linux/arch/x86/include/asm/smp.h

236 lines
5.4 KiB
C
Raw Normal View History

#ifndef _ASM_X86_SMP_H
#define _ASM_X86_SMP_H
#ifndef __ASSEMBLY__
#include <linux/cpumask.h>
#include <linux/init.h>
#include <asm/percpu.h>
/*
* We need the APIC definitions automatically as part of 'smp.h'
*/
#ifdef CONFIG_X86_LOCAL_APIC
# include <asm/mpspec.h>
# include <asm/apic.h>
# ifdef CONFIG_X86_IO_APIC
# include <asm/io_apic.h>
# endif
#endif
#include <asm/thread_info.h>
#include <asm/cpumask.h>
#include <asm/cpufeature.h>
extern int smp_num_siblings;
extern unsigned int num_processors;
static inline bool cpu_has_ht_siblings(void)
{
bool has_siblings = false;
#ifdef CONFIG_SMP
has_siblings = cpu_has_ht && smp_num_siblings > 1;
#endif
return has_siblings;
}
DECLARE_PER_CPU(cpumask_var_t, cpu_sibling_map);
DECLARE_PER_CPU(cpumask_var_t, cpu_core_map);
/* cpus sharing the last level cache: */
DECLARE_PER_CPU(cpumask_var_t, cpu_llc_shared_map);
DECLARE_PER_CPU(u16, cpu_llc_id);
DECLARE_PER_CPU(int, cpu_number);
x86: cleanup early per cpu variables/accesses v4 * Introduce a new PER_CPU macro called "EARLY_PER_CPU". This is used by some per_cpu variables that are initialized and accessed before there are per_cpu areas allocated. ["Early" in respect to per_cpu variables is "earlier than the per_cpu areas have been setup".] This patchset adds these new macros: DEFINE_EARLY_PER_CPU(_type, _name, _initvalue) EXPORT_EARLY_PER_CPU_SYMBOL(_name) DECLARE_EARLY_PER_CPU(_type, _name) early_per_cpu_ptr(_name) early_per_cpu_map(_name, _idx) early_per_cpu(_name, _cpu) The DEFINE macro defines the per_cpu variable as well as the early map and pointer. It also initializes the per_cpu variable and map elements to "_initvalue". The early_* macros provide access to the initial map (usually setup during system init) and the early pointer. This pointer is initialized to point to the early map but is then NULL'ed when the actual per_cpu areas are setup. After that the per_cpu variable is the correct access to the variable. The early_per_cpu() macro is not very efficient but does show how to access the variable if you have a function that can be called both "early" and "late". It tests the early ptr to be NULL, and if not then it's still valid. Otherwise, the per_cpu variable is used instead: #define early_per_cpu(_name, _cpu) \ (early_per_cpu_ptr(_name) ? \ early_per_cpu_ptr(_name)[_cpu] : \ per_cpu(_name, _cpu)) A better method is to actually check the pointer manually. In the case below, numa_set_node can be called both "early" and "late": void __cpuinit numa_set_node(int cpu, int node) { int *cpu_to_node_map = early_per_cpu_ptr(x86_cpu_to_node_map); if (cpu_to_node_map) cpu_to_node_map[cpu] = node; else per_cpu(x86_cpu_to_node_map, cpu) = node; } * Add a flag "arch_provides_topology_pointers" that indicates pointers to topology cpumask_t maps are available. Otherwise, use the function returning the cpumask_t value. This is useful if cpumask_t set size is very large to avoid copying data on to/off of the stack. * The coverage of CONFIG_DEBUG_PER_CPU_MAPS has been increased while the non-debug case has been optimized a bit. * Remove an unreferenced compiler warning in drivers/base/topology.c * Clean up #ifdef in setup.c For inclusion into sched-devel/latest tree. Based on: git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6.git + sched-devel/latest .../mingo/linux-2.6-sched-devel.git Signed-off-by: Mike Travis <travis@sgi.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-05-12 19:21:12 +00:00
static inline struct cpumask *cpu_sibling_mask(int cpu)
{
return per_cpu(cpu_sibling_map, cpu);
}
static inline struct cpumask *cpu_core_mask(int cpu)
{
return per_cpu(cpu_core_map, cpu);
}
static inline struct cpumask *cpu_llc_shared_mask(int cpu)
{
return per_cpu(cpu_llc_shared_map, cpu);
}
