linux-stable/drivers/base/memory.c
Greg Kroah-Hartman b24413180f License cleanup: add SPDX GPL-2.0 license identifier to files with no license
Many source files in the tree are missing licensing information, which
makes it harder for compliance tools to determine the correct license.

By default all files without license information are under the default
license of the kernel, which is GPL version 2.

Update the files which contain no license information with the 'GPL-2.0'
SPDX license identifier.  The SPDX identifier is a legally binding
shorthand, which can be used instead of the full boiler plate text.

This patch is based on work done by Thomas Gleixner and Kate Stewart and
Philippe Ombredanne.

How this work was done:

Patches were generated and checked against linux-4.14-rc6 for a subset of
the use cases:
 - file had no licensing information it it.
 - file was a */uapi/* one with no licensing information in it,
 - file was a */uapi/* one with existing licensing information,

Further patches will be generated in subsequent months to fix up cases
where non-standard license headers were used, and references to license
had to be inferred by heuristics based on keywords.

The analysis to determine which SPDX License Identifier to be applied to
a file was done in a spreadsheet of side by side results from of the
output of two independent scanners (ScanCode & Windriver) producing SPDX
tag:value files created by Philippe Ombredanne.  Philippe prepared the
base worksheet, and did an initial spot review of a few 1000 files.

The 4.13 kernel was the starting point of the analysis with 60,537 files
assessed.  Kate Stewart did a file by file comparison of the scanner
results in the spreadsheet to determine which SPDX license identifier(s)
to be applied to the file. She confirmed any determination that was not
immediately clear with lawyers working with the Linux Foundation.

Criteria used to select files for SPDX license identifier tagging was:
 - Files considered eligible had to be source code files.
 - Make and config files were included as candidates if they contained >5
   lines of source
 - File already had some variant of a license header in it (even if <5
   lines).

All documentation files were explicitly excluded.

The following heuristics were used to determine which SPDX license
identifiers to apply.

 - when both scanners couldn't find any license traces, file was
   considered to have no license information in it, and the top level
   COPYING file license applied.

   For non */uapi/* files that summary was:

   SPDX license identifier                            # files
   ---------------------------------------------------|-------
   GPL-2.0                                              11139

   and resulted in the first patch in this series.

   If that file was a */uapi/* path one, it was "GPL-2.0 WITH
   Linux-syscall-note" otherwise it was "GPL-2.0".  Results of that was:

   SPDX license identifier                            # files
   ---------------------------------------------------|-------
   GPL-2.0 WITH Linux-syscall-note                        930

   and resulted in the second patch in this series.

 - if a file had some form of licensing information in it, and was one
   of the */uapi/* ones, it was denoted with the Linux-syscall-note if
   any GPL family license was found in the file or had no licensing in
   it (per prior point).  Results summary:

   SPDX license identifier                            # files
   ---------------------------------------------------|------
   GPL-2.0 WITH Linux-syscall-note                       270
   GPL-2.0+ WITH Linux-syscall-note                      169
   ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause)    21
   ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause)    17
   LGPL-2.1+ WITH Linux-syscall-note                      15
   GPL-1.0+ WITH Linux-syscall-note                       14
   ((GPL-2.0+ WITH Linux-syscall-note) OR BSD-3-Clause)    5
   LGPL-2.0+ WITH Linux-syscall-note                       4
   LGPL-2.1 WITH Linux-syscall-note                        3
   ((GPL-2.0 WITH Linux-syscall-note) OR MIT)              3
   ((GPL-2.0 WITH Linux-syscall-note) AND MIT)             1

   and that resulted in the third patch in this series.

 - when the two scanners agreed on the detected license(s), that became
   the concluded license(s).

 - when there was disagreement between the two scanners (one detected a
   license but the other didn't, or they both detected different
   licenses) a manual inspection of the file occurred.

 - In most cases a manual inspection of the information in the file
   resulted in a clear resolution of the license that should apply (and
   which scanner probably needed to revisit its heuristics).

 - When it was not immediately clear, the license identifier was
   confirmed with lawyers working with the Linux Foundation.

