From: Heiko Carstens <[email protected]>
Add s390 backend so we can give the scheduler some hints about the
cpu topology.
Signed-off-by: Heiko Carstens <[email protected]>
Signed-off-by: Martin Schwidefsky <[email protected]>
---
arch/s390/Kconfig | 4
arch/s390/defconfig | 1
arch/s390/kernel/Makefile | 2
arch/s390/kernel/setup.c | 2
arch/s390/kernel/smp.c | 4
arch/s390/kernel/topology.c | 271 ++++++++++++++++++++++++++++++++++++++++++++
drivers/s390/sysinfo.c | 2
include/asm-s390/smp.h | 2
include/asm-s390/system.h | 1
include/asm-s390/topology.h | 16 ++
10 files changed, 300 insertions(+), 5 deletions(-)
Index: quilt-2.6/arch/s390/defconfig
===================================================================
--- quilt-2.6.orig/arch/s390/defconfig
+++ quilt-2.6/arch/s390/defconfig
@@ -3,6 +3,7 @@
# Linux kernel version: 2.6.25-rc5
# Wed Mar 12 14:10:52 2008
#
+CONFIG_SCHED_MC=y
CONFIG_MMU=y
CONFIG_ZONE_DMA=y
CONFIG_LOCKDEP_SUPPORT=y
Index: quilt-2.6/arch/s390/Kconfig
===================================================================
--- quilt-2.6.orig/arch/s390/Kconfig
+++ quilt-2.6/arch/s390/Kconfig
@@ -3,6 +3,10 @@
# see Documentation/kbuild/kconfig-language.txt.
#
+config SCHED_MC
+ def_bool y
+ depends on SMP
+
config MMU
def_bool y
Index: quilt-2.6/arch/s390/kernel/Makefile
===================================================================
--- quilt-2.6.orig/arch/s390/kernel/Makefile
+++ quilt-2.6/arch/s390/kernel/Makefile
@@ -19,7 +19,7 @@ obj-y += $(if $(CONFIG_64BIT),reipl64.o,
extra-y += head.o init_task.o vmlinux.lds
obj-$(CONFIG_MODULES) += s390_ksyms.o module.o
-obj-$(CONFIG_SMP) += smp.o
+obj-$(CONFIG_SMP) += smp.o topology.o
obj-$(CONFIG_AUDIT) += audit.o
compat-obj-$(CONFIG_AUDIT) += compat_audit.o
Index: quilt-2.6/arch/s390/kernel/setup.c
===================================================================
--- quilt-2.6.orig/arch/s390/kernel/setup.c
+++ quilt-2.6/arch/s390/kernel/setup.c
@@ -39,6 +39,7 @@
#include <linux/pfn.h>
#include <linux/ctype.h>
#include <linux/reboot.h>
+#include <linux/topology.h>
#include <asm/ipl.h>
#include <asm/uaccess.h>
@@ -830,6 +831,7 @@ setup_arch(char **cmdline_p)
cpu_init();
__cpu_logical_map[0] = S390_lowcore.cpu_data.cpu_addr;
+ s390_init_cpu_topology();
/*
* Setup capabilities (ELF_HWCAP & ELF_PLATFORM).
Index: quilt-2.6/arch/s390/kernel/smp.c
===================================================================
--- quilt-2.6.orig/arch/s390/kernel/smp.c
+++ quilt-2.6/arch/s390/kernel/smp.c
@@ -67,9 +67,7 @@ enum s390_cpu_state {
CPU_STATE_CONFIGURED,
};
-#ifdef CONFIG_HOTPLUG_CPU
-static DEFINE_MUTEX(smp_cpu_state_mutex);
-#endif
+DEFINE_MUTEX(smp_cpu_state_mutex);
static int smp_cpu_state[NR_CPUS];
static DEFINE_PER_CPU(struct cpu, cpu_devices);
Index: quilt-2.6/arch/s390/kernel/topology.c
===================================================================
--- /dev/null
+++ quilt-2.6/arch/s390/kernel/topology.c
@@ -0,0 +1,271 @@
+/*
+ * arch/s390/kernel/topology.c
+ *
+ * Copyright IBM Corp. 2007
+ * Author(s): Heiko Carstens <[email protected]>
+ */
+
+#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 <asm/delay.h>
+#include <asm/s390_ext.h>
+
+#define CPU_BITS 64
+
+struct tl_cpu {
+ unsigned char reserved[6];
+ unsigned short origin;
+ unsigned long mask[CPU_BITS / BITS_PER_LONG];
+};
+
+struct tl_container {
+ unsigned char reserved[8];
+};
+
+union tl_entry {
+ unsigned char nl;
+ struct tl_cpu cpu;
+ struct tl_container container;
+};
+
+#define NR_MAG 6
+
+struct tl_info {
