diff --git a/arch/alpha/kernel/vmlinux.lds.S b/arch/alpha/kernel/vmlinux.lds.S
index 3d890a98a08b..f937ad123852 100644
--- a/arch/alpha/kernel/vmlinux.lds.S
+++ b/arch/alpha/kernel/vmlinux.lds.S
@@ -39,7 +39,7 @@ SECTIONS
 	__init_begin = ALIGN(PAGE_SIZE);
 	INIT_TEXT_SECTION(PAGE_SIZE)
 	INIT_DATA_SECTION(16)
-	PERCPU(L1_CACHE_BYTES, PAGE_SIZE)
+	PERCPU_SECTION(L1_CACHE_BYTES)
 	/* Align to THREAD_SIZE rather than PAGE_SIZE here so any padding page
 	   needed for the THREAD_SIZE aligned init_task gets freed after init */
 	. = ALIGN(THREAD_SIZE);
diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S
index b4348e62ef06..e5287f21badc 100644
--- a/arch/arm/kernel/vmlinux.lds.S
+++ b/arch/arm/kernel/vmlinux.lds.S
@@ -82,7 +82,7 @@ SECTIONS
 #endif
 	}
 
-	PERCPU(32, PAGE_SIZE)
+	PERCPU_SECTION(32)
 
 #ifndef CONFIG_XIP_KERNEL
 	. = ALIGN(PAGE_SIZE);
diff --git a/arch/blackfin/kernel/vmlinux.lds.S b/arch/blackfin/kernel/vmlinux.lds.S
index 854fa49f1c3e..8d85c8c6f857 100644
--- a/arch/blackfin/kernel/vmlinux.lds.S
+++ b/arch/blackfin/kernel/vmlinux.lds.S
@@ -136,7 +136,7 @@ SECTIONS
 
 	. = ALIGN(16);
 	INIT_DATA_SECTION(16)
-	PERCPU(32, PAGE_SIZE)
+	PERCPU_SECTION(32)
 
 	.exit.data :
 	{
diff --git a/arch/cris/kernel/vmlinux.lds.S b/arch/cris/kernel/vmlinux.lds.S
index 728bbd9e7d4c..a6990cb0f098 100644
--- a/arch/cris/kernel/vmlinux.lds.S
+++ b/arch/cris/kernel/vmlinux.lds.S
@@ -102,7 +102,7 @@ SECTIONS
 #endif
 	__vmlinux_end = .;		/* Last address of the physical file. */
 #ifdef CONFIG_ETRAX_ARCH_V32
-	PERCPU(32, PAGE_SIZE)
+	PERCPU_SECTION(32)
 
 	.init.ramfs : {
 		INIT_RAM_FS
diff --git a/arch/frv/kernel/vmlinux.lds.S b/arch/frv/kernel/vmlinux.lds.S
index 0daae8af5787..7e958d829ec9 100644
--- a/arch/frv/kernel/vmlinux.lds.S
+++ b/arch/frv/kernel/vmlinux.lds.S
@@ -37,7 +37,7 @@ SECTIONS
   _einittext = .;
 
   INIT_DATA_SECTION(8)
-  PERCPU(L1_CACHE_BYTES, 4096)
+  PERCPU_SECTION(L1_CACHE_BYTES)
 
   . = ALIGN(PAGE_SIZE);
   __init_end = .;
diff --git a/arch/m32r/kernel/vmlinux.lds.S b/arch/m32r/kernel/vmlinux.lds.S
index cf95aec77460..018e4a711d79 100644
--- a/arch/m32r/kernel/vmlinux.lds.S
+++ b/arch/m32r/kernel/vmlinux.lds.S
@@ -54,7 +54,7 @@ SECTIONS
   __init_begin = .;
   INIT_TEXT_SECTION(PAGE_SIZE)
   INIT_DATA_SECTION(16)
-  PERCPU(32, PAGE_SIZE)
+  PERCPU_SECTION(32)
   . = ALIGN(PAGE_SIZE);
   __init_end = .;
   /* freed after init ends here */
diff --git a/arch/mips/kernel/vmlinux.lds.S b/arch/mips/kernel/vmlinux.lds.S
index 01af3876cf90..a81176f44c74 100644
--- a/arch/mips/kernel/vmlinux.lds.S
+++ b/arch/mips/kernel/vmlinux.lds.S
@@ -118,7 +118,7 @@ SECTIONS
 		EXIT_DATA
 	}
 
