diff --git a/Makefile b/Makefile
index 8e4131b..b62c1e0 100644
--- a/Makefile
+++ b/Makefile
@@ -796,6 +796,10 @@
 quiet_cmd_sysmap = SYSMAP
       cmd_sysmap = $(CONFIG_SHELL) $(srctree)/scripts/mksysmap
 
+# Sort exception table at build time
+quiet_cmd_sortextable = SORTEX
+      cmd_sortextable = $(objtree)/scripts/sortextable
+
 # Link of vmlinux
 # If CONFIG_KALLSYMS is set .version is already updated
 # Generate System.map and verify that the content is consistent
@@ -808,6 +812,12 @@
 	$(call cmd,vmlinux__)
 	$(Q)echo 'cmd_$@ := $(cmd_vmlinux__)' > $(@D)/.$(@F).cmd
 
+	$(if $(CONFIG_BUILDTIME_EXTABLE_SORT),				\
+	  $(Q)$(if $($(quiet)cmd_sortextable),				\
+	    echo '  $($(quiet)cmd_sortextable)  vmlinux' &&)		\
+	  $(cmd_sortextable)  vmlinux)
+
+
 	$(Q)$(if $($(quiet)cmd_sysmap),                                      \
 	  echo '  $($(quiet)cmd_sysmap)  System.map' &&)                     \
 	$(cmd_sysmap) $@ System.map;                                         \
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index f5e1212..85aad03 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -30,6 +30,7 @@
 	select HAVE_MEMBLOCK_NODE_MAP
 	select ARCH_DISCARD_MEMBLOCK
 	select GENERIC_SMP_IDLE_THREAD
+	select BUILDTIME_EXTABLE_SORT
 
 menu "Machine selection"
 
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 7b383d8..21ea6d2 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -83,6 +83,7 @@
 	select DCACHE_WORD_ACCESS
 	select GENERIC_SMP_IDLE_THREAD
 	select HAVE_ARCH_SECCOMP_FILTER
+	select BUILDTIME_EXTABLE_SORT
 
 config INSTRUCTION_DECODER
 	def_bool (KPROBES || PERF_EVENTS)
diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index e3e7340..20e5f7b 100644
--- a/arch/x86/ia32/ia32entry.S
+++ b/arch/x86/ia32/ia32entry.S
@@ -13,6 +13,7 @@
 #include <asm/thread_info.h>	
 #include <asm/segment.h>
 #include <asm/irqflags.h>
+#include <asm/asm.h>
 #include <linux/linkage.h>
 #include <linux/err.h>
 
@@ -146,9 +147,7 @@
  	/* no need to do an access_ok check here because rbp has been
  	   32bit zero extended */ 
 1:	movl	(%rbp),%ebp
- 	.section __ex_table,"a"
- 	.quad 1b,ia32_badarg
- 	.previous	
+	_ASM_EXTABLE(1b,ia32_badarg)
 	orl     $TS_COMPAT,TI_status+THREAD_INFO(%rsp,RIP-ARGOFFSET)
 	testl   $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
 	CFI_REMEMBER_STATE
@@ -303,9 +302,7 @@
 	   32bit zero extended */ 
 	/* hardware stack frame is complete now */	
 1:	movl	(%r8),%r9d
-	.section __ex_table,"a"
-	.quad 1b,ia32_badarg
-	.previous	
+	_ASM_EXTABLE(1b,ia32_badarg)
 	orl     $TS_COMPAT,TI_status+THREAD_INFO(%rsp,RIP-ARGOFFSET)
 	testl   $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
 	CFI_REMEMBER_STATE
diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index 9412d65..1c2d247 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -4,11 +4,9 @@
 #ifdef __ASSEMBLY__
 # define __ASM_FORM(x)	x
 # define __ASM_FORM_COMMA(x) x,
-# define __ASM_EX_SEC	.section __ex_table, "a"
 #else
 # define __ASM_FORM(x)	" " #x " "
 # define __ASM_FORM_COMMA(x) " " #x ","
-# define __ASM_EX_SEC	" .section __ex_table,\"a\"\n"
 #endif
 
 #ifdef CONFIG_X86_32
@@ -42,17 +40,33 @@
 
 /* Exception table entry */
 #ifdef __ASSEMBLY__
-# define _ASM_EXTABLE(from,to)	    \
-	__ASM_EX_SEC ;		    \
-	_ASM_ALIGN ;		    \
-	_ASM_PTR from , to ;	    \
-	.previous
+# define _ASM_EXTABLE(from,to)					\
+	.pushsection "__ex_table","a" ;				\
+	.balign 8 ;						\
+	.long (from) - . ;					\
+	.long (to) - . ;					\
+	.popsection
+
+# define _ASM_EXTABLE_EX(from,to)				\
+	.pushsection "__ex_table","a" ;				\
+	.balign 8 ;						\
+	.long (from) - . ;					\
+	.long (to) - . + 0x7ffffff0 ;				\
+	.popsection
 #else
-# define _ASM_EXTABLE(from,to) \
-	__ASM_EX_SEC	\
-	_ASM_ALIGN "\n" \
-	_ASM_PTR #from "," #to "\n" \
-	" .previous\n"
+# define _ASM_EXTABLE(from,to)					\
+	" .pushsection \"__ex_table\",\"a\"\n"			\
+	" .balign 8\n"						\
+	" .long (" #from ") - .\n"				\
+	" .long (" #to ") - .\n"				\
+	" .popsection\n"
+
+# define _ASM_EXTABLE_EX(from,to)				\
+	" .pushsection \"__ex_table\",\"a\"\n"			\
+	" .balign 8\n"						\
+	" .long (" #from ") - .\n"				\
+	" .long (" #to ") - . + 0x7ffffff0\n"			\
+	" .popsection\n"
 #endif
 
 #endif /* _ASM_X86_ASM_H */
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index e216ba0..e5b97be 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -27,6 +27,7 @@
 #include <asm/desc.h>
 #include <asm/mtrr.h>
 #include <asm/msr-index.h>
+#include <asm/asm.h>
 
 #define KVM_MAX_VCPUS 254
 #define KVM_SOFT_MAX_VCPUS 160
@@ -921,9 +922,7 @@
 	__ASM_SIZE(push) " $666b \n\t"	      \
 	"call kvm_spurious_fault \n\t"	      \
 	".popsection \n\t" \
-	".pushsection __ex_table, \"a\" \n\t" \
-	_ASM_PTR " 666b, 667b \n\t" \
-	".popsection"
+	_ASM_EXTABLE(666b, 667b)
 
 #define __kvm_handle_fault_on_reboot(insn)		\
 	____kvm_handle_fault_on_reboot(insn, "")
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index 95203d4..084ef95 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -169,14 +169,7 @@
 	return native_write_msr_safe(msr, low, high);
 }
 
-/*
- * rdmsr with exception handling.
- *
- * Please note that the exception handling works only after we've
- * switched to the "smart" #GP handler in trap_init() which knows about
- * exception tables - using this macro earlier than that causes machine
- * hangs on boxes which do not implement the @msr in the first argument.
- */
+/* rdmsr with exception handling */
 #define rdmsr_safe(msr, p1, p2)					\
 ({								\
 	int __err;						\
diff --git a/arch/x86/include/asm/nops.h b/arch/x86/include/asm/nops.h
index 405b4032..aff2b33 100644
--- a/arch/x86/include/asm/nops.h
+++ b/arch/x86/include/asm/nops.h
@@ -87,7 +87,11 @@
 #define P6_NOP8	0x0f,0x1f,0x84,0x00,0,0,0,0
 #define P6_NOP5_ATOMIC P6_NOP5
 
+#ifdef __ASSEMBLY__
+#define _ASM_MK_NOP(x) .byte x
+#else
 #define _ASM_MK_NOP(x) ".byte " __stringify(x) "\n"
+#endif
 
 #if defined(CONFIG_MK7)
 #define ASM_NOP1 _ASM_MK_NOP(K7_NOP1)
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index aa0f913..6cbbabf 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -1023,10 +1023,8 @@
 		  call PARA_INDIRECT(pv_cpu_ops+PV_CPU_swapgs)		\
 		 )
 
-#define GET_CR2_INTO_RCX				\
-	call PARA_INDIRECT(pv_mmu_ops+PV_MMU_read_cr2);	\
-	movq %rax, %rcx;				\
-	xorq %rax, %rax;
+#define GET_CR2_INTO_RAX				\
+	call PARA_INDIRECT(pv_mmu_ops+PV_MMU_read_cr2)
 
 #define PARAVIRT_ADJUST_EXCEPTION_FRAME					\
 	PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_adjust_exception_frame), \
diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h
index 1654662..c48a950 100644
--- a/arch/x86/include/asm/segment.h
+++ b/arch/x86/include/asm/segment.h
@@ -205,13 +205,15 @@
 
 #define IDT_ENTRIES 256
 #define NUM_EXCEPTION_VECTORS 32
+/* Bitmask of exception vectors which push an error code on the stack */
+#define EXCEPTION_ERRCODE_MASK  0x00027d00
 #define GDT_SIZE (GDT_ENTRIES * 8)
 #define GDT_ENTRY_TLS_ENTRIES 3
 #define TLS_SIZE (GDT_ENTRY_TLS_ENTRIES * 8)
 
 #ifdef __KERNEL__
 #ifndef __ASSEMBLY__
-extern const char early_idt_handlers[NUM_EXCEPTION_VECTORS][10];
+extern const char early_idt_handlers[NUM_EXCEPTION_VECTORS][2+2+5];
 
 /*
  * Load a segment. Fall back on loading the zero
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index e054459..851fe0d 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -79,11 +79,12 @@
 #define access_ok(type, addr, size) (likely(__range_not_ok(addr, size) == 0))
 
 /*
- * The exception table consists of pairs of addresses: the first is the
- * address of an instruction that is allowed to fault, and the second is
- * the address at which the program should continue.  No registers are
- * modified, so it is entirely up to the continuation code to figure out
- * what to do.
+ * The exception table consists of pairs of addresses relative to the
+ * exception table enty itself: the first is the address of an
+ * instruction that is allowed to fault, and the second is the address
+ * at which the program should continue.  No registers are modified,
+ * so it is entirely up to the continuation code to figure out what to
+ * do.
  *
  * All the routines below use bits of fixup code that are out of line
  * with the main instruction path.  This means when everything is well,
@@ -92,10 +93,14 @@
  */
 
 struct exception_table_entry {
-	unsigned long insn, fixup;
+	int insn, fixup;
 };
+/* This is not the generic standard exception_table_entry format */
+#define ARCH_HAS_SORT_EXTABLE
+#define ARCH_HAS_SEARCH_EXTABLE
 
 extern int fixup_exception(struct pt_regs *regs);
+extern int early_fixup_exception(unsigned long *ip);
 
