Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mingo/linux-2.6-sched-devel

ec965350 · Linus Torvalds <[email protected]> · 2008-04-21 15:40:24 -07:00

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mingo/linux-2.6-sched-devel: (62 commits)
  sched: build fix
  sched: better rt-group documentation
  sched: features fix
  sched: /debug/sched_features
  sched: add SCHED_FEAT_DEADLINE
  sched: debug: show a weight tree
  sched: fair: weight calculations
  sched: fair-group: de-couple load-balancing from the rb-trees
  sched: fair-group scheduling vs latency
  sched: rt-group: optimize dequeue_rt_stack
  sched: debug: add some debug code to handle the full hierarchy
  sched: fair-group: SMP-nice for group scheduling
  sched, cpuset: customize sched domains, core
  sched, cpuset: customize sched domains, docs
  sched: prepatory code movement
  sched: rt: multi level group constraints
  sched: task_group hierarchy
  sched: fix the task_group hierarchy for UID grouping
  sched: allow the group scheduler to have multiple levels
  sched: mix tasks and groups
  ...

Commit: ec965350bb98bd291eb34f6ecddfdcfc36da1e6e
Parents: 5f033bb9 · 486fdae2

Merge commit. Changes below are compared with the first parent: 5f033bb9.

Changes

68 files changed · +3165 −1005

File	Status	Add	Del	Content
Documentation/cpusets.txt	modified	+70	−2	View file
Documentation/scheduler/sched-rt-group.txt	modified	+153	−35	View file
arch/x86/Kconfig	modified	+3	−0	View file
arch/x86/kernel/acpi/cstate.c	modified	+2	−2	View file
arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c	modified	+14	−14	View file
arch/x86/kernel/cpu/cpufreq/powernow-k8.c	modified	+17	−15	View file
arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c	modified	+7	−6	View file
arch/x86/kernel/cpu/cpufreq/speedstep-ich.c	modified	+10	−10	View file
arch/x86/kernel/cpu/intel_cacheinfo.c	modified	+59	−33	View file
arch/x86/kernel/cpu/mcheck/mce_amd_64.c	modified	+23	−23	View file
arch/x86/kernel/io_apic_64.c	modified	+1	−1	View file
arch/x86/kernel/microcode.c	modified	+8	−8	View file
arch/x86/kernel/reboot.c	modified	+1	−1	View file
arch/x86/kernel/setup.c	modified	+27	−1	View file
arch/x86/mm/numa_64.c	modified	+2	−1	View file
arch/x86/oprofile/nmi_int.c	modified	+27	−22	View file
drivers/acpi/processor_throttling.c	modified	+5	−5	View file
drivers/base/cpu.c	modified	+48	−0	View file
drivers/base/node.c	modified	+22	−7	View file
drivers/base/topology.c	modified	+34	−7	View file
drivers/firmware/dcdbas.c	modified	+2	−2	View file
drivers/pci/pci-driver.c	modified	+6	−3	View file
drivers/pci/pci-sysfs.c	modified	+18	−2	View file
drivers/pci/probe.c	modified	+23	−4	View file
include/asm-alpha/topology.h	modified	+1	−2	View file
include/asm-frv/topology.h	modified	+1	−3	View file
include/asm-generic/topology.h	modified	+14	−0	View file
include/asm-ia64/topology.h	modified	+6	−1	View file
include/asm-powerpc/topology.h	modified	+1	−2	View file
include/asm-sh/topology.h	modified	+1	−1	View file
include/asm-x86/topology.h	modified	+14	−8	View file
include/linux/bitmap.h	modified	+1	−0	View file
include/linux/cpumask.h	modified	+22	−3	View file
include/linux/cpuset.h	modified	+7	−6	View file
include/linux/init_task.h	modified	+3	−0	View file
include/linux/ktime.h	modified	+6	−0	View file
include/linux/sched.h	modified	+48	−8	View file
include/linux/sysdev.h	modified	+11	−6	View file
include/linux/topology.h	modified	+8	−38	View file
init/Kconfig	modified	+7	−0	View file
init/main.c	modified	+23	−1	View file
kernel/compat.c	modified	+1	−1	View file
kernel/cpu.c	modified	+3	−3	View file
kernel/cpuset.c	modified	+80	−20	View file
kernel/irq/chip.c	modified	+1	−1	View file
kernel/kmod.c	modified	+1	−1	View file
kernel/kthread.c	modified	+1	−0	View file
kernel/latencytop.c	modified	+17	−10	View file
kernel/rcupreempt.c	modified	+2	−2	View file
kernel/rcutorture.c	modified	+9	−6	View file
kernel/sched.c	modified	+1576	−352	View file
kernel/sched_debug.c	modified	+32	−4	View file
kernel/sched_fair.c	modified	+377	−203	View file
kernel/sched_features.h	added	+10	−0	View file
kernel/sched_rt.c	modified	+176	−51	View file
kernel/sched_stats.h	modified	+6	−2	View file
kernel/softirq.c	modified	+41	−22	View file
kernel/stop_machine.c	modified	+1	−1	View file
kernel/sysctl.c	modified	+2	−13	View file
kernel/time/tick-sched.c	modified	+0	−5	View file
kernel/user.c	modified	+29	−1	View file
lib/bitmap.c	modified	+16	−0	View file
mm/allocpercpu.c	modified	+2	−1	View file
mm/page_alloc.c	modified	+3	−3	View file
mm/pdflush.c	modified	+2	−2	View file
mm/slab.c	modified	+2	−3	View file
mm/vmscan.c	modified	+8	−10	View file
net/sunrpc/svc.c	modified	+11	−5	View file

