lkml.org 
[lkml]   [2010]   [Jul]   [1]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
Date
From
SubjectRe: [PATCH] memory hotplug disable boot option
On Thu, 1 Jul 2010 09:31:30 +0900
KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> wrote:

> I think this change is not very difficult technically but can this kind of
> interface be allowed ?
>
Here is a patch.

But I'm not a specialist of memory hotplug in these days. So, please
modify this as required even when you like this.
This patch is onto mmotm but will not hunk with mainline, I hope.
If nonsense, sorry for noise ;)

-Kame
==

Memory hotplug has interfaces for offlining memory per section.
With large memory/small section machine, we tend to have too many
sysfs directory as
/sys/devices/system/memory/memoryXXX/ (XXX is section name)
But this interface is only necessary when we do hotplug.

This patch adds 2 new interfaces as
/sys/devieces/system/memory/hide
/sys/devieces/system/memory/show

'hide' will remove sysfs directroy of given number's section.
'show' will create sysfs directroy of given number's section.

# echo 120 > /sys/devices/system/memory/hide
....memory120 will be removed.

This patch also adds hidememorysysfs boot option to hide
all sysfs for memory section at boot time.

Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
---
Documentation/kernel-parameters.txt | 2
Documentation/memory-hotplug.txt | 25 +++++
drivers/base/memory.c | 165 +++++++++++++++++++++++++++++++++---
drivers/base/node.c | 2
4 files changed, 184 insertions(+), 10 deletions(-)

Index: mmotm-2.6.35-0611/drivers/base/memory.c
===================================================================
--- mmotm-2.6.35-0611.orig/drivers/base/memory.c
+++ mmotm-2.6.35-0611/drivers/base/memory.c
@@ -23,10 +23,12 @@
#include <linux/mutex.h>
#include <linux/stat.h>
#include <linux/slab.h>
+#include <linux/radix-tree.h>

#include <asm/atomic.h>
#include <asm/uaccess.h>

+DEFINE_MUTEX(mem_sysfs_lock);
#define MEMORY_CLASS_NAME "memory"

static struct sysdev_class memory_sysdev_class = {
@@ -324,6 +326,8 @@ static int block_size_init(void)
&attr_block_size_bytes.attr);
}

+
+
/*
* Some architectures will have custom drivers to do this, and
* will not need to do it from userspace. The fake hot-add code
@@ -363,6 +367,7 @@ static inline int memory_probe_init(void
}
#endif

+
#ifdef CONFIG_MEMORY_FAILURE
/*
* Support for offlining pages of memory
@@ -505,13 +510,14 @@ int remove_memory_block(unsigned long no
struct memory_block *mem;

mem = find_memory_block(section);
+ if (!mem) /* already hidden ? */
+ return 0;
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);
mem_remove_simple_file(mem, removable);
unregister_memory(mem, section);
-
return 0;
}

@@ -521,20 +527,142 @@ int remove_memory_block(unsigned long no
*/
int register_new_memory(int nid, struct mem_section *section)
{
- return add_memory_block(nid, section, MEM_OFFLINE, HOTPLUG);
+ int ret;
+
+ mutex_lock(&mem_sysfs_lock);
+ ret = add_memory_block(nid, section, MEM_OFFLINE, HOTPLUG);
+ mutex_unlock(&mem_sysfs_lock);
+ return ret;
}

int unregister_memory_section(struct mem_section *section)
{
+ int ret;
+
if (!present_section(section))
return -EINVAL;
+ mutex_lock(&mem_sysfs_lock);
+ ret = remove_memory_block(0, section, 0);
+ mutex_unlock(&mem_sysfs_lock);
+ return ret;
+}
+
+/* Remember memory online/offline status for _hidden_ memory */
+
+RADIX_TREE(hidden_mems, GFP_KERNEL);
+static int record_mem_status(unsigned long section_nr, int status)
+{
+ int ret;
+ long lstat = status+1;
+ if (radix_tree_preload(GFP_KERNEL))
+ return -ENOMEM;
+ ret = radix_tree_insert(&hidden_mems, section_nr, (void*)lstat);
+ radix_tree_preload_end();
+ return ret;
+}
+
+static int lookup_mem_status(unsigned long section_nr)
+{
+ void *ptr;
+ /* we already have big mutex */
+ ptr= radix_tree_lookup(&hidden_mems, section_nr);
+ /* treate not-recorded mems'state as ONLINE */
+ if (!ptr)
+ return MEM_ONLINE;
+ return (long)ptr - 1;
+}
+
+static void forget_mem_status(unsigned long section_nr)
+{
+ radix_tree_delete(&hidden_mems, section_nr);
+}
+
+static ssize_t
+memory_show_store(struct class *class, struct class_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct mem_section *section;
+ unsigned long section_nr;
+ int nid, status;
+ ssize_t ret;
+
+ section_nr = simple_strtoull(buf, NULL, 0);
+ if (!present_section_nr(section_nr))
+ return -EINVAL;
+ section = __nr_to_section(section_nr);
+ VM_BUG_ON(!section);
+
+ mutex_lock(&mem_sysfs_lock);
+
+ if (find_memory_block(section)) {
+ ret = -EEXIST;
+ goto out;
+ }
+
+ nid = pfn_to_nid(section_nr_to_pfn(section_nr));
+
+ status = lookup_mem_status(section_nr);
+ ret = add_memory_block(nid, section, status, HOTPLUG);
+ if (ret)
+ goto out;
+ forget_mem_status(section_nr);
+ ret = count;
+out:
+ mutex_unlock(&mem_sysfs_lock);
+ return ret;
+}

