x86/non-x86: percpu, node ids, apic ids x86.git fixup
Mike Travis
travis at sgi.com
Thu Jan 31 05:20:24 EST 2008
Ingo Molnar wrote:
> * Luck, Tony <tony.luck at intel.com> wrote:
>
>>> thanks! Sorry about that: we cross-built on ARM but not on SMP
>>> non-x86 platforms so this dependency/breakage went unnoticed.
>> Yes ... all ia64 builds (UP and SMP) are broken at the moment. Please
>> Cc: me with the fixup patch.
>
> Could you check the patch below? With this applied to latest -git, ia64
> buils fine for me in a cross-compiling environment. (but i dont know
> whether it boots ...)
>
> Ingo
This patch is from a different patch set (aka "zero-based" patch). That
one will be updated and resubmitted soon...
Thanks,
Mike
>
> ----------------->
> Subject: generic: percpu infrastructure to rebase the per cpu area to zero
> From: travis at sgi.com
>
> * Support an option
>
> CONFIG_HAVE_ZERO_BASED_PER_CPU
>
> that makes offsets for per cpu variables to start at zero.
>
> If a percpu area starts at zero then:
>
> - We do not need RELOC_HIDE anymore
>
> - Provides for the future capability of architectures providing
> a per cpu allocator that returns offsets instead of pointers.
> The offsets would be independent of the processor so that
> address calculations can be done in a processor independent way.
> Per cpu instructions can then add the processor specific offset
> at the last minute possibly in an atomic instruction.
>
> The data the linker provides is different for zero based percpu segments:
>
> __per_cpu_load -> The address at which the percpu area was loaded
> __per_cpu_size -> The length of the per cpu area
>
> * Removes the &__per_cpu_x in lockdep. The __per_cpu_x are already
> pointers. There is no need to take the address.
>
> * Changes generic setup_per_cpu_areas to allocate per_cpu space in
> node local memory. This requires a generic early_cpu_to_node function.
>
> Signed-off-by: Mike Travis <travis at sgi.com>
> Reviewed-by: Christoph Lameter <clameter at sgi.com>
> Signed-off-by: Ingo Molnar <mingo at elte.hu>
> ---
> arch/ia64/Kconfig | 2 -
> arch/ia64/kernel/module.c | 11 --------
> arch/powerpc/Kconfig | 2 -
> arch/sparc64/mm/init.c | 5 ++++
> include/asm-alpha/topology.h | 1
> include/asm-generic/percpu.h | 7 ++++-
> include/asm-generic/sections.h | 10 ++++++++
> include/asm-generic/topology.h | 3 ++
> include/asm-generic/vmlinux.lds.h | 15 ++++++++++++
> include/asm-ia64/percpu.h | 29 +++++------------------
> include/asm-ia64/topology.h | 1
> include/asm-mips/mach-ip27/topology.h | 1
> include/asm-powerpc/percpu.h | 29 +----------------------
> include/asm-powerpc/topology.h | 1
> include/asm-s390/percpu.h | 42 +++++++---------------------------
> include/asm-sparc64/percpu.h | 22 ++---------------
> init/main.c | 18 ++++++++------
> kernel/lockdep.c | 4 +--
> 18 files changed, 78 insertions(+), 125 deletions(-)
>
> Index: linux-x86.q/arch/ia64/Kconfig
> ===================================================================
> --- linux-x86.q.orig/arch/ia64/Kconfig
> +++ linux-x86.q/arch/ia64/Kconfig
> @@ -80,7 +80,7 @@ config GENERIC_TIME_VSYSCALL
> bool
> default y
>
> -config ARCH_SETS_UP_PER_CPU_AREA
> +config HAVE_SETUP_PER_CPU_AREA
> def_bool y
>
> config DMI
> Index: linux-x86.q/arch/ia64/kernel/module.c
> ===================================================================