Only the first 600 diff lines are shown. Download the complete patch.

Documentation/cpusets.txt

View file

diff --git a/Documentation/cpusets.txt b/Documentation/cpusets.txt
index ad2bb3b..aa854b9 100644
--- a/Documentation/cpusets.txt
+++ b/Documentation/cpusets.txt
@@ -8,6 +8,7 @@ Portions Copyright (c) 2004-2006 Silicon Graphics, Inc.
 Modified by Paul Jackson <[email protected]>
 Modified by Christoph Lameter <[email protected]>
 Modified by Paul Menage <[email protected]>
+Modified by Hidetoshi Seto <[email protected]>
 
 CONTENTS:
 =========
@@ -20,7 +21,8 @@ CONTENTS:
   1.5 What is memory_pressure ?
   1.6 What is memory spread ?
   1.7 What is sched_load_balance ?
-  1.8 How do I use cpusets ?
+  1.8 What is sched_relax_domain_level ?
+  1.9 How do I use cpusets ?
 2. Usage Examples and Syntax
   2.1 Basic Usage
   2.2 Adding/removing cpus
@@ -497,7 +499,73 @@ the cpuset code to update these sched domains, it compares the new
 partition requested with the current, and updates its sched domains,
 removing the old and adding the new, for each change.
 