+ unsigned char reserved0[2];
+ unsigned short length;
+ unsigned char mag[NR_MAG];
+ unsigned char reserved1;
+ unsigned char mnest;
+ unsigned char reserved2[4];
+ union tl_entry tle[0];
+};
+
+struct core_info {
+ struct core_info *next;
+ cpumask_t mask;
+};
+
+static void topology_work_fn(struct work_struct *work);
+static struct tl_info *tl_info;
+static struct core_info core_info;
+static int machine_has_topology;
+static int machine_has_topology_irq;
+static struct timer_list topology_timer;
+static void set_topology_timer(void);
+static DECLARE_WORK(topology_work, topology_work_fn);
+
+cpumask_t cpu_coregroup_map(unsigned int cpu)
+{
+ struct core_info *core = &core_info;
+ cpumask_t mask;
+
+ cpus_clear(mask);
+ if (!machine_has_topology)
+ return cpu_present_map;
+ mutex_lock(&smp_cpu_state_mutex);
+ while (core) {
+ if (cpu_isset(cpu, core->mask)) {
+ mask = core->mask;
+ break;
+ }
+ core = core->next;
+ }
+ mutex_unlock(&smp_cpu_state_mutex);
+ if (cpus_empty(mask))
+ mask = cpumask_of_cpu(cpu);
+ return mask;
+}
+
+static void add_cpus_to_core(struct tl_cpu *tl_cpu, struct core_info *core)
+{
+ unsigned int cpu;
+
+ for (cpu = find_first_bit(&tl_cpu->mask[0], CPU_BITS);
+ cpu < CPU_BITS;
+ cpu = find_next_bit(&tl_cpu->mask[0], CPU_BITS, cpu + 1))
+ {
+ unsigned int rcpu, lcpu;
+
+ rcpu = CPU_BITS - 1 - cpu + tl_cpu->origin;
+ for_each_present_cpu(lcpu) {
+ if (__cpu_logical_map[lcpu] == rcpu)
+ cpu_set(lcpu, core->mask);
+ }
+ }
+}
+
+static void clear_cores(void)
+{
+ struct core_info *core = &core_info;
+
+ while (core) {
+ cpus_clear(core->mask);
+ core = core->next;
+ }
+}
+
+static union tl_entry *next_tle(union tl_entry *tle)
+{
+ if (tle->nl)
+ return (union tl_entry *)((struct tl_container *)tle + 1);
+ else
+ return (union tl_entry *)((struct tl_cpu *)tle + 1);
+}
+
+static void tl_to_cores(struct tl_info *info)
+{
+ union tl_entry *tle, *end;
+ struct core_info *core = &core_info;
+
+ mutex_lock(&smp_cpu_state_mutex);
+ clear_cores();
+ tle = (union tl_entry *)&info->tle;
+ end = (union tl_entry *)((unsigned long)info + info->length);
+ while (tle < end) {
+ switch (tle->nl) {
+ case 5:
+ case 4:
+ case 3:
+ case 2:
+ break;
+ case 1:
+ core = core->next;
+ break;
+ case 0:
+ add_cpus_to_core(&tle->cpu, core);
+ break;
+ default:
+ clear_cores();
+ machine_has_topology = 0;
+ return;
+ }
+ tle = next_tle(tle);
+ }
+ mutex_unlock(&smp_cpu_state_mutex);
+}
+
+static int ptf(void)
+{
+ int rc;
+
+ asm volatile(
+ " .insn rre,0xb9a20000,%1,%1\n"
+ " ipm %0\n"
+ " srl %0,28\n"
+ : "=d" (rc)
+ : "d" (2UL) : "cc");
+ return rc;
+}
+
+void arch_update_cpu_topology(void)
+{
+ struct tl_info *info = tl_info;
+ struct sys_device *sysdev;
+ int cpu;
+
+ if (!machine_has_topology)
+ return;
+ ptf();
+ stsi(info, 15, 1, 2);
+ tl_to_cores(info);
+ for_each_online_cpu(cpu) {
+ sysdev = get_cpu_sysdev(cpu);
+ kobject_uevent(&sysdev->kobj, KOBJ_CHANGE);
+ }
+}
+
+static void topology_work_fn(struct work_struct *work)
+{
+ arch_reinit_sched_domains();
+}
+
+static void topology_timer_fn(unsigned long ignored)
+{
+ if (ptf())
+ schedule_work(&topology_work);
+ 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 void topology_interrupt(__u16 code)
+{
+ schedule_work(&topology_work);
+}
+
+static int __init init_topology_update(void)
+{
+ int rc;
+
+ if (!machine_has_topology)
+ return 0;
+ init_timer(&topology_timer);
+ if (machine_has_topology_irq) {
+ rc = register_external_interrupt(0x2005, topology_interrupt);
+ if (rc)
