linux_dsm_epyc7002/drivers/macintosh/windfarm_core.c

499 lines
11 KiB
C
Raw Normal View History

/*
* Windfarm PowerMac thermal control. Core
*
* (c) Copyright 2005 Benjamin Herrenschmidt, IBM Corp.
* <benh@kernel.crashing.org>
*
* Released under the term of the GNU GPL v2.
*
* This core code tracks the list of sensors & controls, register
* clients, and holds the kernel thread used for control.
*
* TODO:
*
* Add some information about sensor/control type and data format to
* sensors/controls, and have the sysfs attribute stuff be moved
* generically here instead of hard coded in the platform specific
* driver as it us currently
*
* This however requires solving some annoying lifetime issues with
* sysfs which doesn't seem to have lifetime rules for struct attribute,
* I may have to create full features kobjects for every sensor/control
* instead which is a bit of an overkill imho
*/
#include <linux/types.h>
#include <linux/errno.h>
#include <linux/kernel.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 15:04:11 +07:00
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/spinlock.h>
#include <linux/kthread.h>
#include <linux/jiffies.h>
#include <linux/reboot.h>
#include <linux/device.h>
#include <linux/platform_device.h>
#include <linux/mutex.h>
#include <linux/freezer.h>
#include <asm/prom.h>
#include "windfarm.h"
#define VERSION "0.2"
#undef DEBUG
#ifdef DEBUG
#define DBG(args...) printk(args)
#else
#define DBG(args...) do { } while(0)
#endif
static LIST_HEAD(wf_controls);
static LIST_HEAD(wf_sensors);
static DEFINE_MUTEX(wf_lock);
[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 16:16:30 +07:00
static BLOCKING_NOTIFIER_HEAD(wf_client_list);
static int wf_client_count;
static unsigned int wf_overtemp;
static unsigned int wf_overtemp_counter;
struct task_struct *wf_thread;
static struct platform_device wf_platform_device = {
.name = "windfarm",
};
/*
* Utilities & tick thread
*/
static inline void wf_notify(int event, void *param)
{
[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 16:16:30 +07:00
blocking_notifier_call_chain(&wf_client_list, event, param);
}
int wf_critical_overtemp(void)
{
static char * critical_overtemp_path = "/sbin/critical_overtemp";
char *argv[] = { critical_overtemp_path, NULL };
static char *envp[] = { "HOME=/",
"TERM=linux",
"PATH=/sbin:/usr/sbin:/bin:/usr/bin",
NULL };
return call_usermodehelper(critical_overtemp_path,
argv, envp, UMH_WAIT_EXEC);
}
EXPORT_SYMBOL_GPL(wf_critical_overtemp);
static int wf_thread_func(void *data)
{
unsigned long next, delay;
next = jiffies;
DBG("wf: thread started\n");
set_freezable();
while (!kthread_should_stop()) {
try_to_freeze();
if (time_after_eq(jiffies, next)) {
wf_notify(WF_EVENT_TICK, NULL);
if (wf_overtemp) {
wf_overtemp_counter++;
/* 10 seconds overtemp, notify userland */
if (wf_overtemp_counter > 10)
wf_critical_overtemp();
/* 30 seconds, shutdown */
if (wf_overtemp_counter > 30) {
printk(KERN_ERR "windfarm: Overtemp "
"for more than 30"
" seconds, shutting down\n");
machine_power_off();
}
}
next += HZ;
}
delay = next - jiffies;
if (delay <= HZ)
schedule_timeout_interruptible(delay);
}
DBG("wf: thread stopped\n");
return 0;
}
static void wf_start_thread(void)
{
wf_thread = kthread_run(wf_thread_func, NULL, "kwindfarm");
if (IS_ERR(wf_thread)) {
printk(KERN_ERR "windfarm: failed to create thread,err %ld\n",
PTR_ERR(wf_thread));
wf_thread = NULL;
}
}
static void wf_stop_thread(void)
{
if (wf_thread)
kthread_stop(wf_thread);
wf_thread = NULL;
}
/*
* Controls
*/
static void wf_control_release(struct kref *kref)
{
struct wf_control *ct = container_of(kref, struct wf_control, ref);
DBG("wf: Deleting control %s\n", ct->name);
if (ct->ops && ct->ops->release)
