OpenCloudOS-Kernel/arch/s390/kernel/topology.c

367 lines
7.5 KiB
C
Raw Normal View History

/*
* Copyright IBM Corp. 2007
* Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>
*/
#define KMSG_COMPONENT "cpu"
#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/init.h>
#include <linux/device.h>
#include <linux/bootmem.h>
#include <linux/sched.h>
#include <linux/workqueue.h>
#include <linux/cpu.h>
#include <linux/smp.h>
#include <linux/cpuset.h>
#include <asm/delay.h>
[S390] Vertical cpu management. If vertical cpu polarization is active then the hypervisor will dispatch certain cpus for a longer time than other cpus for maximum performance. For example if a guest would have three virtual cpus, each of them with a share of 33 percent, then in case of vertical cpu polarization all of the processing time would be combined to a single cpu which would run all the time, while the other two cpus would get nearly no cpu time. There are three different types of vertical cpus: high, medium and low. Low cpus hardly get any real cpu time, while high cpus get a full real cpu. Medium cpus get something in between. In order to switch between the two possible modes (default is horizontal) a 0 for horizontal polarization or a 1 for vertical polarization must be written to the dispatching sysfs attribute: /sys/devices/system/cpu/dispatching The polarization of each single cpu can be figured out by the polarization sysfs attribute of each cpu: /sys/devices/system/cpu/cpuX/polarization horizontal, vertical:high, vertical:medium, vertical:low or unknown. When switching polarization the polarization attribute may contain the value unknown until the configuration change is done and the kernel has figured out the new polarization of each cpu. Note that running a system with different types of vertical cpus may result in significant performance regressions. If possible only one type of vertical cpus should be used. All other cpus should be offlined. Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
2008-04-17 13:46:13 +08:00
#define PTF_HORIZONTAL (0UL)
#define PTF_VERTICAL (1UL)
#define PTF_CHECK (2UL)
struct mask_info {
struct mask_info *next;
unsigned char id;
cpumask_t mask;
};
static int topology_enabled = 1;
static void topology_work_fn(struct work_struct *work);
static struct sysinfo_15_1_x *tl_info;
static struct timer_list topology_timer;
static void set_topology_timer(void);
static DECLARE_WORK(topology_work, topology_work_fn);
/* topology_lock protects the core linked list */
static DEFINE_SPINLOCK(topology_lock);
static struct mask_info core_info;
cpumask_t cpu_core_map[NR_CPUS];
unsigned char cpu_core_id[NR_CPUS];
#ifdef CONFIG_SCHED_BOOK
static struct mask_info book_info;
cpumask_t cpu_book_map[NR_CPUS];
unsigned char cpu_book_id[NR_CPUS];
#endif
static cpumask_t cpu_group_map(struct mask_info *info, unsigned int cpu)
{
cpumask_t mask;
cpumask_clear(&mask);
if (!topology_enabled || !MACHINE_HAS_TOPOLOGY) {
cpumask_copy(&mask, cpumask_of(cpu));
return mask;
}
while (info) {
if (cpumask_test_cpu(cpu, &info->mask)) {
mask = info->mask;
break;
}
info = info->next;
}
if (cpumask_empty(&mask))
cpumask_copy(&mask, cpumask_of(cpu));
return mask;
}
static struct mask_info *add_cpus_to_mask(struct topology_cpu *tl_cpu,
struct mask_info *book,
struct mask_info *core,
int z10)
{
unsigned int cpu;
for (cpu = find_first_bit(&tl_cpu->mask[0], TOPOLOGY_CPU_BITS);
cpu < TOPOLOGY_CPU_BITS;
cpu = find_next_bit(&tl_cpu->mask[0], TOPOLOGY_CPU_BITS, cpu + 1))
{
unsigned int rcpu, lcpu;
rcpu = TOPOLOGY_CPU_BITS - 1 - cpu + tl_cpu->origin;
for_each_present_cpu(lcpu) {
if (cpu_logical_map(lcpu) != rcpu)
continue;
#ifdef CONFIG_SCHED_BOOK
cpumask_set_cpu(lcpu, &book->mask);
cpu_book_id[lcpu] = book->id;
#endif
cpumask_set_cpu(lcpu, &core->mask);
if (z10) {
cpu_core_id[lcpu] = rcpu;
core = core->next;
} else {
cpu_core_id[lcpu] = core->id;
}
smp_cpu_polarization[lcpu] = tl_cpu->pp;
}
}
return core;
}
static void clear_masks(void)
{
struct mask_info *info;
info = &core_info;
while (info) {
cpumask_clear(&info->mask);
info = info->next;
}
#ifdef CONFIG_SCHED_BOOK
info = &book_info;
while (info) {
cpumask_clear(&info->mask);
info = info->next;
}
#endif
}
static union topology_entry *next_tle(union topology_entry *tle)
{
if (!tle->nl)
return (union topology_entry *)((struct topology_cpu *)tle + 1);
return (union topology_entry *)((struct topology_container *)tle + 1);
}
