All of lore.kernel.org
 help / color / mirror / Atom feed
From: Ingo Molnar <mingo@elte.hu>
To: Christoph Lameter <clameter@sgi.com>
Cc: Rusty Russell <rusty@rustcorp.com.au>, Andi Kleen <ak@suse.de>,
	Jeremy Fitzhardinge <jeremy@goop.org>,
	linux-kernel@vger.kernel.org,
	Thomas Gleixner <tglx@linutronix.de>
Subject: Re: [patch 0/3] Per cpu relocation to ZERO and x86_32 percpu ops on x86_64
Date: Fri, 30 Nov 2007 12:24:29 +0100	[thread overview]
Message-ID: <20071130112429.GA3605@elte.hu> (raw)
In-Reply-To: <20071130064305.459255715@sgi.com>


* Christoph Lameter <clameter@sgi.com> wrote:

> This patchset allows the use of x86_32 percpu ops on x86_64 while 
> maintaining %gs pointing to the pda. It does that by moving the x86_64 
> pda into the percpu area (thereby pointing %gs at the per cpu area) 
> and then relocating the x86_64 per cpu variables to start at 0.
> 
> Patch applies on top of the per cpu cleanup patches V2. See 
> http://marc.info/?l=linux-kernel&m=119628478316525&w=2
> 
> Ultimately I think we can make the per cpu accessors arch independent 
> (see the RFC at 
> http://marc.info/?l=linux-kernel&m=119552126330405&w=2). There is a 
> performance benefit from using these in core code.

i've picked up your cleanup series and this relocation series as well, 
but it crashed on x86 32-bit UP, with:

 [   78.692936] Freeing unused kernel memory: 656k freed
 [   78.697750] BUG: spinlock wrong owner on CPU#0, /0�

(no other messages, hard lockup)

find below my manual merge against x86.git, maybe i made some merging 
mistake. x86.git can be picked up via:

 git-pull git://git.kernel.org/pub/scm/linux/kernel/git/x86/linux-2.6-x86.git mm

	Ingo

-------------------->
Index: linux-x86.q/arch/ia64/Kconfig
===================================================================
--- linux-x86.q.orig/arch/ia64/Kconfig
+++ linux-x86.q/arch/ia64/Kconfig
@@ -75,6 +75,9 @@ config GENERIC_TIME_VSYSCALL
 	bool
 	default y
 
+config ARCH_SETS_UP_PER_CPU_AREA
+	def_bool y
+
 config DMI
 	bool
 	default y
Index: linux-x86.q/arch/powerpc/Kconfig
===================================================================
--- linux-x86.q.orig/arch/powerpc/Kconfig
+++ linux-x86.q/arch/powerpc/Kconfig
@@ -42,6 +42,9 @@ config GENERIC_HARDIRQS
 	bool
 	default y
 
+config ARCH_SETS_UP_PER_CPU_AREA
+	def_bool PPC64
+
 config IRQ_PER_CPU
 	bool
 	default y
Index: linux-x86.q/arch/sparc64/Kconfig
===================================================================
--- linux-x86.q.orig/arch/sparc64/Kconfig
+++ linux-x86.q/arch/sparc64/Kconfig
@@ -66,6 +66,9 @@ config AUDIT_ARCH
 	bool
 	default y
 
+config ARCH_SETS_UP_PER_CPU_AREA
+	def_bool y
+
 config ARCH_NO_VIRT_TO_BUS
 	def_bool y
 
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
@@ -1323,6 +1323,11 @@ 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/arch/x86/Kconfig
===================================================================
--- linux-x86.q.orig/arch/x86/Kconfig
+++ linux-x86.q/arch/x86/Kconfig
@@ -116,9 +116,13 @@ config GENERIC_TIME_VSYSCALL
 	bool
 	default X86_64
 
+config ARCH_SETS_UP_PER_CPU_AREA
+	def_bool X86_64
 
-
-
+config PERCPU_ZERO_BASED
+	bool
+	depends on X86_64 && SMP
+	default y
 
 config ZONE_DMA32
 	bool
Index: linux-x86.q/arch/x86/kernel/head64.c
===================================================================
--- linux-x86.q.orig/arch/x86/kernel/head64.c
+++ linux-x86.q/arch/x86/kernel/head64.c
@@ -22,6 +22,12 @@
 #include <asm/sections.h>
 #include <asm/kdebug.h>
 
+/*
+ * Only used before the per cpu areas are setup. The use for the non possible
+ * cpus continues after boot
+ */
+static struct x8664_pda boot_cpu_pda[NR_CPUS] __cacheline_aligned;
+
 static void __init zap_identity_mappings(void)
 {
 	pgd_t *pgd = pgd_offset_k(0UL);
Index: linux-x86.q/arch/x86/kernel/setup64.c
===================================================================
--- linux-x86.q.orig/arch/x86/kernel/setup64.c
+++ linux-x86.q/arch/x86/kernel/setup64.c
@@ -30,7 +30,9 @@ cpumask_t cpu_initialized __cpuinitdata 
 
 struct x8664_pda *_cpu_pda[NR_CPUS] __read_mostly;
 EXPORT_SYMBOL(_cpu_pda);
-struct x8664_pda boot_cpu_pda[NR_CPUS] __cacheline_aligned;
+
+DEFINE_PER_CPU_FIRST(struct x8664_pda, pda);
+EXPORT_PER_CPU_SYMBOL(pda);
 
 struct desc_ptr idt_descr = { 256 * 16 - 1, (unsigned long) idt_table };
 