ct->ops->release(ct);
else
kfree(ct);
}
static ssize_t wf_show_control(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct wf_control *ctrl = container_of(attr, struct wf_control, attr);
s32 val = 0;
int err;
err = ctrl->ops->get_value(ctrl, &val);
if (err < 0)
return err;
return sprintf(buf, "%d\n", val);
}
/* This is really only for debugging... */
static ssize_t wf_store_control(struct device *dev,
struct device_attribute *attr,
const char *buf, size_t count)
{
struct wf_control *ctrl = container_of(attr, struct wf_control, attr);
int val;
int err;
char *endp;
val = simple_strtoul(buf, &endp, 0);
while (endp < buf + count && (*endp == ' ' || *endp == '\n'))
++endp;
if (endp - buf < count)
return -EINVAL;
err = ctrl->ops->set_value(ctrl, val);
if (err < 0)
return err;
return count;
}
int wf_register_control(struct wf_control *new_ct)
{
struct wf_control *ct;
mutex_lock(&wf_lock);
list_for_each_entry(ct, &wf_controls, link) {
if (!strcmp(ct->name, new_ct->name)) {
printk(KERN_WARNING "windfarm: trying to register"
" duplicate control %s\n", ct->name);
mutex_unlock(&wf_lock);
return -EEXIST;
}
}
kref_init(&new_ct->ref);
list_add(&new_ct->link, &wf_controls);
sysfs_attr_init(&new_ct->attr.attr);
new_ct->attr.attr.name = new_ct->name;
new_ct->attr.attr.mode = 0644;
new_ct->attr.show = wf_show_control;
new_ct->attr.store = wf_store_control;
if (device_create_file(&wf_platform_device.dev, &new_ct->attr))
printk(KERN_WARNING "windfarm: device_create_file failed"
" for %s\n", new_ct->name);
/* the subsystem still does useful work without the file */
DBG("wf: Registered control %s\n", new_ct->name);
wf_notify(WF_EVENT_NEW_CONTROL, new_ct);
mutex_unlock(&wf_lock);
return 0;
}
EXPORT_SYMBOL_GPL(wf_register_control);
void wf_unregister_control(struct wf_control *ct)
{
mutex_lock(&wf_lock);
list_del(&ct->link);
mutex_unlock(&wf_lock);
DBG("wf: Unregistered control %s\n", ct->name);
kref_put(&ct->ref, wf_control_release);
}
EXPORT_SYMBOL_GPL(wf_unregister_control);
struct wf_control * wf_find_control(const char *name)
{
struct wf_control *ct;
mutex_lock(&wf_lock);
list_for_each_entry(ct, &wf_controls, link) {
if (!strcmp(ct->name, name)) {
if (wf_get_control(ct))
ct = NULL;
mutex_unlock(&wf_lock);
return ct;
}
}
mutex_unlock(&wf_lock);
return NULL;
}
EXPORT_SYMBOL_GPL(wf_find_control);
int wf_get_control(struct wf_control *ct)
{
if (!try_module_get(ct->ops->owner))
return -ENODEV;
kref_get(&ct->ref);
return 0;
}
EXPORT_SYMBOL_GPL(wf_get_control);
void wf_put_control(struct wf_control *ct)
{
struct module *mod = ct->ops->owner;
kref_put(&ct->ref, wf_control_release);
module_put(mod);
}
EXPORT_SYMBOL_GPL(wf_put_control);
/*
* Sensors
*/
static void wf_sensor_release(struct kref *kref)
{
struct wf_sensor *sr = container_of(kref, struct wf_sensor, ref);
DBG("wf: Deleting sensor %s\n", sr->name);
if (sr->ops && sr->ops->release)
sr->ops->release(sr);
else
kfree(sr);
}
static ssize_t wf_show_sensor(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct wf_sensor *sens = container_of(attr, struct wf_sensor, attr);
s32 val = 0;
int err;
err = sens->ops->get_value(sens, &val);
if (err < 0)
return err;
return sprintf(buf, "%d.%03d\n", FIX32TOPRINT(val));
}
int wf_register_sensor(struct wf_sensor *new_sr)
{
struct wf_sensor *sr;
mutex_lock(&wf_lock);
list_for_each_entry(sr, &wf_sensors, link) {
if (!strcmp(sr->name, new_sr->name)) {
printk(KERN_WARNING "windfarm: trying to register"
" duplicate sensor %s\n", sr->name);
mutex_unlock(&wf_lock);
return -EEXIST;
}
}
kref_init(&new_sr->ref);
list_add(&new_sr->link, &wf_sensors);
sysfs_attr_init(&new_sr->attr.attr);
new_sr->attr.attr.name = new_sr->name;
new_sr->attr.attr.mode = 0444;