x86: cleanup early per cpu variables/accesses v4 * Introduce a new PER_CPU macro called "EARLY_PER_CPU". This is used by some per_cpu variables that are initialized and accessed before there are per_cpu areas allocated. ["Early" in respect to per_cpu variables is "earlier than the per_cpu areas have been setup".] This patchset adds these new macros: DEFINE_EARLY_PER_CPU(_type, _name, _initvalue) EXPORT_EARLY_PER_CPU_SYMBOL(_name) DECLARE_EARLY_PER_CPU(_type, _name) early_per_cpu_ptr(_name) early_per_cpu_map(_name, _idx) early_per_cpu(_name, _cpu) The DEFINE macro defines the per_cpu variable as well as the early map and pointer. It also initializes the per_cpu variable and map elements to "_initvalue". The early_* macros provide access to the initial map (usually setup during system init) and the early pointer. This pointer is initialized to point to the early map but is then NULL'ed when the actual per_cpu areas are setup. After that the per_cpu variable is the correct access to the variable. The early_per_cpu() macro is not very efficient but does show how to access the variable if you have a function that can be called both "early" and "late". It tests the early ptr to be NULL, and if not then it's still valid. Otherwise, the per_cpu variable is used instead: #define early_per_cpu(_name, _cpu) \ (early_per_cpu_ptr(_name) ? \ early_per_cpu_ptr(_name)[_cpu] : \ per_cpu(_name, _cpu)) A better method is to actually check the pointer manually. In the case below, numa_set_node can be called both "early" and "late": void __cpuinit numa_set_node(int cpu, int node) { int *cpu_to_node_map = early_per_cpu_ptr(x86_cpu_to_node_map); if (cpu_to_node_map) cpu_to_node_map[cpu] = node; else per_cpu(x86_cpu_to_node_map, cpu) = node; } * Add a flag "arch_provides_topology_pointers" that indicates pointers to topology cpumask_t maps are available. Otherwise, use the function returning the cpumask_t value. This is useful if cpumask_t set size is very large to avoid copying data on to/off of the stack. * The coverage of CONFIG_DEBUG_PER_CPU_MAPS has been increased while the non-debug case has been optimized a bit. * Remove an unreferenced compiler warning in drivers/base/topology.c * Clean up #ifdef in setup.c For inclusion into sched-devel/latest tree. Based on: git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6.git + sched-devel/latest .../mingo/linux-2.6-sched-devel.git Signed-off-by: Mike Travis <travis@sgi.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-05-12 19:21:12 +00:00
DECLARE_EARLY_PER_CPU(u16, x86_cpu_to_apicid);
DECLARE_EARLY_PER_CPU(u16, x86_bios_cpu_apicid);
#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86_32)
DECLARE_EARLY_PER_CPU(int, x86_cpu_to_logical_apicid);
#endif
/* Static state in head.S used to set up a CPU */
extern unsigned long stack_start; /* Initial stack pointer address */
struct smp_ops {
void (*smp_prepare_boot_cpu)(void);
void (*smp_prepare_cpus)(unsigned max_cpus);
void (*smp_cpus_done)(unsigned max_cpus);
void (*stop_other_cpus)(int wait);
void (*smp_send_reschedule)(int cpu);
int (*cpu_up)(unsigned cpu);
int (*cpu_disable)(void);
void (*cpu_die)(unsigned int cpu);
void (*play_dead)(void);
void (*send_call_func_ipi)(const struct cpumask *mask);
void (*send_call_func_single_ipi)(int cpu);
};
/* Globals due to paravirt */
extern void set_cpu_sibling_map(int cpu);
#ifdef CONFIG_SMP
#ifndef CONFIG_PARAVIRT
#define startup_ipi_hook(phys_apicid, start_eip, start_esp) do { } while (0)
#endif
extern struct smp_ops smp_ops;
static inline void smp_send_stop(void)
{
smp_ops.stop_other_cpus(0);
}
static inline void stop_other_cpus(void)
{
smp_ops.stop_other_cpus(1);
}
static inline void smp_prepare_boot_cpu(void)
{
smp_ops.smp_prepare_boot_cpu();
}
static inline void smp_prepare_cpus(unsigned int max_cpus)
{
smp_ops.smp_prepare_cpus(max_cpus);
}
static inline void smp_cpus_done(unsigned int max_cpus)
{
smp_ops.smp_cpus_done(max_cpus);
}
static inline int __cpu_up(unsigned int cpu)
{
return smp_ops.cpu_up(cpu);
}
static inline int __cpu_disable(void)
{
return smp_ops.cpu_disable();
}
static inline void __cpu_die(unsigned int cpu)
{
smp_ops.cpu_die(cpu);
}
static inline void play_dead(void)
{
smp_ops.play_dead();
}