 - If there was any question as to the appropriate license identifier,
   the file was flagged for further research and to be revisited later
   in time.

In total, over 70 hours of logged manual review was done on the
spreadsheet to determine the SPDX license identifiers to apply to the
source files by Kate, Philippe, Thomas and, in some cases, confirmation
by lawyers working with the Linux Foundation.

Kate also obtained a third independent scan of the 4.13 code base from
FOSSology, and compared selected files where the other two scanners
disagreed against that SPDX file, to see if there was new insights.  The
Windriver scanner is based on an older version of FOSSology in part, so
they are related.

Thomas did random spot checks in about 500 files from the spreadsheets
for the uapi headers and agreed with SPDX license identifier in the
files he inspected. For the non-uapi files Thomas did random spot checks
in about 15000 files.

In initial set of patches against 4.14-rc6, 3 files were found to have
copy/paste license identifier errors, and have been fixed to reflect the
correct identifier.

Additionally Philippe spent 10 hours this week doing a detailed manual
inspection and review of the 12,461 patched files from the initial patch
version early this week with:
 - a full scancode scan run, collecting the matched texts, detected
   license ids and scores
 - reviewing anything where there was a license detected (about 500+
   files) to ensure that the applied SPDX license was correct
 - reviewing anything where there was no detection but the patch license
   was not GPL-2.0 WITH Linux-syscall-note to ensure that the applied
   SPDX license was correct

This produced a worksheet with 20 files needing minor correction.  This
worksheet was then exported into 3 different .csv files for the
different types of files to be modified.

These .csv files were then reviewed by Greg.  Thomas wrote a script to
parse the csv files and add the proper SPDX tag to the file, in the
format that the file expected.  This script was further refined by Greg
based on the output to detect more types of files automatically and to
distinguish between header and source .c files (which need different
comment types.)  Finally Greg ran the script using the .csv files to
generate the patches.

Reviewed-by: Kate Stewart <kstewart@linuxfoundation.org>
Reviewed-by: Philippe Ombredanne <pombredanne@nexb.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2017-11-02 11:10:55 +01:00

