Merge branch 'for-next' into for-linus

* pcpu_chunk_page_occupied() doesn't exist in for-next.
* pcpu_chunk_addr_search() updated to use raw_smp_processor_id().

Conflicts:
	mm/percpu.c

49 files changed, 246 insertions, 745 deletions

diff --git a/arch/alpha/include/asm/percpu.h b/arch/alpha/include/asm/percpu.h
index b663f1f10b6..2c12378e3aa 100644
--- a/arch/alpha/include/asm/percpu.h
+++ b/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.
- */
-#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.
+ * Always use weak definitions for percpu variables in modules.
  */
-#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"
-#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 ""
-
+#if defined(MODULE) && defined(CONFIG_SMP)
+#define ARCH_NEEDS_WEAK_PER_CPU
 #endif
 
-#define PER_CPU_ATTRIBUTES
+#include <asm-generic/percpu.h>
 
 #endif /* __ALPHA_PERCPU_H */
diff --git a/arch/alpha/include/asm/tlbflush.h b/arch/alpha/include/asm/tlbflush.h
index 9d87aaa08c0..e89e0c2e15b 100644
--- a/arch/alpha/include/asm/tlbflush.h
+++ b/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>
 
diff --git a/arch/alpha/kernel/vmlinux.lds.S b/arch/alpha/kernel/vmlinux.lds.S
index b9d6568e5f7..6dc03c35caa 100644
--- a/arch/alpha/kernel/vmlinux.lds.S
+++ b/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
 }
diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S
index 69371028a20..5cc4812c976 100644
--- a/arch/arm/kernel/vmlinux.lds.S
+++ b/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
diff --git a/arch/avr32/kernel/vmlinux.lds.S b/arch/avr32/kernel/vmlinux.lds.S
index 7910d41eb88..c4b56654349 100644
--- a/arch/avr32/kernel/vmlinux.lds.S
+++ b/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
 }
diff --git a/arch/blackfin/kernel/vmlinux.lds.S b/arch/blackfin/kernel/vmlinux.lds.S
index 6ac307ca0d8..d7ffe299b97 100644
--- a/arch/blackfin/kernel/vmlinux.lds.S
+++ b/arch/blackfin/kernel/vmlinux.lds.S
@@ -277,8 +277,5 @@ SECTIONS
 
 	DWARF_DEBUG
 
-	/DISCARD/ :
-	{
-		*(.exitcall.exit)
-	}
+	DISCARDS
 }
diff --git a/arch/blackfin/mm/sram-alloc.c b/arch/blackfin/mm/sram-alloc.c
index 0bc3c4ef0aa..99e4dbb1dfd 100644
--- a/arch/blackfin/mm/sram-alloc.c
+++ b/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 */
diff --git a/arch/cris/include/asm/mmu_context.h b/arch/cris/include/asm/mmu_context.h
index 72ba08dcfd1..1d45fd6365b 100644
--- a/arch/cris/include/asm/mmu_context.h
+++ b/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)
 {
diff --git a/arch/cris/kernel/vmlinux.lds.S b/arch/cris/kernel/vmlinux.lds.S
index 0d2adfc794d..6c81836b922 100644
--- a/arch/cris/kernel/vmlinux.lds.S
+++ b/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
 }
diff --git a/arch/cris/mm/fault.c b/arch/cris/mm/fault.c
index f925115e325..4a7cdd9ea1e 100644
--- a/arch/cris/mm/fault.c
+++ b/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;
 
 /*
diff --git a/arch/frv/kernel/vmlinux.lds.S b/arch/frv/kernel/vmlinux.lds.S
index 22d9787406e..7dbf41f68b5 100644
--- a/arch/frv/kernel/vmlinux.lds.S
+++ b/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;
diff --git a/arch/h8300/kernel/vmlinux.lds.S b/arch/h8300/kernel/vmlinux.lds.S
index 43a87b9085b..662b02ecb86 100644
--- a/arch/h8300/kernel/vmlinux.lds.S
+++ b/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
 }
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 170042b420d..328d2f8b8c3 100644
--- a/arch/ia64/Kconfig
+++ b/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
 
diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c
index 1b23ec126b6..1de86c96801 100644
--- a/arch/ia64/kernel/setup.c
+++ b/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:
diff --git a/arch/ia64/kernel/smp.c b/arch/ia64/kernel/smp.c
index f0c521b0ba4..93ebfea43c6 100644
--- a/arch/ia64/kernel/smp.c
+++ b/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
diff --git a/arch/ia64/kernel/vmlinux.lds.S b/arch/ia64/kernel/vmlinux.lds.S
index 4a95e86b9ac..eb4214d1c5a 100644
--- a/arch/ia64/kernel/vmlinux.lds.S
+++ b/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
 }
diff --git a/arch/ia64/sn/kernel/setup.c b/arch/ia64/sn/kernel/setup.c
index e456f062f24..ece1bf99449 100644
--- a/arch/ia64/sn/kernel/setup.c
+++ b/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);
diff --git a/arch/m32r/kernel/vmlinux.lds.S b/arch/m32r/kernel/vmlinux.lds.S
index 4179adf6c62..de5e21cca6a 100644
--- a/arch/m32r/kernel/vmlinux.lds.S
+++ b/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
 }
diff --git a/arch/m68k/kernel/vmlinux-std.lds b/arch/m68k/kernel/vmlinux-std.lds
index 01d212bb05a..47eac19e8f6 100644
--- a/arch/m68k/kernel/vmlinux-std.lds
+++ b/arch/m68k/kernel/vmlinux-std.lds
@@ -82,13 +82,6 @@ SECTIONS
 
   _end = . ;
 
-  /* Sections to be discarded */
-  /DISCARD/ : {
-	EXIT_TEXT
-	EXIT_DATA
-	*(.exitcall.exit)
-	}
-
   /* Stabs debugging sections.  */
   .stab 0 : { *(.stab) }
   .stabstr 0 : { *(.stabstr) }
@@ -97,4 +90,7 @@ SECTIONS
   .stab.index 0 : { *(.stab.index) }
   .stab.indexstr 0 : { *(.stab.indexstr) }
   .comment 0 : { *(.comment) }
+
+  /* Sections to be discarded */
+  DISCARDS
 }
diff --git a/arch/m68k/kernel/vmlinux-sun3.lds b/arch/m68k/kernel/vmlinux-sun3.lds
index c192f773db9..03efaf04d7d 100644
--- a/arch/m68k/kernel/vmlinux-sun3.lds
+++ b/arch/m68k/kernel/vmlinux-sun3.lds
@@ -77,13 +77,6 @@ __init_begin = .;
 
   _end = . ;
 
-  /* Sections to be discarded */
-  /DISCARD/ : {
-	EXIT_TEXT
-	EXIT_DATA
-	*(.exitcall.exit)
-	}
-
   .crap : {
 	/* Stabs debugging sections.  */
 	*(.stab)
@@ -96,4 +89,6 @@ __init_begin = .;
 	*(.note)
   }
 