@@ -109,10 +111,15 @@ void __init setup_per_cpu_areas(void)
 		}
 		if (!ptr)
 			panic("Cannot allocate cpu data for CPU %d\n", i);
-		cpu_pda(i)->data_offset = ptr - __per_cpu_start;
-		memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start);
+		memcpy(ptr, __per_cpu_load, __per_cpu_size);
+		/* Relocate the pda */
+		memcpy(ptr, cpu_pda(i), sizeof(struct x8664_pda));
+		cpu_pda(i) = (struct x8664_pda *)ptr;
+		cpu_pda(i)->data_offset = (unsigned long)ptr;
 	}
-} 
+	/* Fix up pda for this processor .... */
+	pda_init(0);
+}
 
 void pda_init(int cpu)
 { 
Index: linux-x86.q/arch/x86/kernel/smpboot_64.c
===================================================================
--- linux-x86.q.orig/arch/x86/kernel/smpboot_64.c
+++ linux-x86.q/arch/x86/kernel/smpboot_64.c
@@ -556,22 +556,6 @@ static int __cpuinit do_boot_cpu(int cpu
 		return -1;
 	}
 
-	/* Allocate node local memory for AP pdas */
-	if (cpu_pda(cpu) == &boot_cpu_pda[cpu]) {
-		struct x8664_pda *newpda, *pda;
-		int node = cpu_to_node(cpu);
-		pda = cpu_pda(cpu);
-		newpda = kmalloc_node(sizeof (struct x8664_pda), GFP_ATOMIC,
-				      node);
-		if (newpda) {
-			memcpy(newpda, pda, sizeof (struct x8664_pda));
-			cpu_pda(cpu) = newpda;
-		} else
-			printk(KERN_ERR
-		"Could not allocate node local PDA for CPU %d on node %d\n",
-				cpu, node);
-	}
-
 	alternatives_smp_switch(1);
 
 	c_idle.idle = get_idle_for_cpu(cpu);
Index: linux-x86.q/arch/x86/kernel/vmlinux_64.lds.S
===================================================================
--- linux-x86.q.orig/arch/x86/kernel/vmlinux_64.lds.S
+++ linux-x86.q/arch/x86/kernel/vmlinux_64.lds.S
@@ -16,6 +16,7 @@ jiffies_64 = jiffies;
 _proxy_pda = 1;
 PHDRS {
 	text PT_LOAD FLAGS(5);	/* R_E */
+	percpu PT_LOAD FLAGS(4);	/* R__ */
 	data PT_LOAD FLAGS(7);	/* RWE */
 	user PT_LOAD FLAGS(7);	/* RWE */
 	data.init PT_LOAD FLAGS(7);	/* RWE */
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
@@ -3,28 +3,65 @@
 #include <linux/compiler.h>
 #include <linux/threads.h>
 
-#define __GENERIC_PER_CPU
+/*
+ * Determine the real variable name from the name visible in the
+ * kernel sources.
+ */
+#define per_cpu_var(var) per_cpu__##var
+
 #ifdef CONFIG_SMP
 
+/*
+ * per_cpu_offset() is the offset that has to be added to a
+ * percpu variable to get to the instance for a certain processor.
+ *
+ * Most arches use the __per_cpu_offset array for those offsets but
+ * some arches have their own ways of determining the offset (x86_64, s390).
+ */
+#ifndef __per_cpu_offset
 extern unsigned long __per_cpu_offset[NR_CPUS];
-
 #define per_cpu_offset(x) (__per_cpu_offset[x])
+#endif
 