> --- linux-x86.q.orig/arch/ia64/kernel/module.c
> +++ linux-x86.q/arch/ia64/kernel/module.c
> @@ -940,14 +940,3 @@ module_arch_cleanup (struct module *mod)
> if (mod->arch.core_unw_table)
> unw_remove_unwind_table(mod->arch.core_unw_table);
> }
> -
> -#ifdef CONFIG_SMP
> -void
> -percpu_modcopy (void *pcpudst, const void *src, unsigned long size)
> -{
> - unsigned int i;
> - for_each_possible_cpu(i) {
> - memcpy(pcpudst + per_cpu_offset(i), src, size);
> - }
> -}
> -#endif /* CONFIG_SMP */
> Index: linux-x86.q/arch/powerpc/Kconfig
> ===================================================================
> --- linux-x86.q.orig/arch/powerpc/Kconfig
> +++ linux-x86.q/arch/powerpc/Kconfig
> @@ -42,7 +42,7 @@ config GENERIC_HARDIRQS
> bool
> default y
>
> -config ARCH_SETS_UP_PER_CPU_AREA
> +config HAVE_SETUP_PER_CPU_AREA
> def_bool PPC64
>
> config IRQ_PER_CPU
> Index: linux-x86.q/arch/sparc64/mm/init.c
> ===================================================================
> --- linux-x86.q.orig/arch/sparc64/mm/init.c
> +++ linux-x86.q/arch/sparc64/mm/init.c
> @@ -1328,6 +1328,11 @@ pgd_t swapper_pg_dir[2048];
> static void sun4u_pgprot_init(void);
> static void sun4v_pgprot_init(void);
>
> +/* Dummy function */
> +void __init setup_per_cpu_areas(void)
> +{
> +}
> +
> void __init paging_init(void)
> {
> unsigned long end_pfn, pages_avail, shift, phys_base;
> Index: linux-x86.q/include/asm-alpha/topology.h
> ===================================================================
> --- linux-x86.q.orig/include/asm-alpha/topology.h
> +++ linux-x86.q/include/asm-alpha/topology.h
> @@ -6,6 +6,7 @@
> #include <asm/machvec.h>
>
> #ifdef CONFIG_NUMA
> +#define early_cpu_to_node(cpu) cpu_to_node(cpu)
> static inline int cpu_to_node(int cpu)
> {
> int node;
> Index: linux-x86.q/include/asm-generic/percpu.h
> ===================================================================
> --- linux-x86.q.orig/include/asm-generic/percpu.h
> +++ linux-x86.q/include/asm-generic/percpu.h
> @@ -43,7 +43,12 @@ extern unsigned long __per_cpu_offset[NR
> * Only S390 provides its own means of moving the pointer.
> */
> #ifndef SHIFT_PERCPU_PTR
> -#define SHIFT_PERCPU_PTR(__p, __offset) RELOC_HIDE((__p), (__offset))
> +# ifdef CONFIG_HAVE_ZERO_BASED_PER_CPU
> +# define SHIFT_PERCPU_PTR(__p, __offset) \
> + ((__typeof(__p))(((void *)(__p)) + (__offset)))
> +# else
> +# define SHIFT_PERCPU_PTR(__p, __offset) RELOC_HIDE((__p), (__offset))
> +# endif /* CONFIG_HAVE_ZERO_BASED_PER_CPU */
> #endif
>
> /*
> Index: linux-x86.q/include/asm-generic/sections.h
> ===================================================================
> --- linux-x86.q.orig/include/asm-generic/sections.h
> +++ linux-x86.q/include/asm-generic/sections.h
> @@ -11,7 +11,17 @@ extern char _sinittext[], _einittext[];
> extern char _sextratext[] __attribute__((weak));
> extern char _eextratext[] __attribute__((weak));
> extern char _end[];
> +#ifdef CONFIG_HAVE_ZERO_BASED_PER_CPU
> +extern char __per_cpu_load[];
> +extern char ____per_cpu_size[];
> +#define __per_cpu_size ((unsigned long)&____per_cpu_size)
> +#define __per_cpu_start ((char *)0)
> +#define __per_cpu_end ((char *)__per_cpu_size)
> +#else
> extern char __per_cpu_start[], __per_cpu_end[];
> +#define __per_cpu_load __per_cpu_start