+  /* Sections to be discarded */
+  DISCARDS
 }
diff --git a/arch/m68knommu/kernel/vmlinux.lds.S b/arch/m68knommu/kernel/vmlinux.lds.S
index b7fe505e358..2736a5e309c 100644
--- a/arch/m68knommu/kernel/vmlinux.lds.S
+++ b/arch/m68knommu/kernel/vmlinux.lds.S
@@ -184,12 +184,6 @@ SECTIONS {
 		__init_end = .;
 	} > INIT
 
-	/DISCARD/ : {
-		EXIT_TEXT
-		EXIT_DATA
-		*(.exitcall.exit)
-	}
-
 	.bss : {
 		. = ALIGN(4);
 		_sbss = . ;
@@ -200,5 +194,6 @@ SECTIONS {
 	 	_end = . ;
 	} > BSS
 
+	DISCARDS
 }
 
diff --git a/arch/microblaze/kernel/vmlinux.lds.S b/arch/microblaze/kernel/vmlinux.lds.S
index d34d38dcd12..ec5fa91a48d 100644
--- a/arch/microblaze/kernel/vmlinux.lds.S
+++ b/arch/microblaze/kernel/vmlinux.lds.S
@@ -23,8 +23,8 @@ SECTIONS {
 		_stext = . ;
 		*(.text .text.*)
 		*(.fixup)
-
-		*(.exitcall.exit)
+               EXIT_TEXT
+               EXIT_CALL
 		SCHED_TEXT
 		LOCK_TEXT
 		KPROBES_TEXT
@@ -162,4 +162,6 @@ SECTIONS {
 	}
 	. = ALIGN(4096);
 	_end = .;
+
+	DISCARDS
 }
diff --git a/arch/mips/kernel/vmlinux.lds.S b/arch/mips/kernel/vmlinux.lds.S
index 58738c8d754..1474c18fb77 100644
--- a/arch/mips/kernel/vmlinux.lds.S
+++ b/arch/mips/kernel/vmlinux.lds.S
@@ -176,17 +176,6 @@ SECTIONS
 
 	_end = . ;
 
-	/* Sections to be discarded */
-	/DISCARD/ : {
-		*(.exitcall.exit)
-
-		/* ABI crap starts here */
-		*(.MIPS.options)
-		*(.options)
-		*(.pdr)
-		*(.reginfo)
-	}
-
 	/* These mark the ABI of the kernel for debuggers.  */
 	.mdebug.abi32 : {
 		KEEP(*(.mdebug.abi32))
@@ -212,4 +201,14 @@ SECTIONS
 		*(.gptab.bss)
 		*(.gptab.sbss)
 	}
+
+	/* Sections to be discarded */
+	DISCARDS
+	/DISCARD/ : {
+		/* ABI crap starts here */
+		*(.MIPS.options)
+		*(.options)
+		*(.pdr)
+		*(.reginfo)
+	}
 }
diff --git a/arch/mn10300/kernel/vmlinux.lds.S b/arch/mn10300/kernel/vmlinux.lds.S
index f4aa0793465..76f41bdb79c 100644
--- a/arch/mn10300/kernel/vmlinux.lds.S
+++ b/arch/mn10300/kernel/vmlinux.lds.S
@@ -115,12 +115,10 @@ SECTIONS
   . = ALIGN(PAGE_SIZE);
   pg0 = .;
 
-  /* Sections to be discarded */
-  /DISCARD/ : {
-	EXIT_CALL
-	}
-
   STABS_DEBUG
 
   DWARF_DEBUG
+
+  /* Sections to be discarded */
+  DISCARDS
 }
diff --git a/arch/parisc/kernel/vmlinux.lds.S b/arch/parisc/kernel/vmlinux.lds.S
index fd2cc4fd2b6..aea1784edbd 100644
--- a/arch/parisc/kernel/vmlinux.lds.S
+++ b/arch/parisc/kernel/vmlinux.lds.S
@@ -237,9 +237,12 @@ SECTIONS
 	/* freed after init ends here */
 	_end = . ;
 
+	STABS_DEBUG
+	.note 0 : { *(.note) }
+
 	/* Sections to be discarded */
+	DISCARDS
 	/DISCARD/ : {
-		*(.exitcall.exit)
 #ifdef CONFIG_64BIT
 		/* temporary hack until binutils is fixed to not emit these
 	 	 * for static binaries
@@ -252,7 +255,4 @@ SECTIONS
 		*(.gnu.hash)
 #endif
 	}
-
-	STABS_DEBUG
-	.note 0 : { *(.note) }	
 }
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index d00131ca083..2c42e1526d0 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -49,6 +49,9 @@ config GENERIC_HARDIRQS_NO__DO_IRQ
 config HAVE_SETUP_PER_CPU_AREA
 	def_bool PPC64
 
+config NEED_PER_CPU_EMBED_FIRST_CHUNK
+	def_bool PPC64
+
 config IRQ_PER_CPU
 	bool
 	default y
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 1f6816003eb..aa6e4500635 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -57,6 +57,7 @@
 #include <asm/cache.h>
 #include <asm/page.h>
 #include <asm/mmu.h>
+#include <asm/mmu-hash64.h>
 #include <asm/firmware.h>
 #include <asm/xmon.h>
 #include <asm/udbg.h>
@@ -569,25 +570,53 @@ void cpu_die(void)
 }
 
 #ifdef CONFIG_SMP
-void __init setup_per_cpu_areas(void)
+#define PCPU_DYN_SIZE		()
+
+static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align)
 {
-	int i;
-	unsigned long size;
-	char *ptr;
-
-	/* Copy section for each CPU (we discard the original) */
-	size = ALIGN(__per_cpu_end - __per_cpu_start, PAGE_SIZE);
-#ifdef CONFIG_MODULES
-	if (size < PERCPU_ENOUGH_ROOM)
-		size = PERCPU_ENOUGH_ROOM;
-#endif
+	return __alloc_bootmem_node(NODE_DATA(cpu_to_node(cpu)), size, align,
+				    __pa(MAX_DMA_ADDRESS));
+}
 
-	for_each_possible_cpu(i) {
-		ptr = alloc_bootmem_pages_node(NODE_DATA(cpu_to_node(i)), size);
+static void __init pcpu_fc_free(void *ptr, size_t size)
+{
+	free_bootmem(__pa(ptr), size);
+}
 
-		paca[i].data_offset = ptr - __per_cpu_start;
-		memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start);
-	}
+static int pcpu_cpu_distance(unsigned int from, unsigned int to)
+{
+	if (cpu_to_node(from) == cpu_to_node(to))
+		return LOCAL_DISTANCE;
+	else
+		return REMOTE_DISTANCE;
+}
+
+void __init setup_per_cpu_areas(void)
+{
+	const size_t dyn_size = PERCPU_MODULE_RESERVE + PERCPU_DYNAMIC_RESERVE;
+	size_t atom_size;
+	unsigned long delta;
+	unsigned int cpu;
+	int rc;
+
+	/*
+	 * Linear mapping is one of 4K, 1M and 16M.  For 4K, no need
+	 * to group units.  For larger mappings, use 1M atom which
+	 * should be large enough to contain a number of units.
+	 */
+	if (mmu_linear_psize == MMU_PAGE_4K)
+		atom_size = PAGE_SIZE;
+	else
+		atom_size = 1 << 20;
+
+	rc = pcpu_embed_first_chunk(0, dyn_size, atom_size, pcpu_cpu_distance,
+				    pcpu_fc_alloc, pcpu_fc_free);
+	if (rc < 0)
+		panic("cannot initialize percpu area (err=%d)", rc);
+
+	delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start;
+	for_each_possible_cpu(cpu)
+		paca[cpu].data_offset = delta + pcpu_unit_offsets[cpu];
 }
 #endif
 
