Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu: (46 commits)
  powerpc64: convert to dynamic percpu allocator
  sparc64: use embedding percpu first chunk allocator
  percpu: kill lpage first chunk allocator
  x86,percpu: use embedding for 64bit NUMA and page for 32bit NUMA
  percpu: update embedding first chunk allocator to handle sparse units
  percpu: use group information to allocate vmap areas sparsely
  vmalloc: implement pcpu_get_vm_areas()
  vmalloc: separate out insert_vmalloc_vm()
  percpu: add chunk->base_addr
  percpu: add pcpu_unit_offsets[]
  percpu: introduce pcpu_alloc_info and pcpu_group_info
  percpu: move pcpu_lpage_build_unit_map() and pcpul_lpage_dump_cfg() upward
  percpu: add @align to pcpu_fc_alloc_fn_t
  percpu: make @dyn_size mandatory for pcpu_setup_first_chunk()
  percpu: drop @static_size from first chunk allocators
  percpu: generalize first chunk allocator selection
  percpu: build first chunk allocators selectively
  percpu: rename 4k first chunk allocator to page
  percpu: improve boot messages
  percpu: fix pcpu_reclaim() locking
  ...

Fix trivial conflict as by Tejun Heo in kernel/sched.c

Documentation/kernel-parameters.txt

@@ -1971,11 +1971,12 @@ and is between 256 and 4096 characters. It is defined in the file
 			Format: { 0 | 1 }
 			See arch/parisc/kernel/pdc_chassis.c
 
-	percpu_alloc=	[X86] Select which percpu first chunk allocator to use.
-			Allowed values are one of "lpage", "embed" and "4k".
-			See comments in arch/x86/kernel/setup_percpu.c for
-			details on each allocator.  This parameter is primarily
-			for debugging and performance comparison.
+	percpu_alloc=	Select which percpu first chunk allocator to use.
+			Currently supported values are "embed" and "page".
+			Archs may support subset or none of the	selections.
+			See comments in mm/percpu.c for details on each
+			allocator.  This parameter is primarily	for debugging
+			and performance comparison.
 
 	pf.		[PARIDE]
 			See Documentation/blockdev/paride.txt.

Makefile

@@ -325,7 +325,7 @@ CHECKFLAGS     := -D__linux__ -Dlinux -D__STDC__ -Dunix -D__unix__ \
 MODFLAGS	= -DMODULE
 CFLAGS_MODULE   = $(MODFLAGS)
 AFLAGS_MODULE   = $(MODFLAGS)
-LDFLAGS_MODULE  =
+LDFLAGS_MODULE  = -T $(srctree)/scripts/module-common.lds
 CFLAGS_KERNEL	=
 AFLAGS_KERNEL	=
 CFLAGS_GCOV	= -fprofile-arcs -ftest-coverage