 /*
  * These are the main single-value transfer routines.  They automatically
@@ -202,8 +207,8 @@
 	asm volatile("1:	movl %%eax,0(%1)\n"			\
 		     "2:	movl %%edx,4(%1)\n"			\
 		     "3:\n"						\
-		     _ASM_EXTABLE(1b, 2b - 1b)				\
-		     _ASM_EXTABLE(2b, 3b - 2b)				\
+		     _ASM_EXTABLE_EX(1b, 2b)				\
+		     _ASM_EXTABLE_EX(2b, 3b)				\
 		     : : "A" (x), "r" (addr))
 
 #define __put_user_x8(x, ptr, __ret_pu)				\
@@ -408,7 +413,7 @@
 #define __get_user_asm_ex(x, addr, itype, rtype, ltype)			\
 	asm volatile("1:	mov"itype" %1,%"rtype"0\n"		\
 		     "2:\n"						\
-		     _ASM_EXTABLE(1b, 2b - 1b)				\
+		     _ASM_EXTABLE_EX(1b, 2b)				\
 		     : ltype(x) : "m" (__m(addr)))
 
 #define __put_user_nocheck(x, ptr, size)			\
@@ -450,7 +455,7 @@
 #define __put_user_asm_ex(x, addr, itype, rtype, ltype)			\
 	asm volatile("1:	mov"itype" %"rtype"0,%1\n"		\
 		     "2:\n"						\
-		     _ASM_EXTABLE(1b, 2b - 1b)				\
+		     _ASM_EXTABLE_EX(1b, 2b)				\
 		     : : ltype(x), "m" (__m(addr)))
 
 /*
diff --git a/arch/x86/include/asm/xsave.h b/arch/x86/include/asm/xsave.h
index c6ce245..8a1b6f9 100644
--- a/arch/x86/include/asm/xsave.h
+++ b/arch/x86/include/asm/xsave.h
@@ -80,10 +80,7 @@
 			     "3:  movl $-1,%[err]\n"
 			     "    jmp  2b\n"
 			     ".previous\n"
-			     ".section __ex_table,\"a\"\n"
-			     _ASM_ALIGN "\n"
-			     _ASM_PTR "1b,3b\n"
-			     ".previous"
+			     _ASM_EXTABLE(1b,3b)
 			     : [err] "=r" (err)
 			     : "D" (buf), "a" (-1), "d" (-1), "0" (0)
 			     : "memory");
@@ -106,10 +103,7 @@
 			     "3:  movl $-1,%[err]\n"
 			     "    jmp  2b\n"
 			     ".previous\n"
-			     ".section __ex_table,\"a\"\n"
-			     _ASM_ALIGN "\n"
-			     _ASM_PTR "1b,3b\n"
-			     ".previous"
+			     _ASM_EXTABLE(1b,3b)
 			     : [err] "=r" (err)
 			     : "D" (xstate), "a" (lmask), "d" (hmask), "0" (0)
 			     : "memory");	/* memory required? */
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 7b784f4..01ccf9b 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -56,6 +56,7 @@
 #include <asm/irq_vectors.h>
 #include <asm/cpufeature.h>
 #include <asm/alternative-asm.h>
+#include <asm/asm.h>
 
 /* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this.  */
 #include <linux/elf-em.h>
@@ -151,10 +152,8 @@
 .pushsection .fixup, "ax"
 99:	movl $0, (%esp)
 	jmp 98b
-.section __ex_table, "a"
-	.align 4
-	.long 98b, 99b
 .popsection
+	_ASM_EXTABLE(98b,99b)
 .endm
 
 .macro PTGS_TO_GS
@@ -164,10 +163,8 @@
 .pushsection .fixup, "ax"
 99:	movl $0, PT_GS(%esp)
 	jmp 98b
-.section __ex_table, "a"
-	.align 4
-	.long 98b, 99b
 .popsection
+	_ASM_EXTABLE(98b,99b)
 .endm
 
 .macro GS_TO_REG reg
@@ -249,12 +246,10 @@
 	jmp 2b
 6:	movl $0, (%esp)
 	jmp 3b
-.section __ex_table, "a"
-	.align 4
-	.long 1b, 4b
-	.long 2b, 5b
-	.long 3b, 6b
 .popsection
+	_ASM_EXTABLE(1b,4b)
+	_ASM_EXTABLE(2b,5b)
+	_ASM_EXTABLE(3b,6b)
 	POP_GS_EX
 .endm
 
@@ -415,10 +410,7 @@
 	jae syscall_fault
 1:	movl (%ebp),%ebp
 	movl %ebp,PT_EBP(%esp)
-.section __ex_table,"a"
-	.align 4
-	.long 1b,syscall_fault
-.previous
+	_ASM_EXTABLE(1b,syscall_fault)
 
 	GET_THREAD_INFO(%ebp)
 
@@ -485,10 +477,8 @@
 .pushsection .fixup,"ax"
 2:	movl $0,PT_FS(%esp)
 	jmp 1b
-.section __ex_table,"a"
-	.align 4
-	.long 1b,2b
 .popsection
+	_ASM_EXTABLE(1b,2b)
 	PTGS_TO_GS_EX
 ENDPROC(ia32_sysenter_target)
 
@@ -543,10 +533,7 @@
 	pushl $do_iret_error
 	jmp error_code
 .previous
-.section __ex_table,"a"
-	.align 4
-	.long irq_return,iret_exc
-.previous
+	_ASM_EXTABLE(irq_return,iret_exc)
 
 	CFI_RESTORE_STATE
 ldt_ss:
@@ -901,10 +888,7 @@
 #ifdef CONFIG_PARAVIRT
 ENTRY(native_iret)
 	iret
-.section __ex_table,"a"
-	.align 4
-	.long native_iret, iret_exc
-.previous
+	_ASM_EXTABLE(native_iret, iret_exc)
 END(native_iret)
 
 ENTRY(native_irq_enable_sysexit)
@@ -1093,13 +1077,10 @@
 	movl %eax,16(%esp)
 	jmp 4b
 .previous
-.section __ex_table,"a"
-	.align 4
-	.long 1b,6b
-	.long 2b,7b
-	.long 3b,8b
-	.long 4b,9b
-.previous
+	_ASM_EXTABLE(1b,6b)
+	_ASM_EXTABLE(2b,7b)
+	_ASM_EXTABLE(3b,8b)
+	_ASM_EXTABLE(4b,9b)
 ENDPROC(xen_failsafe_callback)
 
 BUILD_INTERRUPT3(xen_hvm_callback_vector, XEN_HVM_EVTCHN_CALLBACK,
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index cdc79b5..320852d 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -55,6 +55,7 @@
 #include <asm/paravirt.h>
 #include <asm/ftrace.h>
 #include <asm/percpu.h>
+#include <asm/asm.h>
 #include <linux/err.h>
 
 /* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this.  */
@@ -900,18 +901,12 @@
 
 irq_return:
 	INTERRUPT_RETURN
-
-	.section __ex_table, "a"
-	.quad irq_return, bad_iret
-	.previous
+	_ASM_EXTABLE(irq_return, bad_iret)
 
 #ifdef CONFIG_PARAVIRT
 ENTRY(native_iret)
 	iretq
-
-	.section __ex_table,"a"
-	.quad native_iret, bad_iret
-	.previous
+	_ASM_EXTABLE(native_iret, bad_iret)
 #endif
 
 	.section .fixup,"ax"
@@ -1181,10 +1176,7 @@
 	CFI_ENDPROC
 END(native_load_gs_index)
 
-	.section __ex_table,"a"
-	.align 8
-	.quad gs_change,bad_gs
-	.previous
+	_ASM_EXTABLE(gs_change,bad_gs)
 	.section .fixup,"ax"
 	/* running with kernelgs */
 bad_gs:
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index ce0be7c..463c979 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -21,6 +21,7 @@
 #include <asm/msr-index.h>
 #include <asm/cpufeature.h>
 #include <asm/percpu.h>
+#include <asm/nops.h>
 
 /* Physical address */
 #define pa(X) ((X) - __PAGE_OFFSET)
@@ -363,28 +364,23 @@
 	pushl $0
 	popfl
 
-#ifdef CONFIG_SMP
-	cmpb $0, ready
-	jnz checkCPUtype
-#endif /* CONFIG_SMP */
-
 /*
  * start system 32-bit setup. We need to re-do some of the things done
  * in 16-bit mode for the "real" operations.
  */
-	call setup_idt
-
-checkCPUtype:
-
-	movl $-1,X86_CPUID		#  -1 for no CPUID initially
-
+	movl setup_once_ref,%eax
+	andl %eax,%eax
+	jz 1f				# Did we do this already?
+	call *%eax
+1:
+	
 /* check if it is 486 or 386. */
 /*
  * XXX - this does a lot of unnecessary setup.  Alignment checks don't
  * apply at our cpl of 0 and the stack ought to be aligned already, and
  * we don't need to preserve eflags.
  */
-
+	movl $-1,X86_CPUID	# -1 for no CPUID initially
 	movb $3,X86		# at least 386
 	pushfl			# push EFLAGS
 	popl %eax		# get EFLAGS
@@ -450,21 +446,6 @@
 	movl $(__KERNEL_PERCPU), %eax
 	movl %eax,%fs			# set this cpu's percpu
 
-#ifdef CONFIG_CC_STACKPROTECTOR
-	/*
-	 * The linker can't handle this by relocation.  Manually set
-	 * base address in stack canary segment descriptor.
-	 */
-	cmpb $0,ready
-	jne 1f
-	movl $gdt_page,%eax
-	movl $stack_canary,%ecx
-	movw %cx, 8 * GDT_ENTRY_STACK_CANARY + 2(%eax)
-	shrl $16, %ecx
-	movb %cl, 8 * GDT_ENTRY_STACK_CANARY + 4(%eax)
-	movb %ch, 8 * GDT_ENTRY_STACK_CANARY + 7(%eax)
-1:
-#endif
 	movl $(__KERNEL_STACK_CANARY),%eax
 	movl %eax,%gs
 
@@ -473,7 +454,6 @@
 
 	cld			# gcc2 wants the direction flag cleared at all times
 	pushl $0		# fake return address for unwinder
-	movb $1, ready
 	jmp *(initial_code)
 
 /*
@@ -495,81 +475,122 @@
 	.byte 0xDB,0xE4		/* fsetpm for 287, ignored by 387 */
 	ret
 