851 lines
20 KiB
C

// SPDX-License-Identifier: GPL-2.0
/*
* 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 <linux/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);
}
/*
* 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);
if (mem->state != MEM_ONLINE)
goto out;
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);
}
out:
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.
* Must already be protected by mem_hotplug_begin().
*/
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;
int ret;
start_pfn = section_nr_to_pfn(phys_index);
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 = MMOP_ONLINE_KEEP;
/* Already under protection of mem_hotplug_begin() */
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;
/* Can't offline block with non-present sections */
if (mem->section_count != sections_per_block)
return -EINVAL;
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 (sysfs_streq(buf, "online_kernel"))
online_type = MMOP_ONLINE_KERNEL;
else if (sysfs_streq(buf, "online_movable"))
online_type = MMOP_ONLINE_MOVABLE;
else if (sysfs_streq(buf, "online"))
online_type = MMOP_ONLINE_KEEP;
else if (sysfs_streq(buf, "offline"))
online_type = MMOP_OFFLINE;
else {
ret = -EINVAL;
goto err;
}
/*
* Memory hotplug needs to hold mem_hotplug_begin() for probe to find
* the correct memory block to online before doing device_online(dev),
* which will take dev->mutex. Take the lock early to prevent an
* inversion, memory_subsys_online() callbacks will be implemented by
* assuming it's already protected.
*/
mem_hotplug_begin();
switch (online_type) {
case MMOP_ONLINE_KERNEL:
case MMOP_ONLINE_MOVABLE:
case MMOP_ONLINE_KEEP:
mem->online_type = online_type;
ret = device_online(&mem->dev);
break;
case MMOP_OFFLINE:
ret = device_offline(&mem->dev);
break;
default:
ret = -EINVAL; /* should never happen */
}
mem_hotplug_done();
err:
unlock_device_hotplug();
if (ret < 0)
return ret;
if (ret)
return -EINVAL;
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);
}
#ifdef CONFIG_MEMORY_HOTREMOVE
static void print_allowed_zone(char *buf, int nid, unsigned long start_pfn,
unsigned long nr_pages, int online_type,
struct zone *default_zone)
{
struct zone *zone;
zone = zone_for_pfn_range(online_type, nid, start_pfn, nr_pages);
if (zone != default_zone) {
strcat(buf, " ");
strcat(buf, zone->name);
}
}
static ssize_t show_valid_zones(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct memory_block *mem = to_memory_block(dev);
unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr);
unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block;
unsigned long valid_start_pfn, valid_end_pfn;
struct zone *default_zone;
int nid;
/*
* The block contains more than one zone can not be offlined.
* This can happen e.g. for ZONE_DMA and ZONE_DMA32
*/
if (!test_pages_in_a_zone(start_pfn, start_pfn + nr_pages, &valid_start_pfn, &valid_end_pfn))
return sprintf(buf, "none\n");
start_pfn = valid_start_pfn;
nr_pages = valid_end_pfn - start_pfn;
/*
* Check the existing zone. Make sure that we do that only on the
* online nodes otherwise the page_zone is not reliable
*/
if (mem->state == MEM_ONLINE) {
strcat(buf, page_zone(pfn_to_page(start_pfn))->name);
goto out;
}
nid = pfn_to_nid(start_pfn);
default_zone = zone_for_pfn_range(MMOP_ONLINE_KEEP, nid, start_pfn, nr_pages);
strcat(buf, default_zone->name);
print_allowed_zone(buf, nid, start_pfn, nr_pages, MMOP_ONLINE_KERNEL,
default_zone);
print_allowed_zone(buf, nid, start_pfn, nr_pages, MMOP_ONLINE_MOVABLE,
default_zone);
out:
strcat(buf, "\n");
return strlen(buf);
}
static DEVICE_ATTR(valid_zones, 0444, show_valid_zones, NULL);
#endif
static DEVICE_ATTR(phys_index, 0444, show_mem_start_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);
/*
* Memory auto online policy.
*/
static ssize_t
show_auto_online_blocks(struct device *dev, struct device_attribute *attr,
char *buf)
{
if (memhp_auto_online)
return sprintf(buf, "online\n");
else
return sprintf(buf, "offline\n");
}
static ssize_t
store_auto_online_blocks(struct device *dev, struct device_attribute *attr,
const char *buf, size_t count)
{
if (sysfs_streq(buf, "online"))
memhp_auto_online = true;
else if (sysfs_streq(buf, "offline"))
memhp_auto_online = false;
else
return -EINVAL;
return count;
}
static DEVICE_ATTR(auto_online_blocks, 0644, show_auto_online_blocks,
store_auto_online_blocks);
/*
* 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, ret;
unsigned long pages_per_block = PAGES_PER_SECTION * sections_per_block;
ret = kstrtoull(buf, 0, &phys_addr);
if (ret)
return ret;
if (phys_addr & ((pages_per_block << PAGE_SHIFT) - 1))
return -EINVAL;
nid = memory_add_physaddr_to_nid(phys_addr);
ret = add_memory(nid, phys_addr,
MIN_MEMORY_BLOCK_SIZE * sections_per_block);
if (ret)
goto out;
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_state.attr,
&dev_attr_phys_device.attr,
&dev_attr_removable.attr,
#ifdef CONFIG_MEMORY_HOTREMOVE
&dev_attr_valid_zones.attr,
#endif
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;
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;
mem->section_count++;
}
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_section(unsigned long node_id,
struct mem_section *section, int phys_device)
{
struct memory_block *mem;
mutex_lock(&mem_sysfs_mutex);
/*
* Some users of the memory hotplug do not want/need memblock to
* track all sections. Skip over those.
*/
mem = find_memory_block(section);
if (!mem)
goto out_unlock;
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);
out_unlock:
mutex_unlock(&mem_sysfs_mutex);
return 0;
}
int unregister_memory_section(struct mem_section *section)
{
if (!present_section(section))
return -EINVAL;
return remove_memory_section(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,
&dev_attr_auto_online_blocks.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) {
/* Don't iterate over sections we know are !present: */
if (i > __highest_present_section_nr)
break;
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;
}