static void tl_to_cores(struct sysinfo_15_1_x *info)
{
#ifdef CONFIG_SCHED_BOOK
struct mask_info *book = &book_info;
struct cpuid cpu_id;
#else
struct mask_info *book = NULL;
#endif
struct mask_info *core = &core_info;
union topology_entry *tle, *end;
int z10 = 0;
#ifdef CONFIG_SCHED_BOOK
get_cpu_id(&cpu_id);
z10 = cpu_id.machine == 0x2097 || cpu_id.machine == 0x2098;
#endif
spin_lock_irq(&topology_lock);
clear_masks();
[S390] Vertical cpu management. If vertical cpu polarization is active then the hypervisor will dispatch certain cpus for a longer time than other cpus for maximum performance. For example if a guest would have three virtual cpus, each of them with a share of 33 percent, then in case of vertical cpu polarization all of the processing time would be combined to a single cpu which would run all the time, while the other two cpus would get nearly no cpu time. There are three different types of vertical cpus: high, medium and low. Low cpus hardly get any real cpu time, while high cpus get a full real cpu. Medium cpus get something in between. In order to switch between the two possible modes (default is horizontal) a 0 for horizontal polarization or a 1 for vertical polarization must be written to the dispatching sysfs attribute: /sys/devices/system/cpu/dispatching The polarization of each single cpu can be figured out by the polarization sysfs attribute of each cpu: /sys/devices/system/cpu/cpuX/polarization horizontal, vertical:high, vertical:medium, vertical:low or unknown. When switching polarization the polarization attribute may contain the value unknown until the configuration change is done and the kernel has figured out the new polarization of each cpu. Note that running a system with different types of vertical cpus may result in significant performance regressions. If possible only one type of vertical cpus should be used. All other cpus should be offlined. Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
2008-04-17 13:46:13 +08:00
tle = info->tle;
end = (union topology_entry *)((unsigned long)info + info->length);
while (tle < end) {
#ifdef CONFIG_SCHED_BOOK
if (z10) {
switch (tle->nl) {
case 1:
book = book->next;
book->id = tle->container.id;
break;
case 0:
core = add_cpus_to_mask(&tle->cpu, book, core, z10);
break;
default:
clear_masks();
goto out;
}
tle = next_tle(tle);
continue;
}
#endif
switch (tle->nl) {
#ifdef CONFIG_SCHED_BOOK
case 2:
book = book->next;
book->id = tle->container.id;
break;
#endif
case 1:
core = core->next;
core->id = tle->container.id;
break;
case 0:
add_cpus_to_mask(&tle->cpu, book, core, z10);
break;
default:
clear_masks();
goto out;
}
tle = next_tle(tle);
}
out:
spin_unlock_irq(&topology_lock);
}
[S390] Vertical cpu management. If vertical cpu polarization is active then the hypervisor will dispatch certain cpus for a longer time than other cpus for maximum performance. For example if a guest would have three virtual cpus, each of them with a share of 33 percent, then in case of vertical cpu polarization all of the processing time would be combined to a single cpu which would run all the time, while the other two cpus would get nearly no cpu time. There are three different types of vertical cpus: high, medium and low. Low cpus hardly get any real cpu time, while high cpus get a full real cpu. Medium cpus get something in between. In order to switch between the two possible modes (default is horizontal) a 0 for horizontal polarization or a 1 for vertical polarization must be written to the dispatching sysfs attribute: /sys/devices/system/cpu/dispatching The polarization of each single cpu can be figured out by the polarization sysfs attribute of each cpu: /sys/devices/system/cpu/cpuX/polarization horizontal, vertical:high, vertical:medium, vertical:low or unknown. When switching polarization the polarization attribute may contain the value unknown until the configuration change is done and the kernel has figured out the new polarization of each cpu. Note that running a system with different types of vertical cpus may result in significant performance regressions. If possible only one type of vertical cpus should be used. All other cpus should be offlined. Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
2008-04-17 13:46:13 +08:00
static void topology_update_polarization_simple(void)
{
int cpu;
mutex_lock(&smp_cpu_state_mutex);
for_each_possible_cpu(cpu)
