Merge remote-tracking branch 'anton/abiv2' into next

This series adds support for building the powerpc 64-bit
LE kernel using the new ABI v2. We already supported
running ABI v2 userspace programs but this adds support
for building the kernel itself using the new ABI.

arch/powerpc/Makefile

@@ -113,8 +113,13 @@ else
 endif
 endif
 
-CFLAGS-$(CONFIG_PPC64)	:= -mtraceback=no -mcall-aixdesc
-CFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mabi=elfv1)
+CFLAGS-$(CONFIG_PPC64)	:= -mtraceback=no
+ifeq ($(CONFIG_CPU_LITTLE_ENDIAN),y)
+CFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mabi=elfv2,-mcall-aixdesc)
+AFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mabi=elfv2)
+else
+CFLAGS-$(CONFIG_PPC64)	+= -mcall-aixdesc
+endif
 CFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mcmodel=medium,-mminimal-toc)
 CFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mno-pointers-to-nested-functions)
 CFLAGS-$(CONFIG_PPC32)	:= -ffixed-r2 $(MULTIPLEWORD)
@@ -151,7 +156,7 @@ endif
 CFLAGS-$(CONFIG_TUNE_CELL) += $(call cc-option,-mtune=cell)
 
 KBUILD_CPPFLAGS	+= -Iarch/$(ARCH)
-KBUILD_AFLAGS	+= -Iarch/$(ARCH)
+KBUILD_AFLAGS	+= -Iarch/$(ARCH) $(AFLAGS-y)
 KBUILD_CFLAGS	+= -msoft-float -pipe -Iarch/$(ARCH) $(CFLAGS-y)
 CPP		= $(CC) -E $(KBUILD_CFLAGS)
 

arch/powerpc/boot/util.S

@@ -45,7 +45,7 @@ udelay:
 	mfspr	r4,SPRN_PVR
 	srwi	r4,r4,16
 	cmpwi	0,r4,1		/* 601 ? */
-	bne	.udelay_not_601
+	bne	.Ludelay_not_601
 00:	li	r0,86	/* Instructions / microsecond? */
 	mtctr	r0
 10:	addi	r0,r0,0 /* NOP */
@@ -54,7 +54,7 @@ udelay:
 	bne	00b
 	blr
 
-.udelay_not_601:
+.Ludelay_not_601:
 	mulli	r4,r3,1000	/* nanoseconds */
 	/*  Change r4 to be the number of ticks using:
 	 *	(nanoseconds + (timebase_period_ns - 1 )) / timebase_period_ns

arch/powerpc/include/asm/code-patching.h

@@ -42,15 +42,47 @@ void __patch_exception(int exc, unsigned long addr);
 } while (0)
 #endif
 
+#define OP_RT_RA_MASK	0xffff0000UL
+#define LIS_R2		0x3c020000UL
+#define ADDIS_R2_R12	0x3c4c0000UL
+#define ADDI_R2_R2	0x38420000UL
+
 static inline unsigned long ppc_function_entry(void *func)
 {
-#ifdef CONFIG_PPC64
+#if defined(CONFIG_PPC64)
+#if defined(_CALL_ELF) && _CALL_ELF == 2
+	u32 *insn = func;
+
 	/*
-	 * On PPC64 the function pointer actually points to the function's
-	 * descriptor. The first entry in the descriptor is the address
-	 * of the function text.
+	 * A PPC64 ABIv2 function may have a local and a global entry
+	 * point. We need to use the local entry point when patching
+	 * functions, so identify and step over the global entry point
+	 * sequence.
+	 *
+	 * The global entry point sequence is always of the form:
+	 *
+	 * addis r2,r12,XXXX
+	 * addi  r2,r2,XXXX
+	 *
+	 * A linker optimisation may convert the addis to lis:
+	 *
+	 * lis   r2,XXXX
+	 * addi  r2,r2,XXXX
+	 */
+	if ((((*insn & OP_RT_RA_MASK) == ADDIS_R2_R12) ||
+	     ((*insn & OP_RT_RA_MASK) == LIS_R2)) &&
+	    ((*(insn+1) & OP_RT_RA_MASK) == ADDI_R2_R2))
+		return (unsigned long)(insn + 2);
+	else
+		return (unsigned long)func;
+#else
+	/*
+	 * On PPC64 ABIv1 the function pointer actually points to the
+	 * function's descriptor. The first entry in the descriptor is the
+	 * address of the function text.
 	 */
 	return ((func_descr_t *)func)->entry;
+#endif
 #else
 	return (unsigned long)func;
 #endif

arch/powerpc/include/asm/context_tracking.h

@@ -2,9 +2,9 @@
 #define _ASM_POWERPC_CONTEXT_TRACKING_H
 
 #ifdef CONFIG_CONTEXT_TRACKING
-#define SCHEDULE_USER bl	.schedule_user
+#define SCHEDULE_USER bl	schedule_user
 #else
-#define SCHEDULE_USER bl	.schedule
+#define SCHEDULE_USER bl	schedule
 #endif
 
 #endif

arch/powerpc/include/asm/exception-64e.h

@@ -174,10 +174,10 @@ exc_##label##_book3e:
 	mtlr	r16;
 #define TLB_MISS_STATS_D(name)						    \
 	addi	r9,r13,MMSTAT_DSTATS+name;				    \
-	bl	.tlb_stat_inc;
+	bl	tlb_stat_inc;
 #define TLB_MISS_STATS_I(name)						    \
 	addi	r9,r13,MMSTAT_ISTATS+name;				    \
-	bl	.tlb_stat_inc;
+	bl	tlb_stat_inc;
 #define TLB_MISS_STATS_X(name)						    \
 	ld	r8,PACA_EXTLB+EX_TLB_ESR(r13);				    \
 	cmpdi	cr2,r8,-1;						    \
@@ -185,7 +185,7 @@ exc_##label##_book3e:
 	addi	r9,r13,MMSTAT_DSTATS+name;				    \
 	b	62f;							    \
 61:	addi	r9,r13,MMSTAT_ISTATS+name;				    \
-62:	bl	.tlb_stat_inc;
+62:	bl	tlb_stat_inc;
 #define TLB_MISS_STATS_SAVE_INFO					    \
 	std	r14,EX_TLB_ESR(r12);	/* save ESR */
 #define TLB_MISS_STATS_SAVE_INFO_BOLTED					    \

arch/powerpc/include/asm/exception-64s.h

@@ -517,7 +517,7 @@ label##_relon_hv:							\
 #define DISABLE_INTS	RECONCILE_IRQ_STATE(r10,r11)
 
 #define ADD_NVGPRS				\
-	bl	.save_nvgprs
+	bl	save_nvgprs
 
 #define RUNLATCH_ON				\
 BEGIN_FTR_SECTION				\

arch/powerpc/include/asm/ftrace.h

@@ -61,6 +61,7 @@ struct dyn_arch_ftrace {
 #endif
 
 #if defined(CONFIG_FTRACE_SYSCALLS) && defined(CONFIG_PPC64) && !defined(__ASSEMBLY__)
+#if !defined(_CALL_ELF) || _CALL_ELF != 2
 #define ARCH_HAS_SYSCALL_MATCH_SYM_NAME
 static inline bool arch_syscall_match_sym_name(const char *sym, const char *name)
 {
@@ -72,6 +73,7 @@ static inline bool arch_syscall_match_sym_name(const char *sym, const char *name
 	 */
 	return !strcmp(sym + 4, name + 3);
 }
+#endif
 #endif /* CONFIG_FTRACE_SYSCALLS && CONFIG_PPC64 && !__ASSEMBLY__ */
 
 #endif /* _ASM_POWERPC_FTRACE */

arch/powerpc/include/asm/irqflags.h

@@ -20,9 +20,9 @@
  */
 #define TRACE_WITH_FRAME_BUFFER(func)		\
 	mflr	r0;				\
-	stdu	r1, -32(r1);			\
+	stdu	r1, -STACK_FRAME_OVERHEAD(r1);	\
 	std	r0, 16(r1);			\
-	stdu	r1, -32(r1);			\
+	stdu	r1, -STACK_FRAME_OVERHEAD(r1);	\
 	bl func;				\
 	ld	r1, 0(r1);			\
 	ld	r1, 0(r1);
@@ -36,8 +36,8 @@
  * have to call a C function so call a wrapper that saves all the
  * C-clobbered registers.
  */
-#define TRACE_ENABLE_INTS	TRACE_WITH_FRAME_BUFFER(.trace_hardirqs_on)
-#define TRACE_DISABLE_INTS	TRACE_WITH_FRAME_BUFFER(.trace_hardirqs_off)
+#define TRACE_ENABLE_INTS	TRACE_WITH_FRAME_BUFFER(trace_hardirqs_on)
+#define TRACE_DISABLE_INTS	TRACE_WITH_FRAME_BUFFER(trace_hardirqs_off)
 
 /*
  * This is used by assembly code to soft-disable interrupts first and

arch/powerpc/include/asm/kprobes.h

@@ -30,6 +30,7 @@
 #include <linux/ptrace.h>
 #include <linux/percpu.h>
 #include <asm/probes.h>
+#include <asm/code-patching.h>
 
 #define  __ARCH_WANT_KPROBES_INSN_SLOT
 
@@ -56,9 +57,9 @@ typedef ppc_opcode_t kprobe_opcode_t;
 		if ((colon = strchr(name, ':')) != NULL) {		\
 			colon++;					\
 			if (*colon != '\0' && *colon != '.')		\
-				addr = *(kprobe_opcode_t **)addr;	\
+				addr = (kprobe_opcode_t *)ppc_function_entry(addr); \
 		} else if (name[0] != '.')				\
-			addr = *(kprobe_opcode_t **)addr;		\
+			addr = (kprobe_opcode_t *)ppc_function_entry(addr); \
 	} else {							\
 		char dot_name[KSYM_NAME_LEN];				\
 		dot_name[0] = '.';					\

arch/powerpc/include/asm/linkage.h

@@ -2,6 +2,7 @@
 #define _ASM_POWERPC_LINKAGE_H
 
 #ifdef CONFIG_PPC64
+#if !defined(_CALL_ELF) || _CALL_ELF != 2
 #define cond_syscall(x) \
 	asm ("\t.weak " #x "\n\t.set " #x ", sys_ni_syscall\n"		\
 	     "\t.weak ." #x "\n\t.set ." #x ", .sys_ni_syscall\n")
@@ -9,5 +10,6 @@
 	asm ("\t.globl " #alias "\n\t.set " #alias ", " #name "\n"	\
 	     "\t.globl ." #alias "\n\t.set ." #alias ", ." #name)
 #endif
+#endif
 
 #endif	/* _ASM_POWERPC_LINKAGE_H */

arch/powerpc/include/asm/module.h

@@ -35,6 +35,7 @@ struct mod_arch_specific {
 #ifdef __powerpc64__
 	unsigned int stubs_section;	/* Index of stubs section in module */
 	unsigned int toc_section;	/* What section is the TOC? */
+	bool toc_fixed;			/* Have we fixed up .TOC.? */
 #ifdef CONFIG_DYNAMIC_FTRACE
 	unsigned long toc;
 	unsigned long tramp;
@@ -77,6 +78,9 @@ struct mod_arch_specific {
 #    endif	/* MODULE */
 #endif
 
+bool is_module_trampoline(u32 *insns);
+int module_trampoline_target(struct module *mod, u32 *trampoline,
+			     unsigned long *target);
 
 struct exception_table_entry;
 void sort_ex_table(struct exception_table_entry *start,

arch/powerpc/include/asm/ppc_asm.h

@@ -57,7 +57,7 @@ BEGIN_FW_FTR_SECTION;							\
 	LDX_BE	r10,0,r10;		/* get log write index */	\
 	cmpd	cr1,r11,r10;						\
 	beq+	cr1,33f;						\
-	bl	.accumulate_stolen_time;				\
+	bl	accumulate_stolen_time;				\
 	ld	r12,_MSR(r1);						\
 	andi.	r10,r12,MSR_PR;		/* Restore cr0 (coming from user) */ \
 33:									\
@@ -189,57 +189,53 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR)
 #define __STK_REG(i)   (112 + ((i)-14)*8)
 #define STK_REG(i)     __STK_REG(__REG_##i)
 
+#if defined(_CALL_ELF) && _CALL_ELF == 2
+#define STK_GOT		24
+#define __STK_PARAM(i)	(32 + ((i)-3)*8)
+#else
+#define STK_GOT		40
 #define __STK_PARAM(i)	(48 + ((i)-3)*8)
+#endif
 #define STK_PARAM(i)	__STK_PARAM(__REG_##i)
 
-#define XGLUE(a,b) a##b
-#define GLUE(a,b) XGLUE(a,b)
+#if defined(_CALL_ELF) && _CALL_ELF == 2
 
 #define _GLOBAL(name) \
 	.section ".text"; \
 	.align 2 ; \
+	.type name,@function; \
 	.globl name; \
-	.globl GLUE(.,name); \
-	.section ".opd","aw"; \
-name: \
-	.quad GLUE(.,name); \
-	.quad .TOC.@tocbase; \
-	.quad 0; \
-	.previous; \
-	.type GLUE(.,name),@function; \
-GLUE(.,name):
+name:
 
-#define _INIT_GLOBAL(name) \
-	__REF; \
+#define _GLOBAL_TOC(name) \
+	.section ".text"; \
 	.align 2 ; \
+	.type name,@function; \
 	.globl name; \
-	.globl GLUE(.,name); \
-	.section ".opd","aw"; \
 name: \
-	.quad GLUE(.,name); \
-	.quad .TOC.@tocbase; \
-	.quad 0; \
-	.previous; \
-	.type GLUE(.,name),@function; \
-GLUE(.,name):
+0:	addis r2,r12,(.TOC.-0b)@ha; \
+	addi r2,r2,(.TOC.-0b)@l; \
+	.localentry name,.-name
 
 #define _KPROBE(name) \
 	.section ".kprobes.text","a"; \
 	.align 2 ; \
+	.type name,@function; \
 	.globl name; \
-	.globl GLUE(.,name); \
-	.section ".opd","aw"; \
-name: \
-	.quad GLUE(.,name); \
-	.quad .TOC.@tocbase; \
-	.quad 0; \
-	.previous; \
-	.type GLUE(.,name),@function; \
-GLUE(.,name):
+name:
+
+#define DOTSYM(a)	a
+
+#else
+
+#define XGLUE(a,b) a##b
+#define GLUE(a,b) XGLUE(a,b)
 
-#define _STATIC(name) \
+#define _GLOBAL(name) \
 	.section ".text"; \
 	.align 2 ; \
+	.globl name; \
+	.globl GLUE(.,name); \
 	.section ".opd","aw"; \
 name: \
 	.quad GLUE(.,name); \
@@ -249,9 +245,13 @@ name: \
 	.type GLUE(.,name),@function; \
 GLUE(.,name):
 
-#define _INIT_STATIC(name) \
-	__REF; \
+#define _GLOBAL_TOC(name) _GLOBAL(name)
+
+#define _KPROBE(name) \
+	.section ".kprobes.text","a"; \
 	.align 2 ; \
+	.globl name; \
+	.globl GLUE(.,name); \
 	.section ".opd","aw"; \
 name: \
 	.quad GLUE(.,name); \
@@ -261,6 +261,10 @@ name: \
 	.type GLUE(.,name),@function; \
 GLUE(.,name):
 
+#define DOTSYM(a)	GLUE(.,a)
+
+#endif
+
 #else /* 32-bit */
 
 #define _ENTRY(n)	\

arch/powerpc/include/asm/sections.h

@@ -39,6 +39,7 @@ static inline int overlaps_kernel_text(unsigned long start, unsigned long end)
 		(unsigned long)_stext < end;
 }
 
+#if !defined(_CALL_ELF) || _CALL_ELF != 2
 #undef dereference_function_descriptor
 static inline void *dereference_function_descriptor(void *ptr)
 {
@@ -49,6 +50,7 @@ static inline void *dereference_function_descriptor(void *ptr)
 		ptr = p;
 	return ptr;
 }
+#endif
 