arch/alpha/include/asm/percpu.h

@@ -1,102 +1,18 @@
 #ifndef __ALPHA_PERCPU_H
 #define __ALPHA_PERCPU_H
 
-#include <linux/compiler.h>
-#include <linux/threads.h>
-#include <linux/percpu-defs.h>
-
 /*
- * 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.
- */
-extern unsigned long __per_cpu_offset[NR_CPUS];
-
-#define per_cpu_offset(x) (__per_cpu_offset[x])
-
-#define __my_cpu_offset per_cpu_offset(raw_smp_processor_id())
-#ifdef CONFIG_DEBUG_PREEMPT
-#define my_cpu_offset per_cpu_offset(smp_processor_id())
-#else
-#define my_cpu_offset __my_cpu_offset
-#endif
-
-#ifndef MODULE
-#define SHIFT_PERCPU_PTR(var, offset) RELOC_HIDE(&per_cpu_var(var), (offset))
-#define PER_CPU_DEF_ATTRIBUTES
-#else
-/*
- * To calculate addresses of locally defined variables, GCC uses 32-bit
- * displacement from the GP. Which doesn't work for per cpu variables in
- * modules, as an offset to the kernel per cpu area is way above 4G.
+ * To calculate addresses of locally defined variables, GCC uses
+ * 32-bit displacement from the GP. Which doesn't work for per cpu
+ * variables in modules, as an offset to the kernel per cpu area is
+ * way above 4G.
  *
- * This forces allocation of a GOT entry for per cpu variable using
- * ldq instruction with a 'literal' relocation.
+ * Always use weak definitions for percpu variables in modules.
  */
-#define SHIFT_PERCPU_PTR(var, offset) ({		\
-	extern int simple_identifier_##var(void);	\
-	unsigned long __ptr, tmp_gp;			\
-	asm (  "br	%1, 1f		  	      \n\
-	1:	ldgp	%1, 0(%1)	    	      \n\
-		ldq %0, per_cpu__" #var"(%1)\t!literal"		\
-		: "=&r"(__ptr), "=&r"(tmp_gp));		\
-	(typeof(&per_cpu_var(var)))(__ptr + (offset)); })
-
-#define PER_CPU_DEF_ATTRIBUTES	__used
-
-#endif /* MODULE */
-
-/*
- * A percpu variable may point to a discarded regions. The following are
- * established ways to produce a usable pointer from the percpu variable
- * offset.
- */
-#define per_cpu(var, cpu) \
-	(*SHIFT_PERCPU_PTR(var, per_cpu_offset(cpu)))
-#define __get_cpu_var(var) \
-	(*SHIFT_PERCPU_PTR(var, my_cpu_offset))
-#define __raw_get_cpu_var(var) \
-	(*SHIFT_PERCPU_PTR(var, __my_cpu_offset))
-
-#else /* ! SMP */
-
-#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)
-
-#define PER_CPU_DEF_ATTRIBUTES
-
-#endif /* SMP */
-
-#ifdef CONFIG_SMP
-#define PER_CPU_BASE_SECTION ".data.percpu"
-#else
-#define PER_CPU_BASE_SECTION ".data"
+#if defined(MODULE) && defined(CONFIG_SMP)
+#define ARCH_NEEDS_WEAK_PER_CPU
 #endif
 
-#ifdef CONFIG_SMP
-
-#ifdef MODULE
-#define PER_CPU_SHARED_ALIGNED_SECTION ""
-#else
-#define PER_CPU_SHARED_ALIGNED_SECTION ".shared_aligned"
-#endif
-#define PER_CPU_FIRST_SECTION ".first"
-
-#else
-
-#define PER_CPU_SHARED_ALIGNED_SECTION ""
-#define PER_CPU_FIRST_SECTION ""
-
-#endif
-
-#define PER_CPU_ATTRIBUTES
+#include <asm-generic/percpu.h>
 
 #endif /* __ALPHA_PERCPU_H */

arch/alpha/include/asm/tlbflush.h

@@ -2,6 +2,7 @@
 #define _ALPHA_TLBFLUSH_H
 
 #include <linux/mm.h>
+#include <linux/sched.h>
 #include <asm/compiler.h>
 #include <asm/pgalloc.h>
 

arch/alpha/kernel/vmlinux.lds.S

@@ -134,13 +134,6 @@ SECTIONS
 	__bss_stop = .;
 	_end = .;
 
-	/* Sections to be discarded */
-	/DISCARD/ : {
-		EXIT_TEXT
-		EXIT_DATA
-		*(.exitcall.exit)
-	}
-
 	.mdebug 0 : {
 		*(.mdebug)
 	}
@@ -150,4 +143,6 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+
+	DISCARDS
 }

arch/arm/kernel/vmlinux.lds.S

@@ -83,6 +83,7 @@ SECTIONS
 		EXIT_TEXT
 		EXIT_DATA
 		*(.exitcall.exit)
+		*(.discard)
 		*(.ARM.exidx.exit.text)
 		*(.ARM.extab.exit.text)
 #ifndef CONFIG_HOTPLUG_CPU

