsystem conversion to using struct dev_pm_ops for power management from Shuah Khan. / -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.19 (GNU/Linux) iQIcBAABCAAGBQJSJcKhAAoJEKhOf7ml8uNsplIQAJSOshxhkkemvFOuHZ+0YIbh R9aufjXeDkMDBi8YtU+tB7ERth1j+0LUSM0NTnP51U7e+7eSGobA9s5jSZQj2l7r HFtnSOegLuKAfqwgfSLK91xa1rTFdfW0Kych9G2nuHtBIt6P0Oc59Cb5M0oy6QXs nVtaDEuU//tmO71+EF5HnMJHabRTrpvtn/7NbDUpU7LZYpWJrHJFT9xt1rXNab7H YRCATPm3kXGRg58Doc3EZE4G3D7DLvq74jWMaI089X/m5Pg1G6upqArypOy6oxdP p2FEzYVrb2bi8fakXp7BBeO1gCJTAqIgAkbSSZHLpGhFaeEMmb9/DWPXdm2TjzMV c1EEucvsqZWoprXgy12i5Hk814xN8d8nBBLg/UYiRJ44nc/hevXfyE9ZYj6bkseJ +GNHmZIa1QYC05nnGli4+W4kHns8EZf/gmvIxnPuco1RN2yMWagrud5/G6Dr9M2B hzJV6qauLVzgZso4oe79zv9aVxe/dPHKANLD/sg23WBiJJbJF1ocBlnj2Xlbpqze pmMUWGiO/gUiS0fmpW/lAJauza5jFmSCjE4E8R0Gyn0j4YXjmMhdEanaU6J3VuCi yVgEzYEth4sowq4AflMMLKYN+WmozDnK7taZRGmT0t+EKRFKLT6EgnNrkQgs1vKl oawD9LM4fZ8E0yroOEme =CgqW -----END PGP SIGNATURE----- Merge tag 'pm+acpi-3.12-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm Pull ACPI and power management updates from Rafael Wysocki: 1) ACPI-based PCI hotplug (ACPIPHP) subsystem rework and introduction of Intel Thunderbolt support on systems that use ACPI for signalling Thunderbolt hotplug events. This also should make ACPIPHP work in some cases in which it was known to have problems. From Rafael J Wysocki, Mika Westerberg and Kirill A Shutemov. 2) ACPI core code cleanups and dock station support cleanups from Jiang Liu and Rafael J Wysocki. 3) Fixes for locking problems related to ACPI device hotplug from Rafael J Wysocki. 4) ACPICA update to version 20130725 includig fixes, cleanups, support for more than 256 GPEs per GPE block and a change to make the ACPI PM Timer optional (we've seen systems without the PM Timer in the field already). One of the fixes, related to the DeRefOf operator, is necessary to prevent some Windows 8 oriented AML from causing problems to happen. From Bob Moore, Lv Zheng, and Jung-uk Kim. 5) Removal of the old and long deprecated /proc/acpi/event interface and related driver changes from Thomas Renninger. 6) ACPI and Xen changes to make the reduced hardware sleep work with the latter from Ben Guthro. 7) ACPI video driver cleanups and a blacklist of systems that should not tell the BIOS that they are compatible with Windows 8 (or ACPI backlight and possibly other things will not work on them). From Felipe Contreras. 8) Assorted ACPI fixes and cleanups from Aaron Lu, Hanjun Guo, Kuppuswamy Sathyanarayanan, Lan Tianyu, Sachin Kamat, Tang Chen, Toshi Kani, and Wei Yongjun. 9) cpufreq ondemand governor target frequency selection change to reduce oscillations between min and max frequencies (essentially, it causes the governor to choose target frequencies proportional to load) from Stratos Karafotis. 10) cpufreq fixes allowing sysfs attributes file permissions to be preserved over suspend/resume cycles Srivatsa S Bhat. 11) Removal of Device Tree parsing for CPU device nodes from multiple cpufreq drivers that required some changes related to of_get_cpu_node() to be made in a few architectures and in the driver core. From Sudeep KarkadaNagesha. 12) cpufreq core fixes and cleanups related to mutual exclusion and driver module references from Viresh Kumar, Lukasz Majewski and Rafael J Wysocki. 13) Assorted cpufreq fixes and cleanups from Amit Daniel Kachhap, Bartlomiej Zolnierkiewicz, Hanjun Guo, Jingoo Han, Joseph Lo, Julia Lawall, Li Zhong, Mark Brown, Sascha Hauer, Stephen Boyd, Stratos Karafotis, and Viresh Kumar. 14) Fixes to prevent race conditions in coupled cpuidle from happening from Colin Cross. 15) cpuidle core fixes and cleanups from Daniel Lezcano and Tuukka Tikkanen. 16) Assorted cpuidle fixes and cleanups from Daniel Lezcano, Geert Uytterhoeven, Jingoo Han, Julia Lawall, Linus Walleij, and Sahara. 