> +#define __per_cpu_size (__per_cpu_end - __per_cpu_start)
> +#endif
> extern char __kprobes_text_start[], __kprobes_text_end[];
> extern char __initdata_begin[], __initdata_end[];
> extern char __start_rodata[], __end_rodata[];
> Index: linux-x86.q/include/asm-generic/topology.h
> ===================================================================
> --- linux-x86.q.orig/include/asm-generic/topology.h
> +++ linux-x86.q/include/asm-generic/topology.h
> @@ -32,6 +32,9 @@
> #ifndef cpu_to_node
> #define cpu_to_node(cpu) (0)
> #endif
> +#ifndef early_cpu_to_node
> +#define early_cpu_to_node(cpu) cpu_to_node(cpu)
> +#endif
> #ifndef parent_node
> #define parent_node(node) (0)
> #endif
> Index: linux-x86.q/include/asm-generic/vmlinux.lds.h
> ===================================================================
> --- linux-x86.q.orig/include/asm-generic/vmlinux.lds.h
> +++ linux-x86.q/include/asm-generic/vmlinux.lds.h
> @@ -341,6 +341,20 @@
> *(.initcall7.init) \
> *(.initcall7s.init)
>
> +#ifdef CONFIG_HAVE_ZERO_BASED_PER_CPU
> +#define PERCPU(align) \
> + . = ALIGN(align); \
> + percpu : { } :percpu \
> + __per_cpu_load = .; \
> + .data.percpu 0 : AT(__per_cpu_load - LOAD_OFFSET) { \
> + *(.data.percpu.first) \
> + *(.data.percpu) \
> + *(.data.percpu.shared_aligned) \
> + ____per_cpu_size = .; \
> + } \
> + . = __per_cpu_load + ____per_cpu_size; \
> + data : { } :data
> +#else
> #define PERCPU(align) \
> . = ALIGN(align); \
> __per_cpu_start = .; \
> @@ -349,3 +363,4 @@
> *(.data.percpu.shared_aligned) \
> } \
> __per_cpu_end = .;
> +#endif
> Index: linux-x86.q/include/asm-ia64/percpu.h
> ===================================================================
> --- linux-x86.q.orig/include/asm-ia64/percpu.h
> +++ linux-x86.q/include/asm-ia64/percpu.h
> @@ -19,34 +19,14 @@
> # define PER_CPU_ATTRIBUTES __attribute__((__model__ (__small__)))
> #endif
>
> -#define DECLARE_PER_CPU(type, name) \
> - extern PER_CPU_ATTRIBUTES __typeof__(type) per_cpu__##name
> -
> -/*
> - * Pretty much a literal copy of asm-generic/percpu.h, except that percpu_modcopy() is an
> - * external routine, to avoid include-hell.
> - */
> #ifdef CONFIG_SMP
>
> -extern unsigned long __per_cpu_offset[NR_CPUS];
> -#define per_cpu_offset(x) (__per_cpu_offset[x])
> -
> -/* Equal to __per_cpu_offset[smp_processor_id()], but faster to access: */
> -DECLARE_PER_CPU(unsigned long, local_per_cpu_offset);
> +#define __my_cpu_offset __ia64_per_cpu_var(local_per_cpu_offset)
>
> -#define per_cpu(var, cpu) (*RELOC_HIDE(&per_cpu__##var, __per_cpu_offset[cpu]))
> -#define __get_cpu_var(var) (*RELOC_HIDE(&per_cpu__##var, __ia64_per_cpu_var(local_per_cpu_offset)))
> -#define __raw_get_cpu_var(var) (*RELOC_HIDE(&per_cpu__##var, __ia64_per_cpu_var(local_per_cpu_offset)))
> -
> -extern void percpu_modcopy(void *pcpudst, const void *src, unsigned long size);
> -extern void setup_per_cpu_areas (void);
> extern void *per_cpu_init(void);
>
> #else /* ! SMP */
>
> -#define per_cpu(var, cpu) (*((void)(cpu), &per_cpu__##var))
> -#define __get_cpu_var(var) per_cpu__##var
> -#define __raw_get_cpu_var(var) per_cpu__##var
> #define per_cpu_init() (__phys_per_cpu_start)
>
> #endif /* SMP */
> @@ -57,7 +37,12 @@ extern void *per_cpu_init(void);
> * On the positive side, using __ia64_per_cpu_var() instead of __get_cpu_var() is slightly
> * more efficient.