+	
+#include "verify_cpu.S"
+
 /*
- *  setup_idt
+ *  setup_once
  *
- *  sets up a idt with 256 entries pointing to
- *  ignore_int, interrupt gates. It doesn't actually load
- *  idt - that can be done only after paging has been enabled
- *  and the kernel moved to PAGE_OFFSET. Interrupts
- *  are enabled elsewhere, when we can be relatively
- *  sure everything is ok.
+ *  The setup work we only want to run on the BSP.
  *
  *  Warning: %esi is live across this function.
  */
-setup_idt:
-	lea ignore_int,%edx
+__INIT
+setup_once:
+	/*
+	 * Set up a idt with 256 entries pointing to ignore_int,
+	 * interrupt gates. It doesn't actually load idt - that needs
+	 * to be done on each CPU. Interrupts are enabled elsewhere,
+	 * when we can be relatively sure everything is ok.
+	 */
+
+	movl $idt_table,%edi
+	movl $early_idt_handlers,%eax
+	movl $NUM_EXCEPTION_VECTORS,%ecx
+1:
+	movl %eax,(%edi)
+	movl %eax,4(%edi)
+	/* interrupt gate, dpl=0, present */
+	movl $(0x8E000000 + __KERNEL_CS),2(%edi)
+	addl $9,%eax
+	addl $8,%edi
+	loop 1b
+
+	movl $256 - NUM_EXCEPTION_VECTORS,%ecx
+	movl $ignore_int,%edx
 	movl $(__KERNEL_CS << 16),%eax
 	movw %dx,%ax		/* selector = 0x0010 = cs */
 	movw $0x8E00,%dx	/* interrupt gate - dpl=0, present */
-
-	lea idt_table,%edi
-	mov $256,%ecx
-rp_sidt:
+2:
 	movl %eax,(%edi)
 	movl %edx,4(%edi)
 	addl $8,%edi
-	dec %ecx
-	jne rp_sidt
+	loop 2b
 
-.macro	set_early_handler handler,trapno
-	lea \handler,%edx
-	movl $(__KERNEL_CS << 16),%eax
-	movw %dx,%ax
-	movw $0x8E00,%dx	/* interrupt gate - dpl=0, present */
-	lea idt_table,%edi
-	movl %eax,8*\trapno(%edi)
-	movl %edx,8*\trapno+4(%edi)
-.endm
+#ifdef CONFIG_CC_STACKPROTECTOR
+	/*
+	 * Configure the stack canary. The linker can't handle this by
+	 * relocation.  Manually set base address in stack canary
+	 * segment descriptor.
+	 */
+	movl $gdt_page,%eax
+	movl $stack_canary,%ecx
+	movw %cx, 8 * GDT_ENTRY_STACK_CANARY + 2(%eax)
+	shrl $16, %ecx
+	movb %cl, 8 * GDT_ENTRY_STACK_CANARY + 4(%eax)
+	movb %ch, 8 * GDT_ENTRY_STACK_CANARY + 7(%eax)
+#endif
 
-	set_early_handler handler=early_divide_err,trapno=0
-	set_early_handler handler=early_illegal_opcode,trapno=6
-	set_early_handler handler=early_protection_fault,trapno=13
-	set_early_handler handler=early_page_fault,trapno=14
-
+	andl $0,setup_once_ref	/* Once is enough, thanks */
 	ret
 
-early_divide_err:
-	xor %edx,%edx
-	pushl $0	/* fake errcode */
-	jmp early_fault
-
-early_illegal_opcode:
-	movl $6,%edx
-	pushl $0	/* fake errcode */
-	jmp early_fault
-
-early_protection_fault:
-	movl $13,%edx
-	jmp early_fault
-
-early_page_fault:
-	movl $14,%edx
-	jmp early_fault
-
-early_fault:
+ENTRY(early_idt_handlers)
+	# 36(%esp) %eflags
+	# 32(%esp) %cs
+	# 28(%esp) %eip
+	# 24(%rsp) error code
+	i = 0
+	.rept NUM_EXCEPTION_VECTORS
+	.if (EXCEPTION_ERRCODE_MASK >> i) & 1
+	ASM_NOP2
+	.else
+	pushl $0		# Dummy error code, to make stack frame uniform
+	.endif
+	pushl $i		# 20(%esp) Vector number
+	jmp early_idt_handler
+	i = i + 1
+	.endr
+ENDPROC(early_idt_handlers)
+	
+	/* This is global to keep gas from relaxing the jumps */
+ENTRY(early_idt_handler)
 	cld
-#ifdef CONFIG_PRINTK
-	pusha
+	cmpl $2,%ss:early_recursion_flag
+	je hlt_loop
+	incl %ss:early_recursion_flag
+
+	push %eax		# 16(%esp)
+	push %ecx		# 12(%esp)
+	push %edx		#  8(%esp)
+	push %ds		#  4(%esp)
+	push %es		#  0(%esp)
 	movl $(__KERNEL_DS),%eax
 	movl %eax,%ds
 	movl %eax,%es
-	cmpl $2,early_recursion_flag
-	je hlt_loop
-	incl early_recursion_flag
+
+	cmpl $(__KERNEL_CS),32(%esp)
+	jne 10f
+
+	leal 28(%esp),%eax	# Pointer to %eip
+	call early_fixup_exception
+	andl %eax,%eax
+	jnz ex_entry		/* found an exception entry */
+
+10:
+#ifdef CONFIG_PRINTK
+	xorl %eax,%eax
+	movw %ax,2(%esp)	/* clean up the segment values on some cpus */
+	movw %ax,6(%esp)
+	movw %ax,34(%esp)
+	leal  40(%esp),%eax
+	pushl %eax		/* %esp before the exception */
+	pushl %ebx
+	pushl %ebp
+	pushl %esi
+	pushl %edi
 	movl %cr2,%eax
 	pushl %eax
-	pushl %edx		/* trapno */
+	pushl (20+6*4)(%esp)	/* trapno */
 	pushl $fault_msg
 	call printk
 #endif
@@ -578,6 +599,17 @@
 	hlt
 	jmp hlt_loop
 
+ex_entry:
+	pop %es
+	pop %ds
+	pop %edx
+	pop %ecx
+	pop %eax
+	addl $8,%esp		/* drop vector number and error code */
+	decl %ss:early_recursion_flag
+	iret
+ENDPROC(early_idt_handler)
+
 /* This is the default interrupt "handler" :-) */
 	ALIGN
 ignore_int:
@@ -611,13 +643,18 @@
 	popl %eax
 #endif
 	iret
+ENDPROC(ignore_int)
+__INITDATA
+	.align 4
+early_recursion_flag:
+	.long 0
 
-#include "verify_cpu.S"
-
-	__REFDATA
-.align 4
+__REFDATA
+	.align 4
 ENTRY(initial_code)
 	.long i386_start_kernel
+ENTRY(setup_once_ref)
+	.long setup_once
 
 /*
  * BSS section
@@ -670,22 +707,19 @@
 ENTRY(stack_start)
 	.long init_thread_union+THREAD_SIZE
 
-early_recursion_flag:
-	.long 0
-
-ready:	.byte 0
-
+__INITRODATA
 int_msg:
 	.asciz "Unknown interrupt or fault at: %p %p %p\n"
 
 fault_msg:
 /* fault info: */
 	.ascii "BUG: Int %d: CR2 %p\n"
-/* pusha regs: */
-	.ascii "     EDI %p  ESI %p  EBP %p  ESP %p\n"
-	.ascii "     EBX %p  EDX %p  ECX %p  EAX %p\n"
+/* regs pushed in early_idt_handler: */
+	.ascii "     EDI %p  ESI %p  EBP %p  EBX %p\n"
+	.ascii "     ESP %p   ES %p   DS %p\n"
+	.ascii "     EDX %p  ECX %p  EAX %p\n"
 /* fault frame: */
-	.ascii "     err %p  EIP %p   CS %p  flg %p\n"
+	.ascii "     vec %p  err %p  EIP %p   CS %p  flg %p\n"
 	.ascii "Stack: %p %p %p %p %p %p %p %p\n"
 	.ascii "       %p %p %p %p %p %p %p %p\n"
 	.asciz "       %p %p %p %p %p %p %p %p\n"
@@ -699,6 +733,7 @@
  * segment size, and 32-bit linear address value:
  */
 
+	.data
 .globl boot_gdt_descr
 .globl idt_descr
 
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 40f4eb3..7a40f24 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -19,12 +19,15 @@
 #include <asm/cache.h>
 #include <asm/processor-flags.h>
 #include <asm/percpu.h>
+#include <asm/nops.h>
 
 #ifdef CONFIG_PARAVIRT
 #include <asm/asm-offsets.h>
 #include <asm/paravirt.h>
+#define GET_CR2_INTO(reg) GET_CR2_INTO_RAX ; movq %rax, reg
 #else
-#define GET_CR2_INTO_RCX movq %cr2, %rcx
+#define GET_CR2_INTO(reg) movq %cr2, reg
+#define INTERRUPT_RETURN iretq
 #endif
 
 /* we are not able to switch in one step to the final KERNEL ADDRESS SPACE
@@ -270,36 +273,56 @@
 	jmp bad_address
 
 	.section ".init.text","ax"
-#ifdef CONFIG_EARLY_PRINTK
 	.globl early_idt_handlers
 early_idt_handlers:
+	# 104(%rsp) %rflags
+	#  96(%rsp) %cs
+	#  88(%rsp) %rip
+	#  80(%rsp) error code
 	i = 0
 	.rept NUM_EXCEPTION_VECTORS
-	movl $i, %esi
+	.if (EXCEPTION_ERRCODE_MASK >> i) & 1
+	ASM_NOP2
+	.else
+	pushq $0		# Dummy error code, to make stack frame uniform
+	.endif
+	pushq $i		# 72(%rsp) Vector number
 	jmp early_idt_handler
 	i = i + 1
 	.endr
-#endif
 
