2005-10-29 19:16:54 -06:00
|
|
|
/*
|
2011-12-21 15:48:43 -07:00
|
|
|
* Memory subsystem support
|
2005-10-29 19:16:54 -06:00
|
|
|
*
|
|
|
|
* 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>
|
2006-01-11 13:17:46 -07:00
|
|
|
#include <linux/capability.h>
|
2005-10-29 19:16:54 -06:00
|
|
|
#include <linux/device.h>
|
|
|
|
#include <linux/memory.h>
|
|
|
|
#include <linux/memory_hotplug.h>
|
|
|
|
#include <linux/mm.h>
|
2008-02-05 00:35:47 -07:00
|
|
|
#include <linux/mutex.h>
|
2008-10-18 21:27:12 -06:00
|
|
|
#include <linux/stat.h>
|
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h
percpu.h is included by sched.h and module.h and thus ends up being
included when building most .c files. percpu.h includes slab.h which
in turn includes gfp.h making everything defined by the two files
universally available and complicating inclusion dependencies.
percpu.h -> slab.h dependency is about to be removed. Prepare for
this change by updating users of gfp and slab facilities include those
headers directly instead of assuming availability. As this conversion
needs to touch large number of source files, the following script is
used as the basis of conversion.
http://userweb.kernel.org/~tj/misc/slabh-sweep.py
The script does the followings.
* Scan files for gfp and slab usages and update includes such that
only the necessary includes are there. ie. if only gfp is used,
gfp.h, if slab is used, slab.h.
* When the script inserts a new include, it looks at the include
blocks and try to put the new include such that its order conforms
to its surrounding. It's put in the include block which contains
core kernel includes, in the same order that the rest are ordered -
alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
doesn't seem to be any matching order.
* If the script can't find a place to put a new include (mostly
because the file doesn't have fitting include block), it prints out
an error message indicating which .h file needs to be added to the
file.
The conversion was done in the following steps.
1. The initial automatic conversion of all .c files updated slightly
over 4000 files, deleting around 700 includes and adding ~480 gfp.h
and ~3000 slab.h inclusions. The script emitted errors for ~400
files.
2. Each error was manually checked. Some didn't need the inclusion,
some needed manual addition while adding it to implementation .h or
embedding .c file was more appropriate for others. This step added
inclusions to around 150 files.
3. The script was run again and the output was compared to the edits
from #2 to make sure no file was left behind.
4. Several build tests were done and a couple of problems were fixed.
e.g. lib/decompress_*.c used malloc/free() wrappers around slab
APIs requiring slab.h to be added manually.
5. The script was run on all .h files but without automatically
editing them as sprinkling gfp.h and slab.h inclusions around .h
files could easily lead to inclusion dependency hell. Most gfp.h
inclusion directives were ignored as stuff from gfp.h was usually
wildly available and often used in preprocessor macros. Each
slab.h inclusion directive was examined and added manually as
necessary.
6. percpu.h was updated not to include slab.h.
7. Build test were done on the following configurations and failures
were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my
distributed build env didn't work with gcov compiles) and a few
more options had to be turned off depending on archs to make things
build (like ipr on powerpc/64 which failed due to missing writeq).
* x86 and x86_64 UP and SMP allmodconfig and a custom test config.
* powerpc and powerpc64 SMP allmodconfig
* sparc and sparc64 SMP allmodconfig
* ia64 SMP allmodconfig
* s390 SMP allmodconfig
* alpha SMP allmodconfig
* um on x86_64 SMP allmodconfig
8. percpu.h modifications were reverted so that it could be applied as
a separate patch and serve as bisection point.
Given the fact that I had only a couple of failures from tests on step
6, I'm fairly confident about the coverage of this conversion patch.
If there is a breakage, it's likely to be something in one of the arch
headers which should be easily discoverable easily on most builds of
the specific arch.
Signed-off-by: Tejun Heo <tj@kernel.org>
Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 02:04:11 -06:00
|
|
|
#include <linux/slab.h>
|
2008-10-18 21:27:12 -06:00
|
|
|
|
2011-07-26 17:09:06 -06:00
|
|
|
#include <linux/atomic.h>
|
2016-12-24 12:46:01 -07:00
|
|
|
#include <linux/uaccess.h>
|
2005-10-29 19:16:54 -06:00
|
|
|
|
2010-10-19 11:45:24 -06:00
|
|
|
static DEFINE_MUTEX(mem_sysfs_mutex);
|
|
|
|
|
2005-10-29 19:16:54 -06:00
|
|
|
#define MEMORY_CLASS_NAME "memory"
|
2011-01-20 09:43:34 -07:00
|
|
|
|
2013-08-28 00:38:27 -06:00
|
|
|
#define to_memory_block(dev) container_of(dev, struct memory_block, dev)
|
|
|
|
|
2011-01-20 09:43:34 -07:00
|
|
|
static int sections_per_block;
|
|
|
|
|
|
|
|
static inline int base_memory_block_id(int section_nr)
|
|
|
|
{
|
|
|
|
return section_nr / sections_per_block;
|
|
|
|
}
|
2005-10-29 19:16:54 -06:00
|
|
|
|
2013-05-08 06:18:37 -06:00
|
|
|
static int memory_subsys_online(struct device *dev);
|
|
|
|
static int memory_subsys_offline(struct device *dev);
|
|
|
|
|
2011-12-21 15:48:43 -07:00
|
|
|
static struct bus_type memory_subsys = {
|
2007-12-19 18:09:39 -07:00
|
|
|
.name = MEMORY_CLASS_NAME,
|
2011-12-21 15:48:43 -07:00
|
|
|
.dev_name = MEMORY_CLASS_NAME,
|
2013-05-08 06:18:37 -06:00
|
|
|
.online = memory_subsys_online,
|
|
|
|
.offline = memory_subsys_offline,
|
2005-10-29 19:16:54 -06:00
|
|
|
};
|
|
|
|
|
[PATCH] Notifier chain update: API changes
The kernel's implementation of notifier chains is unsafe. There is no
protection against entries being added to or removed from a chain while the
chain is in use. The issues were discussed in this thread:
http://marc.theaimsgroup.com/?l=linux-kernel&m=113018709002036&w=2
We noticed that notifier chains in the kernel fall into two basic usage
classes:
"Blocking" chains are always called from a process context
and the callout routines are allowed to sleep;
"Atomic" chains can be called from an atomic context and
the callout routines are not allowed to sleep.
We decided to codify this distinction and make it part of the API. Therefore
this set of patches introduces three new, parallel APIs: one for blocking
notifiers, one for atomic notifiers, and one for "raw" notifiers (which is
really just the old API under a new name). New kinds of data structures are
used for the heads of the chains, and new routines are defined for
registration, unregistration, and calling a chain. The three APIs are
explained in include/linux/notifier.h and their implementation is in
kernel/sys.c.
With atomic and blocking chains, the implementation guarantees that the chain
links will not be corrupted and that chain callers will not get messed up by
entries being added or removed. For raw chains the implementation provides no
guarantees at all; users of this API must provide their own protections. (The
idea was that situations may come up where the assumptions of the atomic and
blocking APIs are not appropriate, so it should be possible for users to
handle these things in their own way.)
There are some limitations, which should not be too hard to live with. For
atomic/blocking chains, registration and unregistration must always be done in
a process context since the chain is protected by a mutex/rwsem. Also, a
callout routine for a non-raw chain must not try to register or unregister
entries on its own chain. (This did happen in a couple of places and the code
had to be changed to avoid it.)
Since atomic chains may be called from within an NMI handler, they cannot use
spinlocks for synchronization. Instead we use RCU. The overhead falls almost
entirely in the unregister routine, which is okay since unregistration is much
less frequent that calling a chain.
Here is the list of chains that we adjusted and their classifications. None
of them use the raw API, so for the moment it is only a placeholder.
ATOMIC CHAINS
-------------
arch/i386/kernel/traps.c: i386die_chain
arch/ia64/kernel/traps.c: ia64die_chain
arch/powerpc/kernel/traps.c: powerpc_die_chain
arch/sparc64/kernel/traps.c: sparc64die_chain
arch/x86_64/kernel/traps.c: die_chain
drivers/char/ipmi/ipmi_si_intf.c: xaction_notifier_list
kernel/panic.c: panic_notifier_list
kernel/profile.c: task_free_notifier
net/bluetooth/hci_core.c: hci_notifier
net/ipv4/netfilter/ip_conntrack_core.c: ip_conntrack_chain
net/ipv4/netfilter/ip_conntrack_core.c: ip_conntrack_expect_chain
net/ipv6/addrconf.c: inet6addr_chain
net/netfilter/nf_conntrack_core.c: nf_conntrack_chain
net/netfilter/nf_conntrack_core.c: nf_conntrack_expect_chain
net/netlink/af_netlink.c: netlink_chain
BLOCKING CHAINS
---------------
arch/powerpc/platforms/pseries/reconfig.c: pSeries_reconfig_chain
arch/s390/kernel/process.c: idle_chain
arch/x86_64/kernel/process.c idle_notifier
drivers/base/memory.c: memory_chain
drivers/cpufreq/cpufreq.c cpufreq_policy_notifier_list
drivers/cpufreq/cpufreq.c cpufreq_transition_notifier_list
drivers/macintosh/adb.c: adb_client_list
drivers/macintosh/via-pmu.c sleep_notifier_list
drivers/macintosh/via-pmu68k.c sleep_notifier_list
drivers/macintosh/windfarm_core.c wf_client_list
drivers/usb/core/notify.c usb_notifier_list
drivers/video/fbmem.c fb_notifier_list
kernel/cpu.c cpu_chain
kernel/module.c module_notify_list
kernel/profile.c munmap_notifier
kernel/profile.c task_exit_notifier
kernel/sys.c reboot_notifier_list
net/core/dev.c netdev_chain
net/decnet/dn_dev.c: dnaddr_chain
net/ipv4/devinet.c: inetaddr_chain
It's possible that some of these classifications are wrong. If they are,
please let us know or submit a patch to fix them. Note that any chain that
gets called very frequently should be atomic, because the rwsem read-locking
used for blocking chains is very likely to incur cache misses on SMP systems.