-/* Separate out the type, so (int[3], foo) works. */
-#define DEFINE_PER_CPU(type, name) \
-    __attribute__((__section__(".data.percpu"))) __typeof__(type) per_cpu__##name
-
-#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name)		\
-    __attribute__((__section__(".data.percpu.shared_aligned"))) \
-    __typeof__(type) per_cpu__##name				\
-    ____cacheline_aligned_in_smp
-
-/* var is in discarded region: offset to particular copy we want */
-#define per_cpu(var, cpu) (*({				\
-	extern int simple_identifier_##var(void);	\
-	RELOC_HIDE(&per_cpu__##var, __per_cpu_offset[cpu]); }))
-#define __get_cpu_var(var) per_cpu(var, smp_processor_id())
-#define __raw_get_cpu_var(var) per_cpu(var, raw_smp_processor_id())
+/*
+ * Determine the offset for the currently active processor.
+ * An arch may define __my_cpu_offset to provide a more effective
+ * means of obtaining the offset to the per cpu variables of the
+ * current processor.
+ */
+#ifndef __my_cpu_offset
+#define __my_cpu_offset per_cpu_offset(raw_smp_processor_id())
+#define my_cpu_offset per_cpu_offset(smp_processor_id())
+#else
+#define my_cpu_offset __my_cpu_offset
+#endif
+
+/*
+ * Add a offset to a pointer but keep the pointer as is.
+ *
+ * Only S390 provides its own means of moving the pointer.
+ */
+#ifndef SHIFT_PTR
+#ifdef CONFIG_PERCPU_ZERO_BASED
+#define SHIFT_PTR(__p, __offset) \
+	((__typeof(__p))(((void *)(__p)) + (__offset)))
+#else
+#define SHIFT_PTR(__p, __offset)	RELOC_HIDE((__p), (__offset))
+#endif /* CONFIG_PER_CPU_ZERO_BASED */
+#endif /* SHIFT_PTR */
+
+/*
+ * A percpu variable may point to a discarded reghions. The following are
+ * established ways to produce a usable pointer from the percpu variable
+ * offset.
+ */
+#define per_cpu(var, cpu) (*SHIFT_PTR(&per_cpu_var(var), per_cpu_offset(cpu)))
+#define __get_cpu_var(var) (*SHIFT_PTR(&per_cpu_var(var), my_cpu_offset))
+#define __raw_get_cpu_var(var) (*SHIFT_PTR(&per_cpu_var(var), __my_cpu_offset))
+
+#ifdef CONFIG_ARCH_SETS_UP_PER_CPU_AREA
+extern void setup_per_cpu_areas(void);
+#endif
 
 /* A macro to avoid #include hell... */
 #define percpu_modcopy(pcpudst, src, size)			\
@@ -36,21 +73,17 @@ do {								\
 } while (0)
 #else /* ! SMP */
 
-#define DEFINE_PER_CPU(type, name) \
-    __typeof__(type) per_cpu__##name
-
-#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name)	\
-    DEFINE_PER_CPU(type, name)
-
-#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(var, cpu)			(*((void)(cpu), &per_cpu_var(var)))
+#define __get_cpu_var(var)			per_cpu_var(var)
+#define __raw_get_cpu_var(var)			per_cpu_var(var)
 
 #endif	/* SMP */
 
-#define DECLARE_PER_CPU(type, name) extern __typeof__(type) per_cpu__##name
+#ifndef PER_CPU_ATTRIBUTES
+#define PER_CPU_ATTRIBUTES
+#endif
 
-#define EXPORT_PER_CPU_SYMBOL(var) EXPORT_SYMBOL(per_cpu__##var)
-#define EXPORT_PER_CPU_SYMBOL_GPL(var) EXPORT_SYMBOL_GPL(per_cpu__##var)
+#define DECLARE_PER_CPU(type, name) extern PER_CPU_ATTRIBUTES \
+					__typeof__(type) per_cpu_var(name)
 
 #endif /* _ASM_GENERIC_PERCPU_H_ */
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_PERCPU_ZERO_BASED
+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/vmlinux.lds.h
===================================================================
--- linux-x86.q.orig/include/asm-generic/vmlinux.lds.h
+++ linux-x86.q/include/asm-generic/vmlinux.lds.h
@@ -255,11 +255,27 @@
   	*(.initcall7.init)						\
   	*(.initcall7s.init)
 
+#ifdef CONFIG_PERCPU_ZERO_BASED
+#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 = .;						\
 	.data.percpu  : AT(ADDR(.data.percpu) - LOAD_OFFSET) {		\
+		*(.data.percpu.first)					\
 		*(.data.percpu)						\
 		*(.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
@@ -12,31 +12,10 @@
 # define THIS_CPU(var)	(per_cpu__##var)  /* use this to mark accesses to per-CPU variables... */
 #else /* !__ASSEMBLY__ */
 
-
 #include <linux/threads.h>
 
 #ifdef HAVE_MODEL_SMALL_ATTRIBUTE
-# define __SMALL_ADDR_AREA	__attribute__((__model__ (__small__)))
-#else
-# define __SMALL_ADDR_AREA
-#endif
-
-#define DECLARE_PER_CPU(type, name)				\
-	extern __SMALL_ADDR_AREA __typeof__(type) per_cpu__##name
-
-/* Separate out the type, so (int[3], foo) works. */
-#define DEFINE_PER_CPU(type, name)				\
-	__attribute__((__section__(".data.percpu")))		\
-	__SMALL_ADDR_AREA __typeof__(type) per_cpu__##name
-
-#ifdef CONFIG_SMP
-#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name)			\
-	__attribute__((__section__(".data.percpu.shared_aligned")))	\
-	__SMALL_ADDR_AREA __typeof__(type) per_cpu__##name		\
-	____cacheline_aligned_in_smp
-#else
-#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name)	\
-	DEFINE_PER_CPU(type, name)
+# define PER_CPU_ATTRIBUTES	__attribute__((__model__ (__small__)))
 #endif
 
 /*
@@ -45,39 +24,29 @@
  */
 #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 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)))
+#define __my_cpu_offset	__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 */
 