 ENTRY(early_idt_handler)
-#ifdef CONFIG_EARLY_PRINTK
+	cld
+
 	cmpl $2,early_recursion_flag(%rip)
 	jz  1f
 	incl early_recursion_flag(%rip)
-	GET_CR2_INTO_RCX
-	movq %rcx,%r9
-	xorl %r8d,%r8d		# zero for error code
-	movl %esi,%ecx		# get vector number
-	# Test %ecx against mask of vectors that push error code.
-	cmpl $31,%ecx
-	ja 0f
-	movl $1,%eax
-	salq %cl,%rax
-	testl $0x27d00,%eax
-	je 0f
-	popq %r8		# get error code
-0:	movq 0(%rsp),%rcx	# get ip
-	movq 8(%rsp),%rdx	# get cs
+
+	pushq %rax		# 64(%rsp)
+	pushq %rcx		# 56(%rsp)
+	pushq %rdx		# 48(%rsp)
+	pushq %rsi		# 40(%rsp)
+	pushq %rdi		# 32(%rsp)
+	pushq %r8		# 24(%rsp)
+	pushq %r9		# 16(%rsp)
+	pushq %r10		#  8(%rsp)
+	pushq %r11		#  0(%rsp)
+
+	cmpl $__KERNEL_CS,96(%rsp)
+	jne 10f
+
+	leaq 88(%rsp),%rdi	# Pointer to %rip
+	call early_fixup_exception
+	andl %eax,%eax
+	jnz 20f			# Found an exception entry
+
+10:
+#ifdef CONFIG_EARLY_PRINTK
+	GET_CR2_INTO(%r9)	# can clobber any volatile register if pv
+	movl 80(%rsp),%r8d	# error code
+	movl 72(%rsp),%esi	# vector number
+	movl 96(%rsp),%edx	# %cs
+	movq 88(%rsp),%rcx	# %rip
 	xorl %eax,%eax
 	leaq early_idt_msg(%rip),%rdi
 	call early_printk
@@ -308,17 +331,32 @@
 	call dump_stack
 #ifdef CONFIG_KALLSYMS	
 	leaq early_idt_ripmsg(%rip),%rdi
-	movq 0(%rsp),%rsi	# get rip again
+	movq 40(%rsp),%rsi	# %rip again
 	call __print_symbol
 #endif
 #endif /* EARLY_PRINTK */
 1:	hlt
 	jmp 1b
 
-#ifdef CONFIG_EARLY_PRINTK
+20:	# Exception table entry found
+	popq %r11
+	popq %r10
+	popq %r9
+	popq %r8
+	popq %rdi
+	popq %rsi
+	popq %rdx
+	popq %rcx
+	popq %rax
+	addq $16,%rsp		# drop vector number and error code
+	decl early_recursion_flag(%rip)
+	INTERRUPT_RETURN
+
+	.balign 4
 early_recursion_flag:
 	.long 0
 
+#ifdef CONFIG_EARLY_PRINTK
 early_idt_msg:
 	.asciz "PANIC: early exception %02lx rip %lx:%lx error %lx cr2 %lx\n"
 early_idt_ripmsg:
diff --git a/arch/x86/kernel/test_rodata.c b/arch/x86/kernel/test_rodata.c
index c29e235..b79133a 100644
--- a/arch/x86/kernel/test_rodata.c
+++ b/arch/x86/kernel/test_rodata.c
@@ -12,6 +12,7 @@
 #include <linux/module.h>
 #include <asm/cacheflush.h>
 #include <asm/sections.h>
+#include <asm/asm.h>
 
 int rodata_test(void)
 {
@@ -42,14 +43,7 @@
 		".section .fixup,\"ax\"\n"
 		"2:	jmp 1b\n"
 		".previous\n"
-		".section __ex_table,\"a\"\n"
-		"       .align 16\n"
-#ifdef CONFIG_X86_32
-		"	.long 0b,2b\n"
-#else
-		"	.quad 0b,2b\n"
-#endif
-		".previous"
+		_ASM_EXTABLE(0b,2b)
 		: [rslt] "=r" (result)
 		: [rodata_test] "r" (&rodata_test_data), [zero] "r" (0UL)
 	);
diff --git a/arch/x86/lib/checksum_32.S b/arch/x86/lib/checksum_32.S
index 78d16a5..2af5df3 100644
--- a/arch/x86/lib/checksum_32.S
+++ b/arch/x86/lib/checksum_32.S
@@ -28,6 +28,7 @@
 #include <linux/linkage.h>
 #include <asm/dwarf2.h>
 #include <asm/errno.h>
+#include <asm/asm.h>
 				
 /*
  * computes a partial checksum, e.g. for TCP/UDP fragments
@@ -282,15 +283,11 @@
 
 #define SRC(y...)			\
 	9999: y;			\
-	.section __ex_table, "a";	\
-	.long 9999b, 6001f	;	\
-	.previous
+	_ASM_EXTABLE(9999b, 6001f)
 
 #define DST(y...)			\
 	9999: y;			\
-	.section __ex_table, "a";	\
-	.long 9999b, 6002f	;	\
-	.previous
+	_ASM_EXTABLE(9999b, 6002f)
 
 #ifndef CONFIG_X86_USE_PPRO_CHECKSUM
 
diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S
index 0248402..5b2995f 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -16,6 +16,7 @@
 #include <asm/thread_info.h>
 #include <asm/cpufeature.h>
 #include <asm/alternative-asm.h>
+#include <asm/asm.h>
 
 /*
  * By placing feature2 after feature1 in altinstructions section, we logically
@@ -63,11 +64,8 @@
 	jmp copy_user_handle_tail
 	.previous
 
-	.section __ex_table,"a"
-	.align 8
-	.quad 100b,103b
-	.quad 101b,103b
-	.previous
+	_ASM_EXTABLE(100b,103b)
+	_ASM_EXTABLE(101b,103b)
 #endif
 	.endm
 
@@ -191,29 +189,26 @@
 60:	jmp copy_user_handle_tail /* ecx is zerorest also */
 	.previous
 
-	.section __ex_table,"a"
-	.align 8
-	.quad 1b,30b
-	.quad 2b,30b
-	.quad 3b,30b
-	.quad 4b,30b
-	.quad 5b,30b
-	.quad 6b,30b
-	.quad 7b,30b
-	.quad 8b,30b
-	.quad 9b,30b
-	.quad 10b,30b
-	.quad 11b,30b
-	.quad 12b,30b
-	.quad 13b,30b
-	.quad 14b,30b
-	.quad 15b,30b
-	.quad 16b,30b
-	.quad 18b,40b
-	.quad 19b,40b
-	.quad 21b,50b
-	.quad 22b,50b
-	.previous
+	_ASM_EXTABLE(1b,30b)
+	_ASM_EXTABLE(2b,30b)
+	_ASM_EXTABLE(3b,30b)
+	_ASM_EXTABLE(4b,30b)
+	_ASM_EXTABLE(5b,30b)
+	_ASM_EXTABLE(6b,30b)
+	_ASM_EXTABLE(7b,30b)
+	_ASM_EXTABLE(8b,30b)
+	_ASM_EXTABLE(9b,30b)
+	_ASM_EXTABLE(10b,30b)
+	_ASM_EXTABLE(11b,30b)
+	_ASM_EXTABLE(12b,30b)
+	_ASM_EXTABLE(13b,30b)
+	_ASM_EXTABLE(14b,30b)
+	_ASM_EXTABLE(15b,30b)
+	_ASM_EXTABLE(16b,30b)
+	_ASM_EXTABLE(18b,40b)
+	_ASM_EXTABLE(19b,40b)
+	_ASM_EXTABLE(21b,50b)
+	_ASM_EXTABLE(22b,50b)
 	CFI_ENDPROC
 ENDPROC(copy_user_generic_unrolled)
 
@@ -259,11 +254,8 @@
 	jmp copy_user_handle_tail
 	.previous
 
-	.section __ex_table,"a"
-	.align 8
-	.quad 1b,11b
-	.quad 3b,12b
-	.previous
+	_ASM_EXTABLE(1b,11b)
+	_ASM_EXTABLE(3b,12b)
 	CFI_ENDPROC
 ENDPROC(copy_user_generic_string)
 
@@ -294,9 +286,6 @@
 	jmp copy_user_handle_tail
 	.previous
 
-	.section __ex_table,"a"
-	.align 8
-	.quad 1b,12b
-	.previous
+	_ASM_EXTABLE(1b,12b)
 	CFI_ENDPROC
 ENDPROC(copy_user_enhanced_fast_string)
diff --git a/arch/x86/lib/copy_user_nocache_64.S b/arch/x86/lib/copy_user_nocache_64.S
index cb0c112..cacddc7 100644
--- a/arch/x86/lib/copy_user_nocache_64.S
+++ b/arch/x86/lib/copy_user_nocache_64.S
@@ -14,6 +14,7 @@
 #include <asm/current.h>
 #include <asm/asm-offsets.h>
 #include <asm/thread_info.h>
+#include <asm/asm.h>
 
 	.macro ALIGN_DESTINATION
 #ifdef FIX_ALIGNMENT
@@ -36,11 +37,8 @@
 	jmp copy_user_handle_tail
 	.previous
 
-	.section __ex_table,"a"
-	.align 8
-	.quad 100b,103b
-	.quad 101b,103b
-	.previous
+	_ASM_EXTABLE(100b,103b)
+	_ASM_EXTABLE(101b,103b)
 #endif
 	.endm
 
@@ -111,27 +109,25 @@
 	jmp copy_user_handle_tail
 	.previous
 
-	.section __ex_table,"a"
-	.quad 1b,30b
-	.quad 2b,30b
-	.quad 3b,30b
-	.quad 4b,30b
-	.quad 5b,30b
-	.quad 6b,30b
-	.quad 7b,30b
-	.quad 8b,30b
-	.quad 9b,30b
-	.quad 10b,30b
-	.quad 11b,30b
-	.quad 12b,30b
-	.quad 13b,30b
-	.quad 14b,30b
-	.quad 15b,30b
-	.quad 16b,30b
-	.quad 18b,40b
-	.quad 19b,40b
-	.quad 21b,50b
-	.quad 22b,50b
-	.previous
+	_ASM_EXTABLE(1b,30b)
+	_ASM_EXTABLE(2b,30b)
+	_ASM_EXTABLE(3b,30b)
+	_ASM_EXTABLE(4b,30b)
+	_ASM_EXTABLE(5b,30b)
+	_ASM_EXTABLE(6b,30b)
+	_ASM_EXTABLE(7b,30b)
+	_ASM_EXTABLE(8b,30b)
+	_ASM_EXTABLE(9b,30b)
+	_ASM_EXTABLE(10b,30b)
+	_ASM_EXTABLE(11b,30b)
+	_ASM_EXTABLE(12b,30b)
+	_ASM_EXTABLE(13b,30b)
+	_ASM_EXTABLE(14b,30b)
+	_ASM_EXTABLE(15b,30b)
+	_ASM_EXTABLE(16b,30b)
+	_ASM_EXTABLE(18b,40b)
+	_ASM_EXTABLE(19b,40b)
+	_ASM_EXTABLE(21b,50b)
+	_ASM_EXTABLE(22b,50b)
 	CFI_ENDPROC
 ENDPROC(__copy_user_nocache)
diff --git a/arch/x86/lib/csum-copy_64.S b/arch/x86/lib/csum-copy_64.S
index fb903b7..2419d5f 100644
--- a/arch/x86/lib/csum-copy_64.S
+++ b/arch/x86/lib/csum-copy_64.S
@@ -8,6 +8,7 @@
 #include <linux/linkage.h>
 #include <asm/dwarf2.h>
 #include <asm/errno.h>
+#include <asm/asm.h>
 