 #endif
 

arch/powerpc/include/asm/systbl.h

@@ -62,7 +62,7 @@ COMPAT_SYS_SPU(fcntl)
 SYSCALL(ni_syscall)
 SYSCALL_SPU(setpgid)
 SYSCALL(ni_syscall)
-SYSX(sys_ni_syscall,sys_olduname, sys_olduname)
+SYSX(sys_ni_syscall,sys_olduname,sys_olduname)
 SYSCALL_SPU(umask)
 SYSCALL_SPU(chroot)
 COMPAT_SYS(ustat)
@@ -258,7 +258,7 @@ SYSCALL_SPU(tgkill)
 COMPAT_SYS_SPU(utimes)
 COMPAT_SYS_SPU(statfs64)
 COMPAT_SYS_SPU(fstatfs64)
-SYSX(sys_ni_syscall, ppc_fadvise64_64, ppc_fadvise64_64)
+SYSX(sys_ni_syscall,ppc_fadvise64_64,ppc_fadvise64_64)
 PPC_SYS_SPU(rtas)
 OLDSYS(debug_setcontext)
 SYSCALL(ni_syscall)
@@ -295,7 +295,7 @@ SYSCALL_SPU(mkdirat)
 SYSCALL_SPU(mknodat)
 SYSCALL_SPU(fchownat)
 COMPAT_SYS_SPU(futimesat)
-SYSX_SPU(sys_newfstatat, sys_fstatat64, sys_fstatat64)
+SYSX_SPU(sys_newfstatat,sys_fstatat64,sys_fstatat64)
 SYSCALL_SPU(unlinkat)
 SYSCALL_SPU(renameat)
 SYSCALL_SPU(linkat)

arch/powerpc/include/uapi/asm/elf.h

@@ -291,9 +291,17 @@ do {									\
 #define R_PPC64_DTPREL16_HIGHERA 104 /* half16	(sym+add)@dtprel@highera */
 #define R_PPC64_DTPREL16_HIGHEST 105 /* half16	(sym+add)@dtprel@highest */
 #define R_PPC64_DTPREL16_HIGHESTA 106 /* half16	(sym+add)@dtprel@highesta */
+#define R_PPC64_TLSGD		107
+#define R_PPC64_TLSLD		108
+#define R_PPC64_TOCSAVE		109
+
+#define R_PPC64_REL16		249
+#define R_PPC64_REL16_LO	250
+#define R_PPC64_REL16_HI	251
+#define R_PPC64_REL16_HA	252
 
 /* Keep this the last entry.  */
-#define R_PPC64_NUM		107
+#define R_PPC64_NUM		253
 
 /* There's actually a third entry here, but it's unused */
 struct ppc64_opd_entry

arch/powerpc/kernel/cpu_setup_fsl_booke.S

@@ -94,12 +94,12 @@ _GLOBAL(setup_altivec_idle)
 _GLOBAL(__setup_cpu_e6500)
 	mflr	r6
 #ifdef CONFIG_PPC64
-	bl	.setup_altivec_ivors
+	bl	setup_altivec_ivors
 	/* Touch IVOR42 only if the CPU supports E.HV category */
 	mfspr	r10,SPRN_MMUCFG
 	rlwinm.	r10,r10,0,MMUCFG_LPIDSIZE
 	beq	1f
-	bl	.setup_lrat_ivor
+	bl	setup_lrat_ivor
 1:
 #endif
 	bl	setup_pw20_idle
@@ -164,15 +164,15 @@ _GLOBAL(__setup_cpu_e5500)
 #ifdef CONFIG_PPC_BOOK3E_64
 _GLOBAL(__restore_cpu_e6500)
 	mflr	r5
-	bl	.setup_altivec_ivors
+	bl	setup_altivec_ivors
 	/* Touch IVOR42 only if the CPU supports E.HV category */
 	mfspr	r10,SPRN_MMUCFG
 	rlwinm.	r10,r10,0,MMUCFG_LPIDSIZE
 	beq	1f
-	bl	.setup_lrat_ivor
+	bl	setup_lrat_ivor
 1:
-	bl	.setup_pw20_idle
-	bl	.setup_altivec_idle
+	bl	setup_pw20_idle
+	bl	setup_altivec_idle
 	bl	__restore_cpu_e5500
 	mtlr	r5
 	blr
@@ -181,9 +181,9 @@ _GLOBAL(__restore_cpu_e5500)
 	mflr	r4
 	bl	__e500_icache_setup
 	bl	__e500_dcache_setup
-	bl	.__setup_base_ivors
-	bl	.setup_perfmon_ivor
-	bl	.setup_doorbell_ivors
+	bl	__setup_base_ivors
+	bl	setup_perfmon_ivor
+	bl	setup_doorbell_ivors
 	/*
 	 * We only want to touch IVOR38-41 if we're running on hardware
 	 * that supports category E.HV.  The architectural way to determine
@@ -192,7 +192,7 @@ _GLOBAL(__restore_cpu_e5500)
 	mfspr	r10,SPRN_MMUCFG
 	rlwinm.	r10,r10,0,MMUCFG_LPIDSIZE
 	beq	1f
-	bl	.setup_ehv_ivors
+	bl	setup_ehv_ivors
 1:
 	mtlr	r4
 	blr
@@ -201,9 +201,9 @@ _GLOBAL(__setup_cpu_e5500)
 	mflr	r5
 	bl	__e500_icache_setup
 	bl	__e500_dcache_setup
-	bl	.__setup_base_ivors
-	bl	.setup_perfmon_ivor
-	bl	.setup_doorbell_ivors
+	bl	__setup_base_ivors
+	bl	setup_perfmon_ivor
+	bl	setup_doorbell_ivors
 	/*
 	 * We only want to touch IVOR38-41 if we're running on hardware
 	 * that supports category E.HV.  The architectural way to determine
@@ -212,7 +212,7 @@ _GLOBAL(__setup_cpu_e5500)
 	mfspr	r10,SPRN_MMUCFG
 	rlwinm.	r10,r10,0,MMUCFG_LPIDSIZE
 	beq	1f
-	bl	.setup_ehv_ivors
+	bl	setup_ehv_ivors
 	b	2f
 1:
 	ld	r10,CPU_SPEC_FEATURES(r4)

arch/powerpc/kernel/entry_64.S

@@ -39,8 +39,8 @@
  * System calls.
  */
 	.section	".toc","aw"
-.SYS_CALL_TABLE:
-	.tc .sys_call_table[TC],.sys_call_table
+SYS_CALL_TABLE:
+	.tc sys_call_table[TC],sys_call_table
 
 /* This value is used to mark exception frames on the stack. */
 exception_marker:
@@ -106,7 +106,7 @@ BEGIN_FW_FTR_SECTION
 	LDX_BE	r10,0,r10		/* get log write index */
 	cmpd	cr1,r11,r10
 	beq+	cr1,33f
-	bl	.accumulate_stolen_time
+	bl	accumulate_stolen_time
 	REST_GPR(0,r1)
 	REST_4GPRS(3,r1)
 	REST_2GPRS(7,r1)
@@ -143,7 +143,7 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR)
 	std	r10,SOFTE(r1)
 
 #ifdef SHOW_SYSCALLS
-	bl	.do_show_syscall
+	bl	do_show_syscall
 	REST_GPR(0,r1)
 	REST_4GPRS(3,r1)
 	REST_2GPRS(7,r1)
@@ -162,7 +162,7 @@ system_call:			/* label this so stack traces look sane */
  * Need to vector to 32 Bit or default sys_call_table here,
  * based on caller's run-mode / personality.
  */
-	ld	r11,.SYS_CALL_TABLE@toc(2)
+	ld	r11,SYS_CALL_TABLE@toc(2)
 	andi.	r10,r10,_TIF_32BIT
 	beq	15f
 	addi	r11,r11,8	/* use 32-bit syscall entries */
@@ -174,14 +174,14 @@ system_call:			/* label this so stack traces look sane */
 	clrldi	r8,r8,32
 15:
 	slwi	r0,r0,4
-	ldx	r10,r11,r0	/* Fetch system call handler [ptr] */
-	mtctr   r10
+	ldx	r12,r11,r0	/* Fetch system call handler [ptr] */
+	mtctr   r12
 	bctrl			/* Call handler */
 
 syscall_exit:
 	std	r3,RESULT(r1)
 #ifdef SHOW_SYSCALLS
-	bl	.do_show_syscall_exit
+	bl	do_show_syscall_exit
 	ld	r3,RESULT(r1)
 #endif
 	CURRENT_THREAD_INFO(r12, r1)
@@ -248,9 +248,9 @@ syscall_error:
 	
 /* Traced system call support */
 syscall_dotrace:
-	bl	.save_nvgprs
+	bl	save_nvgprs
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.do_syscall_trace_enter
+	bl	do_syscall_trace_enter
 	/*
 	 * Restore argument registers possibly just changed.
 	 * We use the return value of do_syscall_trace_enter
@@ -308,7 +308,7 @@ syscall_exit_work:
 4:	/* Anything else left to do? */
 	SET_DEFAULT_THREAD_PPR(r3, r10)		/* Set thread.ppr = 3 */
 	andi.	r0,r9,(_TIF_SYSCALL_T_OR_A|_TIF_SINGLESTEP)
-	beq	.ret_from_except_lite
+	beq	ret_from_except_lite
 
 	/* Re-enable interrupts */
 #ifdef CONFIG_PPC_BOOK3E
@@ -319,10 +319,10 @@ syscall_exit_work:
 	mtmsrd	r10,1
 #endif /* CONFIG_PPC_BOOK3E */
 
-	bl	.save_nvgprs
+	bl	save_nvgprs
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.do_syscall_trace_leave
-	b	.ret_from_except
+	bl	do_syscall_trace_leave
+	b	ret_from_except
 
 /* Save non-volatile GPRs, if not already saved. */
 _GLOBAL(save_nvgprs)
@@ -345,42 +345,44 @@ _GLOBAL(save_nvgprs)
  */
 
 _GLOBAL(ppc_fork)
-	bl	.save_nvgprs
-	bl	.sys_fork
+	bl	save_nvgprs
+	bl	sys_fork
 	b	syscall_exit
 
 _GLOBAL(ppc_vfork)
-	bl	.save_nvgprs
-	bl	.sys_vfork
+	bl	save_nvgprs
+	bl	sys_vfork
 	b	syscall_exit
 
 _GLOBAL(ppc_clone)
-	bl	.save_nvgprs
-	bl	.sys_clone
+	bl	save_nvgprs
+	bl	sys_clone
 	b	syscall_exit
 
 _GLOBAL(ppc32_swapcontext)
-	bl	.save_nvgprs
-	bl	.compat_sys_swapcontext
+	bl	save_nvgprs
+	bl	compat_sys_swapcontext
 	b	syscall_exit
 
 _GLOBAL(ppc64_swapcontext)
-	bl	.save_nvgprs
-	bl	.sys_swapcontext
+	bl	save_nvgprs
+	bl	sys_swapcontext
 	b	syscall_exit
 
 _GLOBAL(ret_from_fork)
-	bl	.schedule_tail
+	bl	schedule_tail
 	REST_NVGPRS(r1)
 	li	r3,0
 	b	syscall_exit
 
 _GLOBAL(ret_from_kernel_thread)
-	bl	.schedule_tail
+	bl	schedule_tail
 	REST_NVGPRS(r1)
-	ld	r14, 0(r14)
 	mtlr	r14
 	mr	r3,r15
+#if defined(_CALL_ELF) && _CALL_ELF == 2
+	mr	r12,r14
+#endif
 	blrl
 	li	r3,0
 	b	syscall_exit
@@ -611,7 +613,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_DSCR)
 _GLOBAL(ret_from_except)
 	ld	r11,_TRAP(r1)
 	andi.	r0,r11,1
-	bne	.ret_from_except_lite
+	bne	ret_from_except_lite
 	REST_NVGPRS(r1)
 
 _GLOBAL(ret_from_except_lite)
@@ -661,23 +663,23 @@ _GLOBAL(ret_from_except_lite)
 #endif
 1:	andi.	r0,r4,_TIF_NEED_RESCHED
 	beq	2f
-	bl	.restore_interrupts
+	bl	restore_interrupts
 	SCHEDULE_USER
-	b	.ret_from_except_lite
+	b	ret_from_except_lite
 2:
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 	andi.	r0,r4,_TIF_USER_WORK_MASK & ~_TIF_RESTORE_TM
 	bne	3f		/* only restore TM if nothing else to do */
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.restore_tm_state
+	bl	restore_tm_state
 	b	restore
 3:
 #endif
-	bl	.save_nvgprs
-	bl	.restore_interrupts
+	bl	save_nvgprs
+	bl	restore_interrupts
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.do_notify_resume
-	b	.ret_from_except
+	bl	do_notify_resume
+	b	ret_from_except
 
 resume_kernel:
 	/* check current_thread_info, _TIF_EMULATE_STACK_STORE */
@@ -730,7 +732,7 @@ resume_kernel:
 	 * sure we are soft-disabled first and reconcile irq state.
 	 */
 	RECONCILE_IRQ_STATE(r3,r4)
-1:	bl	.preempt_schedule_irq
+1:	bl	preempt_schedule_irq
 
 	/* Re-test flags and eventually loop */
 	CURRENT_THREAD_INFO(r9, r1)
@@ -792,7 +794,7 @@ restore_no_replay:
 	 */
 do_restore:
 #ifdef CONFIG_PPC_BOOK3E
-	b	.exception_return_book3e
+	b	exception_return_book3e
 #else
 	/*
 	 * Clear the reservation. If we know the CPU tracks the address of
@@ -907,7 +909,7 @@ restore_check_irq_replay:
 	 *
 	 * Still, this might be useful for things like hash_page
 	 */
-	bl	.__check_irq_replay
+	bl	__check_irq_replay
 	cmpwi	cr0,r3,0
  	beq	restore_no_replay
  
@@ -928,13 +930,13 @@ restore_check_irq_replay:
 	cmpwi	cr0,r3,0x500
 	bne	1f
 	addi	r3,r1,STACK_FRAME_OVERHEAD;
- 	bl	.do_IRQ
-	b	.ret_from_except
+ 	bl	do_IRQ
+	b	ret_from_except
 1:	cmpwi	cr0,r3,0x900
 	bne	1f
 	addi	r3,r1,STACK_FRAME_OVERHEAD;
-	bl	.timer_interrupt
-	b	.ret_from_except
+	bl	timer_interrupt
+	b	ret_from_except
 #ifdef CONFIG_PPC_DOORBELL
 1:
 #ifdef CONFIG_PPC_BOOK3E
@@ -948,14 +950,14 @@ restore_check_irq_replay:
 #endif /* CONFIG_PPC_BOOK3E */
 	bne	1f
 	addi	r3,r1,STACK_FRAME_OVERHEAD;
-	bl	.doorbell_exception
-	b	.ret_from_except
+	bl	doorbell_exception
+	b	ret_from_except
 #endif /* CONFIG_PPC_DOORBELL */
-1:	b	.ret_from_except /* What else to do here ? */
+1:	b	ret_from_except /* What else to do here ? */
  
 unrecov_restore:
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.unrecoverable_exception
+	bl	unrecoverable_exception
 	b	unrecov_restore
 
 #ifdef CONFIG_PPC_RTAS
@@ -1021,7 +1023,7 @@ _GLOBAL(enter_rtas)
         std	r6,PACASAVEDMSR(r13)
 
 	/* Setup our real return addr */	
-	LOAD_REG_ADDR(r4,.rtas_return_loc)
+	LOAD_REG_ADDR(r4,rtas_return_loc)
 	clrldi	r4,r4,2			/* convert to realmode address */
        	mtlr	r4
 
@@ -1045,7 +1047,7 @@ _GLOBAL(enter_rtas)
 	rfid
 	b	.	/* prevent speculative execution */
 
-_STATIC(rtas_return_loc)
+rtas_return_loc:
 	FIXUP_ENDIAN
 
 	/* relocation is off at this point */
@@ -1054,7 +1056,7 @@ _STATIC(rtas_return_loc)
 
 	bcl	20,31,$+4
 0:	mflr	r3
-	ld	r3,(1f-0b)(r3)		/* get &.rtas_restore_regs */
+	ld	r3,(1f-0b)(r3)		/* get &rtas_restore_regs */
 
 	mfmsr   r6
 	li	r0,MSR_RI
@@ -1071,9 +1073,9 @@ _STATIC(rtas_return_loc)
 	b	.	/* prevent speculative execution */
 
 	.align	3
-1:	.llong	.rtas_restore_regs
+1:	.llong	rtas_restore_regs
 
-_STATIC(rtas_restore_regs)
+rtas_restore_regs:
 	/* relocation is on at this point */
 	REST_GPR(2, r1)			/* Restore the TOC */
 	REST_GPR(13, r1)		/* Restore paca */
@@ -1173,7 +1175,7 @@ _GLOBAL(mcount)
 _GLOBAL(_mcount)
 	blr
 
-_GLOBAL(ftrace_caller)
+_GLOBAL_TOC(ftrace_caller)
 	/* Taken from output of objdump from lib64/glibc */
 	mflr	r3
 	ld	r11, 0(r1)
@@ -1197,10 +1199,7 @@ _GLOBAL(ftrace_graph_stub)
 _GLOBAL(ftrace_stub)
 	blr
 #else
-_GLOBAL(mcount)
-	blr
-
-_GLOBAL(_mcount)
+_GLOBAL_TOC(_mcount)
 	/* Taken from output of objdump from lib64/glibc */
 	mflr	r3
 	ld	r11, 0(r1)
@@ -1238,7 +1237,7 @@ _GLOBAL(ftrace_graph_caller)
 	ld	r11, 112(r1)
 	addi	r3, r11, 16
 
-	bl	.prepare_ftrace_return
+	bl	prepare_ftrace_return
 	nop
 
 	ld	r0, 128(r1)
@@ -1254,7 +1253,7 @@ _GLOBAL(return_to_handler)
 	mr	r31, r1
 	stdu	r1, -112(r1)
 
-	bl	.ftrace_return_to_handler
+	bl	ftrace_return_to_handler
 	nop
 
 	/* return value has real return address */
@@ -1284,7 +1283,7 @@ _GLOBAL(mod_return_to_handler)
 	 */
 	ld	r2, PACATOC(r13)
 