new_sr->attr.show = wf_show_sensor;
new_sr->attr.store = NULL;
if (device_create_file(&wf_platform_device.dev, &new_sr->attr))
printk(KERN_WARNING "windfarm: device_create_file failed"
" for %s\n", new_sr->name);
/* the subsystem still does useful work without the file */
DBG("wf: Registered sensor %s\n", new_sr->name);
wf_notify(WF_EVENT_NEW_SENSOR, new_sr);
mutex_unlock(&wf_lock);
return 0;
}
EXPORT_SYMBOL_GPL(wf_register_sensor);
void wf_unregister_sensor(struct wf_sensor *sr)
{
mutex_lock(&wf_lock);
list_del(&sr->link);
mutex_unlock(&wf_lock);
DBG("wf: Unregistered sensor %s\n", sr->name);
wf_put_sensor(sr);
}
EXPORT_SYMBOL_GPL(wf_unregister_sensor);
struct wf_sensor * wf_find_sensor(const char *name)
{
struct wf_sensor *sr;
mutex_lock(&wf_lock);
list_for_each_entry(sr, &wf_sensors, link) {
if (!strcmp(sr->name, name)) {
if (wf_get_sensor(sr))
sr = NULL;
mutex_unlock(&wf_lock);
return sr;
}
}
mutex_unlock(&wf_lock);
return NULL;
}
EXPORT_SYMBOL_GPL(wf_find_sensor);
int wf_get_sensor(struct wf_sensor *sr)
{
if (!try_module_get(sr->ops->owner))
return -ENODEV;
kref_get(&sr->ref);
return 0;
}
EXPORT_SYMBOL_GPL(wf_get_sensor);
void wf_put_sensor(struct wf_sensor *sr)
{
struct module *mod = sr->ops->owner;
kref_put(&sr->ref, wf_sensor_release);
module_put(mod);
}
EXPORT_SYMBOL_GPL(wf_put_sensor);
/*
* Client & notification
*/
int wf_register_client(struct notifier_block *nb)
{
int rc;
struct wf_control *ct;
struct wf_sensor *sr;
mutex_lock(&wf_lock);
[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 16:16:30 +07:00
rc = blocking_notifier_chain_register(&wf_client_list, nb);
if (rc != 0)
goto bail;
wf_client_count++;
list_for_each_entry(ct, &wf_controls, link)
wf_notify(WF_EVENT_NEW_CONTROL, ct);
list_for_each_entry(sr, &wf_sensors, link)
wf_notify(WF_EVENT_NEW_SENSOR, sr);
if (wf_client_count == 1)
wf_start_thread();
bail:
mutex_unlock(&wf_lock);
return rc;
}
EXPORT_SYMBOL_GPL(wf_register_client);
int wf_unregister_client(struct notifier_block *nb)
{
mutex_lock(&wf_lock);
[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 16:16:30 +07:00
blocking_notifier_chain_unregister(&wf_client_list, nb);
wf_client_count++;
if (wf_client_count == 0)
wf_stop_thread();
mutex_unlock(&wf_lock);
return 0;
}
EXPORT_SYMBOL_GPL(wf_unregister_client);
void wf_set_overtemp(void)
{
mutex_lock(&wf_lock);
wf_overtemp++;
if (wf_overtemp == 1) {
printk(KERN_WARNING "windfarm: Overtemp condition detected !\n");
wf_overtemp_counter = 0;
wf_notify(WF_EVENT_OVERTEMP, NULL);
}
mutex_unlock(&wf_lock);
}
EXPORT_SYMBOL_GPL(wf_set_overtemp);
void wf_clear_overtemp(void)
{
mutex_lock(&wf_lock);
WARN_ON(wf_overtemp == 0);
if (wf_overtemp == 0) {
mutex_unlock(&wf_lock);
return;
}
wf_overtemp--;
if (wf_overtemp == 0) {
printk(KERN_WARNING "windfarm: Overtemp condition cleared !\n");
wf_notify(WF_EVENT_NORMALTEMP, NULL);
}
mutex_unlock(&wf_lock);
}
EXPORT_SYMBOL_GPL(wf_clear_overtemp);
int wf_is_overtemp(void)
{
return (wf_overtemp != 0);
}
EXPORT_SYMBOL_GPL(wf_is_overtemp);
static int __init windfarm_core_init(void)
{
DBG("wf: core loaded\n");
/* Don't register on old machines that use therm_pm72 for now */
if (of_machine_is_compatible("PowerMac7,2") ||
of_machine_is_compatible("PowerMac7,3") ||
of_machine_is_compatible("RackMac3,1"))
return -ENODEV;
platform_device_register(&wf_platform_device);
return 0;
}
static void __exit windfarm_core_exit(void)
{
BUG_ON(wf_client_count != 0);
DBG("wf: core unloaded\n");
platform_device_unregister(&wf_platform_device);
}
module_init(windfarm_core_init);
module_exit(windfarm_core_exit);
MODULE_AUTHOR("Benjamin Herrenschmidt <benh@kernel.crashing.org>");
MODULE_DESCRIPTION("Core component of PowerMac thermal control");
MODULE_LICENSE("GPL");