 /*
  * Checksum copy with exception handling.
@@ -31,26 +32,17 @@
 
 	.macro source
 10:
-	.section __ex_table, "a"
-	.align 8
-	.quad 10b, .Lbad_source
-	.previous
+	_ASM_EXTABLE(10b, .Lbad_source)
 	.endm
 
 	.macro dest
 20:
-	.section __ex_table, "a"
-	.align 8
-	.quad 20b, .Lbad_dest
-	.previous
+	_ASM_EXTABLE(20b, .Lbad_dest)
 	.endm
 
 	.macro ignore L=.Lignore
 30:
-	.section __ex_table, "a"
-	.align 8
-	.quad 30b, \L
-	.previous
+	_ASM_EXTABLE(30b, \L)
 	.endm
 
 
diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S
index 51f1504..b33b1fb 100644
--- a/arch/x86/lib/getuser.S
+++ b/arch/x86/lib/getuser.S
@@ -95,10 +95,9 @@
 	CFI_ENDPROC
 END(bad_get_user)
 
-.section __ex_table,"a"
-	_ASM_PTR 1b,bad_get_user
-	_ASM_PTR 2b,bad_get_user
-	_ASM_PTR 3b,bad_get_user
+	_ASM_EXTABLE(1b,bad_get_user)
+	_ASM_EXTABLE(2b,bad_get_user)
+	_ASM_EXTABLE(3b,bad_get_user)
 #ifdef CONFIG_X86_64
-	_ASM_PTR 4b,bad_get_user
+	_ASM_EXTABLE(4b,bad_get_user)
 #endif
diff --git a/arch/x86/lib/putuser.S b/arch/x86/lib/putuser.S
index 36b0d15..7f951c8 100644
--- a/arch/x86/lib/putuser.S
+++ b/arch/x86/lib/putuser.S
@@ -86,12 +86,10 @@
 	EXIT
 END(bad_put_user)
 
-.section __ex_table,"a"
-	_ASM_PTR 1b,bad_put_user
-	_ASM_PTR 2b,bad_put_user
-	_ASM_PTR 3b,bad_put_user
-	_ASM_PTR 4b,bad_put_user
+	_ASM_EXTABLE(1b,bad_put_user)
+	_ASM_EXTABLE(2b,bad_put_user)
+	_ASM_EXTABLE(3b,bad_put_user)
+	_ASM_EXTABLE(4b,bad_put_user)
 #ifdef CONFIG_X86_32
-	_ASM_PTR 5b,bad_put_user
+	_ASM_EXTABLE(5b,bad_put_user)
 #endif
-.previous
diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c
index ef2a6a5..883b216 100644
--- a/arch/x86/lib/usercopy_32.c
+++ b/arch/x86/lib/usercopy_32.c
@@ -13,6 +13,7 @@
 #include <linux/interrupt.h>
 #include <asm/uaccess.h>
 #include <asm/mmx.h>
+#include <asm/asm.h>
 
 #ifdef CONFIG_X86_INTEL_USERCOPY
 /*
@@ -127,10 +128,7 @@
 		"3:	movb $1,%%al\n"
 		"	jmp 1b\n"
 		".previous\n"
-		".section __ex_table,\"a\"\n"
-		"	.align 4\n"
-		"	.long 0b,2b\n"
-		".previous"
+		_ASM_EXTABLE(0b,2b)
 		:"=&r" (n), "=&D" (s), "=&a" (res), "=&c" (tmp)
 		:"0" (n), "1" (s), "2" (0), "3" (mask)
 		:"cc");
@@ -199,47 +197,44 @@
 		       "101:   lea 0(%%eax,%0,4),%0\n"
 		       "       jmp 100b\n"
 		       ".previous\n"
-		       ".section __ex_table,\"a\"\n"
-		       "       .align 4\n"
-		       "       .long 1b,100b\n"
-		       "       .long 2b,100b\n"
-		       "       .long 3b,100b\n"
-		       "       .long 4b,100b\n"
-		       "       .long 5b,100b\n"
-		       "       .long 6b,100b\n"
-		       "       .long 7b,100b\n"
-		       "       .long 8b,100b\n"
-		       "       .long 9b,100b\n"
-		       "       .long 10b,100b\n"
-		       "       .long 11b,100b\n"
-		       "       .long 12b,100b\n"
-		       "       .long 13b,100b\n"
-		       "       .long 14b,100b\n"
-		       "       .long 15b,100b\n"
-		       "       .long 16b,100b\n"
-		       "       .long 17b,100b\n"
-		       "       .long 18b,100b\n"
-		       "       .long 19b,100b\n"
-		       "       .long 20b,100b\n"
-		       "       .long 21b,100b\n"
-		       "       .long 22b,100b\n"
-		       "       .long 23b,100b\n"
-		       "       .long 24b,100b\n"
-		       "       .long 25b,100b\n"
-		       "       .long 26b,100b\n"
-		       "       .long 27b,100b\n"
-		       "       .long 28b,100b\n"
-		       "       .long 29b,100b\n"
-		       "       .long 30b,100b\n"
-		       "       .long 31b,100b\n"
-		       "       .long 32b,100b\n"
-		       "       .long 33b,100b\n"
-		       "       .long 34b,100b\n"
-		       "       .long 35b,100b\n"
-		       "       .long 36b,100b\n"
-		       "       .long 37b,100b\n"
-		       "       .long 99b,101b\n"
-		       ".previous"
+		       _ASM_EXTABLE(1b,100b)
+		       _ASM_EXTABLE(2b,100b)
+		       _ASM_EXTABLE(3b,100b)
+		       _ASM_EXTABLE(4b,100b)
+		       _ASM_EXTABLE(5b,100b)
+		       _ASM_EXTABLE(6b,100b)
+		       _ASM_EXTABLE(7b,100b)
+		       _ASM_EXTABLE(8b,100b)
+		       _ASM_EXTABLE(9b,100b)
+		       _ASM_EXTABLE(10b,100b)
+		       _ASM_EXTABLE(11b,100b)
+		       _ASM_EXTABLE(12b,100b)
+		       _ASM_EXTABLE(13b,100b)
+		       _ASM_EXTABLE(14b,100b)
+		       _ASM_EXTABLE(15b,100b)
+		       _ASM_EXTABLE(16b,100b)
+		       _ASM_EXTABLE(17b,100b)
+		       _ASM_EXTABLE(18b,100b)
+		       _ASM_EXTABLE(19b,100b)
+		       _ASM_EXTABLE(20b,100b)
+		       _ASM_EXTABLE(21b,100b)
+		       _ASM_EXTABLE(22b,100b)
+		       _ASM_EXTABLE(23b,100b)
+		       _ASM_EXTABLE(24b,100b)
+		       _ASM_EXTABLE(25b,100b)
+		       _ASM_EXTABLE(26b,100b)
+		       _ASM_EXTABLE(27b,100b)
+		       _ASM_EXTABLE(28b,100b)
+		       _ASM_EXTABLE(29b,100b)
+		       _ASM_EXTABLE(30b,100b)
+		       _ASM_EXTABLE(31b,100b)
+		       _ASM_EXTABLE(32b,100b)
+		       _ASM_EXTABLE(33b,100b)
+		       _ASM_EXTABLE(34b,100b)
+		       _ASM_EXTABLE(35b,100b)
+		       _ASM_EXTABLE(36b,100b)
+		       _ASM_EXTABLE(37b,100b)
+		       _ASM_EXTABLE(99b,101b)
 		       : "=&c"(size), "=&D" (d0), "=&S" (d1)
 		       :  "1"(to), "2"(from), "0"(size)
 		       : "eax", "edx", "memory");
@@ -312,29 +307,26 @@
 		       "        popl %0\n"
 		       "        jmp 8b\n"
 		       ".previous\n"
-		       ".section __ex_table,\"a\"\n"
-		       "	.align 4\n"
-		       "	.long 0b,16b\n"
-		       "	.long 1b,16b\n"
-		       "	.long 2b,16b\n"
-		       "	.long 21b,16b\n"
-		       "	.long 3b,16b\n"
-		       "	.long 31b,16b\n"
-		       "	.long 4b,16b\n"
-		       "	.long 41b,16b\n"
-		       "	.long 10b,16b\n"
-		       "	.long 51b,16b\n"
-		       "	.long 11b,16b\n"
-		       "	.long 61b,16b\n"
-		       "	.long 12b,16b\n"
-		       "	.long 71b,16b\n"
-		       "	.long 13b,16b\n"
-		       "	.long 81b,16b\n"
-		       "	.long 14b,16b\n"
-		       "	.long 91b,16b\n"
-		       "	.long 6b,9b\n"
-		       "        .long 7b,16b\n"
-		       ".previous"
+		       _ASM_EXTABLE(0b,16b)
+		       _ASM_EXTABLE(1b,16b)
+		       _ASM_EXTABLE(2b,16b)
+		       _ASM_EXTABLE(21b,16b)
+		       _ASM_EXTABLE(3b,16b)
+		       _ASM_EXTABLE(31b,16b)
+		       _ASM_EXTABLE(4b,16b)
+		       _ASM_EXTABLE(41b,16b)
+		       _ASM_EXTABLE(10b,16b)
+		       _ASM_EXTABLE(51b,16b)
+		       _ASM_EXTABLE(11b,16b)
+		       _ASM_EXTABLE(61b,16b)
+		       _ASM_EXTABLE(12b,16b)
+		       _ASM_EXTABLE(71b,16b)
+		       _ASM_EXTABLE(13b,16b)
+		       _ASM_EXTABLE(81b,16b)
+		       _ASM_EXTABLE(14b,16b)
+		       _ASM_EXTABLE(91b,16b)
+		       _ASM_EXTABLE(6b,9b)
+		       _ASM_EXTABLE(7b,16b)
 		       : "=&c"(size), "=&D" (d0), "=&S" (d1)
 		       :  "1"(to), "2"(from), "0"(size)
 		       : "eax", "edx", "memory");
@@ -414,29 +406,26 @@
 	       "        popl %0\n"
 	       "        jmp 8b\n"
 	       ".previous\n"
-	       ".section __ex_table,\"a\"\n"
-	       "	.align 4\n"
-	       "	.long 0b,16b\n"
-	       "	.long 1b,16b\n"
-	       "	.long 2b,16b\n"
-	       "	.long 21b,16b\n"
-	       "	.long 3b,16b\n"
-	       "	.long 31b,16b\n"
-	       "	.long 4b,16b\n"
-	       "	.long 41b,16b\n"
-	       "	.long 10b,16b\n"
-	       "	.long 51b,16b\n"
-	       "	.long 11b,16b\n"
-	       "	.long 61b,16b\n"
-	       "	.long 12b,16b\n"
-	       "	.long 71b,16b\n"
-	       "	.long 13b,16b\n"
-	       "	.long 81b,16b\n"
-	       "	.long 14b,16b\n"
-	       "	.long 91b,16b\n"
-	       "	.long 6b,9b\n"
-	       "        .long 7b,16b\n"
-	       ".previous"
+	       _ASM_EXTABLE(0b,16b)
+	       _ASM_EXTABLE(1b,16b)
+	       _ASM_EXTABLE(2b,16b)
+	       _ASM_EXTABLE(21b,16b)
+	       _ASM_EXTABLE(3b,16b)
+	       _ASM_EXTABLE(31b,16b)
+	       _ASM_EXTABLE(4b,16b)
+	       _ASM_EXTABLE(41b,16b)
+	       _ASM_EXTABLE(10b,16b)
+	       _ASM_EXTABLE(51b,16b)
+	       _ASM_EXTABLE(11b,16b)
+	       _ASM_EXTABLE(61b,16b)
+	       _ASM_EXTABLE(12b,16b)
+	       _ASM_EXTABLE(71b,16b)
+	       _ASM_EXTABLE(13b,16b)
+	       _ASM_EXTABLE(81b,16b)
+	       _ASM_EXTABLE(14b,16b)
+	       _ASM_EXTABLE(91b,16b)
+	       _ASM_EXTABLE(6b,9b)
+	       _ASM_EXTABLE(7b,16b)
 	       : "=&c"(size), "=&D" (d0), "=&S" (d1)
 	       :  "1"(to), "2"(from), "0"(size)
 	       : "eax", "edx", "memory");
@@ -505,29 +494,26 @@
 	       "9:      lea 0(%%eax,%0,4),%0\n"
 	       "16:     jmp 8b\n"
 	       ".previous\n"
-	       ".section __ex_table,\"a\"\n"
-	       "	.align 4\n"
-	       "	.long 0b,16b\n"
-	       "	.long 1b,16b\n"
-	       "	.long 2b,16b\n"
-	       "	.long 21b,16b\n"
-	       "	.long 3b,16b\n"
-	       "	.long 31b,16b\n"
-	       "	.long 4b,16b\n"
-	       "	.long 41b,16b\n"
-	       "	.long 10b,16b\n"
-	       "	.long 51b,16b\n"
-	       "	.long 11b,16b\n"
-	       "	.long 61b,16b\n"
-	       "	.long 12b,16b\n"
-	       "	.long 71b,16b\n"
-	       "	.long 13b,16b\n"
-	       "	.long 81b,16b\n"
-	       "	.long 14b,16b\n"
-	       "	.long 91b,16b\n"
-	       "	.long 6b,9b\n"
-	       "        .long 7b,16b\n"
-	       ".previous"
+	       _ASM_EXTABLE(0b,16b)
+	       _ASM_EXTABLE(1b,16b)
+	       _ASM_EXTABLE(2b,16b)
+	       _ASM_EXTABLE(21b,16b)
+	       _ASM_EXTABLE(3b,16b)
+	       _ASM_EXTABLE(31b,16b)
+	       _ASM_EXTABLE(4b,16b)
+	       _ASM_EXTABLE(41b,16b)
+	       _ASM_EXTABLE(10b,16b)
+	       _ASM_EXTABLE(51b,16b)
+	       _ASM_EXTABLE(11b,16b)
+	       _ASM_EXTABLE(61b,16b)
+	       _ASM_EXTABLE(12b,16b)
+	       _ASM_EXTABLE(71b,16b)
+	       _ASM_EXTABLE(13b,16b)
+	       _ASM_EXTABLE(81b,16b)
+	       _ASM_EXTABLE(14b,16b)
+	       _ASM_EXTABLE(91b,16b)
+	       _ASM_EXTABLE(6b,9b)
+	       _ASM_EXTABLE(7b,16b)
 	       : "=&c"(size), "=&D" (d0), "=&S" (d1)
 	       :  "1"(to), "2"(from), "0"(size)
 	       : "eax", "edx", "memory");
@@ -574,12 +560,9 @@
 		"3:	lea 0(%3,%0,4),%0\n"				\
 		"	jmp 2b\n"					\
 		".previous\n"						\
-		".section __ex_table,\"a\"\n"				\
-		"	.align 4\n"					\
-		"	.long 4b,5b\n"					\
-		"	.long 0b,3b\n"					\
-		"	.long 1b,2b\n"					\
-		".previous"						\
+		_ASM_EXTABLE(4b,5b)					\
+		_ASM_EXTABLE(0b,3b)					\
+		_ASM_EXTABLE(1b,2b)					\
 		: "=&c"(size), "=&D" (__d0), "=&S" (__d1), "=r"(__d2)	\
 		: "3"(size), "0"(size), "1"(to), "2"(from)		\
 		: "memory");						\
@@ -616,12 +599,9 @@
 		"	popl %0\n"					\
 		"	jmp 2b\n"					\
 		".previous\n"						\
-		".section __ex_table,\"a\"\n"				\
-		"	.align 4\n"					\
-		"	.long 4b,5b\n"					\
-		"	.long 0b,3b\n"					\
-		"	.long 1b,6b\n"					\
-		".previous"						\
+		_ASM_EXTABLE(4b,5b)					\
+		_ASM_EXTABLE(0b,3b)					\
+		_ASM_EXTABLE(1b,6b)					\
 		: "=&c"(size), "=&D" (__d0), "=&S" (__d1), "=r"(__d2)	\
 		: "3"(size), "0"(size), "1"(to), "2"(from)		\
 		: "memory");						\
diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c
index 1fb85db..903ec1e 100644
--- a/arch/x86/mm/extable.c
+++ b/arch/x86/mm/extable.c
@@ -1,11 +1,23 @@
 #include <linux/module.h>
 #include <linux/spinlock.h>
+#include <linux/sort.h>
 #include <asm/uaccess.h>
 