-	bl	.ftrace_return_to_handler
+	bl	ftrace_return_to_handler
 	nop
 
 	/* return value has real return address */

arch/powerpc/kernel/exceptions-64e.S

@@ -499,7 +499,7 @@ exc_##n##_bad_stack:							    \
 	CHECK_NAPPING();						\
 	addi	r3,r1,STACK_FRAME_OVERHEAD;				\
 	bl	hdlr;							\
-	b	.ret_from_except_lite;
+	b	ret_from_except_lite;
 
 /* This value is used to mark exception frames on the stack. */
 	.section	".toc","aw"
@@ -550,11 +550,11 @@ interrupt_end_book3e:
 	CRIT_EXCEPTION_PROLOG(0x100, BOOKE_INTERRUPT_CRITICAL,
 			      PROLOG_ADDITION_NONE)
 	EXCEPTION_COMMON_CRIT(0x100)
-	bl	.save_nvgprs
+	bl	save_nvgprs
 	bl	special_reg_save
 	CHECK_NAPPING();
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.unknown_exception
+	bl	unknown_exception
 	b	ret_from_crit_except
 
 /* Machine Check Interrupt */
@@ -562,11 +562,11 @@ interrupt_end_book3e:
 	MC_EXCEPTION_PROLOG(0x000, BOOKE_INTERRUPT_MACHINE_CHECK,
 			    PROLOG_ADDITION_NONE)
 	EXCEPTION_COMMON_MC(0x000)
-	bl	.save_nvgprs
+	bl	save_nvgprs
 	bl	special_reg_save
 	CHECK_NAPPING();
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.machine_check_exception
+	bl	machine_check_exception
 	b	ret_from_mc_except
 
 /* Data Storage Interrupt */
@@ -591,7 +591,7 @@ interrupt_end_book3e:
 
 /* External Input Interrupt */
 	MASKABLE_EXCEPTION(0x500, BOOKE_INTERRUPT_EXTERNAL,
-			   external_input, .do_IRQ, ACK_NONE)
+			   external_input, do_IRQ, ACK_NONE)
 
 /* Alignment */
 	START_EXCEPTION(alignment);
@@ -612,9 +612,9 @@ interrupt_end_book3e:
 	std	r14,_DSISR(r1)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	ld	r14,PACA_EXGEN+EX_R14(r13)
-	bl	.save_nvgprs
-	bl	.program_check_exception
-	b	.ret_from_except
+	bl	save_nvgprs
+	bl	program_check_exception
+	b	ret_from_except
 
 /* Floating Point Unavailable Interrupt */
 	START_EXCEPTION(fp_unavailable);
@@ -625,13 +625,13 @@ interrupt_end_book3e:
 	ld	r12,_MSR(r1)
 	andi.	r0,r12,MSR_PR;
 	beq-	1f
-	bl	.load_up_fpu
+	bl	load_up_fpu
 	b	fast_exception_return
 1:	INTS_DISABLE
-	bl	.save_nvgprs
+	bl	save_nvgprs
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.kernel_fp_unavailable_exception
-	b	.ret_from_except
+	bl	kernel_fp_unavailable_exception
+	b	ret_from_except
 
 /* Altivec Unavailable Interrupt */
 	START_EXCEPTION(altivec_unavailable);
@@ -644,16 +644,16 @@ BEGIN_FTR_SECTION
 	ld	r12,_MSR(r1)
 	andi.	r0,r12,MSR_PR;
 	beq-	1f
-	bl	.load_up_altivec
+	bl	load_up_altivec
 	b	fast_exception_return
 1:
 END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 #endif
 	INTS_DISABLE
-	bl	.save_nvgprs
+	bl	save_nvgprs
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.altivec_unavailable_exception
-	b	.ret_from_except
+	bl	altivec_unavailable_exception
+	b	ret_from_except
 
 /* AltiVec Assist */
 	START_EXCEPTION(altivec_assist);
@@ -662,39 +662,39 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 				PROLOG_ADDITION_NONE)
 	EXCEPTION_COMMON(0x220)
 	INTS_DISABLE
-	bl	.save_nvgprs
+	bl	save_nvgprs
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 #ifdef CONFIG_ALTIVEC
 BEGIN_FTR_SECTION
-	bl	.altivec_assist_exception
+	bl	altivec_assist_exception
 END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 #else
-	bl	.unknown_exception
+	bl	unknown_exception
 #endif
-	b	.ret_from_except
+	b	ret_from_except
 
 
 /* Decrementer Interrupt */
 	MASKABLE_EXCEPTION(0x900, BOOKE_INTERRUPT_DECREMENTER,
-			   decrementer, .timer_interrupt, ACK_DEC)
+			   decrementer, timer_interrupt, ACK_DEC)
 
 /* Fixed Interval Timer Interrupt */
 	MASKABLE_EXCEPTION(0x980, BOOKE_INTERRUPT_FIT,
-			   fixed_interval, .unknown_exception, ACK_FIT)
+			   fixed_interval, unknown_exception, ACK_FIT)
 
 /* Watchdog Timer Interrupt */
 	START_EXCEPTION(watchdog);
 	CRIT_EXCEPTION_PROLOG(0x9f0, BOOKE_INTERRUPT_WATCHDOG,
 			      PROLOG_ADDITION_NONE)
 	EXCEPTION_COMMON_CRIT(0x9f0)
-	bl	.save_nvgprs
+	bl	save_nvgprs
 	bl	special_reg_save
 	CHECK_NAPPING();
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 #ifdef CONFIG_BOOKE_WDT
-	bl	.WatchdogException
+	bl	WatchdogException
 #else
-	bl	.unknown_exception
+	bl	unknown_exception
 #endif
 	b	ret_from_crit_except
 
@@ -712,10 +712,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 				PROLOG_ADDITION_NONE)
 	EXCEPTION_COMMON(0xf20)
 	INTS_DISABLE
-	bl	.save_nvgprs
+	bl	save_nvgprs
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.unknown_exception
-	b	.ret_from_except
+	bl	unknown_exception
+	b	ret_from_except
 
 /* Debug exception as a critical interrupt*/
 	START_EXCEPTION(debug_crit);
@@ -774,9 +774,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 	mr	r4,r14
 	ld	r14,PACA_EXCRIT+EX_R14(r13)
 	ld	r15,PACA_EXCRIT+EX_R15(r13)
-	bl	.save_nvgprs
-	bl	.DebugException
-	b	.ret_from_except
+	bl	save_nvgprs
+	bl	DebugException
+	b	ret_from_except
 
 kernel_dbg_exc:
 	b	.	/* NYI */
@@ -839,9 +839,9 @@ kernel_dbg_exc:
 	mr	r4,r14
 	ld	r14,PACA_EXDBG+EX_R14(r13)
 	ld	r15,PACA_EXDBG+EX_R15(r13)
-	bl	.save_nvgprs
-	bl	.DebugException
-	b	.ret_from_except
+	bl	save_nvgprs
+	bl	DebugException
+	b	ret_from_except
 
 	START_EXCEPTION(perfmon);
 	NORMAL_EXCEPTION_PROLOG(0x260, BOOKE_INTERRUPT_PERFORMANCE_MONITOR,
@@ -850,23 +850,23 @@ kernel_dbg_exc:
 	INTS_DISABLE
 	CHECK_NAPPING()
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.performance_monitor_exception
-	b	.ret_from_except_lite
+	bl	performance_monitor_exception
+	b	ret_from_except_lite
 
 /* Doorbell interrupt */
 	MASKABLE_EXCEPTION(0x280, BOOKE_INTERRUPT_DOORBELL,
-			   doorbell, .doorbell_exception, ACK_NONE)
+			   doorbell, doorbell_exception, ACK_NONE)
 
 /* Doorbell critical Interrupt */
 	START_EXCEPTION(doorbell_crit);
 	CRIT_EXCEPTION_PROLOG(0x2a0, BOOKE_INTERRUPT_DOORBELL_CRITICAL,
 			      PROLOG_ADDITION_NONE)
 	EXCEPTION_COMMON_CRIT(0x2a0)
-	bl	.save_nvgprs
+	bl	save_nvgprs
 	bl	special_reg_save
 	CHECK_NAPPING();
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.unknown_exception
+	bl	unknown_exception
 	b	ret_from_crit_except
 
 /*
@@ -878,21 +878,21 @@ kernel_dbg_exc:
 			        PROLOG_ADDITION_NONE)
 	EXCEPTION_COMMON(0x2c0)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.save_nvgprs
+	bl	save_nvgprs
 	INTS_RESTORE_HARD
-	bl	.unknown_exception
-	b	.ret_from_except
+	bl	unknown_exception
+	b	ret_from_except
 
 /* Guest Doorbell critical Interrupt */
 	START_EXCEPTION(guest_doorbell_crit);
 	CRIT_EXCEPTION_PROLOG(0x2e0, BOOKE_INTERRUPT_GUEST_DBELL_CRIT,
 			      PROLOG_ADDITION_NONE)
 	EXCEPTION_COMMON_CRIT(0x2e0)
-	bl	.save_nvgprs
+	bl	save_nvgprs
 	bl	special_reg_save
 	CHECK_NAPPING();
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.unknown_exception
+	bl	unknown_exception
 	b	ret_from_crit_except
 
 /* Hypervisor call */
@@ -901,10 +901,10 @@ kernel_dbg_exc:
 			        PROLOG_ADDITION_NONE)
 	EXCEPTION_COMMON(0x310)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.save_nvgprs
+	bl	save_nvgprs
 	INTS_RESTORE_HARD
-	bl	.unknown_exception
-	b	.ret_from_except
+	bl	unknown_exception
+	b	ret_from_except
 
 /* Embedded Hypervisor priviledged  */
 	START_EXCEPTION(ehpriv);
@@ -912,10 +912,10 @@ kernel_dbg_exc:
 			        PROLOG_ADDITION_NONE)
 	EXCEPTION_COMMON(0x320)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.save_nvgprs
+	bl	save_nvgprs
 	INTS_RESTORE_HARD
-	bl	.unknown_exception
-	b	.ret_from_except
+	bl	unknown_exception
+	b	ret_from_except
 
 /* LRAT Error interrupt */
 	START_EXCEPTION(lrat_error);
@@ -1014,16 +1014,16 @@ storage_fault_common:
 	mr	r5,r15
 	ld	r14,PACA_EXGEN+EX_R14(r13)
 	ld	r15,PACA_EXGEN+EX_R15(r13)
-	bl	.do_page_fault
+	bl	do_page_fault
 	cmpdi	r3,0
 	bne-	1f
-	b	.ret_from_except_lite
-1:	bl	.save_nvgprs
+	b	ret_from_except_lite
+1:	bl	save_nvgprs
 	mr	r5,r3
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	ld	r4,_DAR(r1)
-	bl	.bad_page_fault
-	b	.ret_from_except
+	bl	bad_page_fault
+	b	ret_from_except
 
 /*
  * Alignment exception doesn't fit entirely in the 0x100 bytes so it
@@ -1035,10 +1035,10 @@ alignment_more:
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	ld	r14,PACA_EXGEN+EX_R14(r13)
 	ld	r15,PACA_EXGEN+EX_R15(r13)
-	bl	.save_nvgprs
+	bl	save_nvgprs
 	INTS_RESTORE_HARD
-	bl	.alignment_exception
-	b	.ret_from_except
+	bl	alignment_exception
+	b	ret_from_except
 
 /*
  * We branch here from entry_64.S for the last stage of the exception
@@ -1172,7 +1172,7 @@ bad_stack_book3e:
 	std	r12,0(r11)
 	ld	r2,PACATOC(r13)
 1:	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.kernel_bad_stack
+	bl	kernel_bad_stack
 	b	1b
 
 /*
@@ -1521,13 +1521,13 @@ _GLOBAL(start_initialization_book3e)
 	 * and always use AS 0, so we just set it up to match our link
 	 * address and never use 0 based addresses.
 	 */
-	bl	.initial_tlb_book3e
+	bl	initial_tlb_book3e
 
 	/* Init global core bits */
-	bl	.init_core_book3e
+	bl	init_core_book3e
 
 	/* Init per-thread bits */
-	bl	.init_thread_book3e
+	bl	init_thread_book3e
 
 	/* Return to common init code */
 	tovirt(r28,r28)
@@ -1548,7 +1548,7 @@ _GLOBAL(start_initialization_book3e)
  */
 _GLOBAL(book3e_secondary_core_init_tlb_set)
 	li	r4,1
-	b	.generic_secondary_smp_init
+	b	generic_secondary_smp_init
 
 _GLOBAL(book3e_secondary_core_init)
 	mflr	r28
@@ -1558,18 +1558,18 @@ _GLOBAL(book3e_secondary_core_init)
 	bne	2f
 
 	/* Setup TLB for this core */
-	bl	.initial_tlb_book3e
+	bl	initial_tlb_book3e
 
 	/* We can return from the above running at a different
 	 * address, so recalculate r2 (TOC)
 	 */
-	bl	.relative_toc
+	bl	relative_toc
 
 	/* Init global core bits */
-2:	bl	.init_core_book3e
+2:	bl	init_core_book3e
 
 	/* Init per-thread bits */
-3:	bl	.init_thread_book3e
+3:	bl	init_thread_book3e
 
 	/* Return to common init code at proper virtual address.
 	 *
@@ -1596,14 +1596,14 @@ _GLOBAL(book3e_secondary_thread_init)
 	mflr	r28
 	b	3b
 
-_STATIC(init_core_book3e)
+init_core_book3e:
 	/* Establish the interrupt vector base */
 	LOAD_REG_IMMEDIATE(r3, interrupt_base_book3e)
 	mtspr	SPRN_IVPR,r3
 	sync
 	blr
 
-_STATIC(init_thread_book3e)
+init_thread_book3e:
 	lis	r3,(SPRN_EPCR_ICM | SPRN_EPCR_GICM)@h
 	mtspr	SPRN_EPCR,r3
 

arch/powerpc/kernel/exceptions-64s.S

@@ -132,12 +132,12 @@ BEGIN_FTR_SECTION
 #endif
 
 	beq	cr1,2f
-	b	.power7_wakeup_noloss
-2:	b	.power7_wakeup_loss
+	b	power7_wakeup_noloss
+2:	b	power7_wakeup_loss
 
 	/* Fast Sleep wakeup on PowerNV */
 8:	GET_PACA(r13)
-	b 	.power7_wakeup_tb_loss
+	b 	power7_wakeup_tb_loss
 
 9:
 END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
@@ -211,16 +211,16 @@ data_access_slb_pSeries:
 #endif /* __DISABLED__ */
 	mfspr	r12,SPRN_SRR1
 #ifndef CONFIG_RELOCATABLE
-	b	.slb_miss_realmode
+	b	slb_miss_realmode
 #else
 	/*
-	 * We can't just use a direct branch to .slb_miss_realmode
+	 * We can't just use a direct branch to slb_miss_realmode
 	 * because the distance from here to there depends on where
 	 * the kernel ends up being put.
 	 */
 	mfctr	r11
 	ld	r10,PACAKBASE(r13)
-	LOAD_HANDLER(r10, .slb_miss_realmode)
+	LOAD_HANDLER(r10, slb_miss_realmode)
 	mtctr	r10
 	bctr
 #endif
@@ -243,11 +243,11 @@ instruction_access_slb_pSeries:
 #endif /* __DISABLED__ */
 	mfspr	r12,SPRN_SRR1
 #ifndef CONFIG_RELOCATABLE
-	b	.slb_miss_realmode
+	b	slb_miss_realmode
 #else
 	mfctr	r11
 	ld	r10,PACAKBASE(r13)
-	LOAD_HANDLER(r10, .slb_miss_realmode)
+	LOAD_HANDLER(r10, slb_miss_realmode)
 	mtctr	r10
 	bctr
 #endif
@@ -524,7 +524,7 @@ do_stab_bolted_pSeries:
 	std	r12,PACA_EXSLB+EX_R12(r13)
 	GET_SCRATCH0(r10)
 	std	r10,PACA_EXSLB+EX_R13(r13)
-	EXCEPTION_PROLOG_PSERIES_1(.do_stab_bolted, EXC_STD)
+	EXCEPTION_PROLOG_PSERIES_1(do_stab_bolted, EXC_STD)
 
 	KVM_HANDLER_SKIP(PACA_EXGEN, EXC_STD, 0x300)
 	KVM_HANDLER_SKIP(PACA_EXSLB, EXC_STD, 0x380)
@@ -769,38 +769,38 @@ kvmppc_skip_Hinterrupt:
 
 /*** Common interrupt handlers ***/
 
-	STD_EXCEPTION_COMMON(0x100, system_reset, .system_reset_exception)
+	STD_EXCEPTION_COMMON(0x100, system_reset, system_reset_exception)
 