-#define EXPORT_PER_CPU_SYMBOL(var)		EXPORT_SYMBOL(per_cpu__##var)
-#define EXPORT_PER_CPU_SYMBOL_GPL(var)		EXPORT_SYMBOL_GPL(per_cpu__##var)
-
 /*
  * Be extremely careful when taking the address of this variable!  Due to virtual
  * remapping, it is different from the canonical address returned by __get_cpu_var(var)!
  * 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-powerpc/percpu.h
===================================================================
--- linux-x86.q.orig/include/asm-powerpc/percpu.h
+++ linux-x86.q/include/asm-powerpc/percpu.h
@@ -16,20 +16,6 @@
 #define __my_cpu_offset() get_paca()->data_offset
 #define per_cpu_offset(x) (__per_cpu_offset(x))
 
-/* Separate out the type, so (int[3], foo) works. */
-#define DEFINE_PER_CPU(type, name) \
-    __attribute__((__section__(".data.percpu"))) __typeof__(type) per_cpu__##name
-
-#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name)		\
-    __attribute__((__section__(".data.percpu.shared_aligned"))) \
-    __typeof__(type) per_cpu__##name				\
-    ____cacheline_aligned_in_smp
-
-/* 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))
-
 /* A macro to avoid #include hell... */
 #define percpu_modcopy(pcpudst, src, size)			\
 do {								\
@@ -39,28 +25,7 @@ do {								\
 		       (src), (size));				\
 } while (0)
 
-extern void setup_per_cpu_areas(void);
-
-#else /* ! SMP */
-
-#define DEFINE_PER_CPU(type, name) \
-    __typeof__(type) per_cpu__##name
-#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name)	\
-    DEFINE_PER_CPU(type, name)
-
-#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
-
-#define EXPORT_PER_CPU_SYMBOL(var) EXPORT_SYMBOL(per_cpu__##var)
-#define EXPORT_PER_CPU_SYMBOL_GPL(var) EXPORT_SYMBOL_GPL(per_cpu__##var)
-
-#else
-#include <asm-generic/percpu.h>
 #endif
-
+#include <asm-generic/percpu.h>
 #endif /* _ASM_POWERPC_PERCPU_H_ */
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
@@ -4,8 +4,6 @@
 #include <linux/compiler.h>
 #include <asm/lowcore.h>
 
-#define __GENERIC_PER_CPU
-
 /*
  * s390 uses its own implementation for per cpu data, the offset of
  * the cpu local data area is cached in the cpu's lowcore memory.
@@ -15,41 +13,24 @@
  */
 #if defined(__s390x__) && defined(MODULE)
 
-#define __reloc_hide(var,offset) (*({			\
+#define SHIFT_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_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
-
-extern unsigned long __per_cpu_offset[NR_CPUS];
-
-/* Separate out the type, so (int[3], foo) works. */
-#define DEFINE_PER_CPU(type, name) \
-    __attribute__((__section__(".data.percpu"))) \
-    __typeof__(type) per_cpu__##name
-
-#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name)		\
-    __attribute__((__section__(".data.percpu.shared_aligned"))) \
-    __typeof__(type) per_cpu__##name				\
-    ____cacheline_aligned_in_smp
-
-#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])
+#define __my_cpu_offset S390_lowcore.percpu_offset
 
 /* A macro to avoid #include hell... */
 #define percpu_modcopy(pcpudst, src, size)			\
@@ -60,22 +41,6 @@ do {								\
 		       (src), (size));				\
 } while (0)
 
-#else /* ! SMP */
-
-#define DEFINE_PER_CPU(type, name) \
-    __typeof__(type) per_cpu__##name
-#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name)	\
-    DEFINE_PER_CPU(type, name)
-
-#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
-
-#define EXPORT_PER_CPU_SYMBOL(var) EXPORT_SYMBOL(per_cpu__##var)
-#define EXPORT_PER_CPU_SYMBOL_GPL(var) EXPORT_SYMBOL_GPL(per_cpu__##var)
+#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;
@@ -16,15 +15,6 @@ extern unsigned long __per_cpu_shift;
 	(__per_cpu_base + ((unsigned long)(__cpu) << __per_cpu_shift))
 #define per_cpu_offset(x) (__per_cpu_offset(x))
 
-/* Separate out the type, so (int[3], foo) works. */
-#define DEFINE_PER_CPU(type, name) \
-    __attribute__((__section__(".data.percpu"))) __typeof__(type) per_cpu__##name
-
-#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name)		\
-    __attribute__((__section__(".data.percpu.shared_aligned"))) \
-    __typeof__(type) per_cpu__##name				\
-    ____cacheline_aligned_in_smp
-
 /* 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))
@@ -41,10 +31,6 @@ do {								\
 #else /* ! SMP */
 
 #define real_setup_per_cpu_areas()		do { } while (0)
-#define DEFINE_PER_CPU(type, name) \
-    __typeof__(type) per_cpu__##name
-#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name)	\
-    DEFINE_PER_CPU(type, name)
 