+static inline unsigned long
+ex_insn_addr(const struct exception_table_entry *x)
+{
+	return (unsigned long)&x->insn + x->insn;
+}
+static inline unsigned long
+ex_fixup_addr(const struct exception_table_entry *x)
+{
+	return (unsigned long)&x->fixup + x->fixup;
+}
 
 int fixup_exception(struct pt_regs *regs)
 {
 	const struct exception_table_entry *fixup;
+	unsigned long new_ip;
 
 #ifdef CONFIG_PNPBIOS
 	if (unlikely(SEGMENT_IS_PNP_CODE(regs->cs))) {
@@ -23,15 +35,135 @@
 
 	fixup = search_exception_tables(regs->ip);
 	if (fixup) {
-		/* If fixup is less than 16, it means uaccess error */
-		if (fixup->fixup < 16) {
+		new_ip = ex_fixup_addr(fixup);
+
+		if (fixup->fixup - fixup->insn >= 0x7ffffff0 - 4) {
+			/* Special hack for uaccess_err */
 			current_thread_info()->uaccess_err = 1;
-			regs->ip += fixup->fixup;
-			return 1;
+			new_ip -= 0x7ffffff0;
 		}
-		regs->ip = fixup->fixup;
+		regs->ip = new_ip;
 		return 1;
 	}
 
 	return 0;
 }
+
+/* Restricted version used during very early boot */
+int __init early_fixup_exception(unsigned long *ip)
+{
+	const struct exception_table_entry *fixup;
+	unsigned long new_ip;
+
+	fixup = search_exception_tables(*ip);
+	if (fixup) {
+		new_ip = ex_fixup_addr(fixup);
+
+		if (fixup->fixup - fixup->insn >= 0x7ffffff0 - 4) {
+			/* uaccess handling not supported during early boot */
+			return 0;
+		}
+
+		*ip = new_ip;
+		return 1;
+	}
+
+	return 0;
+}
+
+/*
+ * Search one exception table for an entry corresponding to the
+ * given instruction address, and return the address of the entry,
+ * or NULL if none is found.
+ * We use a binary search, and thus we assume that the table is
+ * already sorted.
+ */
+const struct exception_table_entry *
+search_extable(const struct exception_table_entry *first,
+	       const struct exception_table_entry *last,
+	       unsigned long value)
+{
+	while (first <= last) {
+		const struct exception_table_entry *mid;
+		unsigned long addr;
+
+		mid = ((last - first) >> 1) + first;
+		addr = ex_insn_addr(mid);
+		if (addr < value)
+			first = mid + 1;
+		else if (addr > value)
+			last = mid - 1;
+		else
+			return mid;
+        }
+        return NULL;
+}
+
+/*
+ * The exception table needs to be sorted so that the binary
+ * search that we use to find entries in it works properly.
+ * This is used both for the kernel exception table and for
+ * the exception tables of modules that get loaded.
+ *
+ */
+static int cmp_ex(const void *a, const void *b)
+{
+	const struct exception_table_entry *x = a, *y = b;
+
+	/*
+	 * This value will always end up fittin in an int, because on
+	 * both i386 and x86-64 the kernel symbol-reachable address
+	 * space is < 2 GiB.
+	 *
+	 * This compare is only valid after normalization.
+	 */
+	return x->insn - y->insn;
+}
+
+void sort_extable(struct exception_table_entry *start,
+		  struct exception_table_entry *finish)
+{
+	struct exception_table_entry *p;
+	int i;
+
+	/* Convert all entries to being relative to the start of the section */
+	i = 0;
+	for (p = start; p < finish; p++) {
+		p->insn += i;
+		i += 4;
+		p->fixup += i;
+		i += 4;
+	}
+
+	sort(start, finish - start, sizeof(struct exception_table_entry),
+	     cmp_ex, NULL);
+
+	/* Denormalize all entries */
+	i = 0;
+	for (p = start; p < finish; p++) {
+		p->insn -= i;
+		i += 4;
+		p->fixup -= i;
+		i += 4;
+	}
+}
+
+#ifdef CONFIG_MODULES
+/*
+ * If the exception table is sorted, any referring to the module init
+ * will be at the beginning or the end.
+ */
+void trim_init_extable(struct module *m)
+{
+	/*trim the beginning*/
+	while (m->num_exentries &&
+	       within_module_init(ex_insn_addr(&m->extable[0]), m)) {
+		m->extable++;
+		m->num_exentries--;
+	}
+	/*trim the end*/
+	while (m->num_exentries &&
+	       within_module_init(ex_insn_addr(&m->extable[m->num_exentries-1]), m))
+		m->num_exentries--;
+}
+#endif /* CONFIG_MODULES */
diff --git a/arch/x86/um/checksum_32.S b/arch/x86/um/checksum_32.S
index f058d2f..8d0c420 100644
--- a/arch/x86/um/checksum_32.S
+++ b/arch/x86/um/checksum_32.S
@@ -26,6 +26,7 @@
  */
 