-1.8 How do I use cpusets ?
+
+1.8 What is sched_relax_domain_level ?
+--------------------------------------
+
+In sched domain, the scheduler migrates tasks in 2 ways; periodic load
+balance on tick, and at time of some schedule events.
+
+When a task is woken up, scheduler try to move the task on idle CPU.
+For example, if a task A running on CPU X activates another task B
+on the same CPU X, and if CPU Y is X's sibling and performing idle,
+then scheduler migrate task B to CPU Y so that task B can start on
+CPU Y without waiting task A on CPU X.
+
+And if a CPU run out of tasks in its runqueue, the CPU try to pull
+extra tasks from other busy CPUs to help them before it is going to
+be idle.
+
+Of course it takes some searching cost to find movable tasks and/or
+idle CPUs, the scheduler might not search all CPUs in the domain
+everytime.  In fact, in some architectures, the searching ranges on
+events are limited in the same socket or node where the CPU locates,
+while the load balance on tick searchs all.
+
+For example, assume CPU Z is relatively far from CPU X.  Even if CPU Z
+is idle while CPU X and the siblings are busy, scheduler can't migrate
+woken task B from X to Z since it is out of its searching range.
+As the result, task B on CPU X need to wait task A or wait load balance
+on the next tick.  For some applications in special situation, waiting
+1 tick may be too long.
+
+The 'sched_relax_domain_level' file allows you to request changing
+this searching range as you like.  This file takes int value which
+indicates size of searching range in levels ideally as follows,
+otherwise initial value -1 that indicates the cpuset has no request.
+
+  -1  : no request. use system default or follow request of others.
+   0  : no search.
+   1  : search siblings (hyperthreads in a core).
+   2  : search cores in a package.
+   3  : search cpus in a node [= system wide on non-NUMA system]
+ ( 4  : search nodes in a chunk of node [on NUMA system] )
+ ( 5~ : search system wide [on NUMA system])
+
+This file is per-cpuset and affect the sched domain where the cpuset
+belongs to.  Therefore if the flag 'sched_load_balance' of a cpuset
+is disabled, then 'sched_relax_domain_level' have no effect since
+there is no sched domain belonging the cpuset.
+
+If multiple cpusets are overlapping and hence they form a single sched
+domain, the largest value among those is used.  Be careful, if one
+requests 0 and others are -1 then 0 is used.
+
+Note that modifying this file will have both good and bad effects,
+and whether it is acceptable or not will be depend on your situation.
+Don't modify this file if you are not sure.
+
+If your situation is:
+ - The migration costs between each cpu can be assumed considerably
+   small(for you) due to your special application's behavior or
+   special hardware support for CPU cache etc.
+ - The searching cost doesn't have impact(for you) or you can make
+   the searching cost enough small by managing cpuset to compact etc.
+ - The latency is required even it sacrifices cache hit rate etc.
+then increasing 'sched_relax_domain_level' would benefit you.
+
+
+1.9 How do I use cpusets ?
 --------------------------
 
 In order to minimize the impact of cpusets on critical kernel

Documentation/scheduler/sched-rt-group.txt

View file

diff --git a/Documentation/scheduler/sched-rt-group.txt b/Documentation/scheduler/sched-rt-group.txt
index 1c6332f..14f901f 100644
--- a/Documentation/scheduler/sched-rt-group.txt
+++ b/Documentation/scheduler/sched-rt-group.txt
@@ -1,59 +1,177 @@
+				Real-Time group scheduling
+				--------------------------
 
+CONTENTS
+========
 
-Real-Time group scheduling.
+1. Overview
+  1.1 The problem
+  1.2 The solution
+2. The interface
+  2.1 System-wide settings
+  2.2 Default behaviour
+  2.3 Basis for grouping tasks
+3. Future plans
 
-The problem space:
 
-In order to schedule multiple groups of realtime tasks each group must
-be assigned a fixed portion of the CPU time available. Without a minimum
-guarantee a realtime group can obviously fall short. A fuzzy upper limit
-is of no use since it cannot be relied upon. Which leaves us with just
-the single fixed portion.
+1. Overview
+===========
 
-CPU time is divided by means of specifying how much time can be spent
-running in a given period. Say a frame fixed realtime renderer must
-deliver 25 frames a second, which yields a period of 0.04s. Now say
-it will also have to play some music and respond to input, leaving it
-with around 80% for the graphics. We can then give this group a runtime
-of 0.8 * 0.04s = 0.032s.
 