 #define per_cpu(var, cpu)			(*((void)cpu, &per_cpu__##var))
 #define __get_cpu_var(var)			per_cpu__##var
@@ -54,7 +40,4 @@ do {								\
 
 #define DECLARE_PER_CPU(type, name) extern __typeof__(type) per_cpu__##name
 
-#define EXPORT_PER_CPU_SYMBOL(var) EXPORT_SYMBOL(per_cpu__##var)
-#define EXPORT_PER_CPU_SYMBOL_GPL(var) EXPORT_SYMBOL_GPL(per_cpu__##var)
-
 #endif /* __ARCH_SPARC64_PERCPU__ */
Index: linux-x86.q/include/asm-x86/pda.h
===================================================================
--- linux-x86.q.orig/include/asm-x86/pda.h
+++ linux-x86.q/include/asm-x86/pda.h
@@ -39,7 +39,6 @@ struct x8664_pda {
 } ____cacheline_aligned_in_smp;
 
 extern struct x8664_pda *_cpu_pda[];
-extern struct x8664_pda boot_cpu_pda[];
 extern void pda_init(int);
 
 #define cpu_pda(i) (_cpu_pda[i])
Index: linux-x86.q/include/asm-x86/percpu.h
===================================================================
--- linux-x86.q.orig/include/asm-x86/percpu.h
+++ linux-x86.q/include/asm-x86/percpu.h
@@ -1,5 +1,152 @@
-#ifdef CONFIG_X86_32
-# include "percpu_32.h"
+#ifndef _ASM_X86_PERCPU_H_
+#define _ASM_X86_PERCPU_H_
+
+#ifdef CONFIG_X86_64
+#include <linux/compiler.h>
+
+/* Same as asm-generic/percpu.h, except that we store the per cpu offset
+   in the PDA. Longer term the PDA and every per cpu variable
+   should be just put into a single section and referenced directly
+   from %gs */
+
+#ifdef CONFIG_SMP
+#include <asm/pda.h>
+
+#define __per_cpu_offset(cpu) (cpu_pda(cpu)->data_offset)
+#define __my_cpu_offset read_pda(data_offset)
+
+#define per_cpu_offset(x) (__per_cpu_offset(x))
+
+#define __percpu_seg "%%gs:"
+
 #else
-# include "percpu_64.h"
+
+#define __percpu_seg ""
+
 #endif
+#include <asm-generic/percpu.h>
+
+DECLARE_PER_CPU(struct x8664_pda, pda);
+
+#else /* CONFIG_X86_64 */
+
+#ifdef __ASSEMBLY__
+
+/*
+ * PER_CPU finds an address of a per-cpu variable.
+ *
+ * Args:
+ *    var - variable name
+ *    reg - 32bit register
+ *
+ * The resulting address is stored in the "reg" argument.
+ *
+ * Example:
+ *    PER_CPU(cpu_gdt_descr, %ebx)
+ */
+#ifdef CONFIG_SMP
+#define PER_CPU(var, reg)				\
+	movl %fs:per_cpu__##this_cpu_off, reg;		\
+	lea per_cpu__##var(reg), reg
+#define PER_CPU_VAR(var)	%fs:per_cpu__##var
+#else /* ! SMP */
+#define PER_CPU(var, reg)			\
+	movl $per_cpu__##var, reg
+#define PER_CPU_VAR(var)	per_cpu__##var
+#endif	/* SMP */
+
+#else /* ...!ASSEMBLY */
+
+/*
+ * PER_CPU finds an address of a per-cpu variable.
+ *
+ * Args:
+ *    var - variable name
+ *    cpu - 32bit register containing the current CPU number
+ *
+ * The resulting address is stored in the "cpu" argument.
+ *
+ * Example:
+ *    PER_CPU(cpu_gdt_descr, %ebx)
+ */
+#ifdef CONFIG_SMP
+
+#define __my_cpu_offset x86_read_percpu(this_cpu_off)
+
+/* fs segment starts at (positive) offset == __per_cpu_offset[cpu] */
+#define __percpu_seg "%%fs:"
+
+#else  /* !SMP */
+
+#define __percpu_seg ""
+
+#endif	/* SMP */
+
+#include <asm-generic/percpu.h>
+
+/* We can use this directly for local CPU (faster). */
+DECLARE_PER_CPU(unsigned long, this_cpu_off);
+
+#endif /* __ASSEMBLY__ */
+#endif /* !CONFIG_X86_64 */
+
+#ifndef __ASSEMBLY__
+
+/* For arch-specific code, we can use direct single-insn ops (they
+ * don't give an lvalue though). */
+extern void __bad_percpu_size(void);
+
+#define percpu_to_op(op,var,val)				\
+	do {							\
+		typedef typeof(var) T__;			\
+		if (0) { T__ tmp__; tmp__ = (val); }		\
+		switch (sizeof(var)) {				\
+		case 1:						\
+			asm(op "b %1,"__percpu_seg"%0"		\
+			    : "+m" (var)			\
+			    :"ri" ((T__)val));			\
+			break;					\
+		case 2:						\
+			asm(op "w %1,"__percpu_seg"%0"		\
+			    : "+m" (var)			\
+			    :"ri" ((T__)val));			\
+			break;					\
+		case 4:						\
+			asm(op "l %1,"__percpu_seg"%0"		\
+			    : "+m" (var)			\
+			    :"ri" ((T__)val));			\
+			break;					\
+		default: __bad_percpu_size();			\
+		}						\
+	} while (0)