(However, if the chain's callout routines may sleep then the chain cannot be
atomic.)
The patch set was written by Alan Stern and Chandra Seetharaman, incorporating
material written by Keith Owens and suggestions from Paul McKenney and Andrew
Morton.
[jes@sgi.com: restructure the notifier chain initialization macros]
Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Chandra Seetharaman <sekharan@us.ibm.com>
Signed-off-by: Jes Sorensen <jes@sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-27 02:16:30 -07:00
|
|
|
static BLOCKING_NOTIFIER_HEAD(memory_chain);
|
2005-10-29 19:16:54 -06:00
|
|
|
|
2006-01-06 01:10:35 -07:00
|
|
|
int register_memory_notifier(struct notifier_block *nb)
|
2005-10-29 19:16:54 -06:00
|
|
|
{
|
2015-03-08 04:48:35 -06:00
|
|
|
return blocking_notifier_chain_register(&memory_chain, nb);
|
2005-10-29 19:16:54 -06:00
|
|
|
}
|
2008-05-07 06:43:01 -06:00
|
|
|
EXPORT_SYMBOL(register_memory_notifier);
|
2005-10-29 19:16:54 -06:00
|
|
|
|
2006-01-06 01:10:35 -07:00
|
|
|
void unregister_memory_notifier(struct notifier_block *nb)
|
2005-10-29 19:16:54 -06:00
|
|
|
{
|
2015-03-08 04:48:35 -06:00
|
|
|
blocking_notifier_chain_unregister(&memory_chain, nb);
|
2005-10-29 19:16:54 -06:00
|
|
|
}
|
2008-05-07 06:43:01 -06:00
|
|
|
EXPORT_SYMBOL(unregister_memory_notifier);
|
2005-10-29 19:16:54 -06:00
|
|
|
|
2009-12-17 07:44:38 -07:00
|
|
|
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);
|
|
|
|
|
2012-12-11 17:00:44 -07:00
|
|
|
static void memory_block_release(struct device *dev)
|
|
|
|
{
|
2013-08-28 00:38:27 -06:00
|
|
|
struct memory_block *mem = to_memory_block(dev);
|
2012-12-11 17:00:44 -07:00
|
|
|
|
|
|
|
kfree(mem);
|
|
|
|
}
|
|
|
|
|
2011-01-20 09:43:34 -07:00
|
|
|
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;
|
|
|
|
}
|
|
|
|
|
2005-10-29 19:16:54 -06:00
|
|
|
/*
|
|
|
|
* use this as the physical section index that this memsection
|
|
|
|
* uses.
|
|
|
|
*/
|
|
|
|
|
2011-12-21 15:48:43 -07:00
|
|
|
static ssize_t show_mem_start_phys_index(struct device *dev,
|
|
|
|
struct device_attribute *attr, char *buf)
|
2005-10-29 19:16:54 -06:00
|
|
|
{
|
2013-08-28 00:38:27 -06:00
|
|
|
struct memory_block *mem = to_memory_block(dev);
|
2011-01-20 09:44:29 -07:00
|
|
|
unsigned long phys_index;
|
|
|
|
|
|
|
|
phys_index = mem->start_section_nr / sections_per_block;
|
|
|
|
return sprintf(buf, "%08lx\n", phys_index);
|
|
|
|
}
|
|
|
|
|
2008-07-23 22:28:19 -06:00
|
|
|
/*
|
|
|
|
* Show whether the section of memory is likely to be hot-removable
|
|
|
|
*/
|
2011-12-21 15:48:43 -07:00
|
|
|
static ssize_t show_mem_removable(struct device *dev,
|
|
|
|
struct device_attribute *attr, char *buf)
|
2008-07-23 22:28:19 -06:00
|
|
|
{
|
2011-01-20 09:43:34 -07:00
|
|
|
unsigned long i, pfn;
|
|
|
|
int ret = 1;
|
2013-08-28 00:38:27 -06:00
|
|
|
struct memory_block *mem = to_memory_block(dev);
|
2008-07-23 22:28:19 -06:00
|
|
|
|
2011-01-20 09:43:34 -07:00
|
|
|
for (i = 0; i < sections_per_block; i++) {
|
2013-08-28 17:35:18 -06:00
|
|
|
if (!present_section_nr(mem->start_section_nr + i))
|
|
|
|
continue;
|
2011-01-20 09:44:29 -07:00
|
|
|
pfn = section_nr_to_pfn(mem->start_section_nr + i);
|
2011-01-20 09:43:34 -07:00
|
|
|
ret &= is_mem_section_removable(pfn, PAGES_PER_SECTION);
|
|
|
|
}
|
|
|
|
|
2008-07-23 22:28:19 -06:00
|
|
|
return sprintf(buf, "%d\n", ret);
|
|
|
|
}
|
|
|
|
|
2005-10-29 19:16:54 -06:00
|
|
|
/*
|
|
|
|
* online, offline, going offline, etc.
|
|
|
|
*/
|
2011-12-21 15:48:43 -07:00
|
|
|
static ssize_t show_mem_state(struct device *dev,
|
|
|
|
struct device_attribute *attr, char *buf)
|
2005-10-29 19:16:54 -06:00
|
|
|
{
|
2013-08-28 00:38:27 -06:00
|
|
|
struct memory_block *mem = to_memory_block(dev);
|
2005-10-29 19:16:54 -06:00
|
|
|
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) {
|
2015-03-08 04:29:04 -06:00
|
|
|
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;
|
2005-10-29 19:16:54 -06:00
|
|
|
}
|
|
|
|
|
|
|
|
return len;
|
|
|
|
}
|
|
|
|
|
2007-10-21 17:41:36 -06:00
|
|
|
int memory_notify(unsigned long val, void *v)
|
2005-10-29 19:16:54 -06:00
|
|
|
{
|
[PATCH] Notifier chain update: API changes
The kernel's implementation of notifier chains is unsafe. There is no
protection against entries being added to or removed from a chain while the
chain is in use. The issues were discussed in this thread:
http://marc.theaimsgroup.com/?l=linux-kernel&m=113018709002036&w=2
We noticed that notifier chains in the kernel fall into two basic usage
classes:
"Blocking" chains are always called from a process context
and the callout routines are allowed to sleep;
"Atomic" chains can be called from an atomic context and
the callout routines are not allowed to sleep.
We decided to codify this distinction and make it part of the API. Therefore
this set of patches introduces three new, parallel APIs: one for blocking
notifiers, one for atomic notifiers, and one for "raw" notifiers (which is
really just the old API under a new name). New kinds of data structures are
used for the heads of the chains, and new routines are defined for
registration, unregistration, and calling a chain. The three APIs are
explained in include/linux/notifier.h and their implementation is in
kernel/sys.c.
With atomic and blocking chains, the implementation guarantees that the chain
links will not be corrupted and that chain callers will not get messed up by
entries being added or removed. For raw chains the implementation provides no
guarantees at all; users of this API must provide their own protections. (The
idea was that situations may come up where the assumptions of the atomic and
blocking APIs are not appropriate, so it should be possible for users to
handle these things in their own way.)
There are some limitations, which should not be too hard to live with. For
atomic/blocking chains, registration and unregistration must always be done in
a process context since the chain is protected by a mutex/rwsem. Also, a
callout routine for a non-raw chain must not try to register or unregister
entries on its own chain. (This did happen in a couple of places and the code
had to be changed to avoid it.)
Since atomic chains may be called from within an NMI handler, they cannot use
spinlocks for synchronization. Instead we use RCU. The overhead falls almost
entirely in the unregister routine, which is okay since unregistration is much
less frequent that calling a chain.
Here is the list of chains that we adjusted and their classifications. None
of them use the raw API, so for the moment it is only a placeholder.
ATOMIC CHAINS
-------------
arch/i386/kernel/traps.c: i386die_chain
arch/ia64/kernel/traps.c: ia64die_chain
arch/powerpc/kernel/traps.c: powerpc_die_chain
arch/sparc64/kernel/traps.c: sparc64die_chain
arch/x86_64/kernel/traps.c: die_chain
drivers/char/ipmi/ipmi_si_intf.c: xaction_notifier_list
kernel/panic.c: panic_notifier_list
kernel/profile.c: task_free_notifier
net/bluetooth/hci_core.c: hci_notifier
net/ipv4/netfilter/ip_conntrack_core.c: ip_conntrack_chain
net/ipv4/netfilter/ip_conntrack_core.c: ip_conntrack_expect_chain
net/ipv6/addrconf.c: inet6addr_chain
net/netfilter/nf_conntrack_core.c: nf_conntrack_chain
net/netfilter/nf_conntrack_core.c: nf_conntrack_expect_chain
net/netlink/af_netlink.c: netlink_chain
BLOCKING CHAINS
---------------
arch/powerpc/platforms/pseries/reconfig.c: pSeries_reconfig_chain
arch/s390/kernel/process.c: idle_chain
arch/x86_64/kernel/process.c idle_notifier
drivers/base/memory.c: memory_chain
drivers/cpufreq/cpufreq.c cpufreq_policy_notifier_list
drivers/cpufreq/cpufreq.c cpufreq_transition_notifier_list
drivers/macintosh/adb.c: adb_client_list
drivers/macintosh/via-pmu.c sleep_notifier_list
drivers/macintosh/via-pmu68k.c sleep_notifier_list
drivers/macintosh/windfarm_core.c wf_client_list
drivers/usb/core/notify.c usb_notifier_list
drivers/video/fbmem.c fb_notifier_list
kernel/cpu.c cpu_chain
kernel/module.c module_notify_list
kernel/profile.c munmap_notifier
kernel/profile.c task_exit_notifier
kernel/sys.c reboot_notifier_list
net/core/dev.c netdev_chain
net/decnet/dn_dev.c: dnaddr_chain
net/ipv4/devinet.c: inetaddr_chain
It's possible that some of these classifications are wrong. If they are,
please let us know or submit a patch to fix them. Note that any chain that
gets called very frequently should be atomic, because the rwsem read-locking
used for blocking chains is very likely to incur cache misses on SMP systems.