-	PERCPU(1 << CONFIG_MIPS_L1_CACHE_SHIFT, PAGE_SIZE)
+	PERCPU_SECTION(1 << CONFIG_MIPS_L1_CACHE_SHIFT)
 	. = ALIGN(PAGE_SIZE);
 	__init_end = .;
 	/* freed after init ends here */
diff --git a/arch/mn10300/kernel/vmlinux.lds.S b/arch/mn10300/kernel/vmlinux.lds.S
index 968bcd2cb022..6f702a6ab395 100644
--- a/arch/mn10300/kernel/vmlinux.lds.S
+++ b/arch/mn10300/kernel/vmlinux.lds.S
@@ -70,7 +70,7 @@ SECTIONS
 	.exit.text : { EXIT_TEXT; }
 	.exit.data : { EXIT_DATA; }
 
-  PERCPU(32, PAGE_SIZE)
+  PERCPU_SECTION(32)
   . = ALIGN(PAGE_SIZE);
   __init_end = .;
   /* freed after init ends here */
diff --git a/arch/parisc/kernel/vmlinux.lds.S b/arch/parisc/kernel/vmlinux.lds.S
index e1a55849bfa7..fa6f2b8163e0 100644
--- a/arch/parisc/kernel/vmlinux.lds.S
+++ b/arch/parisc/kernel/vmlinux.lds.S
@@ -149,7 +149,7 @@ SECTIONS
 		EXIT_DATA
 	}
 
-	PERCPU(L1_CACHE_BYTES, PAGE_SIZE)
+	PERCPU_SECTION(L1_CACHE_BYTES)
 	. = ALIGN(PAGE_SIZE);
 	__init_end = .;
 	/* freed after init ends here */
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index b9150f07d266..920276c0f6a1 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -160,7 +160,7 @@ SECTIONS
 		INIT_RAM_FS
 	}
 
-	PERCPU(L1_CACHE_BYTES, PAGE_SIZE)
+	PERCPU_SECTION(L1_CACHE_BYTES)
 
 	. = ALIGN(8);
 	.machine.desc : AT(ADDR(.machine.desc) - LOAD_OFFSET) {
diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
index 1bc18cdb525b..56fe6bc81fee 100644
--- a/arch/s390/kernel/vmlinux.lds.S
+++ b/arch/s390/kernel/vmlinux.lds.S
@@ -77,7 +77,7 @@ SECTIONS
 	. = ALIGN(PAGE_SIZE);
 	INIT_DATA_SECTION(0x100)
 
-	PERCPU(0x100, PAGE_SIZE)
+	PERCPU_SECTION(0x100)
 	. = ALIGN(PAGE_SIZE);
 	__init_end = .;		/* freed after init ends here */
 
diff --git a/arch/sh/kernel/vmlinux.lds.S b/arch/sh/kernel/vmlinux.lds.S
index af4d46187a79..731c10ce67b5 100644
--- a/arch/sh/kernel/vmlinux.lds.S
+++ b/arch/sh/kernel/vmlinux.lds.S
@@ -66,7 +66,7 @@ SECTIONS
 		__machvec_end = .;
 	}
 
-	PERCPU(L1_CACHE_BYTES, PAGE_SIZE)
+	PERCPU_SECTION(L1_CACHE_BYTES)
 
 	/*
 	 * .exit.text is discarded at runtime, not link time, to deal with
diff --git a/arch/sparc/kernel/vmlinux.lds.S b/arch/sparc/kernel/vmlinux.lds.S
index 92b557afe535..c0220759003e 100644
--- a/arch/sparc/kernel/vmlinux.lds.S
+++ b/arch/sparc/kernel/vmlinux.lds.S
@@ -108,7 +108,7 @@ SECTIONS
 		__sun4v_2insn_patch_end = .;
 	}
 
-	PERCPU(SMP_CACHE_BYTES, PAGE_SIZE)
+	PERCPU_SECTION(SMP_CACHE_BYTES)
 
 	. = ALIGN(PAGE_SIZE);
 	__init_end = .;
diff --git a/arch/tile/kernel/vmlinux.lds.S b/arch/tile/kernel/vmlinux.lds.S
index 38f64fafdc10..631f10de12fe 100644
--- a/arch/tile/kernel/vmlinux.lds.S
+++ b/arch/tile/kernel/vmlinux.lds.S
@@ -60,7 +60,7 @@ SECTIONS
   . = ALIGN(PAGE_SIZE);
   VMLINUX_SYMBOL(_sinitdata) = .;
   INIT_DATA_SECTION(16) :data =0
-  PERCPU(L2_CACHE_BYTES, PAGE_SIZE)
+  PERCPU_SECTION(L2_CACHE_BYTES)
   . = ALIGN(PAGE_SIZE);
   VMLINUX_SYMBOL(_einitdata) = .;
 
diff --git a/arch/um/include/asm/common.lds.S b/arch/um/include/asm/common.lds.S
index 34bede8aad4a..4938de5512d2 100644
--- a/arch/um/include/asm/common.lds.S
+++ b/arch/um/include/asm/common.lds.S
@@ -42,7 +42,7 @@
 	INIT_SETUP(0)
   }
 