+ return rc;
+ ctl_set_bit(0, 8);
+ }
+ else
+ set_topology_timer();
+ return 0;
+}
+__initcall(init_topology_update);
+
+void __init s390_init_cpu_topology(void)
+{
+ unsigned long long facility_bits;
+ struct tl_info *info;
+ struct core_info *core;
+ int nr_cores;
+ int i;
+
+ if (stfle(&facility_bits, 1) <= 0)
+ return;
+ if (!(facility_bits & (1ULL << 52)) || !(facility_bits & (1ULL << 61)))
+ return;
+ machine_has_topology = 1;
+
+ if (facility_bits & (1ULL << 51))
+ machine_has_topology_irq = 1;
+
+ tl_info = alloc_bootmem_pages(PAGE_SIZE);
+ if (!tl_info)
+ goto error;
+ info = tl_info;
+ stsi(info, 15, 1, 2);
+
+ nr_cores = info->mag[NR_MAG - 2];
+ for (i = 0; i < info->mnest - 2; i++)
+ nr_cores *= info->mag[NR_MAG - 3 - i];
+
+ printk(KERN_INFO "CPU topology:");
+ for (i = 0; i < NR_MAG; i++)
+ printk(" %d", info->mag[i]);
+ printk(" / %d\n", info->mnest);
+
+ core = &core_info;
+ for (i = 0; i < nr_cores; i++) {
+ core->next = alloc_bootmem(sizeof(struct core_info));
+ core = core->next;
+ if (!core)
+ goto error;
+ }
+ return;
+error:
+ machine_has_topology = 0;
+ machine_has_topology_irq = 0;
+}
Index: quilt-2.6/drivers/s390/sysinfo.c
===================================================================
--- quilt-2.6.orig/drivers/s390/sysinfo.c
+++ quilt-2.6/drivers/s390/sysinfo.c
@@ -105,7 +105,7 @@ struct sysinfo_3_2_2 {
} vm[8];
};
-static inline int stsi(void *sysinfo, int fc, int sel1, int sel2)
+int stsi(void *sysinfo, int fc, int sel1, int sel2)
{
register int r0 asm("0") = (fc << 28) | sel1;
register int r1 asm("1") = sel2;
Index: quilt-2.6/include/asm-s390/smp.h
===================================================================
--- quilt-2.6.orig/include/asm-s390/smp.h
+++ quilt-2.6/include/asm-s390/smp.h
@@ -90,6 +90,8 @@ extern void __cpu_die (unsigned int cpu)
extern void cpu_die (void) __attribute__ ((noreturn));
extern int __cpu_up (unsigned int cpu);
+extern struct mutex smp_cpu_state_mutex;
+
extern int smp_call_function_mask(cpumask_t mask, void (*func)(void *),
void *info, int wait);
#endif
Index: quilt-2.6/include/asm-s390/system.h
===================================================================
--- quilt-2.6.orig/include/asm-s390/system.h
+++ quilt-2.6/include/asm-s390/system.h
@@ -406,6 +406,7 @@ __set_psw_mask(unsigned long mask)
#define local_mcck_enable() __set_psw_mask(psw_kernel_bits)
#define local_mcck_disable() __set_psw_mask(psw_kernel_bits & ~PSW_MASK_MCHECK)
+int stsi(void *sysinfo, int fc, int sel1, int sel2);
int stfle(unsigned long long *list, int doublewords);
#ifdef CONFIG_SMP
Index: quilt-2.6/include/asm-s390/topology.h
===================================================================
--- quilt-2.6.orig/include/asm-s390/topology.h
+++ quilt-2.6/include/asm-s390/topology.h
@@ -1,6 +1,22 @@
#ifndef _ASM_S390_TOPOLOGY_H
#define _ASM_S390_TOPOLOGY_H
+#include <linux/cpumask.h>
+
+#define mc_capable() (1)
+
+cpumask_t cpu_coregroup_map(unsigned int cpu);
+
+#define topology_core_siblings(cpu) (cpu_coregroup_map(cpu))
+
+#ifdef CONFIG_SMP
+void s390_init_cpu_topology(void);
+#else
+static inline void s390_init_cpu_topology(void)
+{
+};
+#endif
+
#include <asm-generic/topology.h>
#endif /* _ASM_S390_TOPOLOGY_H */
--
blue skies,
Martin.
"Reality continues to ruin my life." - Calvin.
On Wed, 12 Mar 2008 18:32:01 +0100
Martin Schwidefsky <[email protected]> wrote:
> From: Heiko Carstens <[email protected]>
>
> Add s390 backend so we can give the scheduler some hints about the
> cpu topology.