(However, if the chain's callout routines may sleep then the chain cannot be
atomic.)
The patch set was written by Alan Stern and Chandra Seetharaman, incorporating
material written by Keith Owens and suggestions from Paul McKenney and Andrew
Morton.
[jes@sgi.com: restructure the notifier chain initialization macros]
Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Chandra Seetharaman <sekharan@us.ibm.com>
Signed-off-by: Jes Sorensen <jes@sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-27 02:16:30 -07:00
|
|
|
return blocking_notifier_call_chain(&memory_chain, val, v);
|
2005-10-29 19:16:54 -06:00
|
|
|
}
|
|
|
|
|
2009-12-17 07:44:38 -07:00
|
|
|
int memory_isolate_notify(unsigned long val, void *v)
|
|
|
|
{
|
|
|
|
return atomic_notifier_call_chain(&memory_isolate_chain, val, v);
|
|
|
|
}
|
|
|
|
|
2011-10-17 08:38:20 -06:00
|
|
|
/*
|
|
|
|
* The probe routines leave the pages reserved, just as the bootmem code does.
|
|
|
|
* Make sure they're still that way.
|
|
|
|
*/
|
2013-04-29 16:08:40 -06:00
|
|
|
static bool pages_correctly_reserved(unsigned long start_pfn)
|
2011-10-17 08:38:20 -06:00
|
|
|
{
|
|
|
|
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;
|
|
|
|
}
|
|
|
|
|
2005-10-29 19:16:54 -06:00
|
|
|
/*
|
|
|
|
* MEMORY_HOTPLUG depends on SPARSEMEM in mm/Kconfig, so it is
|
|
|
|
* OK to have direct references to sparsemem variables in here.
|
2015-04-14 16:45:11 -06:00
|
|
|
* Must already be protected by mem_hotplug_begin().
|
2005-10-29 19:16:54 -06:00
|
|
|
*/
|
|
|
|
static int
|
mm, memory-hotplug: dynamic configure movable memory and portion memory
Add online_movable and online_kernel for logic memory hotplug. This is
the dynamic version of "movablecore" & "kernelcore".
We have the same reason to introduce it as to introduce "movablecore" &
"kernelcore". It has the same motive as "movablecore" & "kernelcore", but
it is dynamic/running-time:
o We can configure memory as kernelcore or movablecore after boot.
Userspace workload is increased, we need more hugepage, we can't use
"online_movable" to add memory and allow the system use more
THP(transparent-huge-page), vice-verse when kernel workload is increase.
Also help for virtualization to dynamic configure host/guest's memory,
to save/(reduce waste) memory.
Memory capacity on Demand
o When a new node is physically online after boot, we need to use
"online_movable" or "online_kernel" to configure/portion it as we
expected when we logic-online it.
This configuration also helps for physically-memory-migrate.
o all benefit as the same as existed "movablecore" & "kernelcore".
o Preparing for movable-node, which is very important for power-saving,
hardware partitioning and high-available-system(hardware fault
management).
(Note, we don't introduce movable-node here.)
Action behavior:
When a memoryblock/memorysection is onlined by "online_movable", the kernel
will not have directly reference to the page of the memoryblock,
thus we can remove that memory any time when needed.
When it is online by "online_kernel", the kernel can use it.
When it is online by "online", the zone type doesn't changed.
Current constraints:
Only the memoryblock which is adjacent to the ZONE_MOVABLE
can be online from ZONE_NORMAL to ZONE_MOVABLE.
[akpm@linux-foundation.org: use min_t, cleanups]
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: Wen Congyang <wency@cn.fujitsu.com>
Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: Lai Jiangshan <laijs@cn.fujitsu.com>
Cc: Jiang Liu <jiang.liu@huawei.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: David Rientjes <rientjes@google.com>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Greg KH <greg@kroah.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-12-11 17:03:16 -07:00
|
|
|
memory_block_action(unsigned long phys_index, unsigned long action, int online_type)
|
2005-10-29 19:16:54 -06:00
|
|
|
{
|
2012-10-08 17:33:58 -06:00
|
|
|
unsigned long start_pfn;
|
2011-05-11 01:25:14 -06:00
|
|
|
unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block;
|
2005-10-29 19:16:54 -06:00
|
|
|
int ret;
|
|
|
|
|
2015-04-14 16:44:54 -06:00
|
|
|
start_pfn = section_nr_to_pfn(phys_index);
|
2011-10-18 15:00:57 -06:00
|
|
|
|
2005-10-29 19:16:54 -06:00
|
|
|
switch (action) {
|
2015-03-08 04:29:04 -06:00
|
|
|
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;
|
2005-10-29 19:16:54 -06:00
|
|
|
}
|
|
|
|
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2017-02-24 16:00:02 -07:00
|
|
|
static int memory_block_change_state(struct memory_block *mem,
|
2013-08-20 15:05:05 -06:00
|
|
|
unsigned long to_state, unsigned long from_state_req)
|
2005-10-29 19:16:54 -06:00
|
|
|
{
|
2011-10-18 15:00:57 -06:00
|
|
|
int ret = 0;
|
2011-01-20 09:43:34 -07:00
|
|
|
|
2013-05-08 06:18:37 -06:00
|
|
|
if (mem->state != from_state_req)
|
|
|
|
return -EINVAL;
|
2005-10-29 19:16:54 -06:00
|
|
|
|
2011-01-20 09:43:34 -07:00
|
|
|
if (to_state == MEM_OFFLINE)
|
|
|
|
mem->state = MEM_GOING_OFFLINE;
|
|
|
|
|
2013-08-20 15:05:05 -06:00
|
|
|
ret = memory_block_action(mem->start_section_nr, to_state,
|
|
|
|
mem->online_type);
|
|
|
|
|
2013-05-23 02:38:55 -06:00
|
|
|
mem->state = ret ? from_state_req : to_state;
|
2013-08-20 15:05:05 -06:00
|
|
|
|
2013-05-08 06:18:37 -06:00
|
|
|
return ret;
|
|
|
|
}
|
2011-01-20 09:43:34 -07:00
|
|
|
|
2013-08-20 15:05:05 -06:00
|
|
|
/* The device lock serializes operations on memory_subsys_[online|offline] */
|
2013-05-08 06:18:37 -06:00
|
|
|
static int memory_subsys_online(struct device *dev)
|
|
|
|
{
|
2013-08-28 00:38:27 -06:00
|
|
|
struct memory_block *mem = to_memory_block(dev);
|
2013-05-08 06:18:37 -06:00
|
|
|
int ret;
|
2005-10-29 19:16:54 -06:00
|
|
|
|
2013-08-20 15:05:05 -06:00
|
|
|
if (mem->state == MEM_ONLINE)
|
|
|
|
return 0;
|
2013-05-08 06:18:37 -06:00
|
|
|
|
2013-08-20 15:05:05 -06:00
|
|
|
/*
|
|
|
|
* 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)
|
2014-08-06 17:05:13 -06:00
|
|
|
mem->online_type = MMOP_ONLINE_KEEP;
|
2013-05-08 06:18:37 -06:00
|
|
|
|
2015-04-14 16:45:11 -06:00
|
|
|
/* Already under protection of mem_hotplug_begin() */
|
2013-08-20 15:05:05 -06:00
|
|
|
ret = memory_block_change_state(mem, MEM_ONLINE, MEM_OFFLINE);
|
2013-05-08 06:18:37 -06:00
|
|
|
|
2013-08-20 15:05:05 -06:00
|
|
|
/* clear online_type */
|
|
|
|
mem->online_type = -1;
|
2013-05-08 06:18:37 -06:00
|
|
|
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int memory_subsys_offline(struct device *dev)
|
2012-10-08 17:34:01 -06:00
|
|
|
{
|
2013-08-28 00:38:27 -06:00
|
|
|
struct memory_block *mem = to_memory_block(dev);
|
2012-10-08 17:34:01 -06:00
|
|
|
|
2013-08-20 15:05:05 -06:00
|
|
|
if (mem->state == MEM_OFFLINE)
|
|
|
|
return 0;
|
2012-10-08 17:34:01 -06:00
|
|
|
|
2015-12-11 14:40:57 -07:00
|
|
|
/* Can't offline block with non-present sections */
|
|
|
|
if (mem->section_count != sections_per_block)
|
|
|
|
return -EINVAL;
|
|
|
|
|
2013-08-20 15:05:05 -06:00
|
|
|
return memory_block_change_state(mem, MEM_OFFLINE, MEM_ONLINE);
|
2012-10-08 17:34:01 -06:00
|
|
|
}
|
2013-05-08 06:18:37 -06:00
|
|
|
|
2005-10-29 19:16:54 -06:00
|
|
|
static ssize_t
|
2011-12-21 15:48:43 -07:00
|
|
|
store_mem_state(struct device *dev,
|
|
|
|
struct device_attribute *attr, const char *buf, size_t count)
|
2005-10-29 19:16:54 -06:00
|
|
|
{
|
2013-08-28 00:38:27 -06:00
|
|
|
struct memory_block *mem = to_memory_block(dev);
|
2013-08-20 15:05:05 -06:00
|
|
|
int ret, online_type;
|
2005-10-29 19:16:54 -06:00
|
|
|
|
driver core / ACPI: Avoid device hot remove locking issues
device_hotplug_lock is held around the acpi_bus_trim() call in
acpi_scan_hot_remove() which generally removes devices (it removes
ACPI device objects at least, but it may also remove "physical"
device objects through .detach() callbacks of ACPI scan handlers).
