mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-10-12 03:26:26 +00:00
drivers/base/memory: don't store phys_device in memory blocks
[ Upstream commite9a2e48e87
] No need to store the value for each and every memory block, as we can easily query the value at runtime. Reshuffle the members to optimize the memory layout. Also, let's clarify what the interface once was used for and why it's legacy nowadays. "phys_device" was used on s390x in older versions of lsmem[2]/chmem[3], back when they were still part of s390x-tools. They were later replaced by the variants in linux-utils. For example, RHEL6 and RHEL7 contain lsmem/chmem from s390-utils. RHEL8 switched to versions from util-linux on s390x [4]. "phys_device" was added with sysfs support for memory hotplug in commit3947be1969
("[PATCH] memory hotplug: sysfs and add/remove functions") in 2005. It always returned 0. s390x started returning something != 0 on some setups (if sclp.rzm is set by HW) in 2010 via commit57b552ba0b
("memory hotplug/s390: set phys_device"). For s390x, it allowed for identifying which memory block devices belong to the same storage increment (RZM). Only if all memory block devices comprising a single storage increment were offline, the memory could actually be removed in the hypervisor. Since commite5d709bb5f
("s390/memory hotplug: provide memory_block_size_bytes() function") in 2013 a memory block device spans at least one storage increment - which is why the interface isn't really helpful/used anymore (except by old lsmem/chmem tools). There were once RFC patches to make use of "phys_device" in ACPI context; however, the underlying problem could be solved using different interfaces [1]. [1] https://patchwork.kernel.org/patch/2163871/ [2] https://github.com/ibm-s390-tools/s390-tools/blob/v2.1.0/zconf/lsmem [3] https://github.com/ibm-s390-tools/s390-tools/blob/v2.1.0/zconf/chmem [4] https://bugzilla.redhat.com/show_bug.cgi?id=1504134 Link: https://lkml.kernel.org/r/20210201181347.13262-2-david@redhat.com Signed-off-by: David Hildenbrand <david@redhat.com> Acked-by: Michal Hocko <mhocko@suse.com> Reviewed-by: Oscar Salvador <osalvador@suse.de> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: "Rafael J. Wysocki" <rafael@kernel.org> Cc: Mauro Carvalho Chehab <mchehab+huawei@kernel.org> Cc: Ilya Dryomov <idryomov@gmail.com> Cc: Vaibhav Jain <vaibhav@linux.ibm.com> Cc: Tom Rix <trix@redhat.com> Cc: Geert Uytterhoeven <geert+renesas@glider.be> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Sasha Levin <sashal@kernel.org>
This commit is contained in:
parent
e4b98e2260
commit
8876cc237e
4 changed files with 15 additions and 22 deletions
|
@ -26,8 +26,9 @@ Date: September 2008
|
||||||
Contact: Badari Pulavarty <pbadari@us.ibm.com>
|
Contact: Badari Pulavarty <pbadari@us.ibm.com>
|
||||||
Description:
|
Description:
|
||||||
The file /sys/devices/system/memory/memoryX/phys_device
|
The file /sys/devices/system/memory/memoryX/phys_device
|
||||||
is read-only and is designed to show the name of physical
|
is read-only; it is a legacy interface only ever used on s390x
|
||||||
memory device. Implementation is currently incomplete.
|
to expose the covered storage increment.
|
||||||
|
Users: Legacy s390-tools lsmem/chmem
|
||||||
|
|
||||||
What: /sys/devices/system/memory/memoryX/phys_index
|
What: /sys/devices/system/memory/memoryX/phys_index
|
||||||
Date: September 2008
|
Date: September 2008
|
||||||
|
|
|
@ -160,8 +160,8 @@ Under each memory block, you can see 5 files:
|
||||||
|
|
||||||
"online_movable", "online", "offline" command
|
"online_movable", "online", "offline" command
|
||||||
which will be performed on all sections in the block.
|
which will be performed on all sections in the block.
|
||||||
``phys_device`` read-only: designed to show the name of physical memory
|
``phys_device`` read-only: legacy interface only ever used on s390x to
|
||||||
device. This is not well implemented now.
|
expose the covered storage increment.