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 8ef8a14abc9..244e3658983 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -37,12 +37,6 @@ jiffies = jiffies_64 + 4;
 #endif
 SECTIONS
 {
-	/* Sections to be discarded. */
-	/DISCARD/ : {
-	*(.exitcall.exit)
-	EXIT_DATA
-	}
-
 	. = KERNELBASE;
 
 /*
@@ -298,4 +292,7 @@ SECTIONS
 	. = ALIGN(PAGE_SIZE);
 	_end = . ;
 	PROVIDE32 (end = .);
+
+	/* Sections to be discarded. */
+	DISCARDS
 }
diff --git a/arch/powerpc/mm/stab.c b/arch/powerpc/mm/stab.c
index 98cd1dc2ae7..6e9b69c9985 100644
--- a/arch/powerpc/mm/stab.c
+++ b/arch/powerpc/mm/stab.c
@@ -31,7 +31,7 @@ struct stab_entry {
 
 #define NR_STAB_CACHE_ENTRIES 8
 static DEFINE_PER_CPU(long, stab_cache_ptr);
-static DEFINE_PER_CPU(long, stab_cache[NR_STAB_CACHE_ENTRIES]);
+static DEFINE_PER_CPU(long [NR_STAB_CACHE_ENTRIES], stab_cache);
 
 /*
  * Create a segment table entry for the given esid/vsid pair.
diff --git a/arch/powerpc/platforms/ps3/smp.c b/arch/powerpc/platforms/ps3/smp.c
index f6e04bcc70e..51ffde40af2 100644
--- a/arch/powerpc/platforms/ps3/smp.c
+++ b/arch/powerpc/platforms/ps3/smp.c
@@ -37,7 +37,7 @@
   */
 
 #define MSG_COUNT 4
-static DEFINE_PER_CPU(unsigned int, ps3_ipi_virqs[MSG_COUNT]);
+static DEFINE_PER_CPU(unsigned int [MSG_COUNT], ps3_ipi_virqs);
 
 static void do_message_pass(int target, int msg)
 {
diff --git a/arch/s390/include/asm/percpu.h b/arch/s390/include/asm/percpu.h
index 408d60b4f75..f7ad8719d02 100644
--- a/arch/s390/include/asm/percpu.h
+++ b/arch/s390/include/asm/percpu.h
@@ -1,37 +1,21 @@
 #ifndef __ARCH_S390_PERCPU__
 #define __ARCH_S390_PERCPU__
 
-#include <linux/compiler.h>
-#include <asm/lowcore.h>
-
 /*
  * 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.
- * For 64 bit module code s390 forces the use of a GOT slot for the
- * address of the per cpu variable. This is needed because the module
- * may be more than 4G above the per cpu area.
  */
-#if defined(__s390x__) && defined(MODULE)
-
-#define SHIFT_PERCPU_PTR(ptr,offset) (({			\
-	extern int simple_identifier_##var(void);	\
-	unsigned long *__ptr;				\
-	asm ( "larl %0, %1@GOTENT"		\
-	    : "=a" (__ptr) : "X" (ptr) );		\
-	(typeof(ptr))((*__ptr) + (offset));	}))
-
-#else
-
-#define SHIFT_PERCPU_PTR(ptr, offset) (({				\
-	extern int simple_identifier_##var(void);		\
-	unsigned long __ptr;					\
-	asm ( "" : "=a" (__ptr) : "0" (ptr) );			\
-	(typeof(ptr)) (__ptr + (offset)); }))
+#define __my_cpu_offset S390_lowcore.percpu_offset
 
+/*
+ * For 64 bit module code, the module may be more than 4G above the
+ * per cpu area, use weak definitions to force the compiler to
+ * generate external references.
+ */
+#if defined(CONFIG_SMP) && defined(__s390x__) && defined(MODULE)
+#define ARCH_NEEDS_WEAK_PER_CPU
 #endif
 
-#define __my_cpu_offset S390_lowcore.percpu_offset
-
 #include <asm-generic/percpu.h>
 
 #endif /* __ARCH_S390_PERCPU__ */
diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
index a53db23ee09..82415c75b99 100644
--- a/arch/s390/kernel/vmlinux.lds.S
+++ b/arch/s390/kernel/vmlinux.lds.S
@@ -157,13 +157,10 @@ SECTIONS
 
 	_end = . ;
 
-	/* Sections to be discarded */
-	/DISCARD/ : {
-		EXIT_DATA
-		*(.exitcall.exit)
-	}
-
 	/* Debugging sections.	*/
 	STABS_DEBUG
 	DWARF_DEBUG
+
+	/* Sections to be discarded */
+	DISCARDS
 }
diff --git a/arch/sh/kernel/vmlinux.lds.S b/arch/sh/kernel/vmlinux.lds.S
index f53c76acaed..0ce254bca92 100644
--- a/arch/sh/kernel/vmlinux.lds.S
+++ b/arch/sh/kernel/vmlinux.lds.S
@@ -163,16 +163,14 @@ SECTIONS
 		_end = . ;
 	}
 
+	STABS_DEBUG
+	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/ : {
-		*(.exitcall.exit)
-	}
-
-	STABS_DEBUG
-	DWARF_DEBUG
+	DISCARDS
 }
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 3f8b6a92eab..fbd1233b392 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -95,7 +95,7 @@ config AUDIT_ARCH
 config HAVE_SETUP_PER_CPU_AREA
 	def_bool y if SPARC64
 
-config HAVE_DYNAMIC_PER_CPU_AREA
+config NEED_PER_CPU_EMBED_FIRST_CHUNK
 	def_bool y if SPARC64
 
 config GENERIC_HARDIRQS_NO__DO_IRQ
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index 3691907a43b..ff68373ce6d 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -1389,8 +1389,8 @@ void smp_send_stop(void)
  * RETURNS:
  * Pointer to the allocated area on success, NULL on failure.
  */
-static void * __init pcpu_alloc_bootmem(unsigned int cpu, unsigned long size,
-					unsigned long align)
+static void * __init pcpu_alloc_bootmem(unsigned int cpu, size_t size,
+					size_t align)
 {
 	const unsigned long goal = __pa(MAX_DMA_ADDRESS);
 #ifdef CONFIG_NEED_MULTIPLE_NODES
@@ -1415,127 +1415,35 @@ static void * __init pcpu_alloc_bootmem(unsigned int cpu, unsigned long size,
 #endif
 }
 
