* [PATCH 1/3] x86: fix percpu, nodeids, apicids in x86.git
2008-01-22 23:04 [PATCH 0/3] x86/non-x86: percpu, node ids, apic ids x86.git fixup travis
@ 2008-01-22 23:04 ` travis
2008-01-22 23:04 ` [PATCH 2/3] x86: add percpu, cpu_to_node debug options travis
2008-01-22 23:04 ` [PATCH 3/3] generic: fixup percpu Kconfig options, fold percpu_modcopy into module.c travis
2 siblings, 0 replies; 6+ messages in thread
From: travis @ 2008-01-22 23:04 UTC (permalink / raw)
To: mingo
Cc: Andrew Morton, Christoph Lameter, linux-mm, linux-kernel,
David Rientjes, Eric Dumazet, Yinghai Lu
[-- Attachment #1: 01-fix-x86.git-need --]
[-- Type: text/plain, Size: 9211 bytes --]
[ patches for x86.git ]
01-fix-x86.git-need
- fixes up things missing in (08/01/22) x86.git [necessary]
This should bring x86.git up-to-date with changes from -mm specific to x86
Cc: David Rientjes <rientjes@google.com>
Cc: Eric Dumazet <dada1@cosmosbay.com>
Cc: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Mike Travis <travis@sgi.com>
---
arch/x86/Kconfig | 2 +-
arch/x86/kernel/setup64.c | 10 +++++-----
arch/x86/kernel/smpboot_32.c | 2 +-
arch/x86/mm/numa_64.c | 14 ++++++--------
arch/x86/mm/srat_64.c | 2 +-
include/asm-generic/percpu.h | 12 ++----------
include/asm-x86/mmzone_64.h | 6 +++---
include/asm-x86/numa_64.h | 2 +-
include/asm-x86/topology.h | 16 +++++++++-------
init/main.c | 4 ++--
kernel/module.c | 8 ++++++++
11 files changed, 39 insertions(+), 39 deletions(-)
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -100,7 +100,7 @@ config GENERIC_TIME_VSYSCALL
bool
default X86_64
-config ARCH_SETS_UP_PER_CPU_AREA
+config HAVE_SETUP_PER_CPU_AREA
def_bool X86_64
config ARCH_SUPPORTS_OPROFILE
--- a/arch/x86/kernel/setup64.c
+++ b/arch/x86/kernel/setup64.c
@@ -87,10 +87,10 @@ __setup("noexec32=", nonx32_setup);
/*
* Copy data used in early init routines from the initial arrays to the
- * per cpu data areas. These arrays then become expendable and the *_ptrs
- * are zeroed indicating that the static arrays are gone.
+ * per cpu data areas. These arrays then become expendable and the
+ * *_early_ptr's are zeroed indicating that the static arrays are gone.
*/
-void __init setup_percpu_maps(void)
+static void __init setup_per_cpu_maps(void)
{
int cpu;
@@ -114,7 +114,7 @@ void __init setup_percpu_maps(void)
#endif
}
- /* indicate the early static arrays are gone */
+ /* indicate the early static arrays will soon be gone */
x86_cpu_to_apicid_early_ptr = NULL;
x86_bios_cpu_apicid_early_ptr = NULL;
#ifdef CONFIG_NUMA
@@ -157,7 +157,7 @@ void __init setup_per_cpu_areas(void)
}
/* setup percpu data maps early */
- setup_percpu_maps();
+ setup_per_cpu_maps();
}
void pda_init(int cpu)
--- a/arch/x86/kernel/smpboot_32.c