Thus, potentially, device sysfs attributes are removed under that
lock and to remove those attributes it is necessary to hold the
s_active references of their directory entries for writing.
On the other hand, the execution of a .show() or .store() callback
from a sysfs attribute is carried out with that attribute's s_active
reference held for reading. Consequently, if any device sysfs
attribute that may be removed from within acpi_scan_hot_remove()
through acpi_bus_trim() has a .store() or .show() callback which
acquires device_hotplug_lock, the execution of that callback may
deadlock with the removal of the attribute. [Unfortunately, the
"online" device attribute of CPUs and memory blocks is one of them.]
To avoid such deadlocks, make all of the sysfs attribute callbacks
that need to lock device hotplug, for example store_online(), use
a special function, lock_device_hotplug_sysfs(), to lock device
hotplug and return the result of that function immediately if it is
not zero. This will cause the s_active reference of the directory
entry in question to be released and the syscall to be restarted
if device_hotplug_lock cannot be acquired.
[show_online() actually doesn't need to lock device hotplug, but
it is useful to serialize it with respect to device_offline() and
device_online() for the same device (in case user space attempts to
run them concurrently) which can be done with the help of
device_lock().]
Reported-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Reported-and-tested-by: Gu Zheng <guz.fnst@cn.fujitsu.com>
Suggested-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Acked-by: Toshi Kani <toshi.kani@hp.com>
2013-08-28 13:41:01 -06:00
|
|
|
ret = lock_device_hotplug_sysfs();
|
|
|
|
if (ret)
|
|
|
|
return ret;
|
2013-05-08 06:18:37 -06:00
|
|
|
|
mem-hotplug: avoid illegal state prefixed with legal state when changing state of memory_block
We use the following command to online a memory_block:
echo online|online_kernel|online_movable > /sys/devices/system/memory/memoryXXX/state
But, if we do the following:
echo online_fhsjkghfkd > /sys/devices/system/memory/memoryXXX/state
the block will also be onlined.
This is because the following code in store_mem_state() does not compare
the whole string, but only the prefix of the string.
store_mem_state()
{
......
328 if (!strncmp(buf, "online_kernel", min_t(int, count, 13)))
Here, only compare the first 13 letters of the string. If we give "online_kernelXXXXXX",
it will be recognized as online_kernel, which is incorrect.
329 online_type = ONLINE_KERNEL;
330 else if (!strncmp(buf, "online_movable", min_t(int, count, 14)))
We have the same problem here,
331 online_type = ONLINE_MOVABLE;
332 else if (!strncmp(buf, "online", min_t(int, count, 6)))
here,
(Here is more problematic. If we give online_movalbe, which is a typo
of online_movable, it will be recognized as online without noticing the
author.)
333 online_type = ONLINE_KEEP;
334 else if (!strncmp(buf, "offline", min_t(int, count, 7)))
and here.
335 online_type = -1;
336 else {
337 ret = -EINVAL;
338 goto err;
339 }
......
}
This patch fixes this problem by using sysfs_streq() to compare the
whole string.
Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com>
Reported-by: Hu Tao <hutao@cn.fujitsu.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Lai Jiangshan <laijs@cn.fujitsu.com>
Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: Gu Zheng <guz.fnst@cn.fujitsu.com>
Acked-by: Toshi Kani <toshi.kani@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-06 17:05:11 -06:00
|
|
|
if (sysfs_streq(buf, "online_kernel"))
|
2014-08-06 17:05:13 -06:00
|
|
|
online_type = MMOP_ONLINE_KERNEL;
|
mem-hotplug: avoid illegal state prefixed with legal state when changing state of memory_block
We use the following command to online a memory_block:
echo online|online_kernel|online_movable > /sys/devices/system/memory/memoryXXX/state
But, if we do the following:
echo online_fhsjkghfkd > /sys/devices/system/memory/memoryXXX/state
the block will also be onlined.
This is because the following code in store_mem_state() does not compare
the whole string, but only the prefix of the string.
store_mem_state()
{
......
328 if (!strncmp(buf, "online_kernel", min_t(int, count, 13)))
Here, only compare the first 13 letters of the string. If we give "online_kernelXXXXXX",
it will be recognized as online_kernel, which is incorrect.
329 online_type = ONLINE_KERNEL;
330 else if (!strncmp(buf, "online_movable", min_t(int, count, 14)))
We have the same problem here,
331 online_type = ONLINE_MOVABLE;
332 else if (!strncmp(buf, "online", min_t(int, count, 6)))
here,
(Here is more problematic. If we give online_movalbe, which is a typo
of online_movable, it will be recognized as online without noticing the
author.)
333 online_type = ONLINE_KEEP;
334 else if (!strncmp(buf, "offline", min_t(int, count, 7)))
and here.
335 online_type = -1;
336 else {
337 ret = -EINVAL;
338 goto err;
339 }
......
}
This patch fixes this problem by using sysfs_streq() to compare the
whole string.
Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com>
Reported-by: Hu Tao <hutao@cn.fujitsu.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Lai Jiangshan <laijs@cn.fujitsu.com>
Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: Gu Zheng <guz.fnst@cn.fujitsu.com>
Acked-by: Toshi Kani <toshi.kani@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-06 17:05:11 -06:00
|
|
|
else if (sysfs_streq(buf, "online_movable"))
|
2014-08-06 17:05:13 -06:00
|
|
|
online_type = MMOP_ONLINE_MOVABLE;
|
mem-hotplug: avoid illegal state prefixed with legal state when changing state of memory_block
We use the following command to online a memory_block:
echo online|online_kernel|online_movable > /sys/devices/system/memory/memoryXXX/state
But, if we do the following:
echo online_fhsjkghfkd > /sys/devices/system/memory/memoryXXX/state
the block will also be onlined.
This is because the following code in store_mem_state() does not compare
the whole string, but only the prefix of the string.
store_mem_state()
{
......
328 if (!strncmp(buf, "online_kernel", min_t(int, count, 13)))
Here, only compare the first 13 letters of the string. If we give "online_kernelXXXXXX",
it will be recognized as online_kernel, which is incorrect.
329 online_type = ONLINE_KERNEL;
330 else if (!strncmp(buf, "online_movable", min_t(int, count, 14)))
We have the same problem here,
331 online_type = ONLINE_MOVABLE;
332 else if (!strncmp(buf, "online", min_t(int, count, 6)))
here,
(Here is more problematic. If we give online_movalbe, which is a typo
of online_movable, it will be recognized as online without noticing the
author.)
333 online_type = ONLINE_KEEP;
334 else if (!strncmp(buf, "offline", min_t(int, count, 7)))
and here.
335 online_type = -1;
336 else {
337 ret = -EINVAL;
338 goto err;
339 }
......
}
This patch fixes this problem by using sysfs_streq() to compare the
whole string.
Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com>
Reported-by: Hu Tao <hutao@cn.fujitsu.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Lai Jiangshan <laijs@cn.fujitsu.com>
Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: Gu Zheng <guz.fnst@cn.fujitsu.com>
Acked-by: Toshi Kani <toshi.kani@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-06 17:05:11 -06:00
|
|
|
else if (sysfs_streq(buf, "online"))
|
2014-08-06 17:05:13 -06:00
|
|
|
online_type = MMOP_ONLINE_KEEP;
|
mem-hotplug: avoid illegal state prefixed with legal state when changing state of memory_block
We use the following command to online a memory_block:
echo online|online_kernel|online_movable > /sys/devices/system/memory/memoryXXX/state
But, if we do the following:
echo online_fhsjkghfkd > /sys/devices/system/memory/memoryXXX/state
the block will also be onlined.
This is because the following code in store_mem_state() does not compare
the whole string, but only the prefix of the string.
store_mem_state()
{
......
328 if (!strncmp(buf, "online_kernel", min_t(int, count, 13)))
Here, only compare the first 13 letters of the string. If we give "online_kernelXXXXXX",
it will be recognized as online_kernel, which is incorrect.
329 online_type = ONLINE_KERNEL;
330 else if (!strncmp(buf, "online_movable", min_t(int, count, 14)))
We have the same problem here,
331 online_type = ONLINE_MOVABLE;
332 else if (!strncmp(buf, "online", min_t(int, count, 6)))
here,
(Here is more problematic. If we give online_movalbe, which is a typo
of online_movable, it will be recognized as online without noticing the
author.)
333 online_type = ONLINE_KEEP;
334 else if (!strncmp(buf, "offline", min_t(int, count, 7)))
and here.
