diff --git a/arch/alpha/kernel/vmlinux.lds.S b/arch/alpha/kernel/vmlinux.lds.S
index 433be2a24f3149261a03600ca19aa6a33992bbc8..8d57948c0aefad9700ab45542f7610edd3e0b93e 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 b4348e62ef06e7903d07561701dd78c462ff1aaf..e5287f21badc7e87c3c2e7a2d8953d5fb270ec86 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 854fa49f1c3ec964f7f105fd9c0019d133cca420..8d85c8c6f857c5dd985bd4f2bbd07b4668b157fb 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 728bbd9e7d4c1105b802cbc53558e54c350db93a..a6990cb0f098772c8739b8e7e738789414af7dc8 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 0daae8af5787bfd44fe467689b2fdbd2e7b73289..7e958d829ec9810020c75eca7beef1cbfd44a3c2 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 c194d64cdbb9173912ba2962c4a185561a1e2ad4..2e7ccf7299a048731bb9ce31417a501a2b4c1271 100644
--- a/arch/m32r/kernel/vmlinux.lds.S
+++ b/arch/m32r/kernel/vmlinux.lds.S
@@ -53,7 +53,7 @@ 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 832afbb87588bedcf2b8265495fd44b6874ccabb..8616709452b160c481a2109c5723034dcbafdd54 100644
--- a/arch/mips/kernel/vmlinux.lds.S
+++ b/arch/mips/kernel/vmlinux.lds.S
@@ -115,7 +115,7 @@ 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 968bcd2cb0226c325cc37837518e25dafe4ed6b9..6f702a6ab3955531ff31f65fb7ace7c37f01aa1f 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 8f1e4efd143e0f32e40ec48a6afb09247b75f0bc..85b86617fe0beb953d43cff4b76426ca50040a75 100644
--- a/arch/parisc/kernel/vmlinux.lds.S
+++ b/arch/parisc/kernel/vmlinux.lds.S
@@ -145,7 +145,7 @@ 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 b9150f07d2664a9a763ebeda3564b1c08f18fb17..920276c0f6a1d47396451a5a3e9ac0d71d8b3c4c 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 1bc18cdb525b3d838d9b47f7b98fc3474101355f..56fe6bc81fee45804a61c37fb189ccf73a0b72e8 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 af4d46187a79f18bb8ae350294ccb5923f5410fb..731c10ce67b56dd482e95c2ecdb239de023ea831 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 92b557afe535a59e95d8ab185d5d51c254d4d081..c0220759003e13d302a52ebd1ec5e75dd641c531 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 38f64fafdc10a9d8a3271a50d333b9787074ce19..631f10de12feee423e5c3376f56813cc35fb6053 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 34bede8aad4a9ca9c23df9261be3a7c3d8ac20ec..4938de5512d20add327d2865e9c60ce6fb21181a 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/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 624a2016198ef9317992069aaf676da19e5bd6b9..3e9fb5d54f96d98dc9c0463b9f9751724f19ce57 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -319,7 +319,7 @@ 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 a2820065927eaa642224af0d748491506fdd473d..88ecea3facb4e8c81f507a667ed55feda6cfcb1a 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 32c45e5fe0abfa4516fb3b56103b68b134b1d70c..f301cea5ca2d7cab0b52de3f96e6a927a4859173 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 = .;
@@ -709,7 +709,7 @@
  *
  * 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) = .;				\
@@ -729,20 +729,19 @@
 	. = 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) = .;			\
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 04ef830690eceea974d90add3de55b57bc4048f6..d30a502e8c6d345289817b4f16c7d72bb04bc109 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -2860,9 +2860,7 @@ 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 3f930018aa60dc075bc49f7283c57b2b3b6f0035..c5feb79f5995d375f37b17ebe599f3fc407b422a 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -1216,8 +1216,10 @@ 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);