+++ b/arch/x86/kernel/smpboot_32.c
@@ -460,7 +460,7 @@ cpumask_t node_to_cpumask_map[MAX_NUMNOD
{ [0 ... MAX_NUMNODES-1] = CPU_MASK_NONE };
EXPORT_SYMBOL(node_to_cpumask_map);
/* which node each logical CPU is on */
-u8 cpu_to_node_map[NR_CPUS] __read_mostly = { [0 ... NR_CPUS-1] = 0 };
+int cpu_to_node_map[NR_CPUS] __read_mostly = { [0 ... NR_CPUS-1] = 0 };
EXPORT_SYMBOL(cpu_to_node_map);
/* set up a mapping between cpu and node. */
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -31,17 +31,15 @@ bootmem_data_t plat_node_bdata[MAX_NUMNO
struct memnode memnode;
-u16 x86_cpu_to_node_map_init[NR_CPUS] = {
+int x86_cpu_to_node_map_init[NR_CPUS] = {
[0 ... NR_CPUS-1] = NUMA_NO_NODE
};
void *x86_cpu_to_node_map_early_ptr;
-DEFINE_PER_CPU(u16, x86_cpu_to_node_map) = NUMA_NO_NODE;
+DEFINE_PER_CPU(int, x86_cpu_to_node_map) = NUMA_NO_NODE;
EXPORT_PER_CPU_SYMBOL(x86_cpu_to_node_map);
-#ifdef CONFIG_DEBUG_PER_CPU_MAPS
EXPORT_SYMBOL(x86_cpu_to_node_map_early_ptr);
-#endif
-u16 apicid_to_node[MAX_LOCAL_APIC] __cpuinitdata = {
+s16 apicid_to_node[MAX_LOCAL_APIC] __cpuinitdata = {
[0 ... MAX_LOCAL_APIC-1] = NUMA_NO_NODE
};
@@ -65,7 +63,7 @@ static int __init populate_memnodemap(co
unsigned long addr, end;
int i, res = -1;
- memset(memnodemap, 0xff, memnodemapsize);
+ memset(memnodemap, 0xff, sizeof(s16)*memnodemapsize);
for (i = 0; i < numnodes; i++) {
addr = nodes[i].start;
end = nodes[i].end;
@@ -74,7 +72,7 @@ static int __init populate_memnodemap(co
if ((end >> shift) >= memnodemapsize)
return 0;
do {
- if (memnodemap[addr >> shift] != 0xff)
+ if (memnodemap[addr >> shift] != NUMA_NO_NODE)
return -1;
memnodemap[addr >> shift] = i;
addr += (1UL << shift);
@@ -535,7 +533,7 @@ __cpuinit void numa_add_cpu(int cpu)
void __cpuinit numa_set_node(int cpu, int node)
{
- u16 *cpu_to_node_map = x86_cpu_to_node_map_early_ptr;
+ int *cpu_to_node_map = x86_cpu_to_node_map_early_ptr;
cpu_pda(cpu)->nodenumber = node;
--- a/arch/x86/mm/srat_64.c
+++ b/arch/x86/mm/srat_64.c
@@ -397,7 +397,7 @@ int __init acpi_scan_nodes(unsigned long
static int fake_node_to_pxm_map[MAX_NUMNODES] __initdata = {
[0 ... MAX_NUMNODES-1] = PXM_INVAL
};
-static u16 fake_apicid_to_node[MAX_LOCAL_APIC] __initdata = {
+static s16 fake_apicid_to_node[MAX_LOCAL_APIC] __initdata = {
[0 ... MAX_LOCAL_APIC-1] = NUMA_NO_NODE
};
static int __init find_node_by_addr(unsigned long addr)
--- a/include/asm-generic/percpu.h
+++ b/include/asm-generic/percpu.h
@@ -47,7 +47,7 @@ extern unsigned long __per_cpu_offset[NR
#endif
/*
- * A percpu variable may point to a discarded reghions. The following are
+ * A percpu variable may point to a discarded regions. The following are
* established ways to produce a usable pointer from the percpu variable
* offset.