-This way the graphics group will have a 0.04s period with a 0.032s runtime
-limit.
+1.1 The problem
+---------------
 
-Now if the audio thread needs to refill the DMA buffer every 0.005s, but
-needs only about 3% CPU time to do so, it can do with a 0.03 * 0.005s
-= 0.00015s.
+Realtime scheduling is all about determinism, a group has to be able to rely on
+the amount of bandwidth (eg. CPU time) being constant. In order to schedule
+multiple groups of realtime tasks, each group must be assigned a fixed portion
+of the CPU time available.  Without a minimum guarantee a realtime group can
+obviously fall short. A fuzzy upper limit is of no use since it cannot be
+relied upon. Which leaves us with just the single fixed portion.
 
+1.2 The solution
+----------------
 
-The Interface:
+CPU time is divided by means of specifying how much time can be spent running
+in a given period. We allocate this "run time" for each realtime group which
+the other realtime groups will not be permitted to use.
 
-system wide:
+Any time not allocated to a realtime group will be used to run normal priority
+tasks (SCHED_OTHER). Any allocated run time not used will also be picked up by
+SCHED_OTHER.
 
-/proc/sys/kernel/sched_rt_period_ms
-/proc/sys/kernel/sched_rt_runtime_us
+Let's consider an example: a frame fixed realtime renderer must deliver 25
+frames a second, which yields a period of 0.04s per frame. Now say it will also
+have to play some music and respond to input, leaving it with around 80% CPU
+time dedicated for the graphics. We can then give this group a run time of 0.8
+* 0.04s = 0.032s.
 
-CONFIG_FAIR_USER_SCHED
+This way the graphics group will have a 0.04s period with a 0.032s run time
+limit. Now if the audio thread needs to refill the DMA buffer every 0.005s, but
+needs only about 3% CPU time to do so, it can do with a 0.03 * 0.005s =
+0.00015s. So this group can be scheduled with a period of 0.005s and a run time
+of 0.00015s.
 
-/sys/kernel/uids/<uid>/cpu_rt_runtime_us
+The remaining CPU time will be used for user input and other tass. Because
+realtime tasks have explicitly allocated the CPU time they need to perform
+their tasks, buffer underruns in the graphocs or audio can be eliminated.
 
-or
+NOTE: the above example is not fully implemented as of yet (2.6.25). We still
+lack an EDF scheduler to make non-uniform periods usable.
 
-CONFIG_FAIR_CGROUP_SCHED
 
-/cgroup/<cgroup>/cpu.rt_runtime_us
+2. The Interface
+================
 
-[ time is specified in us because the interface is s32; this gives an
-  operating range of ~35m to 1us ]
 
-The period takes values in [ 1, INT_MAX ], runtime in [ -1, INT_MAX - 1 ].
+2.1 System wide settings
+------------------------
 
-A runtime of -1 specifies runtime == period, ie. no limit.
+The system wide settings are configured under the /proc virtual file system:
 
-New groups get the period from /proc/sys/kernel/sched_rt_period_us and
-a runtime of 0.
+/proc/sys/kernel/sched_rt_period_us:
+  The scheduling period that is equivalent to 100% CPU bandwidth
 