- return remove_memory_block(0, section, 0);
+static CLASS_ATTR(show, S_IWUSR, NULL, memory_show_store);
+static inline int memory_show_init(void)
+{
+ return sysfs_create_file(&memory_sysdev_class.kset.kobj,
+ &class_attr_show.attr);
}

+static ssize_t
+memory_hide_store(struct class *class, struct class_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct mem_section *section;
+ struct memory_block *mem;
+ unsigned long section_nr;
+ ssize_t ret = -EINVAL;
+
+ section_nr = simple_strtoull(buf, NULL, 0);
+ if (!present_section_nr(section_nr))
+ return ret;
+ section = __nr_to_section(section_nr);
+ VM_BUG_ON(!section);
+
+ mutex_lock(&mem_sysfs_lock);
+ mem = find_memory_block(section);
+ if (!mem)
+ goto out;
+ record_mem_status(section_nr, mem->state);
+ 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);
+ mem_remove_simple_file(mem, removable);
+ unregister_memory(mem, section);
+ mutex_unlock(&mem_sysfs_lock);
+ ret = count;
+out:
+ return ret;
+}
+
+static CLASS_ATTR(hide, S_IWUSR, NULL, memory_hide_store);
+static inline int memory_hide_init(void)
+{
+ return sysfs_create_file(&memory_sysdev_class.kset.kobj,
+ &class_attr_hide.attr);
+}
+
+
/*
* Initialize the sysfs support for memory devices...
*/
+static int hide_memory_sysfs __initdata;
int __init memory_dev_init(void)
{
unsigned int i;
@@ -550,13 +678,16 @@ int __init memory_dev_init(void)
* 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;
- err = add_memory_block(0, __nr_to_section(i), MEM_ONLINE,
- BOOT);
- if (!ret)
- ret = err;
+ if (!hide_memory_sysfs){
+ 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,
+ BOOT);
+ if (!ret)
+ ret = err;
+ }
}

err = memory_probe_init();
@@ -568,8 +699,22 @@ int __init memory_dev_init(void)
err = block_size_init();
if (!ret)
ret = err;
+ err = memory_show_init();
+ if (!ret)
+ ret = err;
+ err = memory_hide_init();
+ if (!ret)
+ ret = err;
out:
if (ret)
printk(KERN_ERR "%s() failed: %d\n", __func__, ret);
return ret;
}
+
+static int __init hidememorysysfs(char *s)
+{
+ hide_memory_sysfs = 1;
+ return 1;
+}
+__setup("hidememorysysfs", hidememorysysfs);
+
Index: mmotm-2.6.35-0611/drivers/base/node.c
===================================================================
--- mmotm-2.6.35-0611.orig/drivers/base/node.c
+++ mmotm-2.6.35-0611/drivers/base/node.c
@@ -421,6 +421,8 @@ static int link_mem_sections(int nid)
continue;
mem_sect = __nr_to_section(section_nr);
mem_blk = find_memory_block(mem_sect);
+ if (!mem_blk) /* hidden ? */
+ continue;
ret = register_mem_sect_under_node(mem_blk, nid);
if (!err)
err = ret;
Index: mmotm-2.6.35-0611/Documentation/memory-hotplug.txt
===================================================================
--- mmotm-2.6.35-0611.orig/Documentation/memory-hotplug.txt
+++ mmotm-2.6.35-0611/Documentation/memory-hotplug.txt
@@ -15,6 +15,7 @@ be changed often.
1.3. Unit of Memory online/offline operation
2. Kernel Configuration
3. sysfs files for memory hotplug
+ 3.1 hide and show sysfs
4. Physical memory hot-add phase
4.1 Hardware(Firmware) Support
4.2 Notify memory hot-add event by hand
@@ -169,6 +170,30 @@ For example:
A backlink will also be created:
/sys/devices/system/memory/memory9/node0 -> ../../node/node0

+3.1 Hide and Show for sysfs.
+
+On some big memory system, memory syfs may contain too much sysfs
+directory and consume kernel resource too much. To handle that,
+memory sysfs has hide and show interface.
+
+hide : remove memoryXXX directory on demand.
+ A user can remove sysfs entry by writing memory section number.
+
+echo 120 > /sys/devices/system/memory/hide
+...then, memory120 disappears.
+
+show : create memory XXX directroy on demand.
+ A user can add sysfs entry by writing memory section number.
+ If memory doesn't exit, this fails.
+
+echo 120 > /sys/dev/ices/system/memory/show
+...then, memory120 directory is available.
+
+And we have boot option as "hidememorysysfs". This makes all
+memoryXXX sysfs at boot to be hidden. All hot-added sections
+will be visible automatically. Users can make memoryXXX sysfs
+entries by 'show' interface.
+
--------------------------------
4. Physical memory hot-add phase
--------------------------------
Index: mmotm-2.6.35-0611/Documentation/kernel-parameters.txt
===================================================================
--- mmotm-2.6.35-0611.orig/Documentation/kernel-parameters.txt
+++ mmotm-2.6.35-0611/Documentation/kernel-parameters.txt
@@ -853,6 +853,8 @@ and is between 256 and 4096 characters.
corresponding firmware-first mode error processing
logic will be disabled.

+ hidememorysyfs [KNL, BOOT] hides memoryXXX directory in sysfs at BOOT.
+
highmem=nn[KMG] [KNL,BOOT] forces the highmem zone to have an exact
size of <nn>. This works even on boxes that have no
highmem otherwise. This also works to reduce highmem


\
 
 \ /
  Last update: 2010-07-01 07:23    [W:0.504 / U:0.388 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site