17) System sleep tracing changes from Todd E Brandt and Shuah Khan. 18) PNP subsystem conversion to using struct dev_pm_ops for power management from Shuah Khan. * tag 'pm+acpi-3.12-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (217 commits) cpufreq: Don't use smp_processor_id() in preemptible context cpuidle: coupled: fix race condition between pokes and safe state cpuidle: coupled: abort idle if pokes are pending cpuidle: coupled: disable interrupts after entering safe state ACPI / hotplug: Remove containers synchronously driver core / ACPI: Avoid device hot remove locking issues cpufreq: governor: Fix typos in comments cpufreq: governors: Remove duplicate check of target freq in supported range cpufreq: Fix timer/workqueue corruption due to double queueing ACPI / EC: Add ASUSTEK L4R to quirk list in order to validate ECDT ACPI / thermal: Add check of "_TZD" availability and evaluating result cpufreq: imx6q: Fix clock enable balance ACPI: blacklist win8 OSI for buggy laptops cpufreq: tegra: fix the wrong clock name cpuidle: Change struct menu_device field types cpuidle: Add a comment warning about possible overflow cpuidle: Fix variable domains in get_typical_interval() cpuidle: Fix menu_device->intervals type cpuidle: CodingStyle: Break up multiple assignments on single line cpuidle: Check called function parameter in get_typical_interval() ...
742 lines
18 KiB
C
742 lines
18 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/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"
|
|
|
|
#define to_memory_block(dev) container_of(dev, struct memory_block, dev)
|
|
|
|
static int sections_per_block;
|
|
|
|
static inline int base_memory_block_id(int section_nr)
|
|
{
|
|
return section_nr / sections_per_block;
|
|
}
|
|
|
|
static int memory_subsys_online(struct device *dev);
|
|
static int memory_subsys_offline(struct device *dev);
|
|
|
|
static struct bus_type memory_subsys = {
|
|
.name = MEMORY_CLASS_NAME,
|
|
.dev_name = MEMORY_CLASS_NAME,
|
|
.online = memory_subsys_online,
|
|
.offline = memory_subsys_offline,
|
|
};
|
|
|
|
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);
|
|
|
|
static void memory_block_release(struct device *dev)
|
|
{
|
|
struct memory_block *mem = to_memory_block(dev);
|
|
|
|
kfree(mem);
|
|
}
|
|
|
|
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 = to_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 = to_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 = to_memory_block(dev);
|
|
|
|
for (i = 0; i < sections_per_block; i++) {
|
|
if (!present_section_nr(mem->start_section_nr + i))
|
|
continue;
|
|
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 = to_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)
|
|
{
|
|
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, int online_type)
|
|
{
|
|
unsigned long start_pfn;
|
|
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);
|
|
start_pfn = page_to_pfn(first_page);
|
|
|
|
switch (action) {
|
|
case MEM_ONLINE:
|
|
if (!pages_correctly_reserved(start_pfn))
|
|
return -EBUSY;
|
|
|
|
ret = online_pages(start_pfn, nr_pages, online_type);
|
|
break;
|
|
case MEM_OFFLINE:
|
|
ret = offline_pages(start_pfn, nr_pages);
|
|
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;
|
|
|
|
if (mem->state != from_state_req)
|
|
return -EINVAL;
|
|
|
|
if (to_state == MEM_OFFLINE)
|
|
mem->state = MEM_GOING_OFFLINE;
|
|
|
|
ret = memory_block_action(mem->start_section_nr, to_state,
|
|
mem->online_type);
|
|
|
|
mem->state = ret ? from_state_req : to_state;
|
|
|
|
return ret;
|
|
}
|
|
|
|
/* The device lock serializes operations on memory_subsys_[online|offline] */
|
|
static int memory_subsys_online(struct device *dev)
|
|
{
|
|
struct memory_block *mem = to_memory_block(dev);
|
|
int ret;
|
|
|
|
if (mem->state == MEM_ONLINE)
|
|
return 0;
|
|
|
|
/*
|
|
* If we are called from store_mem_state(), online_type will be
|
|
* set >= 0 Otherwise we were called from the device online
|
|
* attribute and need to set the online_type.