+
+#define percpu_from_op(op,var)					\
+	({							\
+		typeof(var) ret__;				\
+		switch (sizeof(var)) {				\
+		case 1:						\
+			asm(op "b "__percpu_seg"%1,%0"		\
+			    : "=r" (ret__)			\
+			    : "m" (var));			\
+			break;					\
+		case 2:						\
+			asm(op "w "__percpu_seg"%1,%0"		\
+			    : "=r" (ret__)			\
+			    : "m" (var));			\
+			break;					\
+		case 4:						\
+			asm(op "l "__percpu_seg"%1,%0"		\
+			    : "=r" (ret__)			\
+			    : "m" (var));			\
+			break;					\
+		default: __bad_percpu_size();			\
+		}						\
+		ret__; })
+
+#define x86_read_percpu(var) percpu_from_op("mov", per_cpu__##var)
+#define x86_write_percpu(var,val) percpu_to_op("mov", per_cpu__##var, val)
+#define x86_add_percpu(var,val) percpu_to_op("add", per_cpu__##var, val)
+#define x86_sub_percpu(var,val) percpu_to_op("sub", per_cpu__##var, val)
+#define x86_or_percpu(var,val) percpu_to_op("or", per_cpu__##var, val)
+#endif /* !__ASSEMBLY__ */
+#endif /* _ASM_X86_PERCPU_H_ */
Index: linux-x86.q/include/asm-x86/percpu_32.h
===================================================================
--- linux-x86.q.orig/include/asm-x86/percpu_32.h
+++ /dev/null
@@ -1,154 +0,0 @@
-#ifndef __ARCH_I386_PERCPU__
-#define __ARCH_I386_PERCPU__
-
-#ifdef __ASSEMBLY__
-
-/*
- * PER_CPU finds an address of a per-cpu variable.
- *
- * Args:
- *    var - variable name
- *    reg - 32bit register
- *
- * The resulting address is stored in the "reg" argument.
- *
- * Example:
- *    PER_CPU(cpu_gdt_descr, %ebx)
- */
-#ifdef CONFIG_SMP
-#define PER_CPU(var, reg)				\
-	movl %fs:per_cpu__##this_cpu_off, reg;		\
-	lea per_cpu__##var(reg), reg
-#define PER_CPU_VAR(var)	%fs:per_cpu__##var
-#else /* ! SMP */
-#define PER_CPU(var, reg)			\
-	movl $per_cpu__##var, reg
-#define PER_CPU_VAR(var)	per_cpu__##var
-#endif	/* SMP */
-
-#else /* ...!ASSEMBLY */
-
-/*
- * PER_CPU finds an address of a per-cpu variable.
- *
- * Args:
- *    var - variable name
- *    cpu - 32bit register containing the current CPU number
- *
- * The resulting address is stored in the "cpu" argument.
- *
- * Example:
- *    PER_CPU(cpu_gdt_descr, %ebx)
- */
-#ifdef CONFIG_SMP
-/* Same as generic implementation except for optimized local access. */
-#define __GENERIC_PER_CPU
-
-/* This is used for other cpus to find our section. */
-extern unsigned long __per_cpu_offset[];
-
-#define per_cpu_offset(x) (__per_cpu_offset[x])
-
-/* Separate out the type, so (int[3], foo) works. */
-#define DECLARE_PER_CPU(type, name) extern __typeof__(type) per_cpu__##name
-#define DEFINE_PER_CPU(type, name) \
-    __attribute__((__section__(".data.percpu"))) __typeof__(type) per_cpu__##name
-
-#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name)		\
-    __attribute__((__section__(".data.percpu.shared_aligned"))) \
-    __typeof__(type) per_cpu__##name				\
-    ____cacheline_aligned_in_smp
-
-/* We can use this directly for local CPU (faster). */
-DECLARE_PER_CPU(unsigned long, this_cpu_off);
-
-/* var is in discarded region: offset to particular copy we want */
-#define per_cpu(var, cpu) (*({				\
-	extern int simple_indentifier_##var(void);	\
-	RELOC_HIDE(&per_cpu__##var, __per_cpu_offset[cpu]); }))
-
-#define __raw_get_cpu_var(var) (*({					\
-	extern int simple_indentifier_##var(void);			\
-	RELOC_HIDE(&per_cpu__##var, x86_read_percpu(this_cpu_off));	\
-}))
-
-#define __get_cpu_var(var) __raw_get_cpu_var(var)
-
-/* 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 EXPORT_PER_CPU_SYMBOL(var) EXPORT_SYMBOL(per_cpu__##var)
-#define EXPORT_PER_CPU_SYMBOL_GPL(var) EXPORT_SYMBOL_GPL(per_cpu__##var)
-
-/* fs segment starts at (positive) offset == __per_cpu_offset[cpu] */
-#define __percpu_seg "%%fs:"
-#else  /* !SMP */
-#include <asm-generic/percpu.h>
-#define __percpu_seg ""
-#endif	/* SMP */
-
-/* For arch-specific code, we can use direct single-insn ops (they
- * don't give an lvalue though). */
-extern void __bad_percpu_size(void);
