summaryrefslogtreecommitdiffstats
path: root/drivers/cpufreq
diff options
context:
space:
mode:
authorAlan Stern <stern@rowland.harvard.edu>2006-03-27 01:16:30 -0800
committerLinus Torvalds <torvalds@g5.osdl.org>2006-03-27 08:44:50 -0800
commite041c683412d5bf44dc2b109053e3b837b71742d (patch)
tree9d271066ef379da0c0fb3b8cb4137abd5d2ebba0 /drivers/cpufreq
parent76b81e2b0e2241accebcc68e126bc5ab958661b9 (diff)
downloadlinux-e041c683412d5bf44dc2b109053e3b837b71742d.tar.gz
linux-e041c683412d5bf44dc2b109053e3b837b71742d.tar.bz2
linux-e041c683412d5bf44dc2b109053e3b837b71742d.zip
[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>
Diffstat (limited to 'drivers/cpufreq')
-rw-r--r--drivers/cpufreq/cpufreq.c61
1 files changed, 26 insertions, 35 deletions
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index aed80e6aec6d..9b6ae7dc8b8a 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -52,9 +52,8 @@ static void handle_update(void *data);
* changes to devices when the CPU clock speed changes.
* The mutex locks both lists.
*/
-static struct notifier_block *cpufreq_policy_notifier_list;
-static struct notifier_block *cpufreq_transition_notifier_list;
-static DECLARE_RWSEM (cpufreq_notifier_rwsem);
+static BLOCKING_NOTIFIER_HEAD(cpufreq_policy_notifier_list);
+static BLOCKING_NOTIFIER_HEAD(cpufreq_transition_notifier_list);
static LIST_HEAD(cpufreq_governor_list);
@@ -247,8 +246,6 @@ void cpufreq_notify_transition(struct cpufreq_freqs *freqs, unsigned int state)
dprintk("notification %u of frequency transition to %u kHz\n",
state, freqs->new);
- down_read(&cpufreq_notifier_rwsem);
-
policy = cpufreq_cpu_data[freqs->cpu];
switch (state) {
@@ -266,20 +263,19 @@ void cpufreq_notify_transition(struct cpufreq_freqs *freqs, unsigned int state)
freqs->old = policy->cur;
}
}
- notifier_call_chain(&cpufreq_transition_notifier_list,
- CPUFREQ_PRECHANGE, freqs);
+ blocking_notifier_call_chain(&cpufreq_transition_notifier_list,
+ CPUFREQ_PRECHANGE, freqs);
adjust_jiffies(CPUFREQ_PRECHANGE, freqs);
break;
case CPUFREQ_POSTCHANGE:
adjust_jiffies(CPUFREQ_POSTCHANGE, freqs);
- notifier_call_chain(&cpufreq_transition_notifier_list,
- CPUFREQ_POSTCHANGE, freqs);
+ blocking_notifier_call_chain(&cpufreq_transition_notifier_list,
+ CPUFREQ_POSTCHANGE, freqs);
if (likely(policy) && likely(policy->cpu == freqs->cpu))
policy->cur = freqs->new;
break;
}
- up_read(&cpufreq_notifier_rwsem);
}
EXPORT_SYMBOL_GPL(cpufreq_notify_transition);
@@ -1007,7 +1003,7 @@ static int cpufreq_suspend(struct sys_device * sysdev, pm_message_t pmsg)
freqs.old = cpu_policy->cur;
freqs.new = cur_freq;
- notifier_call_chain(&cpufreq_transition_notifier_list,
+ blocking_notifier_call_chain(&cpufreq_transition_notifier_list,
CPUFREQ_SUSPENDCHANGE, &freqs);
adjust_jiffies(CPUFREQ_SUSPENDCHANGE, &freqs);
@@ -1088,7 +1084,8 @@ static int cpufreq_resume(struct sys_device * sysdev)
freqs.old = cpu_policy->cur;
freqs.new = cur_freq;
- notifier_call_chain(&cpufreq_transition_notifier_list,
+ blocking_notifier_call_chain(
+ &cpufreq_transition_notifier_list,
CPUFREQ_RESUMECHANGE, &freqs);
adjust_jiffies(CPUFREQ_RESUMECHANGE, &freqs);
@@ -1125,24 +1122,24 @@ static struct sysdev_driver cpufreq_sysdev_driver = {
* changes in cpufreq policy.
*
* This function may sleep, and has the same return conditions as
- * notifier_chain_register.
+ * blocking_notifier_chain_register.
*/
int cpufreq_register_notifier(struct notifier_block *nb, unsigned int list)
{
int ret;
- down_write(&cpufreq_notifier_rwsem);
switch (list) {
case CPUFREQ_TRANSITION_NOTIFIER:
- ret = notifier_chain_register(&cpufreq_transition_notifier_list, nb);
+ ret = blocking_notifier_chain_register(
+ &cpufreq_transition_notifier_list, nb);
break;
case CPUFREQ_POLICY_NOTIFIER:
- ret = notifier_chain_register(&cpufreq_policy_notifier_list, nb);
+ ret = blocking_notifier_chain_register(
+ &cpufreq_policy_notifier_list, nb);
break;
default:
ret = -EINVAL;
}
- up_write(&cpufreq_notifier_rwsem);
return ret;
}
@@ -1157,24 +1154,24 @@ EXPORT_SYMBOL(cpufreq_register_notifier);
* Remove a driver from the CPU frequency notifier list.
*
* This function may sleep, and has the same return conditions as
- * notifier_chain_unregister.
+ * blocking_notifier_chain_unregister.
*/
int cpufreq_unregister_notifier(struct notifier_block *nb, unsigned int list)
{
int ret;
- down_write(&cpufreq_notifier_rwsem);
switch (list) {
case CPUFREQ_TRANSITION_NOTIFIER:
- ret = notifier_chain_unregister(&cpufreq_transition_notifier_list, nb);
+ ret = blocking_notifier_chain_unregister(
+ &cpufreq_transition_notifier_list, nb);
break;
case CPUFREQ_POLICY_NOTIFIER:
- ret = notifier_chain_unregister(&cpufreq_policy_notifier_list, nb);
+ ret = blocking_notifier_chain_unregister(
+ &cpufreq_policy_notifier_list, nb);
break;
default:
ret = -EINVAL;
}
- up_write(&cpufreq_notifier_rwsem);
return ret;
}
@@ -1346,29 +1343,23 @@ static int __cpufreq_set_policy(struct cpufreq_policy *data, struct cpufreq_poli
if (ret)
goto error_out;
- down_read(&cpufreq_notifier_rwsem);
-
/* adjust if necessary - all reasons */
- notifier_call_chain(&cpufreq_policy_notifier_list, CPUFREQ_ADJUST,
- policy);
+ blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
+ CPUFREQ_ADJUST, policy);
/* adjust if necessary - hardware incompatibility*/
- notifier_call_chain(&cpufreq_policy_notifier_list, CPUFREQ_INCOMPATIBLE,
- policy);
+ blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
+ CPUFREQ_INCOMPATIBLE, policy);
/* verify the cpu speed can be set within this limit,
which might be different to the first one */
ret = cpufreq_driver->verify(policy);
- if (ret) {
- up_read(&cpufreq_notifier_rwsem);
+ if (ret)
goto error_out;
- }
/* notification of the new policy */
- notifier_call_chain(&cpufreq_policy_notifier_list, CPUFREQ_NOTIFY,
- policy);
-
- up_read(&cpufreq_notifier_rwsem);
+ blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
+ CPUFREQ_NOTIFY, policy);
data->min = policy->min;
data->max = policy->max;