 	STD_EXCEPTION_COMMON_ASYNC(0x500, hardware_interrupt, do_IRQ)
-	STD_EXCEPTION_COMMON_ASYNC(0x900, decrementer, .timer_interrupt)
-	STD_EXCEPTION_COMMON(0x980, hdecrementer, .hdec_interrupt)
+	STD_EXCEPTION_COMMON_ASYNC(0x900, decrementer, timer_interrupt)
+	STD_EXCEPTION_COMMON(0x980, hdecrementer, hdec_interrupt)
 #ifdef CONFIG_PPC_DOORBELL
-	STD_EXCEPTION_COMMON_ASYNC(0xa00, doorbell_super, .doorbell_exception)
+	STD_EXCEPTION_COMMON_ASYNC(0xa00, doorbell_super, doorbell_exception)
 #else
-	STD_EXCEPTION_COMMON_ASYNC(0xa00, doorbell_super, .unknown_exception)
+	STD_EXCEPTION_COMMON_ASYNC(0xa00, doorbell_super, unknown_exception)
 #endif
-	STD_EXCEPTION_COMMON(0xb00, trap_0b, .unknown_exception)
-	STD_EXCEPTION_COMMON(0xd00, single_step, .single_step_exception)
-	STD_EXCEPTION_COMMON(0xe00, trap_0e, .unknown_exception)
-	STD_EXCEPTION_COMMON(0xe40, emulation_assist, .emulation_assist_interrupt)
-	STD_EXCEPTION_COMMON(0xe60, hmi_exception, .unknown_exception)
+	STD_EXCEPTION_COMMON(0xb00, trap_0b, unknown_exception)
+	STD_EXCEPTION_COMMON(0xd00, single_step, single_step_exception)
+	STD_EXCEPTION_COMMON(0xe00, trap_0e, unknown_exception)
+	STD_EXCEPTION_COMMON(0xe40, emulation_assist, emulation_assist_interrupt)
+	STD_EXCEPTION_COMMON(0xe60, hmi_exception, unknown_exception)
 #ifdef CONFIG_PPC_DOORBELL
-	STD_EXCEPTION_COMMON_ASYNC(0xe80, h_doorbell, .doorbell_exception)
+	STD_EXCEPTION_COMMON_ASYNC(0xe80, h_doorbell, doorbell_exception)
 #else
-	STD_EXCEPTION_COMMON_ASYNC(0xe80, h_doorbell, .unknown_exception)
+	STD_EXCEPTION_COMMON_ASYNC(0xe80, h_doorbell, unknown_exception)
 #endif
-	STD_EXCEPTION_COMMON_ASYNC(0xf00, performance_monitor, .performance_monitor_exception)
-	STD_EXCEPTION_COMMON(0x1300, instruction_breakpoint, .instruction_breakpoint_exception)
-	STD_EXCEPTION_COMMON(0x1502, denorm, .unknown_exception)
+	STD_EXCEPTION_COMMON_ASYNC(0xf00, performance_monitor, performance_monitor_exception)
+	STD_EXCEPTION_COMMON(0x1300, instruction_breakpoint, instruction_breakpoint_exception)
+	STD_EXCEPTION_COMMON(0x1502, denorm, unknown_exception)
 #ifdef CONFIG_ALTIVEC
-	STD_EXCEPTION_COMMON(0x1700, altivec_assist, .altivec_assist_exception)
+	STD_EXCEPTION_COMMON(0x1700, altivec_assist, altivec_assist_exception)
 #else
-	STD_EXCEPTION_COMMON(0x1700, altivec_assist, .unknown_exception)
+	STD_EXCEPTION_COMMON(0x1700, altivec_assist, unknown_exception)
 #endif
 #ifdef CONFIG_CBE_RAS
-	STD_EXCEPTION_COMMON(0x1200, cbe_system_error, .cbe_system_error_exception)
-	STD_EXCEPTION_COMMON(0x1600, cbe_maintenance, .cbe_maintenance_exception)
-	STD_EXCEPTION_COMMON(0x1800, cbe_thermal, .cbe_thermal_exception)
+	STD_EXCEPTION_COMMON(0x1200, cbe_system_error, cbe_system_error_exception)
+	STD_EXCEPTION_COMMON(0x1600, cbe_maintenance, cbe_maintenance_exception)
+	STD_EXCEPTION_COMMON(0x1800, cbe_thermal, cbe_thermal_exception)
 #endif /* CONFIG_CBE_RAS */
 
 	/*
@@ -829,16 +829,16 @@ data_access_slb_relon_pSeries:
 	mfspr	r3,SPRN_DAR
 	mfspr	r12,SPRN_SRR1
 #ifndef CONFIG_RELOCATABLE
-	b	.slb_miss_realmode
+	b	slb_miss_realmode
 #else
 	/*
-	 * We can't just use a direct branch to .slb_miss_realmode
+	 * We can't just use a direct branch to slb_miss_realmode
 	 * because the distance from here to there depends on where
 	 * the kernel ends up being put.
 	 */
 	mfctr	r11
 	ld	r10,PACAKBASE(r13)
-	LOAD_HANDLER(r10, .slb_miss_realmode)
+	LOAD_HANDLER(r10, slb_miss_realmode)
 	mtctr	r10
 	bctr
 #endif
@@ -854,11 +854,11 @@ instruction_access_slb_relon_pSeries:
 	mfspr	r3,SPRN_SRR0		/* SRR0 is faulting address */
 	mfspr	r12,SPRN_SRR1
 #ifndef CONFIG_RELOCATABLE
-	b	.slb_miss_realmode
+	b	slb_miss_realmode
 #else
 	mfctr	r11
 	ld	r10,PACAKBASE(r13)
-	LOAD_HANDLER(r10, .slb_miss_realmode)
+	LOAD_HANDLER(r10, slb_miss_realmode)
 	mtctr	r10
 	bctr
 #endif
@@ -966,7 +966,7 @@ system_call_entry:
 	b	system_call_common
 
 ppc64_runlatch_on_trampoline:
-	b	.__ppc64_runlatch_on
+	b	__ppc64_runlatch_on
 
 /*
  * Here we have detected that the kernel stack pointer is bad.
@@ -1025,7 +1025,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
 	std	r12,RESULT(r1)
 	std	r11,STACK_FRAME_OVERHEAD-16(r1)
 1:	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.kernel_bad_stack
+	bl	kernel_bad_stack
 	b	1b
 
 /*
@@ -1046,7 +1046,7 @@ data_access_common:
 	ld	r3,PACA_EXGEN+EX_DAR(r13)
 	lwz	r4,PACA_EXGEN+EX_DSISR(r13)
 	li	r5,0x300
-	b	.do_hash_page		/* Try to handle as hpte fault */
+	b	do_hash_page		/* Try to handle as hpte fault */
 
 	.align  7
 	.globl  h_data_storage_common
@@ -1056,11 +1056,11 @@ h_data_storage_common:
 	mfspr   r10,SPRN_HDSISR
 	stw     r10,PACA_EXGEN+EX_DSISR(r13)
 	EXCEPTION_PROLOG_COMMON(0xe00, PACA_EXGEN)
-	bl      .save_nvgprs
+	bl      save_nvgprs
 	DISABLE_INTS
 	addi    r3,r1,STACK_FRAME_OVERHEAD
-	bl      .unknown_exception
-	b       .ret_from_except
+	bl      unknown_exception
+	b       ret_from_except
 
 	.align	7
 	.globl instruction_access_common
@@ -1071,9 +1071,9 @@ instruction_access_common:
 	ld	r3,_NIP(r1)
 	andis.	r4,r12,0x5820
 	li	r5,0x400
-	b	.do_hash_page		/* Try to handle as hpte fault */
+	b	do_hash_page		/* Try to handle as hpte fault */
 
-	STD_EXCEPTION_COMMON(0xe20, h_instr_storage, .unknown_exception)
+	STD_EXCEPTION_COMMON(0xe20, h_instr_storage, unknown_exception)
 
 /*
  * Here is the common SLB miss user that is used when going to virtual
@@ -1088,7 +1088,7 @@ slb_miss_user_common:
 	stw	r9,PACA_EXGEN+EX_CCR(r13)
 	std	r10,PACA_EXGEN+EX_LR(r13)
 	std	r11,PACA_EXGEN+EX_SRR0(r13)
-	bl	.slb_allocate_user
+	bl	slb_allocate_user
 
 	ld	r10,PACA_EXGEN+EX_LR(r13)
 	ld	r3,PACA_EXGEN+EX_R3(r13)
@@ -1131,9 +1131,9 @@ slb_miss_fault:
 unrecov_user_slb:
 	EXCEPTION_PROLOG_COMMON(0x4200, PACA_EXGEN)
 	DISABLE_INTS
-	bl	.save_nvgprs
+	bl	save_nvgprs
 1:	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.unrecoverable_exception
+	bl	unrecoverable_exception
 	b	1b
 
 #endif /* __DISABLED__ */
@@ -1158,10 +1158,10 @@ machine_check_common:
 	lwz	r4,PACA_EXGEN+EX_DSISR(r13)
 	std	r3,_DAR(r1)
 	std	r4,_DSISR(r1)
-	bl	.save_nvgprs
+	bl	save_nvgprs
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.machine_check_exception
-	b	.ret_from_except
+	bl	machine_check_exception
+	b	ret_from_except
 
 	.align	7
 	.globl alignment_common
@@ -1175,31 +1175,31 @@ alignment_common:
 	lwz	r4,PACA_EXGEN+EX_DSISR(r13)
 	std	r3,_DAR(r1)
 	std	r4,_DSISR(r1)
-	bl	.save_nvgprs
+	bl	save_nvgprs
 	DISABLE_INTS
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.alignment_exception
-	b	.ret_from_except
+	bl	alignment_exception
+	b	ret_from_except
 
 	.align	7
 	.globl program_check_common
 program_check_common:
 	EXCEPTION_PROLOG_COMMON(0x700, PACA_EXGEN)
-	bl	.save_nvgprs
+	bl	save_nvgprs
 	DISABLE_INTS
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.program_check_exception
-	b	.ret_from_except
+	bl	program_check_exception
+	b	ret_from_except
 
 	.align	7
 	.globl fp_unavailable_common
 fp_unavailable_common:
 	EXCEPTION_PROLOG_COMMON(0x800, PACA_EXGEN)
 	bne	1f			/* if from user, just load it up */
-	bl	.save_nvgprs
+	bl	save_nvgprs
 	DISABLE_INTS
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.kernel_fp_unavailable_exception
+	bl	kernel_fp_unavailable_exception
 	BUG_OPCODE
 1:
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
@@ -1211,15 +1211,15 @@ BEGIN_FTR_SECTION
 	bne-	2f
 END_FTR_SECTION_IFSET(CPU_FTR_TM)
 #endif
-	bl	.load_up_fpu
+	bl	load_up_fpu
 	b	fast_exception_return
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 2:	/* User process was in a transaction */
-	bl	.save_nvgprs
+	bl	save_nvgprs
 	DISABLE_INTS
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.fp_unavailable_tm
-	b	.ret_from_except
+	bl	fp_unavailable_tm
+	b	ret_from_except
 #endif
 	.align	7
 	.globl altivec_unavailable_common
@@ -1237,24 +1237,24 @@ BEGIN_FTR_SECTION
 	bne-	2f
   END_FTR_SECTION_NESTED(CPU_FTR_TM, CPU_FTR_TM, 69)
 #endif
-	bl	.load_up_altivec
+	bl	load_up_altivec
 	b	fast_exception_return
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 2:	/* User process was in a transaction */
-	bl	.save_nvgprs
+	bl	save_nvgprs
 	DISABLE_INTS
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.altivec_unavailable_tm
-	b	.ret_from_except
+	bl	altivec_unavailable_tm
+	b	ret_from_except
 #endif
 1:
 END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 #endif
-	bl	.save_nvgprs
+	bl	save_nvgprs
 	DISABLE_INTS
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.altivec_unavailable_exception
-	b	.ret_from_except
+	bl	altivec_unavailable_exception
+	b	ret_from_except
 
 	.align	7
 	.globl vsx_unavailable_common
@@ -1272,26 +1272,26 @@ BEGIN_FTR_SECTION
 	bne-	2f
   END_FTR_SECTION_NESTED(CPU_FTR_TM, CPU_FTR_TM, 69)
 #endif
-	b	.load_up_vsx
+	b	load_up_vsx
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 2:	/* User process was in a transaction */
-	bl	.save_nvgprs
+	bl	save_nvgprs
 	DISABLE_INTS
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.vsx_unavailable_tm
-	b	.ret_from_except
+	bl	vsx_unavailable_tm
+	b	ret_from_except
 #endif
 1:
 END_FTR_SECTION_IFSET(CPU_FTR_VSX)
 #endif
-	bl	.save_nvgprs
+	bl	save_nvgprs
 	DISABLE_INTS
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.vsx_unavailable_exception
-	b	.ret_from_except
+	bl	vsx_unavailable_exception
+	b	ret_from_except
 
-	STD_EXCEPTION_COMMON(0xf60, facility_unavailable, .facility_unavailable_exception)
-	STD_EXCEPTION_COMMON(0xf80, hv_facility_unavailable, .facility_unavailable_exception)
+	STD_EXCEPTION_COMMON(0xf60, facility_unavailable, facility_unavailable_exception)
+	STD_EXCEPTION_COMMON(0xf80, hv_facility_unavailable, facility_unavailable_exception)
 
 	.align	7
 	.globl	__end_handlers
@@ -1386,9 +1386,9 @@ _GLOBAL(opal_mc_secondary_handler)
 machine_check_handle_early:
 	std	r0,GPR0(r1)	/* Save r0 */
 	EXCEPTION_PROLOG_COMMON_3(0x200)
-	bl	.save_nvgprs
+	bl	save_nvgprs
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.machine_check_early
+	bl	machine_check_early
 	ld	r12,_MSR(r1)
 #ifdef	CONFIG_PPC_P7_NAP
 	/*
@@ -1408,11 +1408,11 @@ machine_check_handle_early:
 	/* Supervisor state loss */
 	li	r0,1
 	stb	r0,PACA_NAPSTATELOST(r13)
-3:	bl	.machine_check_queue_event
+3:	bl	machine_check_queue_event
 	MACHINE_CHECK_HANDLER_WINDUP
 	GET_PACA(r13)
 	ld	r1,PACAR1(r13)
-	b	.power7_enter_nap_mode
+	b	power7_enter_nap_mode
 4:
 #endif
 	/*
@@ -1444,7 +1444,7 @@ machine_check_handle_early:
 	andi.	r11,r12,MSR_RI
 	bne	2f
 1:	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.unrecoverable_exception
+	bl	unrecoverable_exception
 	b	1b
 2:
 	/*
@@ -1452,7 +1452,7 @@ machine_check_handle_early:
 	 * Queue up the MCE event so that we can log it later, while
 	 * returning from kernel or opal call.
 	 */
-	bl	.machine_check_queue_event
+	bl	machine_check_queue_event
 	MACHINE_CHECK_HANDLER_WINDUP
 	rfid
 9:
@@ -1468,7 +1468,7 @@ machine_check_handle_early:
  * r3 is saved in paca->slb_r3
  * We assume we aren't going to take any exceptions during this procedure.
  */
-_GLOBAL(slb_miss_realmode)
+slb_miss_realmode:
 	mflr	r10
 #ifdef CONFIG_RELOCATABLE
 	mtctr	r11
@@ -1477,7 +1477,7 @@ _GLOBAL(slb_miss_realmode)
 	stw	r9,PACA_EXSLB+EX_CCR(r13)	/* save CR in exc. frame */
 	std	r10,PACA_EXSLB+EX_LR(r13)	/* save LR */
 
-	bl	.slb_allocate_realmode
+	bl	slb_allocate_realmode
 
 	/* All done -- return from exception. */
 
@@ -1517,9 +1517,9 @@ _GLOBAL(slb_miss_realmode)
 unrecov_slb:
 	EXCEPTION_PROLOG_COMMON(0x4100, PACA_EXSLB)
 	DISABLE_INTS
-	bl	.save_nvgprs
+	bl	save_nvgprs
 1:	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.unrecoverable_exception
+	bl	unrecoverable_exception
 	b	1b
 
 
@@ -1536,7 +1536,7 @@ power4_fixup_nap:
  * Hash table stuff
  */
 	.align	7
-_STATIC(do_hash_page)
+do_hash_page:
 	std	r3,_DAR(r1)
 	std	r4,_DSISR(r1)
 
@@ -1573,7 +1573,7 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_SLB)
 	 *
 	 * at return r3 = 0 for success, 1 for page fault, negative for error
 	 */
-	bl	.hash_page		/* build HPTE if possible */
+	bl	hash_page		/* build HPTE if possible */
 	cmpdi	r3,0			/* see if hash_page succeeded */
 
 	/* Success */
@@ -1587,35 +1587,35 @@ handle_page_fault:
 11:	ld	r4,_DAR(r1)
 	ld	r5,_DSISR(r1)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.do_page_fault
+	bl	do_page_fault
 	cmpdi	r3,0
 	beq+	12f
-	bl	.save_nvgprs
+	bl	save_nvgprs
 	mr	r5,r3
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	lwz	r4,_DAR(r1)
-	bl	.bad_page_fault
-	b	.ret_from_except
+	bl	bad_page_fault
+	b	ret_from_except
 