arch/avr32/kernel/vmlinux.lds.S

@@ -124,14 +124,11 @@ SECTIONS
 		_end = .;
 	}
 
+	DWARF_DEBUG
+
 	/* When something in the kernel is NOT compiled as a module, the module
 	 * cleanup code and data are put into these segments. Both can then be
 	 * thrown away, as cleanup code is never called unless it's a module.
 	 */
-	/DISCARD/       	: {
-		EXIT_DATA
-		*(.exitcall.exit)
-	}
-
-	DWARF_DEBUG
+	DISCARDS
 }

arch/blackfin/kernel/vmlinux.lds.S

@@ -277,8 +277,5 @@ SECTIONS
 
 	DWARF_DEBUG
 
-	/DISCARD/ :
-	{
-		*(.exitcall.exit)
-	}
+	DISCARDS
 }

arch/blackfin/mm/sram-alloc.c

@@ -42,9 +42,9 @@
 #include <asm/mem_map.h>
 #include "blackfin_sram.h"
 
-static DEFINE_PER_CPU(spinlock_t, l1sram_lock) ____cacheline_aligned_in_smp;
-static DEFINE_PER_CPU(spinlock_t, l1_data_sram_lock) ____cacheline_aligned_in_smp;
-static DEFINE_PER_CPU(spinlock_t, l1_inst_sram_lock) ____cacheline_aligned_in_smp;
+static DEFINE_PER_CPU_SHARED_ALIGNED(spinlock_t, l1sram_lock);
+static DEFINE_PER_CPU_SHARED_ALIGNED(spinlock_t, l1_data_sram_lock);
+static DEFINE_PER_CPU_SHARED_ALIGNED(spinlock_t, l1_inst_sram_lock);
 static spinlock_t l2_sram_lock ____cacheline_aligned_in_smp;
 
 /* the data structure for L1 scratchpad and DATA SRAM */

arch/cris/include/asm/mmu_context.h

@@ -17,7 +17,8 @@ extern void switch_mm(struct mm_struct *prev, struct mm_struct *next,
  * registers like cr3 on the i386
  */
 
-extern volatile DEFINE_PER_CPU(pgd_t *,current_pgd); /* defined in arch/cris/mm/fault.c */
+/* defined in arch/cris/mm/fault.c */
+DECLARE_PER_CPU(pgd_t *, current_pgd);
 
 static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
 {

arch/cris/kernel/vmlinux.lds.S

@@ -140,12 +140,7 @@ SECTIONS
 	_end = .;
 	__end = .;
 
-	/* Sections to be discarded */
-	/DISCARD/ : {
-		EXIT_TEXT
-		EXIT_DATA
-		*(.exitcall.exit)
-        }
-
 	dram_end = dram_start + (CONFIG_ETRAX_DRAM_SIZE - __CONFIG_ETRAX_VMEM_SIZE)*1024*1024;
+
+	DISCARDS
 }

arch/cris/mm/fault.c

@@ -29,7 +29,7 @@ extern void die_if_kernel(const char *, struct pt_regs *, long);
 
 /* current active page directory */
 
-volatile DEFINE_PER_CPU(pgd_t *,current_pgd);
+DEFINE_PER_CPU(pgd_t *, current_pgd);
 unsigned long cris_signal_return_page;
 
 /*

arch/frv/kernel/vmlinux.lds.S

@@ -177,6 +177,8 @@ SECTIONS
   .debug_ranges		0 : { *(.debug_ranges) }
 
   .comment 0 : { *(.comment) }
+
+  DISCARDS
 }
 
 __kernel_image_size_no_bss = __bss_start - __kernel_image_start;

arch/h8300/kernel/vmlinux.lds.S

@@ -152,9 +152,6 @@ SECTIONS
 	__end = . ;
 	__ramstart = .;
 	}
-	/DISCARD/ : {
-		*(.exitcall.exit)
-	}
         .romfs :	
 	{
 		*(.romfs*)
@@ -165,4 +162,6 @@ SECTIONS
 	COMMAND_START = . - 0x200 ;
 	__ramend = . ;
 	}
+
+	DISCARDS
 }

arch/ia64/Kconfig

@@ -89,6 +89,9 @@ config GENERIC_TIME_VSYSCALL
 	bool
 	default y
 
+config HAVE_LEGACY_PER_CPU_AREA
+	def_bool y
+
 config HAVE_SETUP_PER_CPU_AREA
 	def_bool y
 

arch/ia64/kernel/setup.c

@@ -855,11 +855,17 @@ identify_cpu (struct cpuinfo_ia64 *c)
 	c->unimpl_pa_mask = ~((1L<<63) | ((1L << phys_addr_size) - 1));
 }
 