static inline void smp_send_reschedule(int cpu)
{
smp_ops.smp_send_reschedule(cpu);
}
static inline void arch_send_call_function_single_ipi(int cpu)
{
smp_ops.send_call_func_single_ipi(cpu);
}
static inline void arch_send_call_function_ipi_mask(const struct cpumask *mask)
{
smp_ops.send_call_func_ipi(mask);
}
void cpu_disable_common(void);
void native_smp_prepare_boot_cpu(void);
void native_smp_prepare_cpus(unsigned int max_cpus);
void native_smp_cpus_done(unsigned int max_cpus);
int native_cpu_up(unsigned int cpunum);
int native_cpu_disable(void);
void native_cpu_die(unsigned int cpu);
void native_play_dead(void);
void play_dead_common(void);
void wbinvd_on_cpu(int cpu);
int wbinvd_on_all_cpus(void);
void native_send_call_func_ipi(const struct cpumask *mask);
void native_send_call_func_single_ipi(int cpu);
void smp_store_cpu_info(int id);
#define cpu_physical_id(cpu) per_cpu(x86_cpu_to_apicid, cpu)
/* We don't mark CPUs online until __cpu_up(), so we need another measure */
static inline int num_booting_cpus(void)
{
return cpumask_weight(cpu_callout_mask);
}
#else /* !CONFIG_SMP */
#define wbinvd_on_cpu(cpu) wbinvd()
static inline int wbinvd_on_all_cpus(void)
{
wbinvd();
return 0;
}
#endif /* CONFIG_SMP */
extern unsigned disabled_cpus __cpuinitdata;
#ifdef CONFIG_X86_32_SMP
/*
* This function is needed by all SMP systems. It must _always_ be valid
* from the initial startup. We map APIC_BASE very early in page_setup(),
* so this is correct in the x86 case.
*/
#define raw_smp_processor_id() (percpu_read(cpu_number))
extern int safe_smp_processor_id(void);
#elif defined(CONFIG_X86_64_SMP)
#define raw_smp_processor_id() (percpu_read(cpu_number))
#define stack_smp_processor_id() \
({ \
struct thread_info *ti; \
__asm__("andq %%rsp,%0; ":"=r" (ti) : "0" (CURRENT_MASK)); \
ti->cpu; \
})
#define safe_smp_processor_id() smp_processor_id()
#endif
#ifdef CONFIG_X86_LOCAL_APIC
#ifndef CONFIG_X86_64
static inline int logical_smp_processor_id(void)
{
/* we don't want to mark this access volatile - bad code generation */
return GET_APIC_LOGICAL_ID(apic_read(APIC_LDR));
}
x86: support for new UV apic UV supports really big systems. So big, in fact, that the APICID register does not contain enough bits to contain an APICID that is unique across all cpus. The UV BIOS supports 3 APICID modes: - legacy mode. This mode uses the old APIC mode where APICID is in bits [31:24] of the APICID register. - x2apic mode. This mode is whitebox-compatible. APICIDs are unique across all cpus. Standard x2apic APIC operations (Intel-defined) can be used for IPIs. The node identifier fits within the Intel-defined portion of the APICID register. - x2apic-uv mode. In this mode, the APICIDs on each node have unique IDs, but IDs on different node are not unique. For example, if each mode has 32 cpus, the APICIDs on each node might be 0 - 31. Every node has the same set of IDs. The UV hub is used to route IPIs/interrupts to the correct node. Traditional APIC operations WILL NOT WORK. In x2apic-uv mode, the ACPI tables all contain a full unique ID (note: exact bit layout still changing but the following is close): nnnnnnnnnnlc0cch n = unique node number l = socket number on board c = core h = hyperthread Only the "lc0cch" bits are written to the APICID register. The remaining bits are supplied by having the get_apic_id() function "OR" the extra bits into the value read from the APICID register. (Hmmm.. why not keep the ENTIRE APICID register in per-cpu data....) The x2apic-uv mode is recognized by the MADT table containing: oem_id = "SGI" oem_table_id = "UV-X" Signed-off-by: Jack Steiner <steiner@sgi.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-03-28 19:12:16 +00:00
#endif
extern int hard_smp_processor_id(void);
#else /* CONFIG_X86_LOCAL_APIC */
# ifndef CONFIG_SMP
# define hard_smp_processor_id() 0
# endif
#endif /* CONFIG_X86_LOCAL_APIC */
#ifdef CONFIG_DEBUG_NMI_SELFTEST
extern void nmi_selftest(void);
#else
#define nmi_selftest() do { } while (0)
#endif
#endif /* __ASSEMBLY__ */
#endif /* _ASM_X86_SMP_H */