-static size_t pcpur_size __initdata;
-static void **pcpur_ptrs __initdata;
-
-static struct page * __init pcpur_get_page(unsigned int cpu, int pageno)
+static void __init pcpu_free_bootmem(void *ptr, size_t size)
 {
-	size_t off = (size_t)pageno << PAGE_SHIFT;
-
-	if (off >= pcpur_size)
-		return NULL;
-
-	return virt_to_page(pcpur_ptrs[cpu] + off);
+	free_bootmem(__pa(ptr), size);
 }
 
-#define PCPU_CHUNK_SIZE (4UL * 1024UL * 1024UL)
-
-static void __init pcpu_map_range(unsigned long start, unsigned long end,
-				  struct page *page)
+static int pcpu_cpu_distance(unsigned int from, unsigned int to)
 {
-	unsigned long pfn = page_to_pfn(page);
-	unsigned long pte_base;
-
-	BUG_ON((pfn<<PAGE_SHIFT)&(PCPU_CHUNK_SIZE - 1UL));
-
-	pte_base = (_PAGE_VALID | _PAGE_SZ4MB_4U |
-		    _PAGE_CP_4U | _PAGE_CV_4U |
-		    _PAGE_P_4U | _PAGE_W_4U);
-	if (tlb_type == hypervisor)
-		pte_base = (_PAGE_VALID | _PAGE_SZ4MB_4V |
-			    _PAGE_CP_4V | _PAGE_CV_4V |
-			    _PAGE_P_4V | _PAGE_W_4V);
-
-	while (start < end) {
-		pgd_t *pgd = pgd_offset_k(start);
-		unsigned long this_end;
-		pud_t *pud;
-		pmd_t *pmd;
-		pte_t *pte;
-
-		pud = pud_offset(pgd, start);
-		if (pud_none(*pud)) {
-			pmd_t *new;
-
-			new = __alloc_bootmem(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE);
-			pud_populate(&init_mm, pud, new);
-		}
-
-		pmd = pmd_offset(pud, start);
-		if (!pmd_present(*pmd)) {
-			pte_t *new;
-
-			new = __alloc_bootmem(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE);
-			pmd_populate_kernel(&init_mm, pmd, new);
-		}
-
-		pte = pte_offset_kernel(pmd, start);
-		this_end = (start + PMD_SIZE) & PMD_MASK;
-		if (this_end > end)
-			this_end = end;
-
-		while (start < this_end) {
-			unsigned long paddr = pfn << PAGE_SHIFT;
-
-			pte_val(*pte) = (paddr | pte_base);
-
-			start += PAGE_SIZE;
-			pte++;
-			pfn++;
-		}
-	}
+	if (cpu_to_node(from) == cpu_to_node(to))
+		return LOCAL_DISTANCE;
+	else
+		return REMOTE_DISTANCE;
 }
 
 void __init setup_per_cpu_areas(void)
 {
-	size_t dyn_size, static_size = __per_cpu_end - __per_cpu_start;
-	static struct vm_struct vm;
-	unsigned long delta, cpu;
-	size_t pcpu_unit_size;
-	size_t ptrs_size;
-
-	pcpur_size = PFN_ALIGN(static_size + PERCPU_MODULE_RESERVE +
-			       PERCPU_DYNAMIC_RESERVE);
-	dyn_size = pcpur_size - static_size - PERCPU_MODULE_RESERVE;
-
+	unsigned long delta;
+	unsigned int cpu;
+	int rc;
 
-	ptrs_size = PFN_ALIGN(nr_cpu_ids * sizeof(pcpur_ptrs[0]));
-	pcpur_ptrs = alloc_bootmem(ptrs_size);
-
-	for_each_possible_cpu(cpu) {
-		pcpur_ptrs[cpu] = pcpu_alloc_bootmem(cpu, PCPU_CHUNK_SIZE,
-						     PCPU_CHUNK_SIZE);
-
-		free_bootmem(__pa(pcpur_ptrs[cpu] + pcpur_size),
-			     PCPU_CHUNK_SIZE - pcpur_size);
-
-		memcpy(pcpur_ptrs[cpu], __per_cpu_load, static_size);
-	}
-
-	/* allocate address and map */
-	vm.flags = VM_ALLOC;
-	vm.size = nr_cpu_ids * PCPU_CHUNK_SIZE;
-	vm_area_register_early(&vm, PCPU_CHUNK_SIZE);
-
-	for_each_possible_cpu(cpu) {
-		unsigned long start = (unsigned long) vm.addr;
-		unsigned long end;
-
-		start += cpu * PCPU_CHUNK_SIZE;
-		end = start + PCPU_CHUNK_SIZE;
-		pcpu_map_range(start, end, virt_to_page(pcpur_ptrs[cpu]));
-	}
-
-	pcpu_unit_size = pcpu_setup_first_chunk(pcpur_get_page, static_size,
-						PERCPU_MODULE_RESERVE, dyn_size,
-						PCPU_CHUNK_SIZE, vm.addr, NULL);
-
-	free_bootmem(__pa(pcpur_ptrs), ptrs_size);
+	rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE,
+				    PERCPU_DYNAMIC_RESERVE, 4 << 20,
+				    pcpu_cpu_distance, pcpu_alloc_bootmem,
+				    pcpu_free_bootmem);
+	if (rc)
+		panic("failed to initialize first chunk (%d)", rc);
 
 	delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start;
-	for_each_possible_cpu(cpu) {
-		__per_cpu_offset(cpu) = delta + cpu * pcpu_unit_size;
-	}
+	for_each_possible_cpu(cpu)
+		__per_cpu_offset(cpu) = delta + pcpu_unit_offsets[cpu];
 
 	/* Setup %g5 for the boot cpu.  */
 	__local_per_cpu_offset = __per_cpu_offset(smp_processor_id());
diff --git a/arch/sparc/kernel/vmlinux.lds.S b/arch/sparc/kernel/vmlinux.lds.S
index fcbbd000ec0..866390feb68 100644
--- a/arch/sparc/kernel/vmlinux.lds.S
+++ b/arch/sparc/kernel/vmlinux.lds.S
@@ -171,12 +171,8 @@ SECTIONS
 	}
 	_end = . ;
 
-	/DISCARD/ : {
-		EXIT_TEXT
-		EXIT_DATA
-		*(.exitcall.exit)
-	}
-
 	STABS_DEBUG
 	DWARF_DEBUG
+
+	DISCARDS
 }
diff --git a/arch/um/include/asm/common.lds.S b/arch/um/include/asm/common.lds.S
index cb0248616d4..37ecc5577a9 100644
--- a/arch/um/include/asm/common.lds.S
+++ b/arch/um/include/asm/common.lds.S
@@ -123,8 +123,3 @@
 	__initramfs_end = .;
   }
 
-  /* Sections to be discarded */
-  /DISCARD/ : {
- 	*(.exitcall.exit)
-  }
-
diff --git a/arch/um/kernel/dyn.lds.S b/arch/um/kernel/dyn.lds.S
index 9975e1ab44f..715a188c047 100644
--- a/arch/um/kernel/dyn.lds.S
+++ b/arch/um/kernel/dyn.lds.S
@@ -156,4 +156,6 @@ SECTIONS
   STABS_DEBUG
 