335 online_type = -1;
336 else {
337 ret = -EINVAL;
338 goto err;
339 }
......
}
This patch fixes this problem by using sysfs_streq() to compare the
whole string.
Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com>
Reported-by: Hu Tao <hutao@cn.fujitsu.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Lai Jiangshan <laijs@cn.fujitsu.com>
Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: Gu Zheng <guz.fnst@cn.fujitsu.com>
Acked-by: Toshi Kani <toshi.kani@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-06 17:05:11 -06:00
|
|
|
else if (sysfs_streq(buf, "offline"))
|
2014-08-06 17:05:13 -06:00
|
|
|
online_type = MMOP_OFFLINE;
|
2013-10-11 00:36:25 -06:00
|
|
|
else {
|
|
|
|
ret = -EINVAL;
|
|
|
|
goto err;
|
|
|
|
}
|
2013-08-20 15:05:05 -06:00
|
|
|
|
2015-04-14 16:45:11 -06:00
|
|
|
/*
|
|
|
|
* 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();
|
|
|
|
|
2013-08-20 15:05:05 -06:00
|
|
|
switch (online_type) {
|
2014-08-06 17:05:13 -06:00
|
|
|
case MMOP_ONLINE_KERNEL:
|
|
|
|
case MMOP_ONLINE_MOVABLE:
|
|
|
|
case MMOP_ONLINE_KEEP:
|
2013-08-20 15:05:05 -06:00
|
|
|
mem->online_type = online_type;
|
|
|
|
ret = device_online(&mem->dev);
|
|
|
|
break;
|
2014-08-06 17:05:13 -06:00
|
|
|
case MMOP_OFFLINE:
|
2013-08-20 15:05:05 -06:00
|
|
|
ret = device_offline(&mem->dev);
|
|
|
|
break;
|
|
|
|
default:
|
|
|
|
ret = -EINVAL; /* should never happen */
|
2013-05-08 06:18:37 -06:00
|
|
|
}
|
|
|
|
|
2015-04-14 16:45:11 -06:00
|
|
|
mem_hotplug_done();
|
2013-10-11 00:36:25 -06:00
|
|
|
err:
|
2013-05-08 06:18:37 -06:00
|
|
|
unlock_device_hotplug();
|
2011-01-20 09:43:34 -07:00
|
|
|
|
2016-10-07 18:00:15 -06:00
|
|
|
if (ret < 0)
|
2005-10-29 19:16:54 -06:00
|
|
|
return ret;
|
2016-10-07 18:00:15 -06:00
|
|
|
if (ret)
|
|
|
|
return -EINVAL;
|
|
|
|
|
2005-10-29 19:16:54 -06:00
|
|
|
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?
|
|
|
|
*/
|
2011-12-21 15:48:43 -07:00
|
|
|
static ssize_t show_phys_device(struct device *dev,
|
|
|
|
struct device_attribute *attr, char *buf)
|
2005-10-29 19:16:54 -06:00
|
|
|
{
|
2013-08-28 00:38:27 -06:00
|
|
|
struct memory_block *mem = to_memory_block(dev);
|
2005-10-29 19:16:54 -06:00
|
|
|
return sprintf(buf, "%d\n", mem->phys_device);
|
|
|
|
}
|
|
|
|
|
2014-10-09 16:26:31 -06:00
|
|
|
#ifdef CONFIG_MEMORY_HOTREMOVE
|
|
|
|
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, end_pfn;
|
2017-02-03 14:13:23 -07:00
|
|
|
unsigned long valid_start, valid_end, valid_pages;
|
2014-10-09 16:26:31 -06:00
|
|
|
unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block;
|
|
|
|
struct zone *zone;
|
2016-07-26 16:22:27 -06:00
|
|
|
int zone_shift = 0;
|
2014-10-09 16:26:31 -06:00
|
|
|
|
|
|
|
start_pfn = section_nr_to_pfn(mem->start_section_nr);
|
|
|
|
end_pfn = start_pfn + nr_pages;
|
|
|
|
|
|
|
|
/* The block contains more than one zone can not be offlined. */
|
2017-02-03 14:13:23 -07:00
|
|
|
if (!test_pages_in_a_zone(start_pfn, end_pfn, &valid_start, &valid_end))
|
2014-10-09 16:26:31 -06:00
|
|
|
return sprintf(buf, "none\n");
|
|
|
|
|
2017-02-03 14:13:23 -07:00
|
|
|
zone = page_zone(pfn_to_page(valid_start));
|
|
|
|
valid_pages = valid_end - valid_start;
|
2014-10-09 16:26:31 -06:00
|
|
|
|
2016-07-26 16:22:27 -06:00
|
|
|
/* MMOP_ONLINE_KEEP */
|
|
|
|
sprintf(buf, "%s", zone->name);
|
|
|
|
|
|
|
|
/* MMOP_ONLINE_KERNEL */
|
2017-02-03 14:13:23 -07:00
|
|
|
zone_can_shift(valid_start, valid_pages, ZONE_NORMAL, &zone_shift);
|
2016-07-26 16:22:27 -06:00
|
|
|
if (zone_shift) {
|
|
|
|
strcat(buf, " ");
|
|
|
|
strcat(buf, (zone + zone_shift)->name);
|
2014-10-09 16:26:31 -06:00
|
|
|
}
|
|
|
|
|
2016-07-26 16:22:27 -06:00
|
|
|
/* MMOP_ONLINE_MOVABLE */
|
2017-02-03 14:13:23 -07:00
|
|
|
zone_can_shift(valid_start, valid_pages, ZONE_MOVABLE, &zone_shift);
|
2016-07-26 16:22:27 -06:00
|
|
|
if (zone_shift) {
|
|
|
|
strcat(buf, " ");
|
|
|
|
strcat(buf, (zone + zone_shift)->name);
|
2014-10-09 16:26:31 -06:00
|
|
|
}
|
|
|
|
|
2016-07-26 16:22:27 -06:00
|
|
|
strcat(buf, "\n");
|
|
|
|
|
|
|
|
return strlen(buf);
|
2014-10-09 16:26:31 -06:00
|
|
|
}
|
|
|
|
static DEVICE_ATTR(valid_zones, 0444, show_valid_zones, NULL);
|
|
|
|
#endif
|
|
|
|
|
2011-12-21 15:48:43 -07:00
|
|
|
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);
|
2005-10-29 19:16:54 -06:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Block size attribute stuff
|
|
|
|
*/
|
|
|
|
static ssize_t
|
2011-12-21 15:48:43 -07:00
|
|
|
print_block_size(struct device *dev, struct device_attribute *attr,
|
2010-01-05 04:48:06 -07:00
|
|
|
char *buf)
|
2005-10-29 19:16:54 -06:00
|
|
|
{
|
2011-01-20 09:43:34 -07:00
|
|
|
return sprintf(buf, "%lx\n", get_memory_block_size());
|
2005-10-29 19:16:54 -06:00
|
|
|
}
|
|
|
|
|
2011-12-21 15:48:43 -07:00
|
|
|
static DEVICE_ATTR(block_size_bytes, 0444, print_block_size, NULL);
|
2005-10-29 19:16:54 -06:00
|
|
|
|
2016-03-15 15:56:48 -06:00
|
|
|
/*
|
|
|
|
* 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);
|
|
|
|
|
2005-10-29 19:16:54 -06:00
|
|
|
/*
|
|
|
|
* 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
|
2011-12-21 15:48:43 -07:00
|
|
|
memory_probe_store(struct device *dev, struct device_attribute *attr,
|
2010-01-05 04:48:07 -07:00
|
|
|
const char *buf, size_t count)
|
2005-10-29 19:16:54 -06:00
|
|
|
{
|
|
|
|
u64 phys_addr;
|
2016-01-14 16:22:16 -07:00
|
|
|
int nid, ret;
|
2011-09-14 14:26:15 -06:00
|
|
|
unsigned long pages_per_block = PAGES_PER_SECTION * sections_per_block;
|
2005-10-29 19:16:54 -06:00
|
|
|
|
2014-08-06 17:06:06 -06:00
|
|
|
ret = kstrtoull(buf, 0, &phys_addr);
|
|
|
|
if (ret)
|
|
|
|
return ret;
|
2005-10-29 19:16:54 -06:00
|
|
|
|
2011-09-14 14:26:15 -06:00
|
|
|
if (phys_addr & ((pages_per_block << PAGE_SHIFT) - 1))
|
|
|
|
return -EINVAL;
|
|
|
|
|
2016-01-14 16:22:16 -07:00
|
|
|
nid = memory_add_physaddr_to_nid(phys_addr);
|
|
|
|
ret = add_memory(nid, phys_addr,
|
|
|
|
MIN_MEMORY_BLOCK_SIZE * sections_per_block);
|
2011-01-31 09:55:23 -07:00
|
|
|
|
2016-01-14 16:22:16 -07:00
|
|
|
if (ret)
|
|
|
|
goto out;
|
2005-10-29 19:16:54 -06:00
|
|
|
|
2011-03-24 00:16:18 -06:00
|
|
|
ret = count;
|
|
|
|
out:
|
|
|
|
return ret;
|
2005-10-29 19:16:54 -06:00
|
|
|
}
|
|
|
|
|
2013-06-04 13:42:28 -06:00
|
|
|
static DEVICE_ATTR(probe, S_IWUSR, NULL, memory_probe_store);
|
2005-10-29 19:16:54 -06:00
|
|
|
#endif
|
|
|
|
|
2009-12-16 04:20:00 -07:00
|
|
|
#ifdef CONFIG_MEMORY_FAILURE
|
|
|
|
/*
|
|
|
|
* Support for offlining pages of memory
|
|
|
|
*/
|
|
|
|
|
|
|
|
/* Soft offline a page */
|
|
|
|
static ssize_t
|
2011-12-21 15:48:43 -07:00
|
|
|
store_soft_offline_page(struct device *dev,
|
|
|
|
struct device_attribute *attr,
|
2010-01-05 04:48:07 -07:00
|
|
|
const char *buf, size_t count)
|
2009-12-16 04:20:00 -07:00
|
|
|
{
|
|
|
|
int ret;
|
|
|
|
u64 pfn;
|
|
|
|
if (!capable(CAP_SYS_ADMIN))
|
|
|
|
return -EPERM;
|
2013-07-25 22:10:22 -06:00
|
|
|
if (kstrtoull(buf, 0, &pfn) < 0)
|
2009-12-16 04:20:00 -07:00
|
|
|
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
|
2011-12-21 15:48:43 -07:00
|
|
|
store_hard_offline_page(struct device *dev,
|
|
|
|
struct device_attribute *attr,
|
2010-01-05 04:48:07 -07:00
|
|
|
const char *buf, size_t count)
|
2009-12-16 04:20:00 -07:00
|
|
|
{
|
|
|
|
int ret;
|
|
|
|
u64 pfn;
|
|
|
|
if (!capable(CAP_SYS_ADMIN))
|
|
|
|
return -EPERM;
|
2013-07-25 22:10:22 -06:00
|
|
|
if (kstrtoull(buf, 0, &pfn) < 0)
|
2009-12-16 04:20:00 -07:00
|
|
|
return -EINVAL;
|
|
|
|
pfn >>= PAGE_SHIFT;
|
2011-12-15 11:48:12 -07:00
|
|
|
ret = memory_failure(pfn, 0, 0);
|
2009-12-16 04:20:00 -07:00
|
|
|
return ret ? ret : count;
|
|
|
|
}
|
|
|
|
|
2013-02-18 12:09:03 -07:00
|
|
|
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);
|
2009-12-16 04:20:00 -07:00
|
|
|
#endif
|
|
|
|
|
2005-10-29 19:16:54 -06:00
|
|
|
/*
|
|
|
|
* Note that phys_device is optional. It is here to allow for
|
|
|
|
* differentiation between which *physical* devices each
|
|
|
|
* section belongs to...