 #include <asm/errno.h>
+#include <asm/asm.h>
 				
 /*
  * computes a partial checksum, e.g. for TCP/UDP fragments
@@ -232,15 +233,11 @@
 
 #define SRC(y...)			\
 	9999: y;			\
-	.section __ex_table, "a";	\
-	.long 9999b, 6001f	;	\
-	.previous
+	_ASM_EXTABLE(9999b, 6001f)
 
 #define DST(y...)			\
 	9999: y;			\
-	.section __ex_table, "a";	\
-	.long 9999b, 6002f	;	\
-	.previous
+	_ASM_EXTABLE(9999b, 6002f)
 
 .align 4
 
diff --git a/arch/x86/xen/xen-asm_32.S b/arch/x86/xen/xen-asm_32.S
index b040b0e..f9643fc 100644
--- a/arch/x86/xen/xen-asm_32.S
+++ b/arch/x86/xen/xen-asm_32.S
@@ -14,6 +14,7 @@
 #include <asm/thread_info.h>
 #include <asm/processor-flags.h>
 #include <asm/segment.h>
+#include <asm/asm.h>
 
 #include <xen/interface/xen.h>
 
@@ -137,10 +138,7 @@
 
 1:	iret
 xen_iret_end_crit:
-.section __ex_table, "a"
-	.align 4
-	.long 1b, iret_exc
-.previous
+	_ASM_EXTABLE(1b, iret_exc)
 
 hyper_iret:
 	/* put this out of line since its very rarely used */
diff --git a/init/Kconfig b/init/Kconfig
index da2d2d2..a30fe08 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -27,6 +27,9 @@
 	bool
 	depends on HAVE_IRQ_WORK
 
+config BUILDTIME_EXTABLE_SORT
+	bool
+
 menu "General setup"
 
 config EXPERIMENTAL
diff --git a/kernel/extable.c b/kernel/extable.c
index 5339705..fe35a63 100644
--- a/kernel/extable.c
+++ b/kernel/extable.c
@@ -35,10 +35,16 @@
 extern struct exception_table_entry __start___ex_table[];
 extern struct exception_table_entry __stop___ex_table[];
 
+/* Cleared by build time tools if the table is already sorted. */
+u32 __initdata main_extable_sort_needed = 1;
+
 /* Sort the kernel's built-in exception table */
 void __init sort_main_extable(void)
 {
-	sort_extable(__start___ex_table, __stop___ex_table);
+	if (main_extable_sort_needed)
+		sort_extable(__start___ex_table, __stop___ex_table);
+	else
+		pr_notice("__ex_table already sorted, skipping sort\n");
 }
 
 /* Given an address, look for it in the exception tables. */
diff --git a/scripts/.gitignore b/scripts/.gitignore
index 105b21f..65f362d 100644
--- a/scripts/.gitignore
+++ b/scripts/.gitignore
@@ -9,3 +9,4 @@
 ihex2fw
 recordmcount
 docproc
+sortextable
diff --git a/scripts/Makefile b/scripts/Makefile
index 3626666..a55b006 100644
--- a/scripts/Makefile
+++ b/scripts/Makefile
@@ -15,6 +15,9 @@
 hostprogs-$(CONFIG_VT)           += conmakehash
 hostprogs-$(CONFIG_IKCONFIG)     += bin2c
 hostprogs-$(BUILD_C_RECORDMCOUNT) += recordmcount
+hostprogs-$(CONFIG_BUILDTIME_EXTABLE_SORT) += sortextable
+
+HOSTCFLAGS_sortextable.o = -I$(srctree)/tools/include
 
 always		:= $(hostprogs-y) $(hostprogs-m)
 