*/
@@ -59,18 +59,10 @@ extern unsigned long __per_cpu_offset[NR
(*SHIFT_PERCPU_PTR(&per_cpu_var(var), __my_cpu_offset))
-#ifdef CONFIG_ARCH_SETS_UP_PER_CPU_AREA
+#ifdef CONFIG_HAVE_SETUP_PER_CPU_AREA
extern void setup_per_cpu_areas(void);
#endif
-/* 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 per_cpu(var, cpu) (*((void)(cpu), &per_cpu_var(var)))
--- a/include/asm-x86/mmzone_64.h
+++ b/include/asm-x86/mmzone_64.h
@@ -15,9 +15,9 @@
struct memnode {
int shift;
unsigned int mapsize;
- u8 *map;
- u8 embedded_map[64-16];
-} ____cacheline_aligned; /* total size = 64 bytes */
+ s16 *map;
+ s16 embedded_map[64-8];
+} ____cacheline_aligned; /* total size = 128 bytes */
extern struct memnode memnode;
#define memnode_shift memnode.shift
#define memnodemap memnode.map
--- a/include/asm-x86/numa_64.h
+++ b/include/asm-x86/numa_64.h
@@ -20,7 +20,7 @@ extern void numa_set_node(int cpu, int n
extern void srat_reserve_add_area(int nodeid);
extern int hotadd_percent;
-extern u16 apicid_to_node[MAX_LOCAL_APIC];
+extern s16 apicid_to_node[MAX_LOCAL_APIC];
extern void numa_initmem_init(unsigned long start_pfn, unsigned long end_pfn);
extern unsigned long numa_free_all_bootmem(void);
--- a/include/asm-x86/topology.h
+++ b/include/asm-x86/topology.h
@@ -31,17 +31,19 @@
/* Mappings between logical cpu number and node number */
#ifdef CONFIG_X86_32
-extern u8 cpu_to_node_map[];
+extern int cpu_to_node_map[];
#else
-DECLARE_PER_CPU(u16, x86_cpu_to_node_map);
-extern u16 x86_cpu_to_node_map_init[];
+DECLARE_PER_CPU(int, x86_cpu_to_node_map);
+extern int x86_cpu_to_node_map_init[];
extern void *x86_cpu_to_node_map_early_ptr;
+/* Returns the number of the current Node. */
+#define numa_node_id() (early_cpu_to_node(raw_smp_processor_id()))
#endif
extern cpumask_t node_to_cpumask_map[];
-#define NUMA_NO_NODE ((u16)(~0))
+#define NUMA_NO_NODE (-1)
/* Returns the number of the node containing CPU 'cpu' */
#ifdef CONFIG_X86_32
@@ -54,11 +56,11 @@ static inline int cpu_to_node(int cpu)
#else /* CONFIG_X86_64 */
static inline int early_cpu_to_node(int cpu)
{
- u16 *cpu_to_node_map = x86_cpu_to_node_map_early_ptr;
+ int *cpu_to_node_map = x86_cpu_to_node_map_early_ptr;
if (cpu_to_node_map)
return cpu_to_node_map[cpu];
- else if(per_cpu_offset(cpu))
+ else if (per_cpu_offset(cpu))
return per_cpu(x86_cpu_to_node_map, cpu);
else
return NUMA_NO_NODE;
@@ -71,7 +73,7 @@ static inline int cpu_to_node(int cpu)
printk("KERN_NOTICE cpu_to_node(%d): usage too early!\n",
(int)cpu);
dump_stack();
- return ((u16 *)x86_cpu_to_node_map_early_ptr)[cpu];
+ return ((int *)x86_cpu_to_node_map_early_ptr)[cpu];
}
#endif
if (per_cpu_offset(cpu))
--- a/init/main.c
+++ b/init/main.c
@@ -363,7 +363,7 @@ static inline void smp_prepare_cpus(unsi
#else
-#ifndef CONFIG_ARCH_SETS_UP_PER_CPU_AREA
+#ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA
unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
EXPORT_SYMBOL(__per_cpu_offset);
@@ -384,7 +384,7 @@ static void __init setup_per_cpu_areas(v
ptr += size;
}
}
-#endif /* CONFIG_ARCH_SETS_UP_CPU_AREA */
+#endif /* CONFIG_HAVE_SETUP_PER_CPU_AREA */
/* Called by boot processor to activate the rest. */
static void __init smp_init(void)
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -427,6 +427,14 @@ static unsigned int find_pcpusec(Elf_Ehd
return find_sec(hdr, sechdrs, secstrings, ".data.percpu");
}
+static void percpu_modcopy(void *pcpudest, const void *from, unsigned long size)
+{
+ int cpu;
+
+ for_each_possible_cpu(cpu)
+ memcpy(pcpudest + per_cpu_offset(cpu), from, size);
+}
+
static int percpu_modinit(void)
{
pcpu_num_used = 2;
--
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 6+ messages in thread* [PATCH 2/3] x86: add percpu, cpu_to_node debug options
2008-01-22 23:04 [PATCH 0/3] x86/non-x86: percpu, node ids, apic ids x86.git fixup travis
2008-01-22 23:04 ` [PATCH 1/3] x86: fix percpu, nodeids, apicids in x86.git travis
@ 2008-01-22 23:04 ` travis
2008-01-24 15:59 ` Ingo Molnar
2008-01-22 23:04 ` [PATCH 3/3] generic: fixup percpu Kconfig options, fold percpu_modcopy into module.c travis
2 siblings, 1 reply; 6+ messages in thread
From: travis @ 2008-01-22 23:04 UTC (permalink / raw)
To: mingo; +Cc: Andrew Morton, Christoph Lameter, linux-mm, linux-kernel
[-- Attachment #1: 02-fix-x86.git-debug-maxsmp --]
[-- Type: text/plain, Size: 2908 bytes --]
[ patches for x86.git ]
02-fix-x86.git-debug-maxsmp
- adds debug options [do not include, except for DEBUG]
These are debug options only. Should not be applied but are very
helpful when the system panics early or when testing of large count
NR_CPUS is desired.