 /* We have a data breakpoint exception - handle it */
 handle_dabr_fault:
-	bl	.save_nvgprs
+	bl	save_nvgprs
 	ld      r4,_DAR(r1)
 	ld      r5,_DSISR(r1)
 	addi    r3,r1,STACK_FRAME_OVERHEAD
-	bl      .do_break
-12:	b       .ret_from_except_lite
+	bl      do_break
+12:	b       ret_from_except_lite
 
 
 /* We have a page fault that hash_page could handle but HV refused
  * the PTE insertion
  */
-13:	bl	.save_nvgprs
+13:	bl	save_nvgprs
 	mr	r5,r3
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	ld	r4,_DAR(r1)
-	bl	.low_hash_fault
-	b	.ret_from_except
+	bl	low_hash_fault
+	b	ret_from_except
 
 /*
  * We come here as a result of a DSI at a point where we don't want
@@ -1624,16 +1624,16 @@ handle_dabr_fault:
  * were soft-disabled.  We want to invoke the exception handler for
  * the access, or panic if there isn't a handler.
  */
-77:	bl	.save_nvgprs
+77:	bl	save_nvgprs
 	mr	r4,r3
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	li	r5,SIGSEGV
-	bl	.bad_page_fault
-	b	.ret_from_except
+	bl	bad_page_fault
+	b	ret_from_except
 
 	/* here we have a segment miss */
 do_ste_alloc:
-	bl	.ste_allocate		/* try to insert stab entry */
+	bl	ste_allocate		/* try to insert stab entry */
 	cmpdi	r3,0
 	bne-	handle_page_fault
 	b	fast_exception_return
@@ -1646,7 +1646,7 @@ do_ste_alloc:
  * We assume (DAR >> 60) == 0xc.
  */
 	.align	7
-_GLOBAL(do_stab_bolted)
+do_stab_bolted:
 	stw	r9,PACA_EXSLB+EX_CCR(r13)	/* save CR in exc. frame */
 	std	r11,PACA_EXSLB+EX_SRR0(r13)	/* save SRR0 in exc. frame */
 	mfspr	r11,SPRN_DAR			/* ea */

arch/powerpc/kernel/ftrace.c

@@ -105,11 +105,9 @@ __ftrace_make_nop(struct module *mod,
 		  struct dyn_ftrace *rec, unsigned long addr)
 {
 	unsigned int op;
-	unsigned int jmp[5];
 	unsigned long ptr;
 	unsigned long ip = rec->ip;
-	unsigned long tramp;
-	int offset;
+	void *tramp;
 
 	/* read where this goes */
 	if (probe_kernel_read(&op, (void *)ip, sizeof(int)))
@@ -122,96 +120,41 @@ __ftrace_make_nop(struct module *mod,
 	}
 
 	/* lets find where the pointer goes */
-	tramp = find_bl_target(ip, op);
-
-	/*
-	 * On PPC64 the trampoline looks like:
-	 * 0x3d, 0x82, 0x00, 0x00,    addis   r12,r2, <high>
-	 * 0x39, 0x8c, 0x00, 0x00,    addi    r12,r12, <low>
-	 *   Where the bytes 2,3,6 and 7 make up the 32bit offset
-	 *   to the TOC that holds the pointer.
-	 *   to jump to.
-	 * 0xf8, 0x41, 0x00, 0x28,    std     r2,40(r1)
-	 * 0xe9, 0x6c, 0x00, 0x20,    ld      r11,32(r12)
-	 *   The actually address is 32 bytes from the offset
-	 *   into the TOC.
-	 * 0xe8, 0x4c, 0x00, 0x28,    ld      r2,40(r12)
-	 */
-
-	pr_devel("ip:%lx jumps to %lx r2: %lx", ip, tramp, mod->arch.toc);
-
-	/* Find where the trampoline jumps to */
-	if (probe_kernel_read(jmp, (void *)tramp, sizeof(jmp))) {
-		printk(KERN_ERR "Failed to read %lx\n", tramp);
-		return -EFAULT;
-	}
+	tramp = (void *)find_bl_target(ip, op);
 
-	pr_devel(" %08x %08x", jmp[0], jmp[1]);
+	pr_devel("ip:%lx jumps to %p", ip, tramp);
 
-	/* verify that this is what we expect it to be */
-	if (((jmp[0] & 0xffff0000) != 0x3d820000) ||
-	    ((jmp[1] & 0xffff0000) != 0x398c0000) ||
-	    (jmp[2] != 0xf8410028) ||
-	    (jmp[3] != 0xe96c0020) ||
-	    (jmp[4] != 0xe84c0028)) {
+	if (!is_module_trampoline(tramp)) {
 		printk(KERN_ERR "Not a trampoline\n");
 		return -EINVAL;
 	}
 
-	/* The bottom half is signed extended */
-	offset = ((unsigned)((unsigned short)jmp[0]) << 16) +
-		(int)((short)jmp[1]);
-
-	pr_devel(" %x ", offset);
-
-	/* get the address this jumps too */
-	tramp = mod->arch.toc + offset + 32;
-	pr_devel("toc: %lx", tramp);
-
-	if (probe_kernel_read(jmp, (void *)tramp, 8)) {
-		printk(KERN_ERR "Failed to read %lx\n", tramp);
+	if (module_trampoline_target(mod, tramp, &ptr)) {
+		printk(KERN_ERR "Failed to get trampoline target\n");
 		return -EFAULT;
 	}
 
-	pr_devel(" %08x %08x\n", jmp[0], jmp[1]);
-
-#ifdef __LITTLE_ENDIAN__
-	ptr = ((unsigned long)jmp[1] << 32) + jmp[0];
-#else
-	ptr = ((unsigned long)jmp[0] << 32) + jmp[1];
-#endif
+	pr_devel("trampoline target %lx", ptr);
 
 	/* This should match what was called */
 	if (ptr != ppc_function_entry((void *)addr)) {
-		printk(KERN_ERR "addr does not match %lx\n", ptr);
-		return -EINVAL;
-	}
-
-	/*
-	 * We want to nop the line, but the next line is
-	 *  0xe8, 0x41, 0x00, 0x28   ld r2,40(r1)
-	 * This needs to be turned to a nop too.
-	 */
-	if (probe_kernel_read(&op, (void *)(ip+4), MCOUNT_INSN_SIZE))
-		return -EFAULT;
-
-	if (op != 0xe8410028) {
-		printk(KERN_ERR "Next line is not ld! (%08x)\n", op);
+		printk(KERN_ERR "addr %lx does not match expected %lx\n",
+			ptr, ppc_function_entry((void *)addr));
 		return -EINVAL;
 	}
 
 	/*
-	 * Milton Miller pointed out that we can not blindly do nops.
-	 * If a task was preempted when calling a trace function,
-	 * the nops will remove the way to restore the TOC in r2
-	 * and the r2 TOC will get corrupted.
-	 */
-
-	/*
-	 * Replace:
-	 *   bl <tramp>  <==== will be replaced with "b 1f"
-	 *   ld r2,40(r1)
-	 *  1:
+	 * Our original call site looks like:
+	 *
+	 * bl <tramp>
+	 * ld r2,XX(r1)
+	 *
+	 * Milton Miller pointed out that we can not simply nop the branch.
+	 * If a task was preempted when calling a trace function, the nops
+	 * will remove the way to restore the TOC in r2 and the r2 TOC will
+	 * get corrupted.
+	 *
+	 * Use a b +8 to jump over the load.
 	 */
 	op = 0x48000008;	/* b +8 */
 
@@ -349,19 +292,24 @@ static int
 __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 {
 	unsigned int op[2];
-	unsigned long ip = rec->ip;
+	void *ip = (void *)rec->ip;
 
 	/* read where this goes */
-	if (probe_kernel_read(op, (void *)ip, MCOUNT_INSN_SIZE * 2))
+	if (probe_kernel_read(op, ip, sizeof(op)))
 		return -EFAULT;
 
 	/*
-	 * It should be pointing to two nops or
-	 *  b +8; ld r2,40(r1)
+	 * We expect to see:
+	 *
+	 * b +8
+	 * ld r2,XX(r1)
+	 *
+	 * The load offset is different depending on the ABI. For simplicity
+	 * just mask it out when doing the compare.
 	 */
-	if (((op[0] != 0x48000008) || (op[1] != 0xe8410028)) &&
-	    ((op[0] != PPC_INST_NOP) || (op[1] != PPC_INST_NOP))) {
-		printk(KERN_ERR "Expected NOPs but have %x %x\n", op[0], op[1]);
+	if ((op[0] != 0x48000008) || ((op[1] & 0xffff00000) != 0xe8410000)) {
+		printk(KERN_ERR "Unexpected call sequence: %x %x\n",
+			op[0], op[1]);
 		return -EINVAL;
 	}
 
@@ -371,23 +319,16 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 		return -EINVAL;
 	}
 
-	/* create the branch to the trampoline */
-	op[0] = create_branch((unsigned int *)ip,
-			      rec->arch.mod->arch.tramp, BRANCH_SET_LINK);
-	if (!op[0]) {
-		printk(KERN_ERR "REL24 out of range!\n");
+	/* Ensure branch is within 24 bits */
+	if (create_branch(ip, rec->arch.mod->arch.tramp, BRANCH_SET_LINK)) {
+		printk(KERN_ERR "Branch out of range");
 		return -EINVAL;
 	}
 
-	/* ld r2,40(r1) */
-	op[1] = 0xe8410028;
-
-	pr_devel("write to %lx\n", rec->ip);
-
-	if (probe_kernel_write((void *)ip, op, MCOUNT_INSN_SIZE * 2))
-		return -EPERM;
-
-	flush_icache_range(ip, ip + 8);
+	if (patch_branch(ip, rec->arch.mod->arch.tramp, BRANCH_SET_LINK)) {
+		printk(KERN_ERR "REL24 out of range!\n");
+		return -EINVAL;
+	}
 
 	return 0;
 }

arch/powerpc/kernel/head_64.S

@@ -70,16 +70,15 @@ _GLOBAL(__start)
 	/* NOP this out unconditionally */
 BEGIN_FTR_SECTION
 	FIXUP_ENDIAN
-	b	.__start_initialization_multiplatform
+	b	__start_initialization_multiplatform
 END_FTR_SECTION(0, 1)
 
 	/* Catch branch to 0 in real mode */
 	trap
 
-	/* Secondary processors spin on this value until it becomes nonzero.
-	 * When it does it contains the real address of the descriptor
-	 * of the function that the cpu should jump to to continue
-	 * initialization.
+	/* Secondary processors spin on this value until it becomes non-zero.
+	 * When non-zero, it contains the real address of the function the cpu
+	 * should jump to.
 	 */
 	.balign 8
 	.globl  __secondary_hold_spinloop
@@ -140,16 +139,15 @@ __secondary_hold:
 	tovirt(r26,r26)
 #endif
 	/* All secondary cpus wait here until told to start. */
-100:	ld	r4,__secondary_hold_spinloop-_stext(r26)
-	cmpdi	0,r4,0
+100:	ld	r12,__secondary_hold_spinloop-_stext(r26)
+	cmpdi	0,r12,0
 	beq	100b
 
 #if defined(CONFIG_SMP) || defined(CONFIG_KEXEC)
 #ifdef CONFIG_PPC_BOOK3E
-	tovirt(r4,r4)
+	tovirt(r12,r12)
 #endif
-	ld	r4,0(r4)		/* deref function descriptor */
-	mtctr	r4
+	mtctr	r12
 	mr	r3,r24
 	/*
 	 * it may be the case that other platforms have r4 right to
@@ -186,16 +184,16 @@ _GLOBAL(generic_secondary_thread_init)
 	mr	r24,r3
 
 	/* turn on 64-bit mode */
-	bl	.enable_64b_mode
+	bl	enable_64b_mode
 
 	/* get a valid TOC pointer, wherever we're mapped at */
-	bl	.relative_toc
+	bl	relative_toc
 	tovirt(r2,r2)
 
 #ifdef CONFIG_PPC_BOOK3E
 	/* Book3E initialization */
 	mr	r3,r24
-	bl	.book3e_secondary_thread_init
+	bl	book3e_secondary_thread_init
 #endif
 	b	generic_secondary_common_init
 
@@ -214,17 +212,17 @@ _GLOBAL(generic_secondary_smp_init)
 	mr	r25,r4
 
 	/* turn on 64-bit mode */
-	bl	.enable_64b_mode
+	bl	enable_64b_mode
 
 	/* get a valid TOC pointer, wherever we're mapped at */
-	bl	.relative_toc
+	bl	relative_toc
 	tovirt(r2,r2)
 
 #ifdef CONFIG_PPC_BOOK3E
 	/* Book3E initialization */
 	mr	r3,r24
 	mr	r4,r25
-	bl	.book3e_secondary_core_init
+	bl	book3e_secondary_core_init
 #endif
 
 generic_secondary_common_init:
@@ -236,7 +234,7 @@ generic_secondary_common_init:
 	ld	r13,0(r13)		/* Get base vaddr of paca array	 */
 #ifndef CONFIG_SMP
 	addi	r13,r13,PACA_SIZE	/* know r13 if used accidentally */
-	b	.kexec_wait		/* wait for next kernel if !SMP	 */
+	b	kexec_wait		/* wait for next kernel if !SMP	 */
 #else
 	LOAD_REG_ADDR(r7, nr_cpu_ids)	/* Load nr_cpu_ids address       */
 	lwz	r7,0(r7)		/* also the max paca allocated 	 */
@@ -250,7 +248,7 @@ generic_secondary_common_init:
 	blt	1b
 
 	mr	r3,r24			/* not found, copy phys to r3	 */
-	b	.kexec_wait		/* next kernel might do better	 */
+	b	kexec_wait		/* next kernel might do better	 */
 
 2:	SET_PACA(r13)
 #ifdef CONFIG_PPC_BOOK3E
@@ -264,11 +262,13 @@ generic_secondary_common_init:
 	/* See if we need to call a cpu state restore handler */
 	LOAD_REG_ADDR(r23, cur_cpu_spec)
 	ld	r23,0(r23)
-	ld	r23,CPU_SPEC_RESTORE(r23)
-	cmpdi	0,r23,0
+	ld	r12,CPU_SPEC_RESTORE(r23)
+	cmpdi	0,r12,0
 	beq	3f
-	ld	r23,0(r23)
-	mtctr	r23
+#if !defined(_CALL_ELF) || _CALL_ELF != 2
+	ld	r12,0(r12)
+#endif
+	mtctr	r12
 	bctrl
 
 3:	LOAD_REG_ADDR(r3, spinning_secondaries) /* Decrement spinning_secondaries */
@@ -299,7 +299,7 @@ generic_secondary_common_init:
  * Assumes we're mapped EA == RA if the MMU is on.
  */
 #ifdef CONFIG_PPC_BOOK3S
-_STATIC(__mmu_off)
+__mmu_off:
 	mfmsr	r3
 	andi.	r0,r3,MSR_IR|MSR_DR
 	beqlr
@@ -324,12 +324,12 @@ _STATIC(__mmu_off)
  *                 DT block, r4 is a physical pointer to the kernel itself
  *
  */
-_GLOBAL(__start_initialization_multiplatform)
+__start_initialization_multiplatform:
 	/* Make sure we are running in 64 bits mode */
-	bl	.enable_64b_mode
+	bl	enable_64b_mode
 
 	/* Get TOC pointer (current runtime address) */
-	bl	.relative_toc
+	bl	relative_toc
 
 	/* find out where we are now */
 	bcl	20,31,$+4
@@ -342,7 +342,7 @@ _GLOBAL(__start_initialization_multiplatform)
 	 */
 	cmpldi	cr0,r5,0
 	beq	1f
-	b	.__boot_from_prom		/* yes -> prom */
+	b	__boot_from_prom		/* yes -> prom */
 1:
 	/* Save parameters */
 	mr	r31,r3
@@ -354,8 +354,8 @@ _GLOBAL(__start_initialization_multiplatform)
 #endif
 
 #ifdef CONFIG_PPC_BOOK3E
-	bl	.start_initialization_book3e
-	b	.__after_prom_start
+	bl	start_initialization_book3e
+	b	__after_prom_start
 #else
 	/* Setup some critical 970 SPRs before switching MMU off */
 	mfspr	r0,SPRN_PVR
@@ -368,15 +368,15 @@ _GLOBAL(__start_initialization_multiplatform)
 	beq	1f
 	cmpwi	r0,0x45		/* 970GX */
 	bne	2f
-1:	bl	.__cpu_preinit_ppc970
+1:	bl	__cpu_preinit_ppc970
 2:
 
 	/* Switch off MMU if not already off */
-	bl	.__mmu_off
-	b	.__after_prom_start
+	bl	__mmu_off
+	b	__after_prom_start
 #endif /* CONFIG_PPC_BOOK3E */
 
-_INIT_STATIC(__boot_from_prom)
+__boot_from_prom:
 #ifdef CONFIG_PPC_OF_BOOT_TRAMPOLINE
 	/* Save parameters */
 	mr	r31,r3
@@ -395,7 +395,7 @@ _INIT_STATIC(__boot_from_prom)
 #ifdef CONFIG_RELOCATABLE
 	/* Relocate code for where we are now */
 	mr	r3,r26
-	bl	.relocate
+	bl	relocate
 #endif
 