   DWARF_DEBUG
+
+  DISCARDS
 }
diff --git a/arch/um/kernel/uml.lds.S b/arch/um/kernel/uml.lds.S
index 11b835248b8..2ebd39765db 100644
--- a/arch/um/kernel/uml.lds.S
+++ b/arch/um/kernel/uml.lds.S
@@ -100,4 +100,6 @@ SECTIONS
   STABS_DEBUG
 
   DWARF_DEBUG
+
+  DISCARDS
 }
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 13ffa5df37d..869d7d30144 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -150,7 +150,10 @@ config ARCH_HAS_CACHE_LINE_SIZE
 config HAVE_SETUP_PER_CPU_AREA
 	def_bool y
 
-config HAVE_DYNAMIC_PER_CPU_AREA
+config NEED_PER_CPU_EMBED_FIRST_CHUNK
+	def_bool y
+
+config NEED_PER_CPU_PAGE_FIRST_CHUNK
 	def_bool y
 
 config HAVE_CPUMASK_OF_CPU_MAP
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 103f1ddb0d8..a18c038a307 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -156,15 +156,6 @@ do {							\
 /* We can use this directly for local CPU (faster). */
 DECLARE_PER_CPU(unsigned long, this_cpu_off);
 
-#ifdef CONFIG_NEED_MULTIPLE_NODES
-void *pcpu_lpage_remapped(void *kaddr);
-#else
-static inline void *pcpu_lpage_remapped(void *kaddr)
-{
-	return NULL;
-}
-#endif
-
 #endif /* !__ASSEMBLY__ */
 
 #ifdef CONFIG_SMP
diff --git a/arch/x86/kernel/cpu/cpu_debug.c b/arch/x86/kernel/cpu/cpu_debug.c
index 6b2a52dd040..dca325c0399 100644
--- a/arch/x86/kernel/cpu/cpu_debug.c
+++ b/arch/x86/kernel/cpu/cpu_debug.c
@@ -30,8 +30,8 @@
 #include <asm/apic.h>
 #include <asm/desc.h>
 
-static DEFINE_PER_CPU(struct cpu_cpuX_base, cpu_arr[CPU_REG_ALL_BIT]);
-static DEFINE_PER_CPU(struct cpu_private *, priv_arr[MAX_CPU_FILES]);
+static DEFINE_PER_CPU(struct cpu_cpuX_base [CPU_REG_ALL_BIT], cpu_arr);
+static DEFINE_PER_CPU(struct cpu_private * [MAX_CPU_FILES], priv_arr);
 static DEFINE_PER_CPU(int, cpu_priv_count);
 
 static DEFINE_MUTEX(cpu_debug_lock);
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 1cfb623ce11..14ce5d49b2a 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -1091,7 +1091,7 @@ void mce_log_therm_throt_event(__u64 status)
  */
 static int check_interval = 5 * 60; /* 5 minutes */
 
-static DEFINE_PER_CPU(int, next_interval); /* in jiffies */
+static DEFINE_PER_CPU(int, mce_next_interval); /* in jiffies */
 static DEFINE_PER_CPU(struct timer_list, mce_timer);
 
 static void mcheck_timer(unsigned long data)
@@ -1110,7 +1110,7 @@ static void mcheck_timer(unsigned long data)
 	 * Alert userspace if needed.  If we logged an MCE, reduce the
 	 * polling interval, otherwise increase the polling interval.
 	 */
-	n = &__get_cpu_var(next_interval);
+	n = &__get_cpu_var(mce_next_interval);
 	if (mce_notify_irq())
 		*n = max(*n/2, HZ/100);
 	else
@@ -1311,7 +1311,7 @@ static void mce_cpu_features(struct cpuinfo_x86 *c)
 static void mce_init_timer(void)
 {
 	struct timer_list *t = &__get_cpu_var(mce_timer);
-	int *n = &__get_cpu_var(next_interval);
+	int *n = &__get_cpu_var(mce_next_interval);
 
 	if (mce_ignore_ce)
 		return;
@@ -1912,7 +1912,7 @@ mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
 	case CPU_DOWN_FAILED:
 	case CPU_DOWN_FAILED_FROZEN:
 		t->expires = round_jiffies(jiffies +
-						__get_cpu_var(next_interval));
+					   __get_cpu_var(mce_next_interval));
 		add_timer_on(t, cpu);
 		smp_call_function_single(cpu, mce_reenable_cpu, &action, 1);
 		break;
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index ddae21620bd..bd2a2fa8462 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -69,7 +69,7 @@ struct threshold_bank {
 	struct threshold_block	*blocks;
 	cpumask_var_t		cpus;
 };
-static DEFINE_PER_CPU(struct threshold_bank *, threshold_banks[NR_BANKS]);
+static DEFINE_PER_CPU(struct threshold_bank * [NR_BANKS], threshold_banks);
 
 #ifdef CONFIG_SMP
 static unsigned char shared_bank[NR_BANKS] = {
diff --git a/arch/x86/kernel/cpu/perf_counter.c b/arch/x86/kernel/cpu/perf_counter.c
index 900332b800f..3d4ebbd2e12 100644
--- a/arch/x86/kernel/cpu/perf_counter.c
+++ b/arch/x86/kernel/cpu/perf_counter.c
@@ -976,7 +976,7 @@ amd_pmu_disable_counter(struct hw_perf_counter *hwc, int idx)
 	x86_pmu_disable_counter(hwc, idx);
 }
 
-static DEFINE_PER_CPU(u64, prev_left[X86_PMC_IDX_MAX]);
+static DEFINE_PER_CPU(u64 [X86_PMC_IDX_MAX], pmc_prev_left);
 
 /*
  * Set the next IRQ period, based on the hwc->period_left value.
@@ -1015,7 +1015,7 @@ x86_perf_counter_set_period(struct perf_counter *counter,
 	if (left > x86_pmu.max_period)
 		left = x86_pmu.max_period;
 
-	per_cpu(prev_left[idx], smp_processor_id()) = left;
+	per_cpu(pmc_prev_left[idx], smp_processor_id()) = left;
 
 	/*
 	 * The hw counter starts counting from this counter offset,
@@ -1211,7 +1211,7 @@ void perf_counter_print_debug(void)
 		rdmsrl(x86_pmu.eventsel + idx, pmc_ctrl);
 		rdmsrl(x86_pmu.perfctr  + idx, pmc_count);
 
-		prev_left = per_cpu(prev_left[idx], cpu);
+		prev_left = per_cpu(pmc_prev_left[idx], cpu);
 
 		pr_info("CPU#%d:   gen-PMC%d ctrl:  %016llx\n",
 			cpu, idx, pmc_ctrl);
@@ -1798,8 +1798,8 @@ void callchain_store(struct perf_callchain_entry *entry, u64 ip)
 		entry->ip[entry->nr++] = ip;
 }
 