[S390] Vertical cpu management. If vertical cpu polarization is active then the hypervisor will dispatch certain cpus for a longer time than other cpus for maximum performance. For example if a guest would have three virtual cpus, each of them with a share of 33 percent, then in case of vertical cpu polarization all of the processing time would be combined to a single cpu which would run all the time, while the other two cpus would get nearly no cpu time. There are three different types of vertical cpus: high, medium and low. Low cpus hardly get any real cpu time, while high cpus get a full real cpu. Medium cpus get something in between. In order to switch between the two possible modes (default is horizontal) a 0 for horizontal polarization or a 1 for vertical polarization must be written to the dispatching sysfs attribute: /sys/devices/system/cpu/dispatching The polarization of each single cpu can be figured out by the polarization sysfs attribute of each cpu: /sys/devices/system/cpu/cpuX/polarization horizontal, vertical:high, vertical:medium, vertical:low or unknown. When switching polarization the polarization attribute may contain the value unknown until the configuration change is done and the kernel has figured out the new polarization of each cpu. Note that running a system with different types of vertical cpus may result in significant performance regressions. If possible only one type of vertical cpus should be used. All other cpus should be offlined. Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
2008-04-17 13:46:13 +08:00
smp_cpu_polarization[cpu] = POLARIZATION_HRZ;
mutex_unlock(&smp_cpu_state_mutex);
}
static int ptf(unsigned long fc)
{
int rc;
asm volatile(
" .insn rre,0xb9a20000,%1,%1\n"
" ipm %0\n"
" srl %0,28\n"
: "=d" (rc)
[S390] Vertical cpu management. If vertical cpu polarization is active then the hypervisor will dispatch certain cpus for a longer time than other cpus for maximum performance. For example if a guest would have three virtual cpus, each of them with a share of 33 percent, then in case of vertical cpu polarization all of the processing time would be combined to a single cpu which would run all the time, while the other two cpus would get nearly no cpu time. There are three different types of vertical cpus: high, medium and low. Low cpus hardly get any real cpu time, while high cpus get a full real cpu. Medium cpus get something in between. In order to switch between the two possible modes (default is horizontal) a 0 for horizontal polarization or a 1 for vertical polarization must be written to the dispatching sysfs attribute: /sys/devices/system/cpu/dispatching The polarization of each single cpu can be figured out by the polarization sysfs attribute of each cpu: /sys/devices/system/cpu/cpuX/polarization horizontal, vertical:high, vertical:medium, vertical:low or unknown. When switching polarization the polarization attribute may contain the value unknown until the configuration change is done and the kernel has figured out the new polarization of each cpu. Note that running a system with different types of vertical cpus may result in significant performance regressions. If possible only one type of vertical cpus should be used. All other cpus should be offlined. Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
2008-04-17 13:46:13 +08:00
: "d" (fc) : "cc");
return rc;
}
int topology_set_cpu_management(int fc)
{
int cpu;
int rc;
if (!MACHINE_HAS_TOPOLOGY)
[S390] Vertical cpu management. If vertical cpu polarization is active then the hypervisor will dispatch certain cpus for a longer time than other cpus for maximum performance. For example if a guest would have three virtual cpus, each of them with a share of 33 percent, then in case of vertical cpu polarization all of the processing time would be combined to a single cpu which would run all the time, while the other two cpus would get nearly no cpu time. There are three different types of vertical cpus: high, medium and low. Low cpus hardly get any real cpu time, while high cpus get a full real cpu. Medium cpus get something in between. In order to switch between the two possible modes (default is horizontal) a 0 for horizontal polarization or a 1 for vertical polarization must be written to the dispatching sysfs attribute: /sys/devices/system/cpu/dispatching The polarization of each single cpu can be figured out by the polarization sysfs attribute of each cpu: /sys/devices/system/cpu/cpuX/polarization horizontal, vertical:high, vertical:medium, vertical:low or unknown. When switching polarization the polarization attribute may contain the value unknown until the configuration change is done and the kernel has figured out the new polarization of each cpu. Note that running a system with different types of vertical cpus may result in significant performance regressions. If possible only one type of vertical cpus should be used. All other cpus should be offlined. Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