|
|
|
|
*/
|
2010-03-14 22:35:03 -06:00
|
|
|
int __weak arch_get_memory_phys_device(unsigned long start_pfn)
|
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
2005-10-29 19:16:54 -06:00
|
|
|
|
2011-12-21 15:48:43 -07:00
|
|
|
/*
|
|
|
|
* A reference for the returned object is held and the reference for the
|
|
|
|
* hinted object is released.
|
|
|
|
*/
|
2010-09-29 13:00:55 -06:00
|
|
|
struct memory_block *find_memory_block_hinted(struct mem_section *section,
|
|
|
|
struct memory_block *hint)
|
2005-10-29 19:16:54 -06:00
|
|
|
{
|
2011-01-20 09:43:34 -07:00
|
|
|
int block_id = base_memory_block_id(__section_nr(section));
|
2011-12-21 15:48:43 -07:00
|
|
|
struct device *hintdev = hint ? &hint->dev : NULL;
|
|
|
|
struct device *dev;
|
2005-10-29 19:16:54 -06:00
|
|
|
|
2011-12-21 15:48:43 -07:00
|
|
|
dev = subsys_find_device_by_id(&memory_subsys, block_id, hintdev);
|
|
|
|
if (hint)
|
|
|
|
put_device(&hint->dev);
|
|
|
|
if (!dev)
|
2005-10-29 19:16:54 -06:00
|
|
|
return NULL;
|
2013-08-28 00:38:27 -06:00
|
|
|
return to_memory_block(dev);
|
2005-10-29 19:16:54 -06:00
|
|
|
}
|
|
|
|
|
2010-09-29 13:00:55 -06:00
|
|
|
/*
|
|
|
|
* 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.
|
|
|
|
*
|
2011-12-21 15:48:43 -07:00
|
|
|
* This could be made generic for all device subsystems.
|
2010-09-29 13:00:55 -06:00
|
|
|
*/
|
|
|
|
struct memory_block *find_memory_block(struct mem_section *section)
|
|
|
|
{
|
|
|
|
return find_memory_block_hinted(section, NULL);
|
|
|
|
}
|
|
|
|
|
2013-06-04 13:42:28 -06:00
|
|
|
static struct attribute *memory_memblk_attrs[] = {
|
|
|
|
&dev_attr_phys_index.attr,
|
|
|
|
&dev_attr_state.attr,
|
|
|
|
&dev_attr_phys_device.attr,
|
|
|
|
&dev_attr_removable.attr,
|
2014-10-09 16:26:31 -06:00
|
|
|
#ifdef CONFIG_MEMORY_HOTREMOVE
|
|
|
|
&dev_attr_valid_zones.attr,
|
|
|
|
#endif
|
2013-06-04 13:42:28 -06:00
|
|
|
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;
|
Power management and ACPI updates for 3.11-rc1
- Hotplug changes allowing device hot-removal operations to fail
gracefully (instead of crashing the kernel) if they cannot be
carried out completely. From Rafael J Wysocki and Toshi Kani.
- Freezer update from Colin Cross and Mandeep Singh Baines targeted
at making the freezing of tasks a bit less heavy weight operation.
- cpufreq resume fix from Srivatsa S Bhat for a regression introduced
during the 3.10 cycle causing some cpufreq sysfs attributes to
return wrong values to user space after resume.
- New freqdomain_cpus sysfs attribute for the acpi-cpufreq driver to
provide information previously available via related_cpus from
Lan Tianyu.
- cpufreq fixes and cleanups from Viresh Kumar, Jacob Shin,
Heiko Stübner, Xiaoguang Chen, Ezequiel Garcia, Arnd Bergmann, and
Tang Yuantian.
- Fix for an ACPICA regression causing suspend/resume issues to
appear on some systems introduced during the 3.4 development cycle
from Lv Zheng.
- ACPICA fixes and cleanups from Bob Moore, Tomasz Nowicki, Lv Zheng,
Chao Guan, and Zhang Rui.
- New cupidle driver for Xilinx Zynq processors from Michal Simek.
- cpuidle fixes and cleanups from Daniel Lezcano.
- Changes to make suspend/resume work correctly in Xen guests from
Konrad Rzeszutek Wilk.
- ACPI device power management fixes and cleanups from Fengguang Wu
and Rafael J Wysocki.
- ACPI documentation updates from Lv Zheng, Aaron Lu and Hanjun Guo.
- Fix for the IA-64 issue that was the reason for reverting commit
9f29ab1 and updates of the ACPI scan code from Rafael J Wysocki.
- Mechanism for adding CMOS RTC address space handlers from Lan Tianyu
(to allow some EC-related breakage to be fixed on some systems).
- Spec-compliant implementation of acpi_os_get_timer() from
Mika Westerberg.
- Modification of do_acpi_find_child() to execute _STA in order to
to avoid situations in which a pointer to a disabled device object
is returned instead of an enabled one with the same _ADR value.
From Jeff Wu.
- Intel BayTrail PCH (Platform Controller Hub) support for the ACPI
Intel Low-Power Subsystems (LPSS) driver and modificaions of that
driver to work around a couple of known BIOS issues from
Mika Westerberg and Heikki Krogerus.
- EC driver fix from Vasiliy Kulikov to make it use get_user() and
put_user() instead of dereferencing user space pointers blindly.
- Assorted ACPI code cleanups from Bjorn Helgaas, Nicholas Mazzuca and
Toshi Kani.
- Modification of the "runtime idle" helper routine to take the return
values of the callbacks executed by it into account and to call
rpm_suspend() if they return 0, which allows some code bloat
reduction to be done, from Rafael J Wysocki and Alan Stern.
- New trace points for PM QoS from Sahara <keun-o.park@windriver.com>.
- PM QoS documentation update from Lan Tianyu.
- Assorted core PM code cleanups and changes from Bernie Thompson,
Bjorn Helgaas, Julius Werner, and Shuah Khan.
- New devfreq driver for the Exynos5-bus device from Abhilash Kesavan.
- Minor devfreq cleanups, fixes and MAINTAINERS update from
MyungJoo Ham, Abhilash Kesavan, Paul Bolle, Rajagopal Venkat, and
Wei Yongjun.
- OMAP Adaptive Voltage Scaling (AVS) SmartReflex voltage control
driver updates from Andrii Tseglytskyi and Nishanth Menon.