 	/* Restore parameters */
@@ -407,14 +407,14 @@ _INIT_STATIC(__boot_from_prom)
 
 	/* Do all of the interaction with OF client interface */
 	mr	r8,r26
-	bl	.prom_init
+	bl	prom_init
 #endif /* #CONFIG_PPC_OF_BOOT_TRAMPOLINE */
 
 	/* We never return. We also hit that trap if trying to boot
 	 * from OF while CONFIG_PPC_OF_BOOT_TRAMPOLINE isn't selected */
 	trap
 
-_STATIC(__after_prom_start)
+__after_prom_start:
 #ifdef CONFIG_RELOCATABLE
 	/* process relocations for the final address of the kernel */
 	lis	r25,PAGE_OFFSET@highest	/* compute virtual base of kernel */
@@ -424,7 +424,7 @@ _STATIC(__after_prom_start)
 	bne	1f
 	add	r25,r25,r26
 1:	mr	r3,r25
-	bl	.relocate
+	bl	relocate
 #endif
 
 /*
@@ -464,12 +464,12 @@ _STATIC(__after_prom_start)
 	lis	r5,(copy_to_here - _stext)@ha
 	addi	r5,r5,(copy_to_here - _stext)@l /* # bytes of memory to copy */
 
-	bl	.copy_and_flush		/* copy the first n bytes	 */
+	bl	copy_and_flush		/* copy the first n bytes	 */
 					/* this includes the code being	 */
 					/* executed here.		 */
 	addis	r8,r3,(4f - _stext)@ha	/* Jump to the copy of this code */
-	addi	r8,r8,(4f - _stext)@l	/* that we just made */
-	mtctr	r8
+	addi	r12,r8,(4f - _stext)@l	/* that we just made */
+	mtctr	r12
 	bctr
 
 .balign 8
@@ -478,9 +478,9 @@ p_end:	.llong	_end - _stext
 4:	/* Now copy the rest of the kernel up to _end */
 	addis	r5,r26,(p_end - _stext)@ha
 	ld	r5,(p_end - _stext)@l(r5)	/* get _end */
-5:	bl	.copy_and_flush		/* copy the rest */
+5:	bl	copy_and_flush		/* copy the rest */
 
-9:	b	.start_here_multiplatform
+9:	b	start_here_multiplatform
 
 /*
  * Copy routine used to copy the kernel to start at physical address 0
@@ -544,7 +544,7 @@ __secondary_start_pmac_0:
 	
 _GLOBAL(pmac_secondary_start)
 	/* turn on 64-bit mode */
-	bl	.enable_64b_mode
+	bl	enable_64b_mode
 
 	li	r0,0
 	mfspr	r3,SPRN_HID4
@@ -556,11 +556,11 @@ _GLOBAL(pmac_secondary_start)
 	slbia
 
 	/* get TOC pointer (real address) */
-	bl	.relative_toc
+	bl	relative_toc
 	tovirt(r2,r2)
 
 	/* Copy some CPU settings from CPU 0 */
-	bl	.__restore_cpu_ppc970
+	bl	__restore_cpu_ppc970
 
 	/* pSeries do that early though I don't think we really need it */
 	mfmsr	r3
@@ -619,7 +619,7 @@ __secondary_start:
 	std	r14,PACAKSAVE(r13)
 
 	/* Do early setup for that CPU (stab, slb, hash table pointer) */
-	bl	.early_setup_secondary
+	bl	early_setup_secondary
 
 	/*
 	 * setup the new stack pointer, but *don't* use this until
@@ -639,7 +639,7 @@ __secondary_start:
 	stb	r0,PACAIRQHAPPENED(r13)
 
 	/* enable MMU and jump to start_secondary */
-	LOAD_REG_ADDR(r3, .start_secondary_prolog)
+	LOAD_REG_ADDR(r3, start_secondary_prolog)
 	LOAD_REG_IMMEDIATE(r4, MSR_KERNEL)
 
 	mtspr	SPRN_SRR0,r3
@@ -652,11 +652,11 @@ __secondary_start:
  * zero the stack back-chain pointer and get the TOC virtual address
  * before going into C code.
  */
-_GLOBAL(start_secondary_prolog)
+start_secondary_prolog:
 	ld	r2,PACATOC(r13)
 	li	r3,0
 	std	r3,0(r1)		/* Zero the stack frame pointer	*/
-	bl	.start_secondary
+	bl	start_secondary
 	b	.
 /*
  * Reset stack pointer and call start_secondary
@@ -667,14 +667,14 @@ _GLOBAL(start_secondary_resume)
 	ld	r1,PACAKSAVE(r13)	/* Reload kernel stack pointer */
 	li	r3,0
 	std	r3,0(r1)		/* Zero the stack frame pointer	*/
-	bl	.start_secondary
+	bl	start_secondary
 	b	.
 #endif
 
 /*
  * This subroutine clobbers r11 and r12
  */
-_GLOBAL(enable_64b_mode)
+enable_64b_mode:
 	mfmsr	r11			/* grab the current MSR */
 #ifdef CONFIG_PPC_BOOK3E
 	oris	r11,r11,0x8000		/* CM bit set, we'll set ICM later */
@@ -715,9 +715,9 @@ p_toc:	.llong	__toc_start + 0x8000 - 0b
 /*
  * This is where the main kernel code starts.
  */
-_INIT_STATIC(start_here_multiplatform)
+start_here_multiplatform:
 	/* set up the TOC */
-	bl      .relative_toc
+	bl      relative_toc
 	tovirt(r2,r2)
 
 	/* Clear out the BSS. It may have been done in prom_init,
@@ -776,9 +776,9 @@ _INIT_STATIC(start_here_multiplatform)
 
 	/* Restore parameters passed from prom_init/kexec */
 	mr	r3,r31
-	bl	.early_setup		/* also sets r13 and SPRG_PACA */
+	bl	early_setup		/* also sets r13 and SPRG_PACA */
 
-	LOAD_REG_ADDR(r3, .start_here_common)
+	LOAD_REG_ADDR(r3, start_here_common)
 	ld	r4,PACAKMSR(r13)
 	mtspr	SPRN_SRR0,r3
 	mtspr	SPRN_SRR1,r4
@@ -786,7 +786,8 @@ _INIT_STATIC(start_here_multiplatform)
 	b	.	/* prevent speculative execution */
 	
 	/* This is where all platforms converge execution */
-_INIT_GLOBAL(start_here_common)
+
+start_here_common:
 	/* relocation is on at this point */
 	std	r1,PACAKSAVE(r13)
 
@@ -794,7 +795,7 @@ _INIT_GLOBAL(start_here_common)
 	ld	r2,PACATOC(r13)
 
 	/* Do more system initializations in virtual mode */
-	bl	.setup_system
+	bl	setup_system
 
 	/* Mark interrupts soft and hard disabled (they might be enabled
 	 * in the PACA when doing hotplug)
@@ -805,7 +806,7 @@ _INIT_GLOBAL(start_here_common)
 	stb	r0,PACAIRQHAPPENED(r13)
 
 	/* Generic kernel entry */
-	bl	.start_kernel
+	bl	start_kernel
 
 	/* Not reached */
 	BUG_OPCODE

arch/powerpc/kernel/idle_book3e.S

@@ -43,7 +43,7 @@ _GLOBAL(\name)
 	 */
 #ifdef CONFIG_TRACE_IRQFLAGS
 	stdu    r1,-128(r1)
-	bl	.trace_hardirqs_on
+	bl	trace_hardirqs_on
 	addi    r1,r1,128
 #endif
 	li	r0,1

arch/powerpc/kernel/idle_power4.S

@@ -46,7 +46,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_CAN_NAP)
 	mflr	r0
 	std	r0,16(r1)
 	stdu    r1,-128(r1)
-	bl	.trace_hardirqs_on
+	bl	trace_hardirqs_on
 	addi    r1,r1,128
 	ld	r0,16(r1)
 	mtlr	r0

arch/powerpc/kernel/idle_power7.S

@@ -58,7 +58,7 @@ _GLOBAL(power7_powersave_common)
 	/* Make sure FPU, VSX etc... are flushed as we may lose
 	 * state when going to nap mode
 	 */
-	bl	.discard_lazy_cpu_state
+	bl	discard_lazy_cpu_state
 #endif /* CONFIG_SMP */
 
 	/* Hard disable interrupts */
@@ -168,7 +168,7 @@ _GLOBAL(power7_wakeup_loss)
 _GLOBAL(power7_wakeup_noloss)
 	lbz	r0,PACA_NAPSTATELOST(r13)
 	cmpwi	r0,0
-	bne	.power7_wakeup_loss
+	bne	power7_wakeup_loss
 	ld	r1,PACAR1(r13)
 	ld	r4,_MSR(r1)
 	ld	r5,_NIP(r1)

arch/powerpc/kernel/misc_64.S

@@ -34,7 +34,7 @@ _GLOBAL(call_do_softirq)
 	std	r0,16(r1)
 	stdu	r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r3)
 	mr	r1,r3
-	bl	.__do_softirq
+	bl	__do_softirq
 	ld	r1,0(r1)
 	ld	r0,16(r1)
 	mtlr	r0
@@ -45,7 +45,7 @@ _GLOBAL(call_do_irq)
 	std	r0,16(r1)
 	stdu	r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r4)
 	mr	r1,r4
-	bl	.__do_irq
+	bl	__do_irq
 	ld	r1,0(r1)
 	ld	r0,16(r1)
 	mtlr	r0
@@ -506,7 +506,7 @@ _GLOBAL(kexec_smp_wait)
 	stb	r4,PACAKEXECSTATE(r13)
 	SYNC
 
-	b	.kexec_wait
+	b	kexec_wait
 
 /*
  * switch to real mode (turn mmu off)
@@ -576,7 +576,7 @@ _GLOBAL(kexec_sequence)
 
 	/* copy dest pages, flush whole dest image */
 	mr	r3,r29
-	bl	.kexec_copy_flush	/* (image) */
+	bl	kexec_copy_flush	/* (image) */
 
 	/* turn off mmu */
 	bl	real_mode
@@ -586,7 +586,7 @@ _GLOBAL(kexec_sequence)
 	mr	r4,r30		/* start, aka phys mem offset */
 	li	r5,0x100
 	li	r6,0
-	bl	.copy_and_flush	/* (dest, src, copy limit, start offset) */
+	bl	copy_and_flush	/* (dest, src, copy limit, start offset) */
 1:	/* assume normal blr return */
 
 	/* release other cpus to the new kernel secondary start at 0x60 */
@@ -595,8 +595,12 @@ _GLOBAL(kexec_sequence)
 	stw	r6,kexec_flag-1b(5)
 
 	/* clear out hardware hash page table and tlb */
-	ld	r5,0(r27)		/* deref function descriptor */
-	mtctr	r5
+#if !defined(_CALL_ELF) || _CALL_ELF != 2
+	ld	r12,0(r27)		/* deref function descriptor */
+#else
+	mr	r12,r27
+#endif
+	mtctr	r12
 	bctrl				/* ppc_md.hpte_clear_all(void); */
 
 /*
@@ -630,3 +634,31 @@ _GLOBAL(kexec_sequence)
 	li	r5,0
 	blr	/* image->start(physid, image->start, 0); */
 #endif /* CONFIG_KEXEC */
+
+#ifdef CONFIG_MODULES
+#if defined(_CALL_ELF) && _CALL_ELF == 2
+
+#ifdef CONFIG_MODVERSIONS
+.weak __crc_TOC.
+.section "___kcrctab+TOC.","a"
+.globl __kcrctab_TOC.
+__kcrctab_TOC.:
+	.llong	__crc_TOC.
+#endif
+
+/*
+ * Export a fake .TOC. since both modpost and depmod will complain otherwise.
+ * Both modpost and depmod strip the leading . so we do the same here.
+ */
+.section "__ksymtab_strings","a"
+__kstrtab_TOC.:
+	.asciz "TOC."
+
+.section "___ksymtab+TOC.","a"
+/* This symbol name is important: it's used by modpost to find exported syms */
+.globl __ksymtab_TOC.
+__ksymtab_TOC.:
+	.llong 0 /* .value */
+	.llong __kstrtab_TOC.
+#endif /* ELFv2 */
+#endif /* MODULES */

arch/powerpc/kernel/module_64.c

@@ -22,6 +22,7 @@
 #include <linux/vmalloc.h>
 #include <linux/ftrace.h>
 #include <linux/bug.h>
+#include <linux/uaccess.h>
 #include <asm/module.h>
 #include <asm/firmware.h>
 #include <asm/code-patching.h>
@@ -41,46 +42,170 @@
 #define DEBUGP(fmt , ...)
 #endif
 
+#if defined(_CALL_ELF) && _CALL_ELF == 2
+#define R2_STACK_OFFSET 24
+
+/* An address is simply the address of the function. */
+typedef unsigned long func_desc_t;
+
+static func_desc_t func_desc(unsigned long addr)
+{
+	return addr;
+}
+static unsigned long func_addr(unsigned long addr)
+{
+	return addr;
+}
+static unsigned long stub_func_addr(func_desc_t func)
+{
+	return func;
+}
+
+/* PowerPC64 specific values for the Elf64_Sym st_other field.  */
+#define STO_PPC64_LOCAL_BIT	5
+#define STO_PPC64_LOCAL_MASK	(7 << STO_PPC64_LOCAL_BIT)
+#define PPC64_LOCAL_ENTRY_OFFSET(other)					\
+ (((1 << (((other) & STO_PPC64_LOCAL_MASK) >> STO_PPC64_LOCAL_BIT)) >> 2) << 2)
+
+static unsigned int local_entry_offset(const Elf64_Sym *sym)
+{
+	/* sym->st_other indicates offset to local entry point
+	 * (otherwise it will assume r12 is the address of the start
+	 * of function and try to derive r2 from it). */
+	return PPC64_LOCAL_ENTRY_OFFSET(sym->st_other);
+}
+#else
+#define R2_STACK_OFFSET 40
+
+/* An address is address of the OPD entry, which contains address of fn. */
+typedef struct ppc64_opd_entry func_desc_t;
+
+static func_desc_t func_desc(unsigned long addr)
+{
+	return *(struct ppc64_opd_entry *)addr;
+}
+static unsigned long func_addr(unsigned long addr)
+{
+	return func_desc(addr).funcaddr;
+}
+static unsigned long stub_func_addr(func_desc_t func)
+{
+	return func.funcaddr;
+}
+static unsigned int local_entry_offset(const Elf64_Sym *sym)
+{
+	return 0;
+}
+#endif
+
 /* Like PPC32, we need little trampolines to do > 24-bit jumps (into
    the kernel itself).  But on PPC64, these need to be used for every
    jump, actually, to reset r2 (TOC+0x8000). */
 struct ppc64_stub_entry
 {
-	/* 28 byte jump instruction sequence (7 instructions) */
-	unsigned char jump[28];
-	unsigned char unused[4];
+	/* 28 byte jump instruction sequence (7 instructions). We only
+	 * need 6 instructions on ABIv2 but we always allocate 7 so
+	 * so we don't have to modify the trampoline load instruction. */
+	u32 jump[7];
+	u32 unused;
 	/* Data for the above code */
-	struct ppc64_opd_entry opd;
+	func_desc_t funcdata;
 };
 