2008-04-17 13:46:13 +08:00
return -EOPNOTSUPP;
if (fc)
rc = ptf(PTF_VERTICAL);
else
rc = ptf(PTF_HORIZONTAL);
if (rc)
return -EBUSY;
for_each_possible_cpu(cpu)
[S390] Vertical cpu management. If vertical cpu polarization is active then the hypervisor will dispatch certain cpus for a longer time than other cpus for maximum performance. For example if a guest would have three virtual cpus, each of them with a share of 33 percent, then in case of vertical cpu polarization all of the processing time would be combined to a single cpu which would run all the time, while the other two cpus would get nearly no cpu time. There are three different types of vertical cpus: high, medium and low. Low cpus hardly get any real cpu time, while high cpus get a full real cpu. Medium cpus get something in between. In order to switch between the two possible modes (default is horizontal) a 0 for horizontal polarization or a 1 for vertical polarization must be written to the dispatching sysfs attribute: /sys/devices/system/cpu/dispatching The polarization of each single cpu can be figured out by the polarization sysfs attribute of each cpu: /sys/devices/system/cpu/cpuX/polarization horizontal, vertical:high, vertical:medium, vertical:low or unknown. When switching polarization the polarization attribute may contain the value unknown until the configuration change is done and the kernel has figured out the new polarization of each cpu. Note that running a system with different types of vertical cpus may result in significant performance regressions. If possible only one type of vertical cpus should be used. All other cpus should be offlined. Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
2008-04-17 13:46:13 +08:00
smp_cpu_polarization[cpu] = POLARIZATION_UNKNWN;
return rc;
}
static void update_cpu_core_map(void)
{
unsigned long flags;
int cpu;
spin_lock_irqsave(&topology_lock, flags);
for_each_possible_cpu(cpu) {
cpu_core_map[cpu] = cpu_group_map(&core_info, cpu);
#ifdef CONFIG_SCHED_BOOK
cpu_book_map[cpu] = cpu_group_map(&book_info, cpu);
#endif
}
spin_unlock_irqrestore(&topology_lock, flags);
}
void store_topology(struct sysinfo_15_1_x *info)
{
#ifdef CONFIG_SCHED_BOOK
int rc;
rc = stsi(info, 15, 1, 3);
if (rc != -ENOSYS)
return;
#endif
stsi(info, 15, 1, 2);
}
int arch_update_cpu_topology(void)
{
struct sysinfo_15_1_x *info = tl_info;
cpu: convert 'cpu' and 'machinecheck' sysdev_class to a regular subsystem This moves the 'cpu sysdev_class' over to a regular 'cpu' subsystem and converts the devices to regular devices. The sysdev drivers are implemented as subsystem interfaces now. After all sysdev classes are ported to regular driver core entities, the sysdev implementation will be entirely removed from the kernel. Userspace relies on events and generic sysfs subsystem infrastructure from sysdev devices, which are made available with this conversion. Cc: Haavard Skinnemoen <hskinnemoen@gmail.com> Cc: Hans-Christian Egtvedt <egtvedt@samfundet.no> Cc: Tony Luck <tony.luck@intel.com> Cc: Fenghua Yu <fenghua.yu@intel.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: "David S. Miller" <davem@davemloft.net> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Borislav Petkov <bp@amd64.org> Cc: Tigran Aivazian <tigran@aivazian.fsnet.co.uk> Cc: Len Brown <lenb@kernel.org> Cc: Zhang Rui <rui.zhang@intel.com> Cc: Dave Jones <davej@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Russell King <rmk+kernel@arm.linux.org.uk> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: "Rafael J. Wysocki" <rjw@sisk.pl> Cc: "Srivatsa S. Bhat" <srivatsa.bhat@linux.vnet.ibm.com> Signed-off-by: Kay Sievers <kay.sievers@vrfy.org> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2011-12-22 06:29:42 +08:00
struct device *dev;
int cpu;
if (!MACHINE_HAS_TOPOLOGY) {
update_cpu_core_map();