-
-#define percpu_to_op(op,var,val)				\
-	do {							\
-		typedef typeof(var) T__;			\
-		if (0) { T__ tmp__; tmp__ = (val); }		\
-		switch (sizeof(var)) {				\
-		case 1:						\
-			asm(op "b %1,"__percpu_seg"%0"		\
-			    : "+m" (var)			\
-			    :"ri" ((T__)val));			\
-			break;					\
-		case 2:						\
-			asm(op "w %1,"__percpu_seg"%0"		\
-			    : "+m" (var)			\
-			    :"ri" ((T__)val));			\
-			break;					\
-		case 4:						\
-			asm(op "l %1,"__percpu_seg"%0"		\
-			    : "+m" (var)			\
-			    :"ri" ((T__)val));			\
-			break;					\
-		default: __bad_percpu_size();			\
-		}						\
-	} while (0)
-
-#define percpu_from_op(op,var)					\
-	({							\
-		typeof(var) ret__;				\
-		switch (sizeof(var)) {				\
-		case 1:						\
-			asm(op "b "__percpu_seg"%1,%0"		\
-			    : "=r" (ret__)			\
-			    : "m" (var));			\
-			break;					\
-		case 2:						\
-			asm(op "w "__percpu_seg"%1,%0"		\
-			    : "=r" (ret__)			\
-			    : "m" (var));			\
-			break;					\
-		case 4:						\
-			asm(op "l "__percpu_seg"%1,%0"		\
-			    : "=r" (ret__)			\
-			    : "m" (var));			\
-			break;					\
-		default: __bad_percpu_size();			\
-		}						\
-		ret__; })
-
-#define x86_read_percpu(var) percpu_from_op("mov", per_cpu__##var)
-#define x86_write_percpu(var,val) percpu_to_op("mov", per_cpu__##var, val)
-#define x86_add_percpu(var,val) percpu_to_op("add", per_cpu__##var, val)
-#define x86_sub_percpu(var,val) percpu_to_op("sub", per_cpu__##var, val)
-#define x86_or_percpu(var,val) percpu_to_op("or", per_cpu__##var, val)
-#endif /* !__ASSEMBLY__ */
-
-#endif /* __ARCH_I386_PERCPU__ */
Index: linux-x86.q/include/asm-x86/percpu_64.h
===================================================================
--- linux-x86.q.orig/include/asm-x86/percpu_64.h
+++ /dev/null
@@ -1,68 +0,0 @@
-#ifndef _ASM_X8664_PERCPU_H_
-#define _ASM_X8664_PERCPU_H_
-#include <linux/compiler.h>
-
-/* Same as asm-generic/percpu.h, except that we store the per cpu offset
-   in the PDA. Longer term the PDA and every per cpu variable
-   should be just put into a single section and referenced directly
-   from %gs */
-
-#ifdef CONFIG_SMP
-
-#include <asm/pda.h>
-
-#define __per_cpu_offset(cpu) (cpu_pda(cpu)->data_offset)
-#define __my_cpu_offset() read_pda(data_offset)
-
-#define per_cpu_offset(x) (__per_cpu_offset(x))
-
-/* Separate out the type, so (int[3], foo) works. */
-#define DEFINE_PER_CPU(type, name) \
-    __attribute__((__section__(".data.percpu"))) __typeof__(type) per_cpu__##name
-
-#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name)		\
-    __attribute__((__section__(".data.percpu.shared_aligned"))) \
-    __typeof__(type) per_cpu__##name				\
-    ____cacheline_internodealigned_in_smp
-
-/* var is in discarded region: offset to particular copy we want */
-#define per_cpu(var, cpu) (*({				\
-	extern int simple_identifier_##var(void);	\
-	RELOC_HIDE(&per_cpu__##var, __per_cpu_offset(cpu)); }))
-#define __get_cpu_var(var) (*({				\
-	extern int simple_identifier_##var(void);	\
-	RELOC_HIDE(&per_cpu__##var, __my_cpu_offset()); }))
-#define __raw_get_cpu_var(var) (*({			\
-	extern int simple_identifier_##var(void);	\
-	RELOC_HIDE(&per_cpu__##var, __my_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)
-
-extern void setup_per_cpu_areas(void);
-
-#else /* ! SMP */
-
-#define DEFINE_PER_CPU(type, name) \
-    __typeof__(type) per_cpu__##name
-#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name)	\
-    DEFINE_PER_CPU(type, name)
-
-#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
-
-#define EXPORT_PER_CPU_SYMBOL(var) EXPORT_SYMBOL(per_cpu__##var)
-#define EXPORT_PER_CPU_SYMBOL_GPL(var) EXPORT_SYMBOL_GPL(per_cpu__##var)
-
-#endif /* _ASM_X8664_PERCPU_H_ */
Index: linux-x86.q/include/linux/percpu.h
===================================================================
--- linux-x86.q.orig/include/linux/percpu.h
+++ linux-x86.q/include/linux/percpu.h
@@ -9,6 +9,27 @@
 