|
||||||
``removable`` read-only: contains an integer value indicating
|
``removable`` read-only: contains an integer value indicating
|
||||||
whether the memory block is removable or not
|
whether the memory block is removable or not
|
||||||
removable. A value of 1 indicates that the memory
|
removable. A value of 1 indicates that the memory
|
||||||
|
|
|
@ -290,20 +290,20 @@ static ssize_t state_store(struct device *dev, struct device_attribute *attr,
|
||||||
}
|
}
|
||||||
|
|
||||||
/*
|
/*
|
||||||
* phys_device is a bad name for this. What I really want
|
* Legacy interface that we cannot remove: s390x exposes the storage increment
|
||||||
* is a way to differentiate between memory ranges that
|
* covered by a memory block, allowing for identifying which memory blocks
|
||||||
* are part of physical devices that constitute
|
* comprise a storage increment. Since a memory block spans complete
|
||||||
* a complete removable unit or fru.
|
* storage increments nowadays, this interface is basically unused. Other
|
||||||
* i.e. do these ranges belong to the same physical device,
|
* archs never exposed != 0.
|
||||||
* s.t. if I offline all of these sections I can then
|
|
||||||
* remove the physical device?
|
|
||||||
*/
|
*/
|
||||||
static ssize_t phys_device_show(struct device *dev,
|
static ssize_t phys_device_show(struct device *dev,
|
||||||
struct device_attribute *attr, char *buf)
|
struct device_attribute *attr, char *buf)
|
||||||
{
|
{
|
||||||
struct memory_block *mem = to_memory_block(dev);
|
struct memory_block *mem = to_memory_block(dev);
|
||||||
|
unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr);
|
||||||
|
|
||||||
return sysfs_emit(buf, "%d\n", mem->phys_device);
|
return sysfs_emit(buf, "%d\n",
|
||||||
|
arch_get_memory_phys_device(start_pfn));
|
||||||
}
|
}
|
||||||
|
|
||||||
#ifdef CONFIG_MEMORY_HOTREMOVE
|
#ifdef CONFIG_MEMORY_HOTREMOVE
|
||||||
|
@ -488,11 +488,7 @@ static DEVICE_ATTR_WO(soft_offline_page);
|
||||||
static DEVICE_ATTR_WO(hard_offline_page);
|
static DEVICE_ATTR_WO(hard_offline_page);
|
||||||
#endif
|
#endif
|
||||||
|
|
||||||
/*
|
/* See phys_device_show(). */
|
||||||
* 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)
|
int __weak arch_get_memory_phys_device(unsigned long start_pfn)
|
||||||
{
|
{
|
||||||
return 0;
|
return 0;
|
||||||
|
@ -574,7 +570,6 @@ int register_memory(struct memory_block *memory)
|
||||||
static int init_memory_block(unsigned long block_id, unsigned long state)
|
static int init_memory_block(unsigned long block_id, unsigned long state)
|
||||||
{
|
{
|
||||||
struct memory_block *mem;
|
struct memory_block *mem;
|
||||||
unsigned long start_pfn;
|
|
||||||
int ret = 0;
|
int ret = 0;
|
||||||
|
|
||||||
mem = find_memory_block_by_id(block_id);
|
mem = find_memory_block_by_id(block_id);
|
||||||
|
@ -588,8 +583,6 @@ static int init_memory_block(unsigned long block_id, unsigned long state)
|
||||||
|
|
||||||
mem->start_section_nr = block_id * sections_per_block;
|
mem->start_section_nr = block_id * sections_per_block;
|
||||||
mem->state = state;
|
mem->state = state;
|
||||||
start_pfn = section_nr_to_pfn(mem->start_section_nr);
|
|
||||||
mem->phys_device = arch_get_memory_phys_device(start_pfn);
|
|
||||||
mem->nid = NUMA_NO_NODE;
|
mem->nid = NUMA_NO_NODE;
|
||||||
|
|
||||||
ret = register_memory(mem);
|
ret = register_memory(mem);
|
||||||
|
|
|
@ -27,9 +27,8 @@ struct memory_block {
|
||||||
unsigned long start_section_nr;
|
unsigned long start_section_nr;
|
||||||
unsigned long state; /* serialized by the dev->lock */
|
unsigned long state; /* serialized by the dev->lock */
|
||||||
int online_type; /* for passing data to online routine */
|
int online_type; /* for passing data to online routine */
|
||||||
int phys_device; /* to which fru does this belong? */
|
|
||||||
struct device dev;
|
|
||||||
int nid; /* NID for this memory block */
|
int nid; /* NID for this memory block */
|
||||||
|
struct device dev;
|
||||||
};
|
};
|
||||||
|
|
||||||
int arch_get_memory_phys_device(unsigned long start_pfn);
|
int arch_get_memory_phys_device(unsigned long start_pfn);
|
||||||
|
|
Loading…
Reference in a new issue