[S390] Vertical cpu management. If vertical cpu polarization is active then the hypervisor will dispatch certain cpus for a longer time than other cpus for maximum performance. For example if a guest would have three virtual cpus, each of them with a share of 33 percent, then in case of vertical cpu polarization all of the processing time would be combined to a single cpu which would run all the time, while the other two cpus would get nearly no cpu time. There are three different types of vertical cpus: high, medium and low. Low cpus hardly get any real cpu time, while high cpus get a full real cpu. Medium cpus get something in between. In order to switch between the two possible modes (default is horizontal) a 0 for horizontal polarization or a 1 for vertical polarization must be written to the dispatching sysfs attribute: /sys/devices/system/cpu/dispatching The polarization of each single cpu can be figured out by the polarization sysfs attribute of each cpu: /sys/devices/system/cpu/cpuX/polarization horizontal, vertical:high, vertical:medium, vertical:low or unknown. When switching polarization the polarization attribute may contain the value unknown until the configuration change is done and the kernel has figured out the new polarization of each cpu. Note that running a system with different types of vertical cpus may result in significant performance regressions. If possible only one type of vertical cpus should be used. All other cpus should be offlined. Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
2008-04-17 13:46:13 +08:00
topology_update_polarization_simple();
return 0;
[S390] Vertical cpu management. If vertical cpu polarization is active then the hypervisor will dispatch certain cpus for a longer time than other cpus for maximum performance. For example if a guest would have three virtual cpus, each of them with a share of 33 percent, then in case of vertical cpu polarization all of the processing time would be combined to a single cpu which would run all the time, while the other two cpus would get nearly no cpu time. There are three different types of vertical cpus: high, medium and low. Low cpus hardly get any real cpu time, while high cpus get a full real cpu. Medium cpus get something in between. In order to switch between the two possible modes (default is horizontal) a 0 for horizontal polarization or a 1 for vertical polarization must be written to the dispatching sysfs attribute: /sys/devices/system/cpu/dispatching The polarization of each single cpu can be figured out by the polarization sysfs attribute of each cpu: /sys/devices/system/cpu/cpuX/polarization horizontal, vertical:high, vertical:medium, vertical:low or unknown. When switching polarization the polarization attribute may contain the value unknown until the configuration change is done and the kernel has figured out the new polarization of each cpu. Note that running a system with different types of vertical cpus may result in significant performance regressions. If possible only one type of vertical cpus should be used. All other cpus should be offlined. Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
2008-04-17 13:46:13 +08:00
}
store_topology(info);
tl_to_cores(info);
update_cpu_core_map();
for_each_online_cpu(cpu) {
cpu: convert 'cpu' and 'machinecheck' sysdev_class to a regular subsystem This moves the 'cpu sysdev_class' over to a regular 'cpu' subsystem and converts the devices to regular devices. The sysdev drivers are implemented as subsystem interfaces now. After all sysdev classes are ported to regular driver core entities, the sysdev implementation will be entirely removed from the kernel. Userspace relies on events and generic sysfs subsystem infrastructure from sysdev devices, which are made available with this conversion. Cc: Haavard Skinnemoen <hskinnemoen@gmail.com> Cc: Hans-Christian Egtvedt <egtvedt@samfundet.no> Cc: Tony Luck <tony.luck@intel.com> Cc: Fenghua Yu <fenghua.yu@intel.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: "David S. Miller" <davem@davemloft.net> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Borislav Petkov <bp@amd64.org> Cc: Tigran Aivazian <tigran@aivazian.fsnet.co.uk> Cc: Len Brown <lenb@kernel.org> Cc: Zhang Rui <rui.zhang@intel.com> Cc: Dave Jones <davej@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Russell King <rmk+kernel@arm.linux.org.uk> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: "Rafael J. Wysocki" <rjw@sisk.pl> Cc: "Srivatsa S. Bhat" <srivatsa.bhat@linux.vnet.ibm.com> Signed-off-by: Kay Sievers <kay.sievers@vrfy.org> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2011-12-22 06:29:42 +08:00