-/* We use a stub to fix up r2 (TOC ptr) and to jump to the (external)
-   function which may be more than 24-bits away.  We could simply
-   patch the new r2 value and function pointer into the stub, but it's
-   significantly shorter to put these values at the end of the stub
-   code, and patch the stub address (32-bits relative to the TOC ptr,
-   r2) into the stub. */
-static struct ppc64_stub_entry ppc64_stub =
-{ .jump = {
-#ifdef __LITTLE_ENDIAN__
-	0x00, 0x00, 0x82, 0x3d, /* addis   r12,r2, <high> */
-	0x00, 0x00, 0x8c, 0x39, /* addi    r12,r12, <low> */
-	/* Save current r2 value in magic place on the stack. */
-	0x28, 0x00, 0x41, 0xf8, /* std     r2,40(r1) */
-	0x20, 0x00, 0x6c, 0xe9, /* ld      r11,32(r12) */
-	0x28, 0x00, 0x4c, 0xe8, /* ld      r2,40(r12) */
-	0xa6, 0x03, 0x69, 0x7d, /* mtctr   r11 */
-	0x20, 0x04, 0x80, 0x4e  /* bctr */
-#else
-	0x3d, 0x82, 0x00, 0x00, /* addis   r12,r2, <high> */
-	0x39, 0x8c, 0x00, 0x00, /* addi    r12,r12, <low> */
+/*
+ * PPC64 uses 24 bit jumps, but we need to jump into other modules or
+ * the kernel which may be further.  So we jump to a stub.
+ *
+ * For ELFv1 we need to use this to set up the new r2 value (aka TOC
+ * pointer).  For ELFv2 it's the callee's responsibility to set up the
+ * new r2, but for both we need to save the old r2.
+ *
+ * We could simply patch the new r2 value and function pointer into
+ * the stub, but it's significantly shorter to put these values at the
+ * end of the stub code, and patch the stub address (32-bits relative
+ * to the TOC ptr, r2) into the stub.
+ */
+
+static u32 ppc64_stub_insns[] = {
+	0x3d620000,			/* addis   r11,r2, <high> */
+	0x396b0000,			/* addi    r11,r11, <low> */
 	/* Save current r2 value in magic place on the stack. */
-	0xf8, 0x41, 0x00, 0x28, /* std     r2,40(r1) */
-	0xe9, 0x6c, 0x00, 0x20, /* ld      r11,32(r12) */
-	0xe8, 0x4c, 0x00, 0x28, /* ld      r2,40(r12) */
-	0x7d, 0x69, 0x03, 0xa6, /* mtctr   r11 */
-	0x4e, 0x80, 0x04, 0x20  /* bctr */
+	0xf8410000|R2_STACK_OFFSET,	/* std     r2,R2_STACK_OFFSET(r1) */
+	0xe98b0020,			/* ld      r12,32(r11) */
+#if !defined(_CALL_ELF) || _CALL_ELF != 2
+	/* Set up new r2 from function descriptor */
+	0xe84b0026,			/* ld      r2,40(r11) */
+#endif
+	0x7d8903a6,			/* mtctr   r12 */
+	0x4e800420			/* bctr */
+};
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+
+static u32 ppc64_stub_mask[] = {
+	0xffff0000,
+	0xffff0000,
+	0xffffffff,
+	0xffffffff,
+#if !defined(_CALL_ELF) || _CALL_ELF != 2
+	0xffffffff,
+#endif
+	0xffffffff,
+	0xffffffff
+};
+
+bool is_module_trampoline(u32 *p)
+{
+	unsigned int i;
+	u32 insns[ARRAY_SIZE(ppc64_stub_insns)];
+
+	BUILD_BUG_ON(sizeof(ppc64_stub_insns) != sizeof(ppc64_stub_mask));
+
+	if (probe_kernel_read(insns, p, sizeof(insns)))
+		return -EFAULT;
+
+	for (i = 0; i < ARRAY_SIZE(ppc64_stub_insns); i++) {
+		u32 insna = insns[i];
+		u32 insnb = ppc64_stub_insns[i];
+		u32 mask = ppc64_stub_mask[i];
+
+		if ((insna & mask) != (insnb & mask))
+			return false;
+	}
+
+	return true;
+}
+
+int module_trampoline_target(struct module *mod, u32 *trampoline,
+			     unsigned long *target)
+{
+	u32 buf[2];
+	u16 upper, lower;
+	long offset;
+	void *toc_entry;
+
+	if (probe_kernel_read(buf, trampoline, sizeof(buf)))
+		return -EFAULT;
+
+	upper = buf[0] & 0xffff;
+	lower = buf[1] & 0xffff;
+
+	/* perform the addis/addi, both signed */
+	offset = ((short)upper << 16) + (short)lower;
+
+	/*
+	 * Now get the address this trampoline jumps to. This
+	 * is always 32 bytes into our trampoline stub.
+	 */
+	toc_entry = (void *)mod->arch.toc + offset + 32;
+
+	if (probe_kernel_read(target, toc_entry, sizeof(*target)))
+		return -EFAULT;
+
+	return 0;
+}
+
 #endif
-} };
 
 /* Count how many different 24-bit relocations (different symbol,
    different addend) */
@@ -183,6 +308,7 @@ static unsigned long get_stubs_size(const Elf64_Ehdr *hdr,
 	return relocs * sizeof(struct ppc64_stub_entry);
 }
 
+/* Still needed for ELFv2, for .TOC. */
 static void dedotify_versions(struct modversion_info *vers,
 			      unsigned long size)
 {
@@ -193,7 +319,7 @@ static void dedotify_versions(struct modversion_info *vers,
 			memmove(vers->name, vers->name+1, strlen(vers->name));
 }
 
-/* Undefined symbols which refer to .funcname, hack to funcname */
+/* Undefined symbols which refer to .funcname, hack to funcname (or .TOC.) */
 static void dedotify(Elf64_Sym *syms, unsigned int numsyms, char *strtab)
 {
 	unsigned int i;
@@ -207,6 +333,24 @@ static void dedotify(Elf64_Sym *syms, unsigned int numsyms, char *strtab)
 	}
 }
 
+static Elf64_Sym *find_dot_toc(Elf64_Shdr *sechdrs,
+			       const char *strtab,
+			       unsigned int symindex)
+{
+	unsigned int i, numsyms;
+	Elf64_Sym *syms;
+
+	syms = (Elf64_Sym *)sechdrs[symindex].sh_addr;
+	numsyms = sechdrs[symindex].sh_size / sizeof(Elf64_Sym);
+
+	for (i = 1; i < numsyms; i++) {
+		if (syms[i].st_shndx == SHN_UNDEF
+		    && strcmp(strtab + syms[i].st_name, "TOC.") == 0)
+			return &syms[i];
+	}
+	return NULL;
+}
+
 int module_frob_arch_sections(Elf64_Ehdr *hdr,
 			      Elf64_Shdr *sechdrs,
 			      char *secstrings,
@@ -271,21 +415,12 @@ static inline unsigned long my_r2(Elf64_Shdr *sechdrs, struct module *me)
 /* Patch stub to reference function and correct r2 value. */
 static inline int create_stub(Elf64_Shdr *sechdrs,
 			      struct ppc64_stub_entry *entry,
-			      struct ppc64_opd_entry *opd,
+			      unsigned long addr,
 			      struct module *me)
 {
-	Elf64_Half *loc1, *loc2;
 	long reladdr;
 
-	*entry = ppc64_stub;
-
-#ifdef __LITTLE_ENDIAN__
-	loc1 = (Elf64_Half *)&entry->jump[0];
-	loc2 = (Elf64_Half *)&entry->jump[4];
-#else
-	loc1 = (Elf64_Half *)&entry->jump[2];
-	loc2 = (Elf64_Half *)&entry->jump[6];
-#endif
+	memcpy(entry->jump, ppc64_stub_insns, sizeof(ppc64_stub_insns));
 
 	/* Stub uses address relative to r2. */
 	reladdr = (unsigned long)entry - my_r2(sechdrs, me);
@@ -296,35 +431,33 @@ static inline int create_stub(Elf64_Shdr *sechdrs,
 	}
 	DEBUGP("Stub %p get data from reladdr %li\n", entry, reladdr);
 
-	*loc1 = PPC_HA(reladdr);
-	*loc2 = PPC_LO(reladdr);
-	entry->opd.funcaddr = opd->funcaddr;
-	entry->opd.r2 = opd->r2;
+	entry->jump[0] |= PPC_HA(reladdr);
+	entry->jump[1] |= PPC_LO(reladdr);
+	entry->funcdata = func_desc(addr);
 	return 1;
 }
 
-/* Create stub to jump to function described in this OPD: we need the
+/* Create stub to jump to function described in this OPD/ptr: we need the
    stub to set up the TOC ptr (r2) for the function. */
 static unsigned long stub_for_addr(Elf64_Shdr *sechdrs,
-				   unsigned long opdaddr,
+				   unsigned long addr,
 				   struct module *me)
 {
 	struct ppc64_stub_entry *stubs;
-	struct ppc64_opd_entry *opd = (void *)opdaddr;
 	unsigned int i, num_stubs;
 
 	num_stubs = sechdrs[me->arch.stubs_section].sh_size / sizeof(*stubs);
 
 	/* Find this stub, or if that fails, the next avail. entry */
 	stubs = (void *)sechdrs[me->arch.stubs_section].sh_addr;
-	for (i = 0; stubs[i].opd.funcaddr; i++) {
+	for (i = 0; stub_func_addr(stubs[i].funcdata); i++) {
 		BUG_ON(i >= num_stubs);
 
-		if (stubs[i].opd.funcaddr == opd->funcaddr)
+		if (stub_func_addr(stubs[i].funcdata) == func_addr(addr))
 			return (unsigned long)&stubs[i];
 	}
 
-	if (!create_stub(sechdrs, &stubs[i], opd, me))
+	if (!create_stub(sechdrs, &stubs[i], addr, me))
 		return 0;
 
 	return (unsigned long)&stubs[i];
@@ -339,7 +472,8 @@ static int restore_r2(u32 *instruction, struct module *me)
 		       me->name, *instruction);
 		return 0;
 	}
-	*instruction = 0xe8410028;	/* ld r2,40(r1) */
+	/* ld r2,R2_STACK_OFFSET(r1) */
+	*instruction = 0xe8410000 | R2_STACK_OFFSET;
 	return 1;
 }
 
@@ -357,6 +491,17 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 
 	DEBUGP("Applying ADD relocate section %u to %u\n", relsec,
 	       sechdrs[relsec].sh_info);
+
+	/* First time we're called, we can fix up .TOC. */
+	if (!me->arch.toc_fixed) {
+		sym = find_dot_toc(sechdrs, strtab, symindex);
+		/* It's theoretically possible that a module doesn't want a
+		 * .TOC. so don't fail it just for that. */
+		if (sym)
+			sym->st_value = my_r2(sechdrs, me);
+		me->arch.toc_fixed = true;
+	}
+
 	for (i = 0; i < sechdrs[relsec].sh_size / sizeof(*rela); i++) {
 		/* This is where to make the change */
 		location = (void *)sechdrs[sechdrs[relsec].sh_info].sh_addr
@@ -453,7 +598,8 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 					return -ENOENT;
 				if (!restore_r2((u32 *)location + 1, me))
 					return -ENOEXEC;
-			}
+			} else
+				value += local_entry_offset(sym);
 
 			/* Convert value to relative */
 			value -= (unsigned long)location;
@@ -474,6 +620,31 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 			*location = value - (unsigned long)location;
 			break;
 
+		case R_PPC64_TOCSAVE:
+			/*
+			 * Marker reloc indicates we don't have to save r2.
+			 * That would only save us one instruction, so ignore
+			 * it.
+			 */
+			break;
+
+		case R_PPC64_REL16_HA:
+			/* Subtract location pointer */
+			value -= (unsigned long)location;
+			value = ((value + 0x8000) >> 16);
+			*((uint16_t *) location)
+				= (*((uint16_t *) location) & ~0xffff)
+				| (value & 0xffff);
+			break;
+
+		case R_PPC64_REL16_LO:
+			/* Subtract location pointer */
+			value -= (unsigned long)location;
+			*((uint16_t *) location)
+				= (*((uint16_t *) location) & ~0xffff)
+				| (value & 0xffff);
+			break;
+
 		default:
 			printk("%s: Unknown ADD relocation: %lu\n",
 			       me->name,

arch/powerpc/kernel/process.c

@@ -54,6 +54,7 @@
 #ifdef CONFIG_PPC64
 #include <asm/firmware.h>
 #endif
+#include <asm/code-patching.h>
 #include <linux/kprobes.h>
 #include <linux/kdebug.h>
 
@@ -1108,7 +1109,9 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
 		struct thread_info *ti = (void *)task_stack_page(p);
 		memset(childregs, 0, sizeof(struct pt_regs));
 		childregs->gpr[1] = sp + sizeof(struct pt_regs);
-		childregs->gpr[14] = usp;	/* function */
+		/* function */
+		if (usp)
+			childregs->gpr[14] = ppc_function_entry((void *)usp);
 #ifdef CONFIG_PPC64
 		clear_tsk_thread_flag(p, TIF_32BIT);
 		childregs->softe = 1;
@@ -1187,17 +1190,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
 	if (cpu_has_feature(CPU_FTR_HAS_PPR))
 		p->thread.ppr = INIT_PPR;
 #endif
-	/*
-	 * The PPC64 ABI makes use of a TOC to contain function 
-	 * pointers.  The function (ret_from_except) is actually a pointer
-	 * to the TOC entry.  The first entry is a pointer to the actual
-	 * function.
-	 */
-#ifdef CONFIG_PPC64
-	kregs->nip = *((unsigned long *)f);
-#else
-	kregs->nip = (unsigned long)f;
-#endif
+	kregs->nip = ppc_function_entry(f);
 	return 0;
 }
 

arch/powerpc/kernel/prom_init_check.sh

@@ -23,7 +23,7 @@ strcmp strcpy strlcpy strlen strncmp strstr logo_linux_clut224
 reloc_got2 kernstart_addr memstart_addr linux_banner _stext
 opal_query_takeover opal_do_takeover opal_enter_rtas opal_secondary_entry
 boot_command_line __prom_init_toc_start __prom_init_toc_end
-btext_setup_display"
+btext_setup_display TOC."
 
 NM="$1"
 OBJ="$2"

arch/powerpc/kernel/setup_64.c

@@ -341,7 +341,7 @@ void smp_release_cpus(void)
 
 	ptr  = (unsigned long *)((unsigned long)&__secondary_hold_spinloop
 			- PHYSICAL_START);
-	*ptr = __pa(generic_secondary_smp_init);
+	*ptr = ppc_function_entry(generic_secondary_smp_init);
 
 	/* And wait a bit for them to catch up */
 	for (i = 0; i < 100000; i++) {

arch/powerpc/kernel/systbl.S

@@ -17,12 +17,12 @@
 #include <asm/ppc_asm.h>
 
 #ifdef CONFIG_PPC64
-#define SYSCALL(func)		.llong	.sys_##func,.sys_##func
-#define COMPAT_SYS(func)	.llong	.sys_##func,.compat_sys_##func
-#define PPC_SYS(func)		.llong	.ppc_##func,.ppc_##func
-#define OLDSYS(func)		.llong	.sys_ni_syscall,.sys_ni_syscall
-#define SYS32ONLY(func)		.llong	.sys_ni_syscall,.compat_sys_##func
-#define SYSX(f, f3264, f32)	.llong	.f,.f3264
+#define SYSCALL(func)		.llong	DOTSYM(sys_##func),DOTSYM(sys_##func)
+#define COMPAT_SYS(func)	.llong	DOTSYM(sys_##func),DOTSYM(compat_sys_##func)
+#define PPC_SYS(func)		.llong	DOTSYM(ppc_##func),DOTSYM(ppc_##func)
+#define OLDSYS(func)		.llong	DOTSYM(sys_ni_syscall),DOTSYM(sys_ni_syscall)
+#define SYS32ONLY(func)		.llong	DOTSYM(sys_ni_syscall),DOTSYM(compat_sys_##func)
+#define SYSX(f, f3264, f32)	.llong	DOTSYM(f),DOTSYM(f3264)
 #else
 #define SYSCALL(func)		.long	sys_##func
 #define COMPAT_SYS(func)	.long	sys_##func
@@ -36,6 +36,8 @@
 #define PPC_SYS_SPU(func)	PPC_SYS(func)
 #define SYSX_SPU(f, f3264, f32)	SYSX(f, f3264, f32)
 
+.section .rodata,"a"
+
 #ifdef CONFIG_PPC64
 #define sys_sigpending	sys_ni_syscall
 #define sys_old_getrlimit sys_ni_syscall
@@ -43,5 +45,7 @@
 	.p2align	3
 #endif
 
-_GLOBAL(sys_call_table)
+.globl sys_call_table
+sys_call_table:
+
 #include <asm/systbl.h>

arch/powerpc/kernel/tm.S

@@ -42,7 +42,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX);		\
 /* Stack frame offsets for local variables. */
 #define TM_FRAME_L0	TM_FRAME_SIZE-16
 #define TM_FRAME_L1	TM_FRAME_SIZE-8
-#define STACK_PARAM(x)	(48+((x)*8))
 
 
 /* In order to access the TM SPRs, TM must be enabled.  So, do so: */
@@ -109,12 +108,12 @@ _GLOBAL(tm_reclaim)
 	mflr	r0
 	stw	r6, 8(r1)
 	std	r0, 16(r1)
-	std	r2, 40(r1)
+	std	r2, STK_GOT(r1)
 	stdu	r1, -TM_FRAME_SIZE(r1)
 
 	/* We've a struct pt_regs at [r1+STACK_FRAME_OVERHEAD]. */
 
-	std	r3, STACK_PARAM(0)(r1)
+	std	r3, STK_PARAM(R3)(r1)
 	SAVE_NVGPRS(r1)
 
 	/* We need to setup MSR for VSX register save instructions.  Here we
@@ -210,7 +209,7 @@ dont_backup_fp:
 	/* Now get some more GPRS free */
 	std	r7, GPR7(r1)			/* Temporary stash */
 	std	r12, GPR12(r1)			/* ''   ''    ''   */
-	ld	r12, STACK_PARAM(0)(r1)		/* Param 0, thread_struct * */
+	ld	r12, STK_PARAM(R3)(r1)		/* Param 0, thread_struct * */
 
 	std	r11, THREAD_TM_PPR(r12)		/* Store PPR and free r11 */
 
@@ -297,7 +296,7 @@ dont_backup_fp:
 	ld	r0, 16(r1)
 	mtcr	r4
 	mtlr	r0
-	ld	r2, 40(r1)
+	ld	r2, STK_GOT(r1)
 