+/*
+ * In UP configuration, setup_per_cpu_areas() is defined in
+ * include/linux/percpu.h
+ */
+#ifdef CONFIG_SMP
 void __init
 setup_per_cpu_areas (void)
 {
 	/* start_kernel() requires this... */
 }
+#endif
 
 /*
  * Do the following calculations:

arch/ia64/kernel/smp.c

@@ -58,7 +58,8 @@ static struct local_tlb_flush_counts {
 	unsigned int count;
 } __attribute__((__aligned__(32))) local_tlb_flush_counts[NR_CPUS];
 
-static DEFINE_PER_CPU(unsigned short, shadow_flush_counts[NR_CPUS]) ____cacheline_aligned;
+static DEFINE_PER_CPU_SHARED_ALIGNED(unsigned short [NR_CPUS],
+				     shadow_flush_counts);
 
 #define IPI_CALL_FUNC		0
 #define IPI_CPU_STOP		1

arch/ia64/kernel/vmlinux.lds.S

@@ -24,14 +24,14 @@ PHDRS {
 }
 SECTIONS
 {
-  /* Sections to be discarded */
+  /* unwind exit sections must be discarded before the rest of the
+     sections get included. */
   /DISCARD/ : {
-	EXIT_TEXT
-	EXIT_DATA
-	*(.exitcall.exit)
 	*(.IA_64.unwind.exit.text)
 	*(.IA_64.unwind_info.exit.text)
-	}
+	*(.comment)
+	*(.note)
+  }
 
   v = PAGE_OFFSET;	/* this symbol is here to make debugging easier... */
   phys_start = _start - LOAD_OFFSET;
@@ -316,7 +316,7 @@ SECTIONS
   .debug_funcnames 0 : { *(.debug_funcnames) }
   .debug_typenames 0 : { *(.debug_typenames) }
   .debug_varnames  0 : { *(.debug_varnames) }
-  /* These must appear regardless of  .  */
-  /DISCARD/ : { *(.comment) }
-  /DISCARD/ : { *(.note) }
+
+  /* Default discards */
+  DISCARDS
 }

arch/ia64/sn/kernel/setup.c

@@ -71,7 +71,7 @@ EXPORT_SYMBOL(sn_rtc_cycles_per_second);
 DEFINE_PER_CPU(struct sn_hub_info_s, __sn_hub_info);
 EXPORT_PER_CPU_SYMBOL(__sn_hub_info);
 
-DEFINE_PER_CPU(short, __sn_cnodeid_to_nasid[MAX_COMPACT_NODES]);
+DEFINE_PER_CPU(short [MAX_COMPACT_NODES], __sn_cnodeid_to_nasid);
 EXPORT_PER_CPU_SYMBOL(__sn_cnodeid_to_nasid);
 
 DEFINE_PER_CPU(struct nodepda_s *, __sn_nodepda);

arch/m32r/kernel/vmlinux.lds.S

@@ -120,13 +120,6 @@ SECTIONS
 
   _end = . ;
 
-  /* Sections to be discarded */
-  /DISCARD/ : {
-	EXIT_TEXT
-	EXIT_DATA
-	*(.exitcall.exit)
-	}
-
   /* Stabs debugging sections.  */
   .stab 0 : { *(.stab) }
   .stabstr 0 : { *(.stabstr) }
@@ -135,4 +128,7 @@ SECTIONS
   .stab.index 0 : { *(.stab.index) }
   .stab.indexstr 0 : { *(.stab.indexstr) }
   .comment 0 : { *(.comment) }
+
+  /* Sections to be discarded */
+  DISCARDS
 }