>
> ===================================================================
> --- /dev/null
> +++ quilt-2.6/arch/s390/kernel/topology.c
> @@ -0,0 +1,271 @@
> +/*
> + * arch/s390/kernel/topology.c
> + *
> + * Copyright IBM Corp. 2007
> + * Author(s): Heiko Carstens <[email protected]>
> + */
> +
> +#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 <asm/delay.h>
> +#include <asm/s390_ext.h>
> +
> +#define CPU_BITS 64
> +
> +struct tl_cpu {
> + unsigned char reserved[6];
> + unsigned short origin;
> + unsigned long mask[CPU_BITS / BITS_PER_LONG];
> +};
mask[] will be too small for CPU_BITS=65 ;)
> ...
>
> +static union tl_entry *next_tle(union tl_entry *tle)
> +{
> + if (tle->nl)
> + return (union tl_entry *)((struct tl_container *)tle + 1);
> + else
> + return (union tl_entry *)((struct tl_cpu *)tle + 1);
> +}
omg.
> +static void tl_to_cores(struct tl_info *info)
> +{
> + union tl_entry *tle, *end;
> + struct core_info *core = &core_info;
> +
> + mutex_lock(&smp_cpu_state_mutex);
> + clear_cores();
> + tle = (union tl_entry *)&info->tle;
and this cast was unneeded!
> + end = (union tl_entry *)((unsigned long)info + info->length);
I'd suggest that you take a look at all the pointer arith games which are
being played in this code and see if it can be done better with a more
appropriate use of the C type system. Before someone dies.
On Wed, 2008-03-12 at 16:11 -0700, Andrew Morton wrote:
> > +#include <asm/delay.h>
> > +#include <asm/s390_ext.h>
> > +
> > +#define CPU_BITS 64
> > +
> > +struct tl_cpu {
> > + unsigned char reserved[6];
> > + unsigned short origin;
> > + unsigned long mask[CPU_BITS / BITS_PER_LONG];
> > +};
>
> mask[] will be too small for CPU_BITS=65 ;)
We could add the +(BITS_PER_LONG - 1) logic but what for? The CPU_BITS
is defined right above and it will be increased in steps of 64.
> > ...
> >
> > +static union tl_entry *next_tle(union tl_entry *tle)
> > +{
> > + if (tle->nl)
> > + return (union tl_entry *)((struct tl_container *)tle + 1);
> > + else
> > + return (union tl_entry *)((struct tl_cpu *)tle + 1);
> > +}
>
> omg.
The length of the current tle depends on the type, the next type is
located behind the current one. Expect for the typecasting and the union
trick this is what needs to be done.
> > +static void tl_to_cores(struct tl_info *info)
> > +{
> > + union tl_entry *tle, *end;
> > + struct core_info *core = &core_info;
> > +
> > + mutex_lock(&smp_cpu_state_mutex);
> > + clear_cores();
> > + tle = (union tl_entry *)&info->tle;
>
> and this cast was unneeded!
>
> > + end = (union tl_entry *)((unsigned long)info + info->length);
>
> I'd suggest that you take a look at all the pointer arith games which are
> being played in this code and see if it can be done better with a more
> appropriate use of the C type system. Before someone dies.
The only thing that I can see that we could do is to get rid of the
unions and do the pointer arithmetic with the tl_cpu / tl_container
structs by hand. The data stored by ptf is structured in a way that
makes it rather hard to write decent C code.
--
blue skies,
Martin.
"Reality continues to ruin my life." - Calvin.
On Thu, Mar 13, 2008 at 01:28:27PM +0100, Martin Schwidefsky wrote:
> On Wed, 2008-03-12 at 16:11 -0700, Andrew Morton wrote:
> > > +#define CPU_BITS 64
> > > +
> > > +struct tl_cpu {
> > > + unsigned char reserved[6];
> > > + unsigned short origin;
> > > + unsigned long mask[CPU_BITS / BITS_PER_LONG];
> > > +};
> >
> > mask[] will be too small for CPU_BITS=65 ;)
>
> We could add the +(BITS_PER_LONG - 1) logic but what for? The CPU_BITS
> is defined right above and it will be increased in steps of 64.
It will always be 64 and won't be increased. For more than 64 cpus "origin"
in the hardware structure above will be > 0 and each bit in the mask
would represent cpu "origin + bit number".
> > > + end = (union tl_entry *)((unsigned long)info + info->length);
> >
> > I'd suggest that you take a look at all the pointer arith games which are
> > being played in this code and see if it can be done better with a more
> > appropriate use of the C type system. Before someone dies.
>
> The only thing that I can see that we could do is to get rid of the
> unions and do the pointer arithmetic with the tl_cpu / tl_container
> structs by hand. The data stored by ptf is structured in a way that
> makes it rather hard to write decent C code.
Please leave as is. I did have a few different implementations but they
all looked even worse than this one. If you read the hardware specs then
the current code should be rather easily understandable.
And since the whole documentation is publically availabe in the meantime
I could even add some comments ;)