-Settings are constrained to:
+/proc/sys/kernel/sched_rt_runtime_us:
+  A global limit on how much time realtime scheduling may use.  Even without
+  CONFIG_RT_GROUP_SCHED enabled, this will limit time reserved to realtime
+  processes. With CONFIG_RT_GROUP_SCHED it signifies the total bandwidth
+  available to all realtime groups.
+
+  * Time is specified in us because the interface is s32. This gives an
+    operating range from 1us to about 35 minutes.
+  * sched_rt_period_us takes values from 1 to INT_MAX.
+  * sched_rt_runtime_us takes values from -1 to (INT_MAX - 1).
+  * A run time of -1 specifies runtime == period, ie. no limit.
+
+
+2.2 Default behaviour
+---------------------
+
+The default values for sched_rt_period_us (1000000 or 1s) and
+sched_rt_runtime_us (950000 or 0.95s).  This gives 0.05s to be used by
+SCHED_OTHER (non-RT tasks). These defaults were chosen so that a run-away
+realtime tasks will not lock up the machine but leave a little time to recover
+it.  By setting runtime to -1 you'd get the old behaviour back.
+
+By default all bandwidth is assigned to the root group and new groups get the
+period from /proc/sys/kernel/sched_rt_period_us and a run time of 0. If you
+want to assign bandwidth to another group, reduce the root group's bandwidth
+and assign some or all of the difference to another group.
+
+Realtime group scheduling means you have to assign a portion of total CPU
+bandwidth to the group before it will accept realtime tasks. Therefore you will
+not be able to run realtime tasks as any user other than root until you have
+done that, even if the user has the rights to run processes with realtime
+priority!
+
+
+2.3 Basis for grouping tasks
+----------------------------
+
+There are two compile-time settings for allocating CPU bandwidth. These are
+configured using the "Basis for grouping tasks" multiple choice menu under
+General setup > Group CPU Scheduler:
+
+a. CONFIG_USER_SCHED (aka "Basis for grouping tasks" =  "user id")
+
+This lets you use the virtual files under
+"/sys/kernel/uids/<uid>/cpu_rt_runtime_us" to control he CPU time reserved for
+each user .
+
+The other option is:
+
+.o CONFIG_CGROUP_SCHED (aka "Basis for grouping tasks" = "Control groups")
+
+This uses the /cgroup virtual file system and "/cgroup/<cgroup>/cpu.rt_runtime_us"
+to control the CPU time reserved for each control group instead.
+
+For more information on working with control groups, you should read
+Documentation/cgroups.txt as well.
+
+Group settings are checked against the following limits in order to keep the configuration
+schedulable:
 
    \Sum_{i} runtime_{i} / global_period <= global_runtime / global_period
 
-in order to keep the configuration schedulable.
+For now, this can be simplified to just the following (but see Future plans):
+
+   \Sum_{i} runtime_{i} <= global_runtime
+
+
+3. Future plans
+===============
+
+There is work in progress to make the scheduling period for each group
+("/sys/kernel/uids/<uid>/cpu_rt_period_us" or
+"/cgroup/<cgroup>/cpu.rt_period_us" respectively) configurable as well.
+
+The constraint on the period is that a subgroup must have a smaller or
+equal period to its parent. But realistically its not very useful _yet_
+as its prone to starvation without deadline scheduling.
+
+Consider two sibling groups A and B; both have 50% bandwidth, but A's
+period is twice the length of B's.
+
+* group A: period=100000us, runtime=10000us
+	- this runs for 0.01s once every 0.1s
+
+* group B: period= 50000us, runtime=10000us
+	- this runs for 0.01s twice every 0.1s (or once every 0.05 sec).
+
+This means that currently a while (1) loop in A will run for the full period of
+B and can starve B's tasks (assuming they are of lower priority) for a whole
+period.
+
+The next project will be SCHED_EDF (Earliest Deadline First scheduling) to bring
+full deadline scheduling to the linux kernel. Deadline scheduling the above
+groups and treating end of the period as a deadline will ensure that they both
+get their allocated time.
+
+Implementing SCHED_EDF might take a while to complete. Priority Inheritance is
+the biggest challenge as the current linux PI infrastructure is geared towards
+the limited static priority levels 0-139. With deadline scheduling you need to
+do deadline inheritance (since priority is inversely proportional to the
+deadline delta (deadline - now).
+
+This means the whole PI machinery will have to be reworked - and that is one of
+the most complex pieces of code we have.

arch/x86/Kconfig

View file

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 07cf771..87a693c 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -117,6 +117,9 @@ config ARCH_HAS_CPU_RELAX
 config HAVE_SETUP_PER_CPU_AREA
 	def_bool X86_64 || (X86_SMP && !X86_VOYAGER)
 