-static DEFINE_PER_CPU(struct perf_callchain_entry, irq_entry);
-static DEFINE_PER_CPU(struct perf_callchain_entry, nmi_entry);
+static DEFINE_PER_CPU(struct perf_callchain_entry, pmc_irq_entry);
+static DEFINE_PER_CPU(struct perf_callchain_entry, pmc_nmi_entry);
 static DEFINE_PER_CPU(int, in_nmi_frame);
 
 
@@ -1952,9 +1952,9 @@ struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
 	struct perf_callchain_entry *entry;
 
 	if (in_nmi())
-		entry = &__get_cpu_var(nmi_entry);
+		entry = &__get_cpu_var(pmc_nmi_entry);
 	else
-		entry = &__get_cpu_var(irq_entry);
+		entry = &__get_cpu_var(pmc_irq_entry);
 
 	entry->nr = 0;
 
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 07d81916f21..d559af913e1 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -55,6 +55,7 @@ EXPORT_SYMBOL(__per_cpu_offset);
 #define PERCPU_FIRST_CHUNK_RESERVE	0
 #endif
 
+#ifdef CONFIG_X86_32
 /**
  * pcpu_need_numa - determine percpu allocation needs to consider NUMA
  *
@@ -83,6 +84,7 @@ static bool __init pcpu_need_numa(void)
 #endif
 	return false;
 }
+#endif
 
 /**
  * pcpu_alloc_bootmem - NUMA friendly alloc_bootmem wrapper for percpu
@@ -124,308 +126,35 @@ static void * __init pcpu_alloc_bootmem(unsigned int cpu, unsigned long size,
 }
 
 /*
- * Large page remap allocator
- *
- * This allocator uses PMD page as unit.  A PMD page is allocated for
- * each cpu and each is remapped into vmalloc area using PMD mapping.
- * As PMD page is quite large, only part of it is used for the first
- * chunk.  Unused part is returned to the bootmem allocator.
- *
- * So, the PMD pages are mapped twice - once to the physical mapping
- * and to the vmalloc area for the first percpu chunk.  The double
- * mapping does add one more PMD TLB entry pressure but still is much
- * better than only using 4k mappings while still being NUMA friendly.
+ * Helpers for first chunk memory allocation
  */
-#ifdef CONFIG_NEED_MULTIPLE_NODES
-struct pcpul_ent {
-	unsigned int	cpu;
-	void		*ptr;
-};
-
-static size_t pcpul_size;
-static struct pcpul_ent *pcpul_map;
-static struct vm_struct pcpul_vm;
-
-static struct page * __init pcpul_get_page(unsigned int cpu, int pageno)
+static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align)
 {
-	size_t off = (size_t)pageno << PAGE_SHIFT;
-
-	if (off >= pcpul_size)
-		return NULL;
-
-	return virt_to_page(pcpul_map[cpu].ptr + off);
+	return pcpu_alloc_bootmem(cpu, size, align);
 }
 
-static ssize_t __init setup_pcpu_lpage(size_t static_size, bool chosen)
+static void __init pcpu_fc_free(void *ptr, size_t size)
 {
-	size_t map_size, dyn_size;
-	unsigned int cpu;
-	int i, j;
-	ssize_t ret;
-
-	if (!chosen) {
-		size_t vm_size = VMALLOC_END - VMALLOC_START;
-		size_t tot_size = nr_cpu_ids * PMD_SIZE;
-
-		/* on non-NUMA, embedding is better */
-		if (!pcpu_need_numa())
-			return -EINVAL;
-
-		/* don't consume more than 20% of vmalloc area */
-		if (tot_size > vm_size / 5) {
-			pr_info("PERCPU: too large chunk size %zuMB for "
-				"large page remap\n", tot_size >> 20);
-			return -EINVAL;
-		}
-	}
-
-	/* need PSE */
-	if (!cpu_has_pse) {
-		pr_warning("PERCPU: lpage allocator requires PSE\n");
-		return -EINVAL;
-	}
-
-	/*
-	 * Currently supports only single page.  Supporting multiple
-	 * pages won't be too difficult if it ever becomes necessary.
-	 */
-	pcpul_size = PFN_ALIGN(static_size + PERCPU_MODULE_RESERVE +
-			       PERCPU_DYNAMIC_RESERVE);
-	if (pcpul_size > PMD_SIZE) {
-		pr_warning("PERCPU: static data is larger than large page, "
-			   "can't use large page\n");
-		return -EINVAL;
-	}
-	dyn_size = pcpul_size - static_size - PERCPU_FIRST_CHUNK_RESERVE;
-
-	/* allocate pointer array and alloc large pages */
-	map_size = PFN_ALIGN(nr_cpu_ids * sizeof(pcpul_map[0]));
-	pcpul_map = alloc_bootmem(map_size);
-
-	for_each_possible_cpu(cpu) {
-		pcpul_map[cpu].cpu = cpu;
-		pcpul_map[cpu].ptr = pcpu_alloc_bootmem(cpu, PMD_SIZE,
-							PMD_SIZE);
-		if (!pcpul_map[cpu].ptr) {
-			pr_warning("PERCPU: failed to allocate large page "
-				   "for cpu%u\n", cpu);
-			goto enomem;
-		}
-
-		/*
-		 * Only use pcpul_size bytes and give back the rest.
-		 *
-		 * Ingo: The 2MB up-rounding bootmem is needed to make
-		 * sure the partial 2MB page is still fully RAM - it's
-		 * not well-specified to have a PAT-incompatible area
-		 * (unmapped RAM, device memory, etc.) in that hole.
-		 */
-		free_bootmem(__pa(pcpul_map[cpu].ptr + pcpul_size),
-			     PMD_SIZE - pcpul_size);
-
-		memcpy(pcpul_map[cpu].ptr, __per_cpu_load, static_size);
-	}
-
-	/* allocate address and map */
-	pcpul_vm.flags = VM_ALLOC;
-	pcpul_vm.size = nr_cpu_ids * PMD_SIZE;
-	vm_area_register_early(&pcpul_vm, PMD_SIZE);
-
-	for_each_possible_cpu(cpu) {
-		pmd_t *pmd, pmd_v;
-
-		pmd = populate_extra_pmd((unsigned long)pcpul_vm.addr +
-					 cpu * PMD_SIZE);
-		pmd_v = pfn_pmd(page_to_pfn(virt_to_page(pcpul_map[cpu].ptr)),
-				PAGE_KERNEL_LARGE);
-		set_pmd(pmd, pmd_v);
-	}
-
-	/* we're ready, commit */
-	pr_info("PERCPU: Remapped at %p with large pages, static data "
-		"%zu bytes\n", pcpul_vm.addr, static_size);
-
-	ret = pcpu_setup_first_chunk(pcpul_get_page, static_size,
-				     PERCPU_FIRST_CHUNK_RESERVE, dyn_size,
-				     PMD_SIZE, pcpul_vm.addr, NULL);
-
-	/* sort pcpul_map array for pcpu_lpage_remapped() */
-	for (i = 0; i < nr_cpu_ids - 1; i++)
-		for (j = i + 1; j < nr_cpu_ids; j++)
-			if (pcpul_map[i].ptr > pcpul_map[j].ptr) {
-				struct pcpul_ent tmp = pcpul_map[i];
-				pcpul_map[i] = pcpul_map[j];
-				pcpul_map[j] = tmp;
-			}
-
-	return ret;
-
-enomem:
-	for_each_possible_cpu(cpu)
-		if (pcpul_map[cpu].ptr)
-			free_bootmem(__pa(pcpul_map[cpu].ptr), pcpul_size);
-	free_bootmem(__pa(pcpul_map), map_size);
-	return -ENOMEM;
+	free_bootmem(__pa(ptr), size);
 }
 