/
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2.0.19 (GNU/Linux)
iQIcBAABAgAGBQJR0ZNOAAoJEKhOf7ml8uNsDLYP/0EU4rmvw0TWTITfp6RS1KDE
9GwBn96ZR4Q5bJd9gBCTPSqhHOYMqxWEUp99sn/M2wehG1pk/jw5LO56+2IhM3UZ
g1HDcJ7te2nVT/iXsKiAGTVhU9Rk0aYwoVSknwk27qpIBGxW9w/s5tLX8pY3Q3Zq
wL/7aTPjyL+PFFFEaxgH7qLqsl3DhbtYW5AriUBTkXout/tJ4eO1b7MNBncLDh8X
VQ/0DNCKE95VEJfkO4rk9RKUyVp9GDn0i+HXCD/FS4IA5oYzePdVdNDmXf7g+swe
CGlTZq8pB+oBpDiHl4lxzbNrKQjRNbGnDUkoRcWqn0nAw56xK+vmYnWJhW99gQ/I
fKnvxeLca5po1aiqmC4VSJxZIatFZqLrZAI4dzoCLWY+bGeTnCKmj0/F8ytFnZA2
8IuLLs7/dFOaHXV/pKmpg6FAlFa9CPxoqRFoyqb4M0GjEarADyalXUWsPtG+6xCp
R/p0CISpwk+guKZR/qPhL7M654S7SHrPwd2DPF0KgGsvk+G2GhoB8EzvD8BVp98Z
9siCGCdgKQfJQVI6R0k9aFmn/4gRQIAgyPhkhv9tqULUUkiaXki+/t8kPfnb8O/d
zep+CA57E2G8MYLkDJfpFeKS7GpPD6TIdgFdGmOUC0Y6sl9iTdiw4yTx8O2JM37z
rHBZfYGkJBrbGRu+Q1gs
=VBBq
-----END PGP SIGNATURE-----
Merge tag 'pm+acpi-3.11-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm
Pull power management and ACPI updates from Rafael Wysocki:
"This time the total number of ACPI commits is slightly greater than
the number of cpufreq commits, but Viresh Kumar (who works on cpufreq)
remains the most active patch submitter.
To me, the most significant change is the addition of offline/online
device operations to the driver core (with the Greg's blessing) and
the related modifications of the ACPI core hotplug code. Next are the
freezer updates from Colin Cross that should make the freezing of
tasks a bit less heavy weight.
We also have a couple of regression fixes, a number of fixes for
issues that have not been identified as regressions, two new drivers
and a bunch of cleanups all over.
Highlights:
- Hotplug changes to support graceful hot-removal failures.
It sometimes is necessary to fail device hot-removal operations
gracefully if they cannot be carried out completely. For example,
if memory from a memory module being hot-removed has been allocated
for the kernel's own use and cannot be moved elsewhere, it's
desirable to fail the hot-removal operation in a graceful way
rather than to crash the kernel, but currenty a success or a kernel
crash are the only possible outcomes of an attempted memory
hot-removal. Needless to say, that is not a very attractive
alternative and it had to be addressed.
However, in order to make it work for memory, I first had to make
it work for CPUs and for this purpose I needed to modify the ACPI
processor driver. It's been split into two parts, a resident one
handling the low-level initialization/cleanup and a modular one
playing the actual driver's role (but it binds to the CPU system
device objects rather than to the ACPI device objects representing
processors). That's been sort of like a live brain surgery on a
patient who's riding a bike.
So this is a little scary, but since we found and fixed a couple of
regressions it caused to happen during the early linux-next testing
(a month ago), nobody has complained.
As a bonus we remove some duplicated ACPI hotplug code, because the
ACPI-based CPU hotplug is now going to use the common ACPI hotplug
code.
- Lighter weight freezing of tasks.
These changes from Colin Cross and Mandeep Singh Baines are
targeted at making the freezing of tasks a bit less heavy weight
operation. They reduce the number of tasks woken up every time
during the freezing, by using the observation that the freezer
simply doesn't need to wake up some of them and wait for them all
to call refrigerator(). The time needed for the freezer to decide
to report a failure is reduced too.
Also reintroduced is the check causing a lockdep warining to
trigger when try_to_freeze() is called with locks held (which is
generally unsafe and shouldn't happen).
- cpufreq updates
First off, a commit from Srivatsa S Bhat fixes a resume regression
introduced during the 3.10 cycle causing some cpufreq sysfs
attributes to return wrong values to user space after resume. The
fix is kind of fresh, but also it's pretty obvious once Srivatsa
has identified the root cause.
Second, we have a new freqdomain_cpus sysfs attribute for the
acpi-cpufreq driver to provide information previously available via
related_cpus. From Lan Tianyu.
Finally, we fix a number of issues, mostly related to the
CPUFREQ_POSTCHANGE notifier and cpufreq Kconfig options and clean
up some code. The majority of changes from Viresh Kumar with bits
from Jacob Shin, Heiko Stübner, Xiaoguang Chen, Ezequiel Garcia,
Arnd Bergmann, and Tang Yuantian.
- ACPICA update
A usual bunch of updates from the ACPICA upstream.
During the 3.4 cycle we introduced support for ACPI 5 extended
sleep registers, but they are only supposed to be used if the
HW-reduced mode bit is set in the FADT flags and the code attempted
to use them without checking that bit. That caused suspend/resume
regressions to happen on some systems. Fix from Lv Zheng causes
those registers to be used only if the HW-reduced mode bit is set.
Apart from this some other ACPICA bugs are fixed and code cleanups
are made by Bob Moore, Tomasz Nowicki, Lv Zheng, Chao Guan, and
Zhang Rui.
- cpuidle updates
New driver for Xilinx Zynq processors is added by Michal Simek.
Multidriver support simplification, addition of some missing
kerneldoc comments and Kconfig-related fixes come from Daniel
Lezcano.
- ACPI power management updates
Changes to make suspend/resume work correctly in Xen guests from
Konrad Rzeszutek Wilk, sparse warning fix from Fengguang Wu and
cleanups and fixes of the ACPI device power state selection
routine.
- ACPI documentation updates
Some previously missing pieces of ACPI documentation are added by
Lv Zheng and Aaron Lu (hopefully, that will help people to
uderstand how the ACPI subsystem works) and one outdated doc is
updated by Hanjun Guo.
- Assorted ACPI updates
We finally nailed down the IA-64 issue that was the reason for
reverting commit 9f29ab11ddbf ("ACPI / scan: do not match drivers
against objects having scan handlers"), so we can fix it and move
the ACPI scan handler check added to the ACPI video driver back to
the core.
A mechanism for adding CMOS RTC address space handlers is
introduced by Lan Tianyu to allow some EC-related breakage to be
fixed on some systems.
A spec-compliant implementation of acpi_os_get_timer() is added by
Mika Westerberg.
The evaluation of _STA is added to do_acpi_find_child() to avoid
situations in which a pointer to a disabled device object is
returned instead of an enabled one with the same _ADR value. From
Jeff Wu.
Intel BayTrail PCH (Platform Controller Hub) support is added to
the ACPI driver for Intel Low-Power Subsystems (LPSS) and that
driver is modified to work around a couple of known BIOS issues.
Changes from Mika Westerberg and Heikki Krogerus.
The EC driver is fixed by Vasiliy Kulikov to use get_user() and
put_user() instead of dereferencing user space pointers blindly.
Code cleanups are made by Bjorn Helgaas, Nicholas Mazzuca and Toshi
Kani.
- Assorted power management updates
The "runtime idle" helper routine is changed to take the return
values of the callbacks executed by it into account and to call
rpm_suspend() if they return 0, which allows us to reduce the
overall code bloat a bit (by dropping some code that's not
necessary any more after that modification).
The runtime PM documentation is updated by Alan Stern (to reflect
the "runtime idle" behavior change).
New trace points for PM QoS are added by Sahara
(<keun-o.park@windriver.com>).
PM QoS documentation is updated by Lan Tianyu.
Code cleanups are made and minor issues are addressed by Bernie
Thompson, Bjorn Helgaas, Julius Werner, and Shuah Khan.
- devfreq updates
New driver for the Exynos5-bus device from Abhilash Kesavan.
Minor cleanups, fixes and MAINTAINERS update from MyungJoo Ham,
Abhilash Kesavan, Paul Bolle, Rajagopal Venkat, and Wei Yongjun.
- OMAP power management updates
Adaptive Voltage Scaling (AVS) SmartReflex voltage control driver
updates from Andrii Tseglytskyi and Nishanth Menon."
* tag 'pm+acpi-3.11-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (162 commits)
cpufreq: Fix cpufreq regression after suspend/resume
ACPI / PM: Fix possible NULL pointer deref in acpi_pm_device_sleep_state()
PM / Sleep: Warn about system time after resume with pm_trace
cpufreq: don't leave stale policy pointer in cdbs->cur_policy
acpi-cpufreq: Add new sysfs attribute freqdomain_cpus
cpufreq: make sure frequency transitions are serialized
ACPI: implement acpi_os_get_timer() according the spec
ACPI / EC: Add HP Folio 13 to ec_dmi_table in order to skip DSDT scan
ACPI: Add CMOS RTC Operation Region handler support
ACPI / processor: Drop unused variable from processor_perflib.c
cpufreq: tegra: call CPUFREQ_POSTCHANGE notfier in error cases
cpufreq: s3c64xx: call CPUFREQ_POSTCHANGE notfier in error cases
cpufreq: omap: call CPUFREQ_POSTCHANGE notfier in error cases
cpufreq: imx6q: call CPUFREQ_POSTCHANGE notfier in error cases
cpufreq: exynos: call CPUFREQ_POSTCHANGE notfier in error cases
cpufreq: dbx500: call CPUFREQ_POSTCHANGE notfier in error cases
cpufreq: davinci: call CPUFREQ_POSTCHANGE notfier in error cases
cpufreq: arm-big-little: call CPUFREQ_POSTCHANGE notfier in error cases
cpufreq: powernow-k8: call CPUFREQ_POSTCHANGE notfier in error cases
cpufreq: pcc: call CPUFREQ_POSTCHANGE notfier in error cases
...