 #include <asm/percpu.h>
 
+#define DEFINE_PER_CPU(type, name)					\
+	__attribute__((__section__(".data.percpu")))			\
+	PER_CPU_ATTRIBUTES __typeof__(type) per_cpu__##name
+
+#ifdef CONFIG_SMP
+#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name)			\
+	__attribute__((__section__(".data.percpu.shared_aligned")))	\
+	PER_CPU_ATTRIBUTES __typeof__(type) per_cpu__##name		\
+	____cacheline_aligned_in_smp
+#else
+#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name)		      \
+	DEFINE_PER_CPU(type, name)
+#endif
+
+#define DEFINE_PER_CPU_FIRST(type, name)				\
+	__attribute__((__section__(".data.percpu.first")))		\
+	PER_CPU_ATTRIBUTES __typeof__(type) per_cpu__##name
+
+#define EXPORT_PER_CPU_SYMBOL(var) EXPORT_SYMBOL(per_cpu__##var)
+#define EXPORT_PER_CPU_SYMBOL_GPL(var) EXPORT_SYMBOL_GPL(per_cpu__##var)
+
 /* Enough to cover all DEFINE_PER_CPUs in kernel, including modules. */
 #ifndef PERCPU_ENOUGH_ROOM
 #ifdef CONFIG_MODULES
Index: linux-x86.q/init/main.c
===================================================================
--- linux-x86.q.orig/init/main.c
+++ linux-x86.q/init/main.c
@@ -363,28 +363,29 @@ static inline void smp_prepare_cpus(unsi
 
 #else
 
-#ifdef __GENERIC_PER_CPU
+#ifndef CONFIG_ARCH_SETS_UP_PER_CPU_AREA
 unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
 
 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;
+	for_each_possible_cpu(cpu) {
+		char *ptr;
+
+		ptr = alloc_bootmem_pages_node(NODE_DATA(cpu_to_node(cpu)),
+								size);
+		__per_cpu_offset[cpu] = ptr - __per_cpu_start;
+		memcpy(ptr, __per_cpu_load, __per_cpu_size);
 	}
 }
-#endif /* !__GENERIC_PER_CPU */
+#endif /* CONFIG_ARCH_SETS_UP_CPU_AREA */
 
 /* Called by boot processor to activate the rest. */
 static void __init smp_init(void)
Index: linux-x86.q/kernel/lockdep.c
===================================================================
--- linux-x86.q.orig/kernel/lockdep.c
+++ linux-x86.q/kernel/lockdep.c
@@ -613,8 +613,8 @@ 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))

  parent reply	other threads:[~2007-11-30 11:25 UTC|newest]

Thread overview: 23+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2007-11-30  6:43 [patch 0/3] Per cpu relocation to ZERO and x86_32 percpu ops on x86_64 Christoph Lameter
2007-11-30  6:43 ` [patch 1/3] Percpu infrastructure to rebase the per cpu area to 0UL Christoph Lameter
2007-12-02  3:04   ` Rusty Russell
2007-12-02  3:13   ` Rusty Russell
2007-11-30  6:43 ` [patch 2/3] X86_64: Declare pda as per cpu data thereby moving it into the cpu area Christoph Lameter
2007-11-30  6:43 ` [patch 3/3] x86_64: Make the x86_32 percpu operations usable on x86_64 Christoph Lameter
2007-11-30 20:07   ` Christoph Lameter
2007-11-30 11:24 ` Ingo Molnar [this message]
2007-11-30 11:26   ` [patch 0/3] Per cpu relocation to ZERO and x86_32 percpu ops " Ingo Molnar
2007-11-30 17:08     ` Christoph Lameter
2007-11-30 17:19     ` Christoph Lameter
2007-11-30 18:00       ` Ingo Molnar
2007-11-30 18:24         ` Christoph Lameter
2007-11-30 18:35           ` Ingo Molnar
2007-11-30 18:47             ` Christoph Lameter
2007-11-30 19:45               ` Ingo Molnar
2007-11-30 19:59                 ` Christoph Lameter
2007-11-30 20:06                   ` Ingo Molnar
2007-11-30 20:09                     ` Christoph Lameter
2007-11-30 20:26                   ` Ingo Molnar
2007-11-30 20:43                     ` Ingo Molnar
2007-11-30 18:41           ` Ingo Molnar
2007-11-30 18:43             ` Christoph Lameter

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20071130112429.GA3605@elte.hu \
    --to=mingo@elte.hu \
    --cc=ak@suse.de \
    --cc=clameter@sgi.com \
    --cc=jeremy@goop.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=rusty@rustcorp.com.au \
    --cc=tglx@linutronix.de \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.