Signed-off-by: Mike Travis <travis@sgi.com>
---
arch/x86/Kconfig | 22 ++++++++++++++++------
include/asm-x86/page_64.h | 4 ++++
lib/Kconfig.debug | 12 ++++++++++++
3 files changed, 32 insertions(+), 6 deletions(-)
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -467,19 +467,28 @@ config SWIOTLB
config NR_CPUS
- int "Maximum number of CPUs (2-255)"
- range 2 255
+ int "Maximum number of CPUs (2-4096)"
+ range 2 4096
depends on SMP
default "32" if X86_NUMAQ || X86_SUMMIT || X86_BIGSMP || X86_ES7000
- default "8"
+ default "1024" if X86_64
help
This allows you to specify the maximum number of CPUs which this
- kernel will support. The maximum supported value is 255 and the
+ kernel will support. The maximum supported value is 4096 and the
minimum value which makes sense is 2.
This is purely to save memory - each supported CPU adds
approximately eight kilobytes to the kernel image.
+config THREAD_ORDER
+ int "Kernel stack size (in page order)"
+ range 1 3
+ depends on X86_64
+ default "3" if X86_SMP
+ default "1"
+ help
+ Increases kernel stack size.
+
config SCHED_SMT
bool "SMT (Hyperthreading) scheduler support"
depends on (X86_64 && SMP) || (X86_32 && X86_HT)
@@ -862,8 +871,9 @@ config NUMA_EMU
number of nodes. This is only useful for debugging.
config NODES_SHIFT
- int
- default "6" if X86_64
+ int "NODES_SHIFT"
+ range 1 15 if X86_64
+ default "9" if X86_64
default "4" if X86_NUMAQ
default "3"
depends on NEED_MULTIPLE_NODES
--- a/include/asm-x86/page_64.h
+++ b/include/asm-x86/page_64.h
@@ -3,7 +3,11 @@
#define PAGETABLE_LEVELS 4
+#ifdef CONFIG_THREAD_ORDER
+#define THREAD_ORDER CONFIG_THREAD_ORDER
+#else
#define THREAD_ORDER 1
+#endif
#define THREAD_SIZE (PAGE_SIZE << THREAD_ORDER)
#define CURRENT_MASK (~(THREAD_SIZE-1))
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -570,6 +570,18 @@ config PROVIDE_OHCI1394_DMA_INIT
See Documentation/debugging-via-ohci1394.txt for more information.
+config DEBUG_PER_CPU
+ bool "Debug per_cpu usage"
+ depends on DEBUG_KERNEL
+ depends on SMP
+ default n
+ help
+ Say Y here to add code that verifies the per_cpu area is
+ setup before accessing a per_cpu variable. It does add a
+ significant amount of code to kernel memory.
+
+ If unsure, say N.
+
source "samples/Kconfig"
source "lib/Kconfig.kgdb"
--
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 6+ messages in thread* Re: [PATCH 2/3] x86: add percpu, cpu_to_node debug options
2008-01-22 23:04 ` [PATCH 2/3] x86: add percpu, cpu_to_node debug options travis
@ 2008-01-24 15:59 ` Ingo Molnar
2008-01-24 16:24 ` Mike Travis
0 siblings, 1 reply; 6+ messages in thread
From: Ingo Molnar @ 2008-01-24 15:59 UTC (permalink / raw)
To: travis; +Cc: Andrew Morton, Christoph Lameter, linux-mm, linux-kernel
* travis@sgi.com <travis@sgi.com> wrote:
> +config THREAD_ORDER
> + int "Kernel stack size (in page order)"
> + range 1 3
> + depends on X86_64
> + default "3" if X86_SMP
> + default "1"
> + help
> + Increases kernel stack size.
you keep sending this broken portion, please dont ...