|
|
*/
|
|
if (mem->online_type < 0)
|
|
mem->online_type = ONLINE_KEEP;
|
|
|
|
ret = memory_block_change_state(mem, MEM_ONLINE, MEM_OFFLINE);
|
|
|
|
/* clear online_type */
|
|
mem->online_type = -1;
|
|
|
|
return ret;
|
|
}
|
|
|
|
static int memory_subsys_offline(struct device *dev)
|
|
{
|
|
struct memory_block *mem = to_memory_block(dev);
|
|
|
|
if (mem->state == MEM_OFFLINE)
|
|
return 0;
|
|
|
|
return memory_block_change_state(mem, MEM_OFFLINE, MEM_ONLINE);
|
|
}
|
|
|
|
static ssize_t
|
|
store_mem_state(struct device *dev,
|
|
struct device_attribute *attr, const char *buf, size_t count)
|
|
{
|
|
struct memory_block *mem = to_memory_block(dev);
|
|
int ret, online_type;
|
|
|
|
ret = lock_device_hotplug_sysfs();
|
|
if (ret)
|
|
return ret;
|
|
|
|
if (!strncmp(buf, "online_kernel", min_t(int, count, 13)))
|
|
online_type = ONLINE_KERNEL;
|
|
else if (!strncmp(buf, "online_movable", min_t(int, count, 14)))
|
|
online_type = ONLINE_MOVABLE;
|
|
else if (!strncmp(buf, "online", min_t(int, count, 6)))
|
|
online_type = ONLINE_KEEP;
|
|
else if (!strncmp(buf, "offline", min_t(int, count, 7)))
|
|
online_type = -1;
|
|
else
|
|
return -EINVAL;
|
|
|
|
switch (online_type) {
|
|
case ONLINE_KERNEL:
|
|
case ONLINE_MOVABLE:
|
|
case ONLINE_KEEP:
|
|
/*
|
|
* mem->online_type is not protected so there can be a
|
|
* race here. However, when racing online, the first
|
|
* will succeed and the second will just return as the
|
|
* block will already be online. The online type
|
|
* could be either one, but that is expected.
|
|
*/
|
|
mem->online_type = online_type;
|
|
ret = device_online(&mem->dev);
|
|
break;
|
|
case -1:
|
|
ret = device_offline(&mem->dev);
|
|
break;
|
|
default:
|
|
ret = -EINVAL; /* should never happen */
|
|
}
|
|
|
|
unlock_device_hotplug();
|
|
|
|
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 = to_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);
|
|
|
|
/*
|
|
* 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);
|
|
|
|
/*
|
|
* 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);
|
|
#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 (kstrtoull(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 (kstrtoull(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, S_IWUSR, NULL, store_soft_offline_page);
|
|
static DEVICE_ATTR(hard_offline_page, S_IWUSR, NULL, store_hard_offline_page);
|
|
#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 to_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 struct attribute *memory_memblk_attrs[] = {
|
|
&dev_attr_phys_index.attr,
|
|
&dev_attr_end_phys_index.attr,
|
|
&dev_attr_state.attr,
|
|
&dev_attr_phys_device.attr,
|
|
&dev_attr_removable.attr,
|
|
NULL
|
|
};
|
|
|
|
static struct attribute_group memory_memblk_attr_group = {
|
|
.attrs = memory_memblk_attrs,
|
|
};
|
|
|
|
static const struct attribute_group *memory_memblk_attr_groups[] = {
|
|
&memory_memblk_attr_group,
|
|
NULL,
|
|
};
|
|
|
|
/*
|
|
* register_memory - Setup a sysfs device for a memory block
|
|
*/
|
|
static
|
|
int register_memory(struct memory_block *memory)
|
|
{
|
|
memory->dev.bus = &memory_subsys;
|
|
memory->dev.id = memory->start_section_nr / sections_per_block;
|
|
memory->dev.release = memory_block_release;
|
|
memory->dev.groups = memory_memblk_attr_groups;
|
|
memory->dev.offline = memory->state == MEM_OFFLINE;
|
|
|
|
return device_register(&memory->dev);
|
|
}
|
|
|
|