+config HAVE_CPUMASK_OF_CPU_MAP
+	def_bool X86_64_SMP
+
 config ARCH_HIBERNATION_POSSIBLE
 	def_bool y
 	depends on !SMP || !X86_VOYAGER

arch/x86/kernel/acpi/cstate.c

View file

diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c
index 9366fb6..c2502eb 100644
--- a/arch/x86/kernel/acpi/cstate.c
+++ b/arch/x86/kernel/acpi/cstate.c
@@ -91,7 +91,7 @@ int acpi_processor_ffh_cstate_probe(unsigned int cpu,
 
 	/* Make sure we are running on right CPU */
 	saved_mask = current->cpus_allowed;
-	retval = set_cpus_allowed(current, cpumask_of_cpu(cpu));
+	retval = set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu));
 	if (retval)
 		return -1;
 
@@ -128,7 +128,7 @@ int acpi_processor_ffh_cstate_probe(unsigned int cpu,
 		 cx->address);
 
 out:
-	set_cpus_allowed(current, saved_mask);
+	set_cpus_allowed_ptr(current, &saved_mask);
 	return retval;
 }
 EXPORT_SYMBOL_GPL(acpi_processor_ffh_cstate_probe);

arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c

View file

diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
index a962dcb..e2d870d 100644
--- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
+++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
@@ -192,9 +192,9 @@ static void drv_read(struct drv_cmd *cmd)
 	cpumask_t saved_mask = current->cpus_allowed;
 	cmd->val = 0;
 
-	set_cpus_allowed(current, cmd->mask);
+	set_cpus_allowed_ptr(current, &cmd->mask);
 	do_drv_read(cmd);
-	set_cpus_allowed(current, saved_mask);
+	set_cpus_allowed_ptr(current, &saved_mask);
 }
 
 static void drv_write(struct drv_cmd *cmd)
@@ -203,30 +203,30 @@ static void drv_write(struct drv_cmd *cmd)
 	unsigned int i;
 
 	for_each_cpu_mask(i, cmd->mask) {
-		set_cpus_allowed(current, cpumask_of_cpu(i));
+		set_cpus_allowed_ptr(current, &cpumask_of_cpu(i));
 		do_drv_write(cmd);
 	}
 
-	set_cpus_allowed(current, saved_mask);
+	set_cpus_allowed_ptr(current, &saved_mask);
 	return;
 }
 
-static u32 get_cur_val(cpumask_t mask)
+static u32 get_cur_val(const cpumask_t *mask)
 {
 	struct acpi_processor_performance *perf;
 	struct drv_cmd cmd;
 
-	if (unlikely(cpus_empty(mask)))
+	if (unlikely(cpus_empty(*mask)))
 		return 0;
 
-	switch (per_cpu(drv_data, first_cpu(mask))->cpu_feature) {
+	switch (per_cpu(drv_data, first_cpu(*mask))->cpu_feature) {
 	case SYSTEM_INTEL_MSR_CAPABLE:
 		cmd.type = SYSTEM_INTEL_MSR_CAPABLE;
 		cmd.addr.msr.reg = MSR_IA32_PERF_STATUS;
 		break;
 	case SYSTEM_IO_CAPABLE:
 		cmd.type = SYSTEM_IO_CAPABLE;
-		perf = per_cpu(drv_data, first_cpu(mask))->acpi_data;
+		perf = per_cpu(drv_data, first_cpu(*mask))->acpi_data;
 		cmd.addr.io.port = perf->control_register.address;
 		cmd.addr.io.bit_width = perf->control_register.bit_width;
 		break;
@@ -234,7 +234,7 @@ static u32 get_cur_val(cpumask_t mask)
 		return 0;
 	}
 
-	cmd.mask = mask;
+	cmd.mask = *mask;
 
 	drv_read(&cmd);
 