2013-07-03 15:35:40 -06:00
|
|
|
memory->dev.offline = memory->state == MEM_OFFLINE;
|
2013-06-04 13:42:28 -06:00
|
|
|
|
2013-08-20 11:12:58 -06:00
|
|
|
return device_register(&memory->dev);
|
2013-06-04 13:42:28 -06:00
|
|
|
}
|
|
|
|
|
2011-01-20 09:43:34 -07:00
|
|
|
static int init_memory_block(struct memory_block **memory,
|
|
|
|
struct mem_section *section, unsigned long state)
|
2010-10-19 11:44:20 -06:00
|
|
|
{
|
2011-01-20 09:43:34 -07:00
|
|
|
struct memory_block *mem;
|
2010-10-19 11:44:20 -06:00
|
|
|
unsigned long start_pfn;
|
2011-01-20 09:43:34 -07:00
|
|
|
int scn_nr;
|
2010-10-19 11:44:20 -06:00
|
|
|
int ret = 0;
|
|
|
|
|
2011-01-20 09:43:34 -07:00
|
|
|
mem = kzalloc(sizeof(*mem), GFP_KERNEL);
|
2010-10-19 11:44:20 -06:00
|
|
|
if (!mem)
|
|
|
|
return -ENOMEM;
|
|
|
|
|
2011-01-20 09:43:34 -07:00
|
|
|
scn_nr = __section_nr(section);
|
2011-01-20 09:44:29 -07:00
|
|
|
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;
|
2010-10-19 11:44:20 -06:00
|
|
|
mem->state = state;
|
2011-01-20 09:44:29 -07:00
|
|
|
start_pfn = section_nr_to_pfn(mem->start_section_nr);
|
2010-10-19 11:44:20 -06:00
|
|
|
mem->phys_device = arch_get_memory_phys_device(start_pfn);
|
|
|
|
|
2011-01-20 09:43:34 -07:00
|
|
|
ret = register_memory(mem);
|
|
|
|
|
|
|
|
*memory = mem;
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2013-08-20 11:13:03 -06:00
|
|
|
static int add_memory_block(int base_section_nr)
|
2011-01-20 09:43:34 -07:00
|
|
|
{
|
2013-08-20 11:13:03 -06:00
|
|
|
struct memory_block *mem;
|
|
|
|
int i, ret, section_count = 0, section_nr;
|
2011-01-20 09:43:34 -07:00
|
|
|
|
2013-08-20 11:13:03 -06:00
|
|
|
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++;
|
2010-10-19 11:44:20 -06:00
|
|
|
}
|
|
|
|
|
2013-08-20 11:13:03 -06:00
|
|
|
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;
|
2010-10-19 11:44:20 -06:00
|
|
|
}
|
|
|
|
|
2016-01-15 17:56:17 -07:00
|
|
|
static bool is_zone_device_section(struct mem_section *ms)
|
|
|
|
{
|
|
|
|
struct page *page;
|
|
|
|
|
|
|
|
page = sparse_decode_mem_map(ms->section_mem_map, __section_nr(ms));
|
|
|
|
return is_zone_device_page(page);
|
|
|
|
}
|
2013-08-20 11:13:03 -06:00
|
|
|
|
2013-04-29 16:08:22 -06:00
|
|
|
/*
|
|
|
|
* 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)
|
|
|
|
{
|
2013-08-20 11:13:00 -06:00
|
|
|
int ret = 0;
|
|
|
|
struct memory_block *mem;
|
2013-08-20 11:12:57 -06:00
|
|
|
|
2016-01-15 17:56:17 -07:00
|
|
|
if (is_zone_device_section(section))
|
|
|
|
return 0;
|
|
|
|
|
2013-08-20 11:12:57 -06:00
|
|
|
mutex_lock(&mem_sysfs_mutex);
|
|
|
|
|
2013-08-20 11:13:00 -06:00
|
|
|
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;
|
2016-01-14 16:20:21 -07:00
|
|
|
mem->section_count++;
|
2013-08-20 11:13:00 -06:00
|
|
|
}
|
|
|
|
|
|
|
|
if (mem->section_count == sections_per_block)
|
|
|
|
ret = register_mem_sect_under_node(mem, nid);
|
|
|
|
out:
|
|
|
|
mutex_unlock(&mem_sysfs_mutex);
|
2013-08-20 11:12:57 -06:00
|
|
|
return ret;
|
2013-04-29 16:08:22 -06:00
|
|
|
}
|
|
|
|
|
|
|
|
#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() */
|
2013-08-20 11:12:59 -06:00
|
|
|
put_device(&memory->dev);
|
2013-04-29 16:08:22 -06:00
|
|
|
device_unregister(&memory->dev);
|
|
|
|
}
|
|
|
|
|
2016-01-14 16:20:24 -07:00
|
|
|
static int remove_memory_section(unsigned long node_id,
|
2013-04-29 16:08:22 -06:00
|
|
|
struct mem_section *section, int phys_device)
|
2005-10-29 19:16:54 -06:00
|
|
|
{
|
|
|
|
struct memory_block *mem;
|
|
|
|
|
2016-01-15 17:56:17 -07:00
|
|
|
if (is_zone_device_section(section))
|
|
|
|
return 0;
|
|
|
|
|
2010-10-19 11:45:24 -06:00
|
|
|
mutex_lock(&mem_sysfs_mutex);
|
2005-10-29 19:16:54 -06:00
|
|
|
mem = find_memory_block(section);
|
2011-01-20 09:44:29 -07:00
|
|
|
unregister_mem_sect_under_nodes(mem, __section_nr(section));
|
2010-10-19 11:46:19 -06:00
|
|
|
|
|
|
|
mem->section_count--;
|
2013-06-04 13:42:28 -06:00
|
|
|
if (mem->section_count == 0)
|
2011-01-20 09:43:34 -07:00
|
|
|
unregister_memory(mem);
|
2013-06-04 13:42:28 -06:00
|
|
|
else
|
2013-08-20 11:12:59 -06:00
|
|
|
put_device(&mem->dev);
|
2005-10-29 19:16:54 -06:00
|
|
|
|
2010-10-19 11:45:24 -06:00
|
|
|
mutex_unlock(&mem_sysfs_mutex);
|
2005-10-29 19:16:54 -06:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
int unregister_memory_section(struct mem_section *section)
|
|
|
|
{
|
2007-10-16 02:24:11 -06:00
|
|
|
if (!present_section(section))
|
2005-10-29 19:16:54 -06:00
|
|
|
return -EINVAL;
|
|
|
|
|
2016-01-14 16:20:24 -07:00
|
|
|
return remove_memory_section(0, section, 0);
|
2005-10-29 19:16:54 -06:00
|
|
|
}
|
2013-04-29 16:08:22 -06:00
|
|
|
#endif /* CONFIG_MEMORY_HOTREMOVE */
|
2005-10-29 19:16:54 -06:00
|
|
|
|
2013-02-22 17:32:52 -07:00
|
|
|
/* return true if the memory block is offlined, otherwise, return false */
|
|
|
|
bool is_memblock_offlined(struct memory_block *mem)
|
|
|
|
{
|
|
|
|
return mem->state == MEM_OFFLINE;
|
|
|
|
}
|
|
|
|
|
2013-06-04 13:42:28 -06:00
|
|
|
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,
|
2016-03-15 15:56:48 -06:00
|
|
|
&dev_attr_auto_online_blocks.attr,
|
2013-06-04 13:42:28 -06:00
|
|
|
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,
|
|
|
|
};
|
|
|
|
|
2005-10-29 19:16:54 -06:00
|
|
|
/*
|
|
|
|
* Initialize the sysfs support for memory devices...
|
|
|
|
*/
|
|
|
|
int __init memory_dev_init(void)
|
|
|
|
{
|
|
|
|
unsigned int i;
|
|
|
|
int ret;
|
2006-12-06 21:37:29 -07:00
|
|
|
int err;
|
2011-01-20 09:43:34 -07:00
|
|
|
unsigned long block_sz;
|
2005-10-29 19:16:54 -06:00
|
|
|
|
2013-06-04 13:42:28 -06:00
|
|
|
ret = subsys_system_register(&memory_subsys, memory_root_attr_groups);
|
2006-12-06 21:37:29 -07:00
|
|
|
if (ret)
|
|
|
|
goto out;
|
2005-10-29 19:16:54 -06:00
|
|
|
|
2011-01-20 09:43:34 -07:00
|
|
|
block_sz = get_memory_block_size();
|
|
|
|
sections_per_block = block_sz / MIN_MEMORY_BLOCK_SIZE;
|
|
|
|
|
2005-10-29 19:16:54 -06:00
|
|
|
/*
|
|
|
|
* Create entries for memory sections that were found
|
|
|
|
* during boot and have been initialized
|
|
|
|
*/
|
2013-08-20 11:12:57 -06:00
|
|
|
mutex_lock(&mem_sysfs_mutex);
|
2013-08-20 11:13:03 -06:00
|
|
|
for (i = 0; i < NR_MEM_SECTIONS; i += sections_per_block) {
|
|
|
|
err = add_memory_block(i);
|
2006-12-06 21:37:29 -07:00
|
|
|
if (!ret)
|
|
|
|
ret = err;
|
2005-10-29 19:16:54 -06:00
|
|
|
}
|
2013-08-20 11:12:57 -06:00
|
|
|
mutex_unlock(&mem_sysfs_mutex);
|
2005-10-29 19:16:54 -06:00
|
|
|
|
2006-12-06 21:37:29 -07:00
|
|
|
out:
|
|
|
|
if (ret)
|
2008-03-04 17:41:05 -07:00
|
|
|
printk(KERN_ERR "%s() failed: %d\n", __func__, ret);
|
2005-10-29 19:16:54 -06:00
|
|
|
return ret;
|
|
|
|
}
|