dev = get_cpu_device(cpu);
kobject_uevent(&dev->kobj, KOBJ_CHANGE);
}
return 1;
}
[S390] cpu topology: Fix possible deadlock. When we get a notification that cpu topology changed, we schedule a work struct which just calls arch_reinit_sched_domains. This function in turn calls get_online_cpus() which results int the lockdep warning below. After all it turnded out that it's not legal to call get_online_cpus() from the context of a multi-threaded work queue. It could deadlock this way: process 0 (events/cpu-x): -> run_workqueue -> removes my work_struct from the work queue -> calls work_struct->fn -> get_online_cpus() -> locks on cpu_hotplug.lock since process 1 below is doing cpu hotplug process 1: -> cpu_down (for cpu-x) -> cpu_hotplug_begin (holds cpu_hotplug.lock now) -> cpu-x dead -> notifier_call_chain with CPU_DEAD -> cleanup_workqueue_thread -> flush_cpu_workqueue (succeeds) -> kthread_stop for events/cpu-x -> now kthread_stop waits for my work_struct to complete from within process 0. -> dead. A single threaded workqueue wouldn't have such problems, however there is no such common queue available and it's not worth to create one for the very rare calls to arch_reinit_sched_domains. So we just create a kernel thread from our work struct which calls arch_reinit_sched_domains and are done with it. Thanks to Oleg Nesterov and Peter Zijlstra for helping me figuring out that this isn't a false positive lockdep warning: ======================================================= [ INFO: possible circular locking dependency detected ] 2.6.25-03562-g3dc5063-dirty #12 ------------------------------------------------------- events/3/14 is trying to acquire lock: (&cpu_hotplug.lock){--..}, at: [<0000000000076094>] get_online_cpus+0x50/0x78 but task is already holding lock: (topology_work){--..}, at: [<0000000000059cde>] run_workqueue+0x106/0x278 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #2 (topology_work){--..}: [<000000000006fc74>] __lock_acquire+0x1010/0x111c [<000000000006fe40>] lock_acquire+0xc0/0xf8 [<0000000000059d48>] run_workqueue+0x170/0x278 [<0000000000059edc>] worker_thread+0x8c/0xf0 [<000000000005f5bc>] kthread+0x68/0xa0 [<000000000001a33e>] kernel_thread_starter+0x6/0xc [<000000000001a338>] kernel_thread_starter+0x0/0xc -> #1 (events){--..}: [<000000000006fc74>] __lock_acquire+0x1010/0x111c [<000000000006fe40>] lock_acquire+0xc0/0xf8 [<000000000005a23c>] cleanup_workqueue_thread+0x60/0xa8 [<00000000003b2ab8>] workqueue_cpu_callback+0xbc/0x170 [<00000000003bba80>] notifier_call_chain+0x5c/0xa4 [<00000000000655a2>] __raw_notifier_call_chain+0x26/0x38 [<00000000000655e2>] raw_notifier_call_chain+0x2e/0x40 [<0000000000075e00>] cpu_down+0x228/0x31c [<00000000003b1dd8>] store_online+0x64/0xb8 [<00000000001e7128>] sysdev_store+0x48/0x58 [<0000000000121cd2>] sysfs_write_file+0x126/0x1c0 [<00000000000c1944>] vfs_write+0xb0/0x15c [<00000000000c20e6>] sys_write+0x56/0x88 [<0000000000027a68>] sys32_write+0x34/0x4c [<0000000000023f70>] sysc_noemu+0x10/0x16 [<0000000077f3f186>] 0x77f3f186 -> #0 (&cpu_hotplug.lock){--..}: [<000000000006fa84>] __lock_acquire+0xe20/0x111c [<000000000006fe40>] lock_acquire+0xc0/0xf8 [<00000000003b701c>] mutex_lock_nested+0xd0/0x364 [<0000000000076094>] get_online_cpus+0x50/0x78 [<000000000003a03e>] arch_reinit_sched_domains+0x26/0x58 [<000000000002700e>] topology_work_fn+0x26/0x34 [<0000000000059d4e>] run_workqueue+0x176/0x278 [<0000000000059edc>] worker_thread+0x8c/0xf0 [<000000000005f5bc>] kthread+0x68/0xa0 [<000000000001a33e>] kernel_thread_starter+0x6/0xc [<000000000001a338>] kernel_thread_starter+0x0/0xc other info that might help us debug this: 2 locks held by events/3/14: #0: (events){--..}, at: [<0000000000059cde>] run_workqueue+0x106/0x278 #1: (topology_work){--..