@@ -271,7 +271,7 @@ static unsigned int get_measured_perf(unsigned int cpu)
 	unsigned int retval;
 
 	saved_mask = current->cpus_allowed;
-	set_cpus_allowed(current, cpumask_of_cpu(cpu));
+	set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu));
 	if (get_cpu() != cpu) {
 		/* We were not able to run on requested processor */
 		put_cpu();
@@ -329,7 +329,7 @@ static unsigned int get_measured_perf(unsigned int cpu)
 	retval = per_cpu(drv_data, cpu)->max_freq * perf_percent / 100;
 
 	put_cpu();
-	set_cpus_allowed(current, saved_mask);
+	set_cpus_allowed_ptr(current, &saved_mask);
 
 	dprintk("cpu %d: performance percent %d\n", cpu, perf_percent);
 	return retval;
@@ -347,13 +347,13 @@ static unsigned int get_cur_freq_on_cpu(unsigned int cpu)
 		return 0;
 	}
 
-	freq = extract_freq(get_cur_val(cpumask_of_cpu(cpu)), data);
+	freq = extract_freq(get_cur_val(&cpumask_of_cpu(cpu)), data);
 	dprintk("cur freq = %u\n", freq);
 
 	return freq;
 }
 
-static unsigned int check_freqs(cpumask_t mask, unsigned int freq,
+static unsigned int check_freqs(const cpumask_t *mask, unsigned int freq,
 				struct acpi_cpufreq_data *data)
 {
 	unsigned int cur_freq;
@@ -449,7 +449,7 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy,
 	drv_write(&cmd);
 
 	if (acpi_pstate_strict) {
-		if (!check_freqs(cmd.mask, freqs.new, data)) {
+		if (!check_freqs(&cmd.mask, freqs.new, data)) {
 			dprintk("acpi_cpufreq_target failed (%d)\n",
 				policy->cpu);
 			return -EAGAIN;

arch/x86/kernel/cpu/cpufreq/powernow-k8.c

View file

diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
index c99d59d..46d4034 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
@@ -478,12 +478,12 @@ static int core_voltage_post_transition(struct powernow_k8_data *data, u32 reqvi
 
 static int check_supported_cpu(unsigned int cpu)
 {
-	cpumask_t oldmask = CPU_MASK_ALL;
+	cpumask_t oldmask;
 	u32 eax, ebx, ecx, edx;
 	unsigned int rc = 0;
 
 	oldmask = current->cpus_allowed;
-	set_cpus_allowed(current, cpumask_of_cpu(cpu));
+	set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu));
 
 	if (smp_processor_id() != cpu) {
 		printk(KERN_ERR PFX "limiting to cpu %u failed\n", cpu);
@@ -528,7 +528,7 @@ static int check_supported_cpu(unsigned int cpu)
 	rc = 1;
 
 out:
-	set_cpus_allowed(current, oldmask);
+	set_cpus_allowed_ptr(current, &oldmask);
 	return rc;
 }
 
@@ -1015,7 +1015,7 @@ static int transition_frequency_pstate(struct powernow_k8_data *data, unsigned i
 /* Driver entry point to switch to the target frequency */
 static int powernowk8_target(struct cpufreq_policy *pol, unsigned targfreq, unsigned relation)
 {
-	cpumask_t oldmask = CPU_MASK_ALL;
+	cpumask_t oldmask;
 	struct powernow_k8_data *data = per_cpu(powernow_data, pol->cpu);
 	u32 checkfid;
 	u32 checkvid;
@@ -1030,7 +1030,7 @@ static int powernowk8_target(struct cpufreq_policy *pol, unsigned targfreq, unsi
 
 	/* only run on specific CPU from here on */
 	oldmask = current->cpus_allowed;
-	set_cpus_allowed(current, cpumask_of_cpu(pol->cpu));
+	set_cpus_allowed_ptr(current, &cpumask_of_cpu(pol->cpu));
 
 	if (smp_processor_id() != pol->cpu) {
 		printk(KERN_ERR PFX "limiting to cpu %u failed\n", pol->cpu);
@@ -1085,7 +1085,7 @@ static int powernowk8_target(struct cpufreq_policy *pol, unsigned targfreq, unsi
 	ret = 0;
 
 err_out:
-	set_cpus_allowed(current, oldmask);
+	set_cpus_allowed_ptr(current, &oldmask);
 	return ret;
 }
 