> */
> -#define __ia64_per_cpu_var(var) (per_cpu__##var)
> +#define __ia64_per_cpu_var(var) per_cpu__##var
> +
> +#include <asm-generic/percpu.h>
> +
> +/* Equal to __per_cpu_offset[smp_processor_id()], but faster to access: */
> +DECLARE_PER_CPU(unsigned long, local_per_cpu_offset);
>
> #endif /* !__ASSEMBLY__ */
>
> Index: linux-x86.q/include/asm-ia64/topology.h
> ===================================================================
> --- linux-x86.q.orig/include/asm-ia64/topology.h
> +++ linux-x86.q/include/asm-ia64/topology.h
> @@ -31,6 +31,7 @@
> * Returns the number of the node containing CPU 'cpu'
> */
> #define cpu_to_node(cpu) (int)(cpu_to_node_map[cpu])
> +#define early_cpu_to_node(cpu) cpu_to_node(cpu)
>
> /*
> * Returns a bitmask of CPUs on Node 'node'.
> Index: linux-x86.q/include/asm-mips/mach-ip27/topology.h
> ===================================================================
> --- linux-x86.q.orig/include/asm-mips/mach-ip27/topology.h
> +++ linux-x86.q/include/asm-mips/mach-ip27/topology.h
> @@ -23,6 +23,7 @@ struct cpuinfo_ip27 {
> extern struct cpuinfo_ip27 sn_cpu_info[NR_CPUS];
>
> #define cpu_to_node(cpu) (sn_cpu_info[(cpu)].p_nodeid)
> +#define early_cpu_to_node(cpu) cpu_to_node(cpu)
> #define parent_node(node) (node)
> #define node_to_cpumask(node) (hub_data(node)->h_cpus)
> #define node_to_first_cpu(node) (first_cpu(node_to_cpumask(node)))
> Index: linux-x86.q/include/asm-powerpc/percpu.h
> ===================================================================
> --- linux-x86.q.orig/include/asm-powerpc/percpu.h
> +++ linux-x86.q/include/asm-powerpc/percpu.h
> @@ -16,34 +16,9 @@
> #define __my_cpu_offset() get_paca()->data_offset
> #define per_cpu_offset(x) (__per_cpu_offset(x))
>
> -/* var is in discarded region: offset to particular copy we want */
> -#define per_cpu(var, cpu) (*RELOC_HIDE(&per_cpu__##var, __per_cpu_offset(cpu)))
> -#define __get_cpu_var(var) (*RELOC_HIDE(&per_cpu__##var, __my_cpu_offset()))
> -#define __raw_get_cpu_var(var) (*RELOC_HIDE(&per_cpu__##var, local_paca->data_offset))
> +#endif /* CONFIG_SMP */
> +#endif /* __powerpc64__ */
>
> -/* A macro to avoid #include hell... */
> -#define percpu_modcopy(pcpudst, src, size) \
> -do { \
> - unsigned int __i; \
> - for_each_possible_cpu(__i) \
> - memcpy((pcpudst)+__per_cpu_offset(__i), \
> - (src), (size)); \
> -} while (0)
> -
> -extern void setup_per_cpu_areas(void);
> -
> -#else /* ! SMP */
> -
> -#define per_cpu(var, cpu) (*((void)(cpu), &per_cpu__##var))
> -#define __get_cpu_var(var) per_cpu__##var
> -#define __raw_get_cpu_var(var) per_cpu__##var
> -
> -#endif /* SMP */
> -
> -#define DECLARE_PER_CPU(type, name) extern __typeof__(type) per_cpu__##name
> -
> -#else
> #include <asm-generic/percpu.h>
> -#endif
>
> #endif /* _ASM_POWERPC_PERCPU_H_ */
> Index: linux-x86.q/include/asm-powerpc/topology.h
> ===================================================================