 	/* Load system default DSCR */
 	ld	r4, DSCR_DEFAULT@toc(r2)
@@ -320,7 +319,7 @@ _GLOBAL(__tm_recheckpoint)
 	mflr	r0
 	stw	r5, 8(r1)
 	std	r0, 16(r1)
-	std	r2, 40(r1)
+	std	r2, STK_GOT(r1)
 	stdu	r1, -TM_FRAME_SIZE(r1)
 
 	/* We've a struct pt_regs at [r1+STACK_FRAME_OVERHEAD].
@@ -478,7 +477,7 @@ restore_gprs:
 	ld	r0, 16(r1)
 	mtcr	r4
 	mtlr	r0
-	ld	r2, 40(r1)
+	ld	r2, STK_GOT(r1)
 
 	/* Load system default DSCR */
 	ld	r4, DSCR_DEFAULT@toc(r2)

arch/powerpc/kvm/book3s_hv_interrupts.S

@@ -171,7 +171,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 #endif /* CONFIG_SMP */
 
 	/* Jump to partition switch code */
-	bl	.kvmppc_hv_entry_trampoline
+	bl	kvmppc_hv_entry_trampoline
 	nop
 
 /*

arch/powerpc/kvm/book3s_hv_rmhandlers.S

@@ -1658,7 +1658,7 @@ kvmppc_hdsi:
 	/* Search the hash table. */
 	mr	r3, r9			/* vcpu pointer */
 	li	r7, 1			/* data fault */
-	bl	.kvmppc_hpte_hv_fault
+	bl	kvmppc_hpte_hv_fault
 	ld	r9, HSTATE_KVM_VCPU(r13)
 	ld	r10, VCPU_PC(r9)
 	ld	r11, VCPU_MSR(r9)
@@ -1732,7 +1732,7 @@ kvmppc_hisi:
 	mr	r4, r10
 	mr	r6, r11
 	li	r7, 0			/* instruction fault */
-	bl	.kvmppc_hpte_hv_fault
+	bl	kvmppc_hpte_hv_fault
 	ld	r9, HSTATE_KVM_VCPU(r13)
 	ld	r10, VCPU_PC(r9)
 	ld	r11, VCPU_MSR(r9)
@@ -1806,16 +1806,16 @@ hcall_real_fallback:
 	.globl	hcall_real_table
 hcall_real_table:
 	.long	0		/* 0 - unused */
-	.long	.kvmppc_h_remove - hcall_real_table
-	.long	.kvmppc_h_enter - hcall_real_table
-	.long	.kvmppc_h_read - hcall_real_table
+	.long	DOTSYM(kvmppc_h_remove) - hcall_real_table
+	.long	DOTSYM(kvmppc_h_enter) - hcall_real_table
+	.long	DOTSYM(kvmppc_h_read) - hcall_real_table
 	.long	0		/* 0x10 - H_CLEAR_MOD */
 	.long	0		/* 0x14 - H_CLEAR_REF */
-	.long	.kvmppc_h_protect - hcall_real_table
-	.long	.kvmppc_h_get_tce - hcall_real_table
-	.long	.kvmppc_h_put_tce - hcall_real_table
+	.long	DOTSYM(kvmppc_h_protect) - hcall_real_table
+	.long	DOTSYM(kvmppc_h_get_tce) - hcall_real_table
+	.long	DOTSYM(kvmppc_h_put_tce) - hcall_real_table
 	.long	0		/* 0x24 - H_SET_SPRG0 */
-	.long	.kvmppc_h_set_dabr - hcall_real_table
+	.long	DOTSYM(kvmppc_h_set_dabr) - hcall_real_table
 	.long	0		/* 0x2c */
 	.long	0		/* 0x30 */
 	.long	0		/* 0x34 */
@@ -1831,11 +1831,11 @@ hcall_real_table:
 	.long	0		/* 0x5c */
 	.long	0		/* 0x60 */
 #ifdef CONFIG_KVM_XICS
-	.long	.kvmppc_rm_h_eoi - hcall_real_table
-	.long	.kvmppc_rm_h_cppr - hcall_real_table
-	.long	.kvmppc_rm_h_ipi - hcall_real_table
+	.long	DOTSYM(kvmppc_rm_h_eoi) - hcall_real_table
+	.long	DOTSYM(kvmppc_rm_h_cppr) - hcall_real_table
+	.long	DOTSYM(kvmppc_rm_h_ipi) - hcall_real_table
 	.long	0		/* 0x70 - H_IPOLL */
-	.long	.kvmppc_rm_h_xirr - hcall_real_table
+	.long	DOTSYM(kvmppc_rm_h_xirr) - hcall_real_table
 #else
 	.long	0		/* 0x64 - H_EOI */
 	.long	0		/* 0x68 - H_CPPR */
@@ -1869,7 +1869,7 @@ hcall_real_table:
 	.long	0		/* 0xd4 */
 	.long	0		/* 0xd8 */
 	.long	0		/* 0xdc */
-	.long	.kvmppc_h_cede - hcall_real_table
+	.long	DOTSYM(kvmppc_h_cede) - hcall_real_table
 	.long	0		/* 0xe4 */
 	.long	0		/* 0xe8 */
 	.long	0		/* 0xec */
@@ -1886,11 +1886,11 @@ hcall_real_table:
 	.long	0		/* 0x118 */
 	.long	0		/* 0x11c */
 	.long	0		/* 0x120 */
-	.long	.kvmppc_h_bulk_remove - hcall_real_table
+	.long	DOTSYM(kvmppc_h_bulk_remove) - hcall_real_table
 	.long	0		/* 0x128 */
 	.long	0		/* 0x12c */
 	.long	0		/* 0x130 */
-	.long	.kvmppc_h_set_xdabr - hcall_real_table
+	.long	DOTSYM(kvmppc_h_set_xdabr) - hcall_real_table
 hcall_real_table_end:
 
 ignore_hdec:
@@ -2115,7 +2115,7 @@ kvm_cede_exit:
 	/* Try to handle a machine check in real mode */
 machine_check_realmode:
 	mr	r3, r9		/* get vcpu pointer */
-	bl	.kvmppc_realmode_machine_check
+	bl	kvmppc_realmode_machine_check
 	nop
 	cmpdi	r3, 0		/* continue exiting from guest? */
 	ld	r9, HSTATE_KVM_VCPU(r13)

arch/powerpc/lib/copypage_64.S

@@ -20,7 +20,7 @@ _GLOBAL(copy_page)
 BEGIN_FTR_SECTION
 	lis	r5,PAGE_SIZE@h
 FTR_SECTION_ELSE
-	b	.copypage_power7
+	b	copypage_power7
 ALT_FTR_SECTION_END_IFCLR(CPU_FTR_VMX_COPY)
 	ori	r5,r5,PAGE_SIZE@l
 BEGIN_FTR_SECTION

arch/powerpc/lib/copypage_power7.S

@@ -56,15 +56,15 @@ _GLOBAL(copypage_power7)
 
 #ifdef CONFIG_ALTIVEC
 	mflr	r0
-	std	r3,48(r1)
-	std	r4,56(r1)
+	std	r3,-STACKFRAMESIZE+STK_REG(R31)(r1)
+	std	r4,-STACKFRAMESIZE+STK_REG(R30)(r1)
 	std	r0,16(r1)
 	stdu	r1,-STACKFRAMESIZE(r1)
-	bl	.enter_vmx_copy
+	bl	enter_vmx_copy
 	cmpwi	r3,0
 	ld	r0,STACKFRAMESIZE+16(r1)
-	ld	r3,STACKFRAMESIZE+48(r1)
-	ld	r4,STACKFRAMESIZE+56(r1)
+	ld	r3,STK_REG(R31)(r1)
+	ld	r4,STK_REG(R30)(r1)
 	mtlr	r0
 
 	li	r0,(PAGE_SIZE/128)
@@ -103,7 +103,7 @@ _GLOBAL(copypage_power7)
 	addi	r3,r3,128
 	bdnz	1b
 
-	b	.exit_vmx_copy		/* tail call optimise */
+	b	exit_vmx_copy		/* tail call optimise */
 
 #else
 	li	r0,(PAGE_SIZE/128)

arch/powerpc/lib/copyuser_64.S

@@ -18,7 +18,7 @@
 #endif
 
 	.align	7
-_GLOBAL(__copy_tofrom_user)
+_GLOBAL_TOC(__copy_tofrom_user)
 BEGIN_FTR_SECTION
 	nop
 FTR_SECTION_ELSE

arch/powerpc/lib/copyuser_power7.S

@@ -66,7 +66,7 @@
 	ld	r15,STK_REG(R15)(r1)
 	ld	r14,STK_REG(R14)(r1)
 .Ldo_err3:
-	bl	.exit_vmx_usercopy
+	bl	exit_vmx_usercopy
 	ld	r0,STACKFRAMESIZE+16(r1)
 	mtlr	r0
 	b	.Lexit
@@ -85,9 +85,9 @@
 .Lexit:
 	addi	r1,r1,STACKFRAMESIZE
 .Ldo_err1:
-	ld	r3,48(r1)
-	ld	r4,56(r1)
-	ld	r5,64(r1)
+	ld	r3,-STACKFRAMESIZE+STK_REG(R31)(r1)
+	ld	r4,-STACKFRAMESIZE+STK_REG(R30)(r1)
+	ld	r5,-STACKFRAMESIZE+STK_REG(R29)(r1)
 	b	__copy_tofrom_user_base
 
 
@@ -96,18 +96,18 @@ _GLOBAL(__copy_tofrom_user_power7)
 	cmpldi	r5,16
 	cmpldi	cr1,r5,4096
 
-	std	r3,48(r1)
-	std	r4,56(r1)
-	std	r5,64(r1)
+	std	r3,-STACKFRAMESIZE+STK_REG(R31)(r1)
+	std	r4,-STACKFRAMESIZE+STK_REG(R30)(r1)
+	std	r5,-STACKFRAMESIZE+STK_REG(R29)(r1)
 
 	blt	.Lshort_copy
 	bgt	cr1,.Lvmx_copy
 #else
 	cmpldi	r5,16
 
-	std	r3,48(r1)
-	std	r4,56(r1)
-	std	r5,64(r1)
+	std	r3,-STACKFRAMESIZE+STK_REG(R31)(r1)
+	std	r4,-STACKFRAMESIZE+STK_REG(R30)(r1)
+	std	r5,-STACKFRAMESIZE+STK_REG(R29)(r1)
 
 	blt	.Lshort_copy
 #endif
@@ -295,12 +295,12 @@ err1;	stb	r0,0(r3)
 	mflr	r0
 	std	r0,16(r1)
 	stdu	r1,-STACKFRAMESIZE(r1)
-	bl	.enter_vmx_usercopy
+	bl	enter_vmx_usercopy
 	cmpwi	cr1,r3,0
 	ld	r0,STACKFRAMESIZE+16(r1)
-	ld	r3,STACKFRAMESIZE+48(r1)
-	ld	r4,STACKFRAMESIZE+56(r1)
-	ld	r5,STACKFRAMESIZE+64(r1)
+	ld	r3,STK_REG(R31)(r1)
+	ld	r4,STK_REG(R30)(r1)
+	ld	r5,STK_REG(R29)(r1)
 	mtlr	r0
 
 	/*
@@ -514,7 +514,7 @@ err3;	lbz	r0,0(r4)
 err3;	stb	r0,0(r3)
 
 15:	addi	r1,r1,STACKFRAMESIZE
-	b	.exit_vmx_usercopy	/* tail call optimise */
+	b	exit_vmx_usercopy	/* tail call optimise */
 
 .Lvmx_unaligned_copy:
 	/* Get the destination 16B aligned */
@@ -717,5 +717,5 @@ err3;	lbz	r0,0(r4)
 err3;	stb	r0,0(r3)
 
 15:	addi	r1,r1,STACKFRAMESIZE
-	b	.exit_vmx_usercopy	/* tail call optimise */
+	b	exit_vmx_usercopy	/* tail call optimise */
 #endif /* CONFiG_ALTIVEC */

arch/powerpc/lib/hweight_64.S

@@ -24,7 +24,7 @@
 
 _GLOBAL(__arch_hweight8)
 BEGIN_FTR_SECTION
-	b .__sw_hweight8
+	b __sw_hweight8
 	nop
 	nop
 FTR_SECTION_ELSE
@@ -35,7 +35,7 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_POPCNTB)
 
 _GLOBAL(__arch_hweight16)
 BEGIN_FTR_SECTION
-	b .__sw_hweight16
+	b __sw_hweight16
 	nop
 	nop
 	nop
@@ -57,7 +57,7 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_POPCNTB)
 
 _GLOBAL(__arch_hweight32)
 BEGIN_FTR_SECTION
-	b .__sw_hweight32
+	b __sw_hweight32
 	nop
 	nop
 	nop
@@ -82,7 +82,7 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_POPCNTB)
 
 _GLOBAL(__arch_hweight64)
 BEGIN_FTR_SECTION
-	b .__sw_hweight64
+	b __sw_hweight64
 	nop
 	nop
 	nop

arch/powerpc/lib/mem_64.S

@@ -79,8 +79,8 @@ _GLOBAL(memset)
 
 _GLOBAL(memmove)
 	cmplw	0,r3,r4
-	bgt	.backwards_memcpy
-	b	.memcpy
+	bgt	backwards_memcpy
+	b	memcpy
 
 _GLOBAL(backwards_memcpy)
 	rlwinm.	r7,r5,32-3,3,31		/* r0 = r5 >> 3 */

arch/powerpc/lib/memcpy_64.S

@@ -10,12 +10,12 @@
 #include <asm/ppc_asm.h>
 
 	.align	7
-_GLOBAL(memcpy)
+_GLOBAL_TOC(memcpy)
 BEGIN_FTR_SECTION
 #ifdef __LITTLE_ENDIAN__
 	cmpdi	cr7,r5,0
 #else
-	std	r3,48(r1)	/* save destination pointer for return value */
+	std	r3,-STACKFRAMESIZE+STK_REG(R31)(r1)	/* save destination pointer for return value */
 #endif
 FTR_SECTION_ELSE
 #ifndef SELFTEST
@@ -88,7 +88,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD)
 2:	bf	cr7*4+3,3f
 	lbz	r9,8(r4)
 	stb	r9,0(r3)
-3:	ld	r3,48(r1)	/* return dest pointer */
+3:	ld	r3,-STACKFRAMESIZE+STK_REG(R31)(r1)	/* return dest pointer */
 	blr
 
 .Lsrc_unaligned:
@@ -171,7 +171,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD)
 2:	bf	cr7*4+3,3f
 	rotldi	r9,r9,8
 	stb	r9,0(r3)
-3:	ld	r3,48(r1)	/* return dest pointer */
+3:	ld	r3,-STACKFRAMESIZE+STK_REG(R31)(r1)	/* return dest pointer */
 	blr
 
 .Ldst_unaligned:
@@ -216,6 +216,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD)
 3:	bf	cr7*4+3,4f
 	lbz	r0,0(r4)
 	stb	r0,0(r3)
-4:	ld	r3,48(r1)	/* return dest pointer */
+4:	ld	r3,-STACKFRAMESIZE+STK_REG(R31)(r1)	/* return dest pointer */
 	blr
 #endif

arch/powerpc/lib/memcpy_power7.S

@@ -33,14 +33,14 @@ _GLOBAL(memcpy_power7)
 	cmpldi	r5,16
 	cmpldi	cr1,r5,4096
 
-	std	r3,48(r1)
+	std	r3,-STACKFRAMESIZE+STK_REG(R31)(r1)
 
 	blt	.Lshort_copy
 	bgt	cr1,.Lvmx_copy
 #else
 	cmpldi	r5,16
 
-	std	r3,48(r1)
+	std	r3,-STACKFRAMESIZE+STK_REG(R31)(r1)
 
 	blt	.Lshort_copy
 #endif
@@ -216,7 +216,7 @@ _GLOBAL(memcpy_power7)
 	lbz	r0,0(r4)
 	stb	r0,0(r3)
 
-15:	ld	r3,48(r1)
+15:	ld	r3,-STACKFRAMESIZE+STK_REG(R31)(r1)
 	blr
 
 .Lunwind_stack_nonvmx_copy:
@@ -226,16 +226,16 @@ _GLOBAL(memcpy_power7)
 #ifdef CONFIG_ALTIVEC
 .Lvmx_copy:
 	mflr	r0
-	std	r4,56(r1)
-	std	r5,64(r1)
+	std	r4,-STACKFRAMESIZE+STK_REG(R30)(r1)
+	std	r5,-STACKFRAMESIZE+STK_REG(R29)(r1)
 	std	r0,16(r1)
 	stdu	r1,-STACKFRAMESIZE(r1)
-	bl	.enter_vmx_copy
+	bl	enter_vmx_copy
 	cmpwi	cr1,r3,0
 	ld	r0,STACKFRAMESIZE+16(r1)
-	ld	r3,STACKFRAMESIZE+48(r1)
-	ld	r4,STACKFRAMESIZE+56(r1)
-	ld	r5,STACKFRAMESIZE+64(r1)
+	ld	r3,STK_REG(R31)(r1)
+	ld	r4,STK_REG(R30)(r1)
+	ld	r5,STK_