}, at: [<0000000000059cde>] run_workqueue+0x106/0x278 stack backtrace: CPU: 3 Not tainted 2.6.25-03562-g3dc5063-dirty #12 Process events/3 (pid: 14, task: 000000002fb04038, ksp: 000000002fb0bd70) 0400000000000000 000000002fb0ba40 0000000000000002 0000000000000000 000000002fb0bae0 000000002fb0ba58 000000002fb0ba58 0000000000016488 0000000000000000 000000002fb0bd70 0000000000000000 0000000000000000 000000002fb0ba40 000000000000000c 000000002fb0ba40 000000002fb0bab0 00000000003c99e0 0000000000016488 000000002fb0ba40 000000002fb0ba90 Call Trace: ([<00000000000163fc>] show_trace+0x138/0x158) [<00000000000164e2>] show_stack+0xc6/0xf8 [<0000000000016624>] dump_stack+0xb0/0xc0 [<000000000006cd36>] print_circular_bug_tail+0xa2/0xb4 [<000000000006fa84>] __lock_acquire+0xe20/0x111c [<000000000006fe40>] lock_acquire+0xc0/0xf8 [<00000000003b701c>] mutex_lock_nested+0xd0/0x364 [<0000000000076094>] get_online_cpus+0x50/0x78 [<000000000003a03e>] arch_reinit_sched_domains+0x26/0x58 [<000000000002700e>] topology_work_fn+0x26/0x34 [<0000000000059d4e>] run_workqueue+0x176/0x278 [<0000000000059edc>] worker_thread+0x8c/0xf0 [<000000000005f5bc>] kthread+0x68/0xa0 [<000000000001a33e>] kernel_thread_starter+0x6/0xc [<000000000001a338>] kernel_thread_starter+0x0/0xc INFO: lockdep is turned off. Cc: Oleg Nesterov <oleg@tv-sign.ru> Cc: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2008-04-30 19:38:41 +08:00
static void topology_work_fn(struct work_struct *work)
{
rebuild_sched_domains();
}
[S390] Vertical cpu management. If vertical cpu polarization is active then the hypervisor will dispatch certain cpus for a longer time than other cpus for maximum performance. For example if a guest would have three virtual cpus, each of them with a share of 33 percent, then in case of vertical cpu polarization all of the processing time would be combined to a single cpu which would run all the time, while the other two cpus would get nearly no cpu time. There are three different types of vertical cpus: high, medium and low. Low cpus hardly get any real cpu time, while high cpus get a full real cpu. Medium cpus get something in between. In order to switch between the two possible modes (default is horizontal) a 0 for horizontal polarization or a 1 for vertical polarization must be written to the dispatching sysfs attribute: /sys/devices/system/cpu/dispatching The polarization of each single cpu can be figured out by the polarization sysfs attribute of each cpu: /sys/devices/system/cpu/cpuX/polarization horizontal, vertical:high, vertical:medium, vertical:low or unknown. When switching polarization the polarization attribute may contain the value unknown until the configuration change is done and the kernel has figured out the new polarization of each cpu. Note that running a system with different types of vertical cpus may result in significant performance regressions. If possible only one type of vertical cpus should be used. All other cpus should be offlined. Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
2008-04-17 13:46:13 +08:00
void topology_schedule_update(void)
{
schedule_work(&topology_work);
}
static void topology_timer_fn(unsigned long ignored)
{
[S390] Vertical cpu management. If vertical cpu polarization is active then the hypervisor will dispatch certain cpus for a longer time than other cpus for maximum performance. For example if a guest would have three virtual cpus, each of them with a share of 33 percent, then in case of vertical cpu polarization all of the processing time would be combined to a single cpu which would run all the time, while the other two cpus would get nearly no cpu time. There are three different types of vertical cpus: high, medium and low. Low cpus hardly get any real cpu time, while high cpus get a full real cpu. Medium cpus get something in between. In order to switch between the two possible modes (default is horizontal) a 0 for horizontal polarization or a 1 for vertical polarization must be written to the dispatching sysfs attribute: /sys/devices/system/cpu/dispatching The polarization of each single cpu can be figured out by the polarization sysfs attribute of each cpu: /sys/devices/system/cpu/cpuX/polarization horizontal, vertical:high, vertical:medium, vertical:low or unknown. When switching polarization the polarization attribute may contain the value unknown until the configuration change is done and the kernel has figured out the new polarization of each cpu. Note that running a system with different types of vertical cpus may result in significant performance regressions. If possible only one type of vertical cpus should be used. All other cpus should be offlined. Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
2008-04-17 13:46:13 +08:00
if (ptf(PTF_CHECK))
topology_schedule_update();
set_topology_timer();
}
static void set_topology_timer(void)
{
topology_timer.function = topology_timer_fn;
topology_timer.data = 0;
topology_timer.expires = jiffies + 60 * HZ;
add_timer(&topology_timer);
}