> --- linux-x86.q.orig/include/asm-powerpc/topology.h
> +++ linux-x86.q/include/asm-powerpc/topology.h
> @@ -15,6 +15,7 @@ static inline int cpu_to_node(int cpu)
> return numa_cpu_lookup_table[cpu];
> }
>
> +#define early_cpu_to_node(cpu) cpu_to_node(cpu)
> #define parent_node(node) (node)
>
> static inline cpumask_t node_to_cpumask(int node)
> Index: linux-x86.q/include/asm-s390/percpu.h
> ===================================================================
> --- linux-x86.q.orig/include/asm-s390/percpu.h
> +++ linux-x86.q/include/asm-s390/percpu.h
> @@ -13,49 +13,25 @@
> */
> #if defined(__s390x__) && defined(MODULE)
>
> -#define __reloc_hide(var,offset) (*({ \
> +#define SHIFT_PERCPU_PTR(ptr,offset) (({ \
> extern int simple_identifier_##var(void); \
> unsigned long *__ptr; \
> - asm ( "larl %0,per_cpu__"#var"@GOTENT" \
> - : "=a" (__ptr) : "X" (per_cpu__##var) ); \
> - (typeof(&per_cpu__##var))((*__ptr) + (offset)); }))
> + asm ( "larl %0, %1 at GOTENT" \
> + : "=a" (__ptr) : "X" (ptr) ); \
> + (typeof(ptr))((*__ptr) + (offset)); }))
>
> #else
>
> -#define __reloc_hide(var, offset) (*({ \
> +#define SHIFT_PERCPU_PTR(ptr, offset) (({ \
> extern int simple_identifier_##var(void); \
> unsigned long __ptr; \
> - asm ( "" : "=a" (__ptr) : "0" (&per_cpu__##var) ); \
> - (typeof(&per_cpu__##var)) (__ptr + (offset)); }))
> + asm ( "" : "=a" (__ptr) : "0" (ptr) ); \
> + (typeof(ptr)) (__ptr + (offset)); }))
>
> #endif
>
> -#ifdef CONFIG_SMP
> +#define __my_cpu_offset S390_lowcore.percpu_offset
>
> -extern unsigned long __per_cpu_offset[NR_CPUS];
> -
> -#define __get_cpu_var(var) __reloc_hide(var,S390_lowcore.percpu_offset)
> -#define __raw_get_cpu_var(var) __reloc_hide(var,S390_lowcore.percpu_offset)
> -#define per_cpu(var,cpu) __reloc_hide(var,__per_cpu_offset[cpu])
> -#define per_cpu_offset(x) (__per_cpu_offset[x])
> -
> -/* A macro to avoid #include hell... */
> -#define percpu_modcopy(pcpudst, src, size) \
> -do { \
> - unsigned int __i; \
> - for_each_possible_cpu(__i) \
> - memcpy((pcpudst)+__per_cpu_offset[__i], \
> - (src), (size)); \
> -} while (0)
> -
> -#else /* ! SMP */
> -
> -#define __get_cpu_var(var) __reloc_hide(var,0)
> -#define __raw_get_cpu_var(var) __reloc_hide(var,0)
> -#define per_cpu(var,cpu) __reloc_hide(var,0)
> -
> -#endif /* SMP */
> -
> -#define DECLARE_PER_CPU(type, name) extern __typeof__(type) per_cpu__##name
> +#include <asm-generic/percpu.h>
>
> #endif /* __ARCH_S390_PERCPU__ */
> Index: linux-x86.q/include/asm-sparc64/percpu.h
> ===================================================================
> --- linux-x86.q.orig/include/asm-sparc64/percpu.h
> +++ linux-x86.q/include/asm-sparc64/percpu.h
> @@ -7,7 +7,6 @@ register unsigned long __local_per_cpu_o
>
> #ifdef CONFIG_SMP
>
> -#define setup_per_cpu_areas() do { } while (0)
> extern void real_setup_per_cpu_areas(void);
>
> extern unsigned long __per_cpu_base;
> @@ -16,29 +15,14 @@ extern unsigned long __per_cpu_shift;