-  PERCPU(32, 32)
+  PERCPU_SECTION(32)
 	
   .initcall.init : {
 	INIT_CALLS
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 53278b0dfdf6..a0a9779084d1 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -509,6 +509,11 @@ do {									\
  * it in software.  The address used in the cmpxchg16 instruction must be
  * aligned to a 16 byte boundary.
  */
+#ifdef CONFIG_SMP
+#define CMPXCHG16B_EMU_CALL "call this_cpu_cmpxchg16b_emu\n\t" ASM_NOP3
+#else
+#define CMPXCHG16B_EMU_CALL "call this_cpu_cmpxchg16b_emu\n\t" ASM_NOP2
+#endif
 #define percpu_cmpxchg16b_double(pcp1, o1, o2, n1, n2)			\
 ({									\
 	char __ret;							\
@@ -517,7 +522,7 @@ do {									\
 	typeof(o2) __o2 = o2;						\
 	typeof(o2) __n2 = n2;						\
 	typeof(o2) __dummy;						\
-	alternative_io("call this_cpu_cmpxchg16b_emu\n\t" ASM_NOP4,	\
+	alternative_io(CMPXCHG16B_EMU_CALL,				\
 		       "cmpxchg16b " __percpu_prefix "(%%rsi)\n\tsetz %0\n\t",	\
 		       X86_FEATURE_CX16,				\
 		       ASM_OUTPUT2("=a"(__ret), "=d"(__dummy)),		\
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 49927a863cc1..61682f0ac264 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -326,7 +326,7 @@ SECTIONS
 	}
 
 #if !defined(CONFIG_X86_64) || !defined(CONFIG_SMP)
-	PERCPU(INTERNODE_CACHE_BYTES, PAGE_SIZE)
+	PERCPU_SECTION(INTERNODE_CACHE_BYTES)
 #endif
 
 	. = ALIGN(PAGE_SIZE);
diff --git a/arch/xtensa/kernel/vmlinux.lds.S b/arch/xtensa/kernel/vmlinux.lds.S
index a2820065927e..88ecea3facb4 100644
--- a/arch/xtensa/kernel/vmlinux.lds.S
+++ b/arch/xtensa/kernel/vmlinux.lds.S
@@ -155,7 +155,7 @@ SECTIONS
     INIT_RAM_FS
   }
 
-  PERCPU(XCHAL_ICACHE_LINESIZE, PAGE_SIZE)
+  PERCPU_SECTION(XCHAL_ICACHE_LINESIZE)
 
   /* We need this dummy segment here */
 
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 077c00d94f6e..db22d136ad08 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -15,7 +15,7 @@
  *	HEAD_TEXT_SECTION
  *	INIT_TEXT_SECTION(PAGE_SIZE)
  *	INIT_DATA_SECTION(...)
- *	PERCPU(CACHELINE_SIZE, PAGE_SIZE)
+ *	PERCPU_SECTION(CACHELINE_SIZE)
  *	__init_end = .;
  *
  *	_stext = .;
@@ -681,6 +681,28 @@
 	*(.discard.*)							\
 	}
 
+/**
+ * PERCPU_INPUT - the percpu input sections
+ * @cacheline: cacheline size
+ *
+ * The core percpu section names and core symbols which do not rely
+ * directly upon load addresses.
+ *
+ * @cacheline is used to align subsections to avoid false cacheline
+ * sharing between subsections for different purposes.
+ */
+#define PERCPU_INPUT(cacheline)						\
+	VMLINUX_SYMBOL(__per_cpu_start) = .;				\
+	*(.data..percpu..first)						\
+	. = ALIGN(PAGE_SIZE);						\
+	*(.data..percpu..page_aligned)					\
+	. = ALIGN(cacheline);						\
+	*(.data..percpu..readmostly)					\
+	. = ALIGN(cacheline);						\
+	*(.data..percpu)						\
+	*(.data..percpu..shared_aligned)				\
+	VMLINUX_SYMBOL(__per_cpu_end) = .;
+
 /**
  * PERCPU_VADDR - define output section for percpu area
  * @cacheline: cacheline size
@@ -703,52 +725,33 @@
  *
  * Note that this macros defines __per_cpu_load as an absolute symbol.
  * If there is no need to put the percpu section at a predetermined
- * address, use PERCPU().
+ * address, use PERCPU_SECTION.
  */
 #define PERCPU_VADDR(cacheline, vaddr, phdr)				\
 	VMLINUX_SYMBOL(__per_cpu_load) = .;				\
 	.data..percpu vaddr : AT(VMLINUX_SYMBOL(__per_cpu_load)		\
 				- LOAD_OFFSET) {			\
-		VMLINUX_SYMBOL(__per_cpu_start) = .;			\
-		*(.data..percpu..first)					\
-		. = ALIGN(PAGE_SIZE);					\
-		*(.data..percpu..page_aligned)				\
-		. = ALIGN(cacheline);					\
-		*(.data..percpu..readmostly)				\
-		. = ALIGN(cacheline);					\
-		*(.data..percpu)					\
-		*(.data..percpu..shared_aligned)			\
-		VMLINUX_SYMBOL(__per_cpu_end) = .;			\
+		PERCPU_INPUT(cacheline)					\
 	} phdr								\
 	. = VMLINUX_SYMBOL(__per_cpu_load) + SIZEOF(.data..percpu);
 