static int __init early_parse_topology(char *p)
{
if (strncmp(p, "off", 3))
return 0;
topology_enabled = 0;
return 0;
}
early_param("topology", early_parse_topology);
static int __init init_topology_update(void)
{
int rc;
rc = 0;
if (!MACHINE_HAS_TOPOLOGY) {
[S390] Vertical cpu management. If vertical cpu polarization is active then the hypervisor will dispatch certain cpus for a longer time than other cpus for maximum performance. For example if a guest would have three virtual cpus, each of them with a share of 33 percent, then in case of vertical cpu polarization all of the processing time would be combined to a single cpu which would run all the time, while the other two cpus would get nearly no cpu time. There are three different types of vertical cpus: high, medium and low. Low cpus hardly get any real cpu time, while high cpus get a full real cpu. Medium cpus get something in between. In order to switch between the two possible modes (default is horizontal) a 0 for horizontal polarization or a 1 for vertical polarization must be written to the dispatching sysfs attribute: /sys/devices/system/cpu/dispatching The polarization of each single cpu can be figured out by the polarization sysfs attribute of each cpu: /sys/devices/system/cpu/cpuX/polarization horizontal, vertical:high, vertical:medium, vertical:low or unknown. When switching polarization the polarization attribute may contain the value unknown until the configuration change is done and the kernel has figured out the new polarization of each cpu. Note that running a system with different types of vertical cpus may result in significant performance regressions. If possible only one type of vertical cpus should be used. All other cpus should be offlined. Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
2008-04-17 13:46:13 +08:00
topology_update_polarization_simple();
goto out;
[S390] Vertical cpu management. If vertical cpu polarization is active then the hypervisor will dispatch certain cpus for a longer time than other cpus for maximum performance. For example if a guest would have three virtual cpus, each of them with a share of 33 percent, then in case of vertical cpu polarization all of the processing time would be combined to a single cpu which would run all the time, while the other two cpus would get nearly no cpu time. There are three different types of vertical cpus: high, medium and low. Low cpus hardly get any real cpu time, while high cpus get a full real cpu. Medium cpus get something in between. In order to switch between the two possible modes (default is horizontal) a 0 for horizontal polarization or a 1 for vertical polarization must be written to the dispatching sysfs attribute: /sys/devices/system/cpu/dispatching The polarization of each single cpu can be figured out by the polarization sysfs attribute of each cpu: /sys/devices/system/cpu/cpuX/polarization horizontal, vertical:high, vertical:medium, vertical:low or unknown. When switching polarization the polarization attribute may contain the value unknown until the configuration change is done and the kernel has figured out the new polarization of each cpu. Note that running a system with different types of vertical cpus may result in significant performance regressions. If possible only one type of vertical cpus should be used. All other cpus should be offlined. Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
2008-04-17 13:46:13 +08:00
}
init_timer_deferrable(&topology_timer);
set_topology_timer();
out:
update_cpu_core_map();
return rc;
}
__initcall(init_topology_update);
static void __init alloc_masks(struct sysinfo_15_1_x *info,
struct mask_info *mask, int offset)
{
int i, nr_masks;
nr_masks = info->mag[TOPOLOGY_NR_MAG - offset];
for (i = 0; i < info->mnest - offset; i++)
nr_masks *= info->mag[TOPOLOGY_NR_MAG - offset - 1 - i];
nr_masks = max(nr_masks, 1);
for (i = 0; i < nr_masks; i++) {
mask->next = alloc_bootmem(sizeof(struct mask_info));
mask = mask->next;
}
}
void __init s390_init_cpu_topology(void)
{
struct sysinfo_15_1_x *info;
int i;
if (!MACHINE_HAS_TOPOLOGY)
return;
tl_info = alloc_bootmem_pages(PAGE_SIZE);
info = tl_info;
store_topology(info);
pr_info("The CPU configuration topology of the machine is:");
for (i = 0; i < TOPOLOGY_NR_MAG; i++)
printk(" %d", info->mag[i]);
printk(" / %d\n", info->mnest);
alloc_masks(info, &core_info, 1);
#ifdef CONFIG_SCHED_BOOK
alloc_masks(info, &book_info, 2);
#endif
}