@@ -1104,7 +1104,7 @@ static int powernowk8_verify(struct cpufreq_policy *pol)
 static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
 {
 	struct powernow_k8_data *data;
-	cpumask_t oldmask = CPU_MASK_ALL;
+	cpumask_t oldmask;
 	int rc;
 
 	if (!cpu_online(pol->cpu))
@@ -1145,7 +1145,7 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
 
 	/* only run on specific CPU from here on */
 	oldmask = current->cpus_allowed;
-	set_cpus_allowed(current, cpumask_of_cpu(pol->cpu));
+	set_cpus_allowed_ptr(current, &cpumask_of_cpu(pol->cpu));
 
 	if (smp_processor_id() != pol->cpu) {
 		printk(KERN_ERR PFX "limiting to cpu %u failed\n", pol->cpu);
@@ -1164,7 +1164,7 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
 		fidvid_msr_init();
 
 	/* run on any CPU again */
-	set_cpus_allowed(current, oldmask);
+	set_cpus_allowed_ptr(current, &oldmask);
 
 	if (cpu_family == CPU_HW_PSTATE)
 		pol->cpus = cpumask_of_cpu(pol->cpu);
@@ -1205,7 +1205,7 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
 	return 0;
 
 err_out:
-	set_cpus_allowed(current, oldmask);
+	set_cpus_allowed_ptr(current, &oldmask);
 	powernow_k8_cpu_exit_acpi(data);
 
 	kfree(data);
@@ -1242,10 +1242,11 @@ static unsigned int powernowk8_get (unsigned int cpu)
 	if (!data)
 		return -EINVAL;
 
-	set_cpus_allowed(current, cpumask_of_cpu(cpu));
+	set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu));
 	if (smp_processor_id() != cpu) {
-		printk(KERN_ERR PFX "limiting to CPU %d failed in powernowk8_get\n", cpu);
-		set_cpus_allowed(current, oldmask);
+		printk(KERN_ERR PFX
+			"limiting to CPU %d failed in powernowk8_get\n", cpu);
+		set_cpus_allowed_ptr(current, &oldmask);
 		return 0;
 	}
 
@@ -1253,13 +1254,14 @@ static unsigned int powernowk8_get (unsigned int cpu)
 		goto out;
 
 	if (cpu_family == CPU_HW_PSTATE)
-		khz = find_khz_freq_from_pstate(data->powernow_table, data->currpstate);
+		khz = find_khz_freq_from_pstate(data->powernow_table,
+						data->currpstate);
 	else
 		khz = find_khz_freq_from_fid(data->currfid);
 
 
 out:
-	set_cpus_allowed(current, oldmask);
+	set_cpus_allowed_ptr(current, &oldmask);
 	return khz;
 }
 

arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c

View file

diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c b/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c
index 3031f11..908dd34 100644
--- a/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c
+++ b/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c
@@ -315,7 +315,7 @@ static unsigned int get_cur_freq(unsigned int cpu)
 	cpumask_t saved_mask;
 
 	saved_mask = current->cpus_allowed;
-	set_cpus_allowed(current, cpumask_of_cpu(cpu));
+	set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu));
 	if (smp_processor_id() != cpu)
 		return 0;
 
@@ -333,7 +333,7 @@ static unsigned int get_cur_freq(unsigned int cpu)
 		clock_freq = extract_clock(l, cpu, 1);
 	}
 
-	set_cpus_allowed(current, saved_mask);
+	set_cpus_allowed_ptr(current, &saved_mask);
 	return clock_freq;
 }
 