> (__per_cpu_base + ((unsigned long)(__cpu) << __per_cpu_shift))
> #define per_cpu_offset(x) (__per_cpu_offset(x))
>
> -/* var is in discarded region: offset to particular copy we want */
> -#define per_cpu(var, cpu) (*RELOC_HIDE(&per_cpu__##var, __per_cpu_offset(cpu)))
> -#define __get_cpu_var(var) (*RELOC_HIDE(&per_cpu__##var, __local_per_cpu_offset))
> -#define __raw_get_cpu_var(var) (*RELOC_HIDE(&per_cpu__##var, __local_per_cpu_offset))
> -
> -/* A macro to avoid #include hell... */
> -#define percpu_modcopy(pcpudst, src, size) \
> -do { \
> - unsigned int __i; \
> - for_each_possible_cpu(__i) \
> - memcpy((pcpudst)+__per_cpu_offset(__i), \
> - (src), (size)); \
> -} while (0)
> +#define __my_cpu_offset __local_per_cpu_offset
> +
> #else /* ! SMP */
>
> #define real_setup_per_cpu_areas() do { } while (0)
>
> -#define per_cpu(var, cpu) (*((void)cpu, &per_cpu__##var))
> -#define __get_cpu_var(var) per_cpu__##var
> -#define __raw_get_cpu_var(var) per_cpu__##var
> -
> #endif /* SMP */
>
> -#define DECLARE_PER_CPU(type, name) extern __typeof__(type) per_cpu__##name
> +#include <asm-generic/percpu.h>
>
> #endif /* __ARCH_SPARC64_PERCPU__ */
> Index: linux-x86.q/init/main.c
> ===================================================================
> --- linux-x86.q.orig/init/main.c
> +++ linux-x86.q/init/main.c
> @@ -374,18 +374,20 @@ EXPORT_SYMBOL(__per_cpu_offset);
>
> static void __init setup_per_cpu_areas(void)
> {
> - unsigned long size, i;
> - char *ptr;
> - unsigned long nr_possible_cpus = num_possible_cpus();
> + unsigned long size;
> + int cpu;
>
> /* Copy section for each CPU (we discard the original) */
> size = ALIGN(PERCPU_ENOUGH_ROOM, PAGE_SIZE);
> - ptr = alloc_bootmem_pages(size * nr_possible_cpus);
>
> - for_each_possible_cpu(i) {
> - __per_cpu_offset[i] = ptr - __per_cpu_start;
> - memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start);
> - ptr += size;
> + printk(KERN_INFO "(generic)PERCPU: Allocating %lu bytes of per cpu data\n", size);
> +
> + for_each_possible_cpu(cpu) {
> + char *ptr = alloc_bootmem_pages_node(
> + NODE_DATA(early_cpu_to_node(cpu)), size);
> +
> + __per_cpu_offset[cpu] = ptr - __per_cpu_start;
> + memcpy(ptr, __per_cpu_load, __per_cpu_size);
> }
> }
> #endif /* CONFIG_HAVE_SETUP_PER_CPU_AREA */
> Index: linux-x86.q/kernel/lockdep.c
> ===================================================================
> --- linux-x86.q.orig/kernel/lockdep.c
> +++ linux-x86.q/kernel/lockdep.c
> @@ -609,8 +609,8 @@ static int static_obj(void *obj)
> * percpu var?
> */
> for_each_possible_cpu(i) {
> - start = (unsigned long) &__per_cpu_start + per_cpu_offset(i);
> - end = (unsigned long) &__per_cpu_start + PERCPU_ENOUGH_ROOM
> + start = (unsigned long) __per_cpu_start + per_cpu_offset(i);
> + end = (unsigned long) __per_cpu_start + PERCPU_ENOUGH_ROOM
> + per_cpu_offset(i);
>
> if ((addr >= start) && (addr < end))
More information about the Linuxppc-dev
mailing list