 /**
- * PERCPU - define output section for percpu area, simple version
+ * PERCPU_SECTION - define output section for percpu area, simple version
  * @cacheline: cacheline size
- * @align: required alignment
  *
- * Align to @align and outputs output section for percpu area.  This macro
- * doesn't manipulate @vaddr or @phdr and __per_cpu_load and
+ * Align to PAGE_SIZE and outputs output section for percpu area.  This
+ * macro doesn't manipulate @vaddr or @phdr and __per_cpu_load and
  * __per_cpu_start will be identical.
  *
- * This macro is equivalent to ALIGN(@align); PERCPU_VADDR(@cacheline,,)
+ * This macro is equivalent to ALIGN(PAGE_SIZE); PERCPU_VADDR(@cacheline,,)
  * except that __per_cpu_load is defined as a relative symbol against
  * .data..percpu which is required for relocatable x86_32 configuration.
  */
-#define PERCPU(cacheline, align)					\
-	. = ALIGN(align);						\
+#define PERCPU_SECTION(cacheline)					\
+	. = ALIGN(PAGE_SIZE);						\
 	.data..percpu	: AT(ADDR(.data..percpu) - LOAD_OFFSET) {	\
 		VMLINUX_SYMBOL(__per_cpu_load) = .;			\
-		VMLINUX_SYMBOL(__per_cpu_start) = .;			\
-		*(.data..percpu..first)					\
-		. = ALIGN(PAGE_SIZE);					\
-		*(.data..percpu..page_aligned)				\
-		. = ALIGN(cacheline);					\
-		*(.data..percpu..readmostly)				\
-		. = ALIGN(cacheline);					\
-		*(.data..percpu)					\
-		*(.data..percpu..shared_aligned)			\
-		VMLINUX_SYMBOL(__per_cpu_end) = .;			\
+		PERCPU_INPUT(cacheline)					\
 	}
 
 
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index e3378e8d3a5c..0400553f0d04 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -2866,9 +2866,7 @@ static int alloc_cwqs(struct workqueue_struct *wq)
 		}
 	}
 
-	/* just in case, make sure it's actually aligned
-	 * - this is affected by PERCPU() alignment in vmlinux.lds.S
-	 */
+	/* just in case, make sure it's actually aligned */
 	BUG_ON(!IS_ALIGNED(wq->cpu_wq.v, align));
 	return wq->cpu_wq.v ? 0 : -ENOMEM;
 }
diff --git a/mm/percpu.c b/mm/percpu.c
index a160db39b810..bf80e55dbed7 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -1215,8 +1215,10 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
 	PCPU_SETUP_BUG_ON(ai->nr_groups <= 0);
 #ifdef CONFIG_SMP
 	PCPU_SETUP_BUG_ON(!ai->static_size);
+	PCPU_SETUP_BUG_ON((unsigned long)__per_cpu_start & ~PAGE_MASK);
 #endif
 	PCPU_SETUP_BUG_ON(!base_addr);
+	PCPU_SETUP_BUG_ON((unsigned long)base_addr & ~PAGE_MASK);
 	PCPU_SETUP_BUG_ON(ai->unit_size < size_sum);
 	PCPU_SETUP_BUG_ON(ai->unit_size & ~PAGE_MASK);
 	PCPU_SETUP_BUG_ON(ai->unit_size < PCPU_MIN_UNIT_SIZE);
@@ -1645,8 +1647,8 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size,
 	/* warn if maximum distance is further than 75% of vmalloc space */
 	if (max_distance > (VMALLOC_END - VMALLOC_START) * 3 / 4) {
 		pr_warning("PERCPU: max_distance=0x%zx too large for vmalloc "
-			   "space 0x%lx\n",
-			   max_distance, VMALLOC_END - VMALLOC_START);
+			   "space 0x%lx\n", max_distance,
+			   (unsigned long)(VMALLOC_END - VMALLOC_START));
 #ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK
 		/* and fail if we have fallback */
 		rc = -EINVAL;