-/**
- * pcpu_lpage_remapped - determine whether a kaddr is in pcpul recycled area
- * @kaddr: the kernel address in question
- *
- * Determine whether @kaddr falls in the pcpul recycled area.  This is
- * used by pageattr to detect VM aliases and break up the pcpu PMD
- * mapping such that the same physical page is not mapped under
- * different attributes.
- *
- * The recycled area is always at the tail of a partially used PMD
- * page.
- *
- * RETURNS:
- * Address of corresponding remapped pcpu address if match is found;
- * otherwise, NULL.
- */
-void *pcpu_lpage_remapped(void *kaddr)
+static int __init pcpu_cpu_distance(unsigned int from, unsigned int to)
 {
-	void *pmd_addr = (void *)((unsigned long)kaddr & PMD_MASK);
-	unsigned long offset = (unsigned long)kaddr & ~PMD_MASK;
-	int left = 0, right = nr_cpu_ids - 1;
-	int pos;
-
-	/* pcpul in use at all? */
-	if (!pcpul_map)
-		return NULL;
-
-	/* okay, perform binary search */
-	while (left <= right) {
-		pos = (left + right) / 2;
-
-		if (pcpul_map[pos].ptr < pmd_addr)
-			left = pos + 1;
-		else if (pcpul_map[pos].ptr > pmd_addr)
-			right = pos - 1;
-		else {
-			/* it shouldn't be in the area for the first chunk */
-			WARN_ON(offset < pcpul_size);
-
-			return pcpul_vm.addr +
-				pcpul_map[pos].cpu * PMD_SIZE + offset;
-		}
-	}
-
-	return NULL;
-}
+#ifdef CONFIG_NEED_MULTIPLE_NODES
+	if (early_cpu_to_node(from) == early_cpu_to_node(to))
+		return LOCAL_DISTANCE;
+	else
+		return REMOTE_DISTANCE;
 #else
-static ssize_t __init setup_pcpu_lpage(size_t static_size, bool chosen)
-{
-	return -EINVAL;
-}
+	return LOCAL_DISTANCE;
 #endif
-
-/*
- * Embedding allocator
- *
- * The first chunk is sized to just contain the static area plus
- * module and dynamic reserves and embedded into linear physical
- * mapping so that it can use PMD mapping without additional TLB
- * pressure.
- */
-static ssize_t __init setup_pcpu_embed(size_t static_size, bool chosen)
-{
-	size_t reserve = PERCPU_MODULE_RESERVE + PERCPU_DYNAMIC_RESERVE;
-
-	/*
-	 * If large page isn't supported, there's no benefit in doing
-	 * this.  Also, embedding allocation doesn't play well with
-	 * NUMA.
-	 */
-	if (!chosen && (!cpu_has_pse || pcpu_need_numa()))
-		return -EINVAL;
-
-	return pcpu_embed_first_chunk(static_size, PERCPU_FIRST_CHUNK_RESERVE,
-				      reserve - PERCPU_FIRST_CHUNK_RESERVE, -1);
 }
 
-/*
- * 4k page allocator
- *
- * This is the basic allocator.  Static percpu area is allocated
- * page-by-page and most of initialization is done by the generic
- * setup function.
- */
-static struct page **pcpu4k_pages __initdata;
-static int pcpu4k_nr_static_pages __initdata;
-
-static struct page * __init pcpu4k_get_page(unsigned int cpu, int pageno)
-{
-	if (pageno < pcpu4k_nr_static_pages)
-		return pcpu4k_pages[cpu * pcpu4k_nr_static_pages + pageno];
-	return NULL;
-}
-
-static void __init pcpu4k_populate_pte(unsigned long addr)
+static void __init pcpup_populate_pte(unsigned long addr)
 {
 	populate_extra_pte(addr);
 }
 
-static ssize_t __init setup_pcpu_4k(size_t static_size)
-{
-	size_t pages_size;
-	unsigned int cpu;
-	int i, j;
-	ssize_t ret;
-
-	pcpu4k_nr_static_pages = PFN_UP(static_size);
-
-	/* unaligned allocations can't be freed, round up to page size */
-	pages_size = PFN_ALIGN(pcpu4k_nr_static_pages * nr_cpu_ids
-			       * sizeof(pcpu4k_pages[0]));
-	pcpu4k_pages = alloc_bootmem(pages_size);
-
-	/* allocate and copy */
-	j = 0;
-	for_each_possible_cpu(cpu)
-		for (i = 0; i < pcpu4k_nr_static_pages; i++) {
-			void *ptr;
-
-			ptr = pcpu_alloc_bootmem(cpu, PAGE_SIZE, PAGE_SIZE);
-			if (!ptr) {
-				pr_warning("PERCPU: failed to allocate "
-					   "4k page for cpu%u\n", cpu);
-				goto enomem;
-			}
-
-			memcpy(ptr, __per_cpu_load + i * PAGE_SIZE, PAGE_SIZE);
-			pcpu4k_pages[j++] = virt_to_page(ptr);
-		}
-
-	/* we're ready, commit */
-	pr_info("PERCPU: Allocated %d 4k pages, static data %zu bytes\n",
-		pcpu4k_nr_static_pages, static_size);
-
-	ret = pcpu_setup_first_chunk(pcpu4k_get_page, static_size,
-				     PERCPU_FIRST_CHUNK_RESERVE, -1,
-				     -1, NULL, pcpu4k_populate_pte);
-	goto out_free_ar;
-
-enomem:
-	while (--j >= 0)
-		free_bootmem(__pa(page_address(pcpu4k_pages[j])), PAGE_SIZE);
-	ret = -ENOMEM;
-out_free_ar:
-	free_bootmem(__pa(pcpu4k_pages), pages_size);
-	return ret;
-}
-
-/* for explicit first chunk allocator selection */
-static char pcpu_chosen_alloc[16] __initdata;
-
-static int __init percpu_alloc_setup(char *str)
-{
-	strncpy(pcpu_chosen_alloc, str, sizeof(pcpu_chosen_alloc) - 1);
-	return 0;
-}
-early_param("percpu_alloc", percpu_alloc_setup);
-
 static inline void setup_percpu_segment(int cpu)
 {
 #ifdef CONFIG_X86_32
@@ -441,52 +170,49 @@ static inline void setup_percpu_segment(int cpu)
 
 void __init setup_per_cpu_areas(void)
 {
-	size_t static_size = __per_cpu_end - __per_cpu_start;
 	unsigned int cpu;
 	unsigned long delta;
-	size_t pcpu_unit_size;
-	ssize_t ret;
+	int rc;
 
 	pr_info("NR_CPUS:%d nr_cpumask_bits:%d nr_cpu_ids:%d nr_node_ids:%d\n",
 		NR_CPUS, nr_cpumask_bits, nr_cpu_ids, nr_node_ids);
 