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++;
|
|
start_pfn = section_nr_to_pfn(mem->start_section_nr);
|
|
mem->phys_device = arch_get_memory_phys_device(start_pfn);
|
|
|
|
ret = register_memory(mem);
|
|
|
|
*memory = mem;
|
|
return ret;
|
|
}
|
|
|
|
static int add_memory_block(int base_section_nr)
|
|
{
|
|
struct memory_block *mem;
|
|
int i, ret, section_count = 0, section_nr;
|
|
|
|
for (i = base_section_nr;
|
|
(i < base_section_nr + sections_per_block) && i < NR_MEM_SECTIONS;
|
|
i++) {
|
|
if (!present_section_nr(i))
|
|
continue;
|
|
if (section_count == 0)
|
|
section_nr = i;
|
|
section_count++;
|
|
}
|
|
|
|
if (section_count == 0)
|
|
return 0;
|
|
ret = init_memory_block(&mem, __nr_to_section(section_nr), MEM_ONLINE);
|
|
if (ret)
|
|
return ret;
|
|
mem->section_count = section_count;
|
|
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)
|
|
{
|
|
int ret = 0;
|
|
struct memory_block *mem;
|
|
|
|
mutex_lock(&mem_sysfs_mutex);
|
|
|
|
mem = find_memory_block(section);
|
|
if (mem) {
|
|
mem->section_count++;
|
|
put_device(&mem->dev);
|
|
} else {
|
|
ret = init_memory_block(&mem, section, MEM_OFFLINE);
|
|
if (ret)
|
|
goto out;
|
|
}
|
|
|
|
if (mem->section_count == sections_per_block)
|
|
ret = register_mem_sect_under_node(mem, nid);
|
|
out:
|
|
mutex_unlock(&mem_sysfs_mutex);
|
|
return ret;
|
|
}
|
|
|
|
#ifdef CONFIG_MEMORY_HOTREMOVE
|
|
static void
|
|
unregister_memory(struct memory_block *memory)
|
|
{
|
|
BUG_ON(memory->dev.bus != &memory_subsys);
|
|
|
|
/* drop the ref. we got in remove_memory_block() */
|
|
put_device(&memory->dev);
|
|
device_unregister(&memory->dev);
|
|
}
|
|
|
|
static 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)
|
|
unregister_memory(mem);
|
|
else
|
|
put_device(&mem->dev);
|
|
|
|
mutex_unlock(&mem_sysfs_mutex);
|
|
return 0;
|
|
}
|
|
|
|
int unregister_memory_section(struct mem_section *section)
|
|
{
|
|
if (!present_section(section))
|
|
return -EINVAL;
|
|
|
|
return remove_memory_block(0, section, 0);
|
|
}
|
|
#endif /* CONFIG_MEMORY_HOTREMOVE */
|
|
|
|
/* return true if the memory block is offlined, otherwise, return false */
|
|
bool is_memblock_offlined(struct memory_block *mem)
|
|
{
|
|
return mem->state == MEM_OFFLINE;
|
|
}
|
|
|
|
static struct attribute *memory_root_attrs[] = {
|
|
#ifdef CONFIG_ARCH_MEMORY_PROBE
|
|
&dev_attr_probe.attr,
|
|
#endif
|
|
|
|
#ifdef CONFIG_MEMORY_FAILURE
|
|
&dev_attr_soft_offline_page.attr,
|
|
&dev_attr_hard_offline_page.attr,
|
|
#endif
|
|
|
|
&dev_attr_block_size_bytes.attr,
|
|
NULL
|
|
};
|
|
|
|
static struct attribute_group memory_root_attr_group = {
|
|
.attrs = memory_root_attrs,
|
|
};
|
|
|
|
static const struct attribute_group *memory_root_attr_groups[] = {
|
|
&memory_root_attr_group,
|
|
NULL,
|
|
};
|
|
|
|
/*
|
|
* Initialize the sysfs support for memory devices...
|
|
*/
|
|
int __init memory_dev_init(void)
|
|
{
|
|
unsigned int i;
|
|
int ret;
|
|
int err;
|
|
unsigned long block_sz;
|
|
|
|
ret = subsys_system_register(&memory_subsys, memory_root_attr_groups);
|
|
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
|
|
*/
|
|
mutex_lock(&mem_sysfs_mutex);
|
|
for (i = 0; i < NR_MEM_SECTIONS; i += sections_per_block) {
|
|
err = add_memory_block(i);
|
|
if (!ret)
|
|
ret = err;
|
|
}
|
|
mutex_unlock(&mem_sysfs_mutex);
|
|
|
|
out:
|
|
if (ret)
|
|
printk(KERN_ERR "%s() failed: %d\n", __func__, ret);
|
|
return ret;
|
|
}
|