Ingo
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [PATCH 2/3] x86: add percpu, cpu_to_node debug options
2008-01-24 15:59 ` Ingo Molnar
@ 2008-01-24 16:24 ` Mike Travis
0 siblings, 0 replies; 6+ messages in thread
From: Mike Travis @ 2008-01-24 16:24 UTC (permalink / raw)
To: Ingo Molnar; +Cc: Andrew Morton, Christoph Lameter, linux-mm, linux-kernel
Ingo Molnar wrote:
> * travis@sgi.com <travis@sgi.com> wrote:
>
>> +config THREAD_ORDER
>> + int "Kernel stack size (in page order)"
>> + range 1 3
>> + depends on X86_64
>> + default "3" if X86_SMP
>> + default "1"
>> + help
>> + Increases kernel stack size.
>
> you keep sending this broken portion, please dont ...
>
> Ingo
Sorry, I noted in the comments that that's only for the DEBUG patch, and
you shouldn't apply that, except when attempting to up the NR_CPUS count
for testing. (I should perhaps just quit submitting it? ;-)
As a side note, soon we should be able to up NR_CPUS and not worry about
stack overflows.
Thanks,
Mike
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 6+ messages in thread
* [PATCH 3/3] generic: fixup percpu Kconfig options, fold percpu_modcopy into module.c
2008-01-22 23:04 [PATCH 0/3] x86/non-x86: percpu, node ids, apic ids x86.git fixup travis
2008-01-22 23:04 ` [PATCH 1/3] x86: fix percpu, nodeids, apicids in x86.git travis
2008-01-22 23:04 ` [PATCH 2/3] x86: add percpu, cpu_to_node debug options travis
@ 2008-01-22 23:04 ` travis
2 siblings, 0 replies; 6+ messages in thread
From: travis @ 2008-01-22 23:04 UTC (permalink / raw)
To: mingo
Cc: Andrew Morton, Christoph Lameter, linux-mm, linux-kernel,
David Miller, linux-ia64, Paul Mackerras, schwidefsky, tony.luck
[-- Attachment #1: 03-fix-x86.git-non-x86-changes --]
[-- Type: text/plain, Size: 8989 bytes --]
[ patches for x86.git ]
03-fix-x86.git-non-x86-changes
- non-x86 changes that should fix build errors when x86.git
is merged into -mm. [necessary for -mm merge]
[percpu_modcopy() being the primary problem but also the
config option name for "HAVE_PER_CPU_SETUP" is different.]
Cc: David Miller <davem@davemloft.net>
Cc: linux-ia64@vger.kernel.org
Cc: Paul Mackerras <paulus@samba.org>
Cc: schwidefsky@de.ibm.com
Cc: tony.luck@intel.com
Signed-off-by: Mike Travis <travis@sgi.com>
---
arch/ia64/Kconfig | 2 +-
arch/ia64/kernel/module.c | 11 -----------
arch/powerpc/Kconfig | 2 +-
arch/sparc64/mm/init.c | 5 +++++
include/asm-ia64/percpu.h | 29 +++++++----------------------
include/asm-powerpc/percpu.h | 29 ++---------------------------
include/asm-s390/percpu.h | 42 +++++++++---------------------------------
include/asm-sparc64/percpu.h | 22 +++-------------------
8 files changed, 28 insertions(+), 114 deletions(-)
--- a/arch/ia64/Kconfig
+++ b/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
--- a/arch/ia64/kernel/module.c
+++ b/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 */
--- a/arch/powerpc/Kconfig
+++ b/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
--- a/arch/sparc64/mm/init.c
+++ b/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;
--- a/include/asm-ia64/percpu.h
+++ b/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__ */
--- a/include/asm-powerpc/percpu.h
+++ b/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_ */
--- a/include/asm-s390/percpu.h
+++ b/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@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__ */
--- a/include/asm-sparc64/percpu.h
+++ b/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__ */
--
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 6+ messages in thread