 	/*
-	 * Allocate percpu area.  If PSE is supported, try to make use
-	 * of large page mappings.  Please read comments on top of
-	 * each allocator for details.
+	 * Allocate percpu area.  Embedding allocator is our favorite;
+	 * however, on NUMA configurations, it can result in very
+	 * sparse unit mapping and vmalloc area isn't spacious enough
+	 * on 32bit.  Use page in that case.
 	 */
-	ret = -EINVAL;
-	if (strlen(pcpu_chosen_alloc)) {
-		if (strcmp(pcpu_chosen_alloc, "4k")) {
-			if (!strcmp(pcpu_chosen_alloc, "lpage"))
-				ret = setup_pcpu_lpage(static_size, true);
-			else if (!strcmp(pcpu_chosen_alloc, "embed"))
-				ret = setup_pcpu_embed(static_size, true);
-			else
-				pr_warning("PERCPU: unknown allocator %s "
-					   "specified\n", pcpu_chosen_alloc);
-			if (ret < 0)
-				pr_warning("PERCPU: %s allocator failed (%zd), "
-					   "falling back to 4k\n",
-					   pcpu_chosen_alloc, ret);
-		}
-	} else {
-		ret = setup_pcpu_lpage(static_size, false);
-		if (ret < 0)
-			ret = setup_pcpu_embed(static_size, false);
+#ifdef CONFIG_X86_32
+	if (pcpu_chosen_fc == PCPU_FC_AUTO && pcpu_need_numa())
+		pcpu_chosen_fc = PCPU_FC_PAGE;
+#endif
+	rc = -EINVAL;
+	if (pcpu_chosen_fc != PCPU_FC_PAGE) {
+		const size_t atom_size = cpu_has_pse ? PMD_SIZE : PAGE_SIZE;
+		const size_t dyn_size = PERCPU_MODULE_RESERVE +
+			PERCPU_DYNAMIC_RESERVE - PERCPU_FIRST_CHUNK_RESERVE;
+
+		rc = pcpu_embed_first_chunk(PERCPU_FIRST_CHUNK_RESERVE,
+					    dyn_size, atom_size,
+					    pcpu_cpu_distance,
+					    pcpu_fc_alloc, pcpu_fc_free);
+		if (rc < 0)
+			pr_warning("PERCPU: %s allocator failed (%d), "
+				   "falling back to page size\n",
+				   pcpu_fc_names[pcpu_chosen_fc], rc);
 	}
-	if (ret < 0)
-		ret = setup_pcpu_4k(static_size);
-	if (ret < 0)
-		panic("cannot allocate static percpu area (%zu bytes, err=%zd)",
-		      static_size, ret);
-
-	pcpu_unit_size = ret;
+	if (rc < 0)
+		rc = pcpu_page_first_chunk(PERCPU_FIRST_CHUNK_RESERVE,
+					   pcpu_fc_alloc, pcpu_fc_free,
+					   pcpup_populate_pte);
+	if (rc < 0)
+		panic("cannot initialize percpu area (err=%d)", rc);
 
 	/* alrighty, percpu areas up and running */
 	delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start;
 	for_each_possible_cpu(cpu) {
-		per_cpu_offset(cpu) = delta + cpu * pcpu_unit_size;
+		per_cpu_offset(cpu) = delta + pcpu_unit_offsets[cpu];
 		per_cpu(this_cpu_off, cpu) = per_cpu_offset(cpu);
 		per_cpu(cpu_number, cpu) = cpu;
 		setup_percpu_segment(cpu);
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 78d185d797d..bbf4fd044d0 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -380,15 +380,12 @@ SECTIONS
 		_end = .;
 	}
 
-	/* Sections to be discarded */
-	/DISCARD/ : {
-		*(.exitcall.exit)
-		*(.eh_frame)
-		*(.discard)
-	}
-
         STABS_DEBUG
         DWARF_DEBUG
+
+	/* Sections to be discarded */
+	DISCARDS
+	/DISCARD/ : { *(.eh_frame) }
 }
 
 
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 7e600c1962d..f53cfc7f963 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -12,6 +12,7 @@
 #include <linux/seq_file.h>
 #include <linux/debugfs.h>
 #include <linux/pfn.h>
+#include <linux/percpu.h>
 
 #include <asm/e820.h>
 #include <asm/processor.h>
@@ -686,7 +687,7 @@ static int cpa_process_alias(struct cpa_data *cpa)
 {
 	struct cpa_data alias_cpa;
 	unsigned long laddr = (unsigned long)__va(cpa->pfn << PAGE_SHIFT);
-	unsigned long vaddr, remapped;
+	unsigned long vaddr;
 	int ret;
 
 	if (cpa->pfn >= max_pfn_mapped)
@@ -744,24 +745,6 @@ static int cpa_process_alias(struct cpa_data *cpa)
 	}
 #endif
 
-	/*
-	 * If the PMD page was partially used for per-cpu remapping,
-	 * the recycled area needs to be split and modified.  Because
-	 * the area is always proper subset of a PMD page
-	 * cpa->numpages is guaranteed to be 1 for these areas, so
-	 * there's no need to loop over and check for further remaps.
-	 */
-	remapped = (unsigned long)pcpu_lpage_remapped((void *)laddr);
-	if (remapped) {
-		WARN_ON(cpa->numpages > 1);
-		alias_cpa = *cpa;
-		alias_cpa.vaddr = &remapped;
-		alias_cpa.flags &= ~(CPA_PAGES_ARRAY | CPA_ARRAY);
-		ret = __change_page_attr_set_clr(&alias_cpa, 0);
-		if (ret)
-			return ret;
-	}
-
 	return 0;
 }
 
diff --git a/arch/xtensa/kernel/vmlinux.lds.S b/arch/xtensa/kernel/vmlinux.lds.S
index 41c159cd872..921b6ff3b64 100644
--- a/arch/xtensa/kernel/vmlinux.lds.S
+++ b/arch/xtensa/kernel/vmlinux.lds.S
@@ -280,15 +280,6 @@ SECTIONS
     *(.ResetVector.text)
   }
 
-  /* Sections to be discarded */
-  /DISCARD/ :
-  {
-	*(.exit.literal)
-	EXIT_TEXT
-	EXIT_DATA
-        *(.exitcall.exit)
-  }
-
   .xt.lit : { *(.xt.lit) }
   .xt.prop : { *(.xt.prop) }
 
@@ -321,4 +312,8 @@ SECTIONS
     *(.xt.lit)
     *(.gnu.linkonce.p*)
   }
+
+  /* Sections to be discarded */
+  DISCARDS
+  /DISCARD/ : { *(.exit.literal) }
 }