diff --git a/scripts/sortextable.c b/scripts/sortextable.c
new file mode 100644
index 0000000..1ca9ceb
--- /dev/null
+++ b/scripts/sortextable.c
@@ -0,0 +1,322 @@
+/*
+ * sortextable.c: Sort the kernel's exception table
+ *
+ * Copyright 2011 - 2012 Cavium, Inc.
+ *
+ * Based on code taken from recortmcount.c which is:
+ *
+ * Copyright 2009 John F. Reiser <jreiser@BitWagon.com>.  All rights reserved.
+ * Licensed under the GNU General Public License, version 2 (GPLv2).
+ *
+ * Restructured to fit Linux format, as well as other updates:
+ *  Copyright 2010 Steven Rostedt <srostedt@redhat.com>, Red Hat Inc.
+ */
+
+/*
+ * Strategy: alter the vmlinux file in-place.
+ */
+
+#include <sys/types.h>
+#include <sys/mman.h>
+#include <sys/stat.h>
+#include <getopt.h>
+#include <elf.h>
+#include <fcntl.h>
+#include <setjmp.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+
+#include <tools/be_byteshift.h>
+#include <tools/le_byteshift.h>
+
+static int fd_map;	/* File descriptor for file being modified. */
+static int mmap_failed; /* Boolean flag. */
+static void *ehdr_curr; /* current ElfXX_Ehdr *  for resource cleanup */
+static struct stat sb;	/* Remember .st_size, etc. */
+static jmp_buf jmpenv;	/* setjmp/longjmp per-file error escape */
+
+/* setjmp() return values */
+enum {
+	SJ_SETJMP = 0,  /* hardwired first return */
+	SJ_FAIL,
+	SJ_SUCCEED
+};
+
+/* Per-file resource cleanup when multiple files. */
+static void
+cleanup(void)
+{
+	if (!mmap_failed)
+		munmap(ehdr_curr, sb.st_size);
+	close(fd_map);
+}
+
+static void __attribute__((noreturn))
+fail_file(void)
+{
+	cleanup();
+	longjmp(jmpenv, SJ_FAIL);
+}
+
+static void __attribute__((noreturn))
+succeed_file(void)
+{
+	cleanup();
+	longjmp(jmpenv, SJ_SUCCEED);
+}
+
+
+/*
+ * Get the whole file as a programming convenience in order to avoid
+ * malloc+lseek+read+free of many pieces.  If successful, then mmap
+ * avoids copying unused pieces; else just read the whole file.
+ * Open for both read and write.
+ */
+static void *mmap_file(char const *fname)
+{
+	void *addr;
+
+	fd_map = open(fname, O_RDWR);
+	if (fd_map < 0 || fstat(fd_map, &sb) < 0) {
+		perror(fname);
+		fail_file();
+	}
+	if (!S_ISREG(sb.st_mode)) {
+		fprintf(stderr, "not a regular file: %s\n", fname);
+		fail_file();
+	}
+	addr = mmap(0, sb.st_size, PROT_READ|PROT_WRITE, MAP_SHARED,
+		    fd_map, 0);
+	if (addr == MAP_FAILED) {
+		mmap_failed = 1;
+		fprintf(stderr, "Could not mmap file: %s\n", fname);
+		fail_file();
+	}
+	return addr;
+}
+
+static uint64_t r8be(const uint64_t *x)
+{
+	return get_unaligned_be64(x);
+}
+static uint32_t rbe(const uint32_t *x)
+{
+	return get_unaligned_be32(x);
+}
+static uint16_t r2be(const uint16_t *x)
+{
+	return get_unaligned_be16(x);
+}
+static uint64_t r8le(const uint64_t *x)
+{
+	return get_unaligned_le64(x);
+}
+static uint32_t rle(const uint32_t *x)
+{
+	return get_unaligned_le32(x);
+}
+static uint16_t r2le(const uint16_t *x)
+{
+	return get_unaligned_le16(x);
+}
+
+static void w8be(uint64_t val, uint64_t *x)
+{
+	put_unaligned_be64(val, x);
+}
+static void wbe(uint32_t val, uint32_t *x)
+{
+	put_unaligned_be32(val, x);
+}
+static void w2be(uint16_t val, uint16_t *x)
+{
+	put_unaligned_be16(val, x);
+}
+static void w8le(uint64_t val, uint64_t *x)
+{
+	put_unaligned_le64(val, x);
+}
+static void wle(uint32_t val, uint32_t *x)
+{
+	put_unaligned_le32(val, x);
+}
+static void w2le(uint16_t val, uint16_t *x)
+{
+	put_unaligned_le16(val, x);
+}
+
+static uint64_t (*r8)(const uint64_t *);
+static uint32_t (*r)(const uint32_t *);
+static uint16_t (*r2)(const uint16_t *);
+static void (*w8)(uint64_t, uint64_t *);
+static void (*w)(uint32_t, uint32_t *);
+static void (*w2)(uint16_t, uint16_t *);
+
+typedef void (*table_sort_t)(char *, int);
+
+/* 32 bit and 64 bit are very similar */
+#include "sortextable.h"
+#define SORTEXTABLE_64
+#include "sortextable.h"
+
+static int compare_x86_table(const void *a, const void *b)
+{
+	int32_t av = (int32_t)r(a);
+	int32_t bv = (int32_t)r(b);
+
+	if (av < bv)
+		return -1;
+	if (av > bv)
+		return 1;
+	return 0;
+}
+
+static void sort_x86_table(char *extab_image, int image_size)
+{
+	int i;
+
+	/*
+	 * Do the same thing the runtime sort does, first normalize to
+	 * being relative to the start of the section.
+	 */
+	i = 0;
+	while (i < image_size) {
+		uint32_t *loc = (uint32_t *)(extab_image + i);
+		w(r(loc) + i, loc);
+		i += 4;
+	}
+
+	qsort(extab_image, image_size / 8, 8, compare_x86_table);
+
+	/* Now denormalize. */
+	i = 0;
+	while (i < image_size) {
+		uint32_t *loc = (uint32_t *)(extab_image + i);
+		w(r(loc) - i, loc);
+		i += 4;
+	}
+}
+
+static void
+do_file(char const *const fname)
+{
+	table_sort_t custom_sort;
+	Elf32_Ehdr *ehdr = mmap_file(fname);
+
+	ehdr_curr = ehdr;
+	switch (ehdr->e_ident[EI_DATA]) {
+	default:
+		fprintf(stderr, "unrecognized ELF data encoding %d: %s\n",
+			ehdr->e_ident[EI_DATA], fname);
+		fail_file();
+		break;
+	case ELFDATA2LSB:
+		r = rle;
+		r2 = r2le;
+		r8 = r8le;
+		w = wle;
+		w2 = w2le;
+		w8 = w8le;
+		break;
+	case ELFDATA2MSB:
+		r = rbe;
+		r2 = r2be;
+		r8 = r8be;
+		w = wbe;
+		w2 = w2be;
+		w8 = w8be;
+		break;
+	}  /* end switch */
+	if (memcmp(ELFMAG, ehdr->e_ident, SELFMAG) != 0
+	||  r2(&ehdr->e_type) != ET_EXEC
+	||  ehdr->e_ident[EI_VERSION] != EV_CURRENT) {
+		fprintf(stderr, "unrecognized ET_EXEC file %s\n", fname);
+		fail_file();
+	}
+
+	custom_sort = NULL;
+	switch (r2(&ehdr->e_machine)) {
+	default:
+		fprintf(stderr, "unrecognized e_machine %d %s\n",
+			r2(&ehdr->e_machine), fname);
+		fail_file();
+		break;
+	case EM_386:
+	case EM_X86_64:
+		custom_sort = sort_x86_table;
+		break;
+	case EM_MIPS:
+		break;
+	}  /* end switch */
+
+	switch (ehdr->e_ident[EI_CLASS]) {
+	default:
+		fprintf(stderr, "unrecognized ELF class %d %s\n",
+			ehdr->e_ident[EI_CLASS], fname);
+		fail_file();
+		break;
+	case ELFCLASS32:
+		if (r2(&ehdr->e_ehsize) != sizeof(Elf32_Ehdr)
+		||  r2(&ehdr->e_shentsize) != sizeof(Elf32_Shdr)) {
+			fprintf(stderr,
+				"unrecognized ET_EXEC file: %s\n", fname);
+			fail_file();
+		}
+		do32(ehdr, fname, custom_sort);
+		break;
+	case ELFCLASS64: {
+		Elf64_Ehdr *const ghdr = (Elf64_Ehdr *)ehdr;
+		if (r2(&ghdr->e_ehsize) != sizeof(Elf64_Ehdr)
+		||  r2(&ghdr->e_shentsize) != sizeof(Elf64_Shdr)) {
+			fprintf(stderr,
+				"unrecognized ET_EXEC file: %s\n", fname);
+			fail_file();
+		}
+		do64(ghdr, fname, custom_sort);
+		break;
+	}
+	}  /* end switch */
+
+	cleanup();
+}
+
+int
+main(int argc, char *argv[])
+{
+	int n_error = 0;  /* gcc-4.3.0 false positive complaint */
+	int i;
+
+	if (argc < 2) {
+		fprintf(stderr, "usage: sortextable vmlinux...\n");
+		return 0;
+	}
+
+	/* Process each file in turn, allowing deep failure. */
+	for (i = 1; i < argc; i++) {
+		char *file = argv[i];
+		int const sjval = setjmp(jmpenv);
+
+		switch (sjval) {
+		default:
+			fprintf(stderr, "internal error: %s\n", file);
+			exit(1);
+			break;
+		case SJ_SETJMP:    /* normal sequence */
+			/* Avoid problems if early cleanup() */
+			fd_map = -1;
+			ehdr_curr = NULL;
+			mmap_failed = 1;
+			do_file(file);
+			break;
+		case SJ_FAIL:    /* error in do_file or below */
+			++n_error;
+			break;
+		case SJ_SUCCEED:    /* premature success */
+			/* do nothing */
+			break;
+		}  /* end switch */
+	}
+	return !!n_error;
+}
diff --git a/scripts/sortextable.h b/scripts/sortextable.h
new file mode 100644
index 0000000..e4fd45b
--- /dev/null
+++ b/scripts/sortextable.h
@@ -0,0 +1,191 @@
+/*
+ * sortextable.h
+ *
+ * Copyright 2011 - 2012 Cavium, Inc.
+ *
+ * Some of this code was taken out of recordmcount.h written by:
+ *
+ * Copyright 2009 John F. Reiser <jreiser@BitWagon.com>.  All rights reserved.
+ * Copyright 2010 Steven Rostedt <srostedt@redhat.com>, Red Hat Inc.
+ *
+ *
+ * Licensed under the GNU General Public License, version 2 (GPLv2).
+ */
+
+#undef extable_ent_size
+#undef compare_extable
+#undef do_func
+#undef Elf_Addr
+#undef Elf_Ehdr
+#undef Elf_Shdr
+#undef Elf_Rel
+#undef Elf_Rela
+#undef Elf_Sym
+#undef ELF_R_SYM
+#undef Elf_r_sym
+#undef ELF_R_INFO
+#undef Elf_r_info
+#undef ELF_ST_BIND
+#undef ELF_ST_TYPE
+#undef fn_ELF_R_SYM
+#undef fn_ELF_R_INFO
+#undef uint_t
+#undef _r
+#undef _w
+
+#ifdef SORTEXTABLE_64
+# define extable_ent_size	16
+# define compare_extable	compare_extable_64
+# define do_func		do64
+# define Elf_Addr		Elf64_Addr
+# define Elf_Ehdr		Elf64_Ehdr
+# define Elf_Shdr		Elf64_Shdr
+# define Elf_Rel		Elf64_Rel
+# define Elf_Rela		Elf64_Rela
+# define Elf_Sym		Elf64_Sym
+# define ELF_R_SYM		ELF64_R_SYM
+# define Elf_r_sym		Elf64_r_sym
+# define ELF_R_INFO		ELF64_R_INFO
+# define Elf_r_info		Elf64_r_info
+# define ELF_ST_BIND		ELF64_ST_BIND
+# define ELF_ST_TYPE		ELF64_ST_TYPE
+# define fn_ELF_R_SYM		fn_ELF64_R_SYM
+# define fn_ELF_R_INFO		fn_ELF64_R_INFO
+# define uint_t			uint64_t
+# define _r			r8
+# define _w			w8
+#else
+# define extable_ent_size	8
+# define compare_extable	compare_extable_32
+# define do_func		do32
+# define Elf_Addr		Elf32_Addr
+# define Elf_Ehdr		Elf32_Ehdr
+# define Elf_Shdr		Elf32_Shdr
+# define Elf_Rel		Elf32_Rel
+# define Elf_Rela		Elf32_Rela
+# define Elf_Sym		Elf32_Sym
+# define ELF_R_SYM		ELF32_R_SYM
+# define Elf_r_sym		Elf32_r_sym
+# define ELF_R_INFO		ELF32_R_INFO
+# define Elf_r_info		Elf32_r_info
+# define ELF_ST_BIND		ELF32_ST_BIND
+# define ELF_ST_TYPE		ELF32_ST_TYPE
+# define fn_ELF_R_SYM		fn_ELF32_R_SYM
+# define fn_ELF_R_INFO		fn_ELF32_R_INFO
+# define uint_t			uint32_t
+# define _r			r
+# define _w			w
+#endif
+
+static int compare_extable(const void *a, const void *b)
+{
+	Elf_Addr av = _r(a);
+	Elf_Addr bv = _r(b);
+
+	if (av < bv)
+		return -1;
+	if (av > bv)
+		return 1;
+	return 0;
+}
+
+static void
+do_func(Elf_Ehdr *ehdr, char const *const fname, table_sort_t custom_sort)
+{
+	Elf_Shdr *shdr;
+	Elf_Shdr *shstrtab_sec;
+	Elf_Shdr *strtab_sec = NULL;
+	Elf_Shdr *symtab_sec = NULL;
+	Elf_Shdr *extab_sec = NULL;
+	Elf_Sym *sym;
+	Elf_Sym *sort_needed_sym;
+	Elf_Shdr *sort_needed_sec;
+	Elf_Rel *relocs = NULL;
+	int relocs_size;
+	uint32_t *sort_done_location;
+	const char *secstrtab;
+	const char *strtab;
+	char *extab_image;
+	int extab_index = 0;
+	int i;
+	int idx;
+
+	shdr = (Elf_Shdr *)((char *)ehdr + _r(&ehdr->e_shoff));
+	shstrtab_sec = shdr + r2(&ehdr->e_shstrndx);
+	secstrtab = (const char *)ehdr + _r(&shstrtab_sec->sh_offset);
+	for (i = 0; i < r2(&ehdr->e_shnum); i++) {
+		idx = r(&shdr[i].sh_name);
+		if (strcmp(secstrtab + idx, "__ex_table") == 0) {
+			extab_sec = shdr + i;
+			extab_index = i;
+		}
+		if ((r(&shdr[i].sh_type) == SHT_REL ||
+		     r(&shdr[i].sh_type) == SHT_RELA) &&
+		    r(&shdr[i].sh_info) == extab_index) {
+			relocs = (void *)ehdr + _r(&shdr[i].sh_offset);
+			relocs_size = _r(&shdr[i].sh_size);
+		}
+		if (strcmp(secstrtab + idx, ".symtab") == 0)
+			symtab_sec = shdr + i;
+		if (strcmp(secstrtab + idx, ".strtab") == 0)
+			strtab_sec = shdr + i;
+	}
+	if (strtab_sec == NULL) {
+		fprintf(stderr,	"no .strtab in  file: %s\n", fname);
+		fail_file();
+	}
+	if (symtab_sec == NULL) {
+		fprintf(stderr,	"no .symtab in  file: %s\n", fname);
+		fail_file();
+	}
+	if (extab_sec == NULL) {
+		fprintf(stderr,	"no __ex_table in  file: %s\n", fname);
+		fail_file();
+	}
+	strtab = (const char *)ehdr + _r(&strtab_sec->sh_offset);
+
+	extab_image = (void *)ehdr + _r(&extab_sec->sh_offset);
+
+	if (custom_sort) {
+		custom_sort(extab_image, _r(&extab_sec->sh_size));
+	} else {
+		int num_entries = _r(&extab_sec->sh_size) / extable_ent_size;
+		qsort(extab_image, num_entries,
+		      extable_ent_size, compare_extable);
+	}
+	/* If there were relocations, we no longer need them. */
+	if (relocs)
+		memset(relocs, 0, relocs_size);
+
+	/* find main_extable_sort_needed */
+	sort_needed_sym = NULL;
+	for (i = 0; i < _r(&symtab_sec->sh_size) / sizeof(Elf_Sym); i++) {
+		sym = (void *)ehdr + _r(&symtab_sec->sh_offset);
+		sym += i;
+		if (ELF_ST_TYPE(sym->st_info) != STT_OBJECT)
+			continue;
+		idx = r(&sym->st_name);
+		if (strcmp(strtab + idx, "main_extable_sort_needed") == 0) {
+			sort_needed_sym = sym;
+			break;
+		}
+	}
+	if (sort_needed_sym == NULL) {
+		fprintf(stderr,
+			"no main_extable_sort_needed symbol in  file: %s\n",
+			fname);
+		fail_file();
+	}
+	sort_needed_sec = &shdr[r2(&sort_needed_sym->st_shndx)];
+	sort_done_location = (void *)ehdr +
+		_r(&sort_needed_sec->sh_offset) +
+		_r(&sort_needed_sym->st_value) -
+		_r(&sort_needed_sec->sh_addr);
+
+#if 1
+	printf("sort done marker at %lx\n",
+	       (unsigned long)((char *)sort_done_location - (char *)ehdr));
+#endif
+	/* We sorted it, clear the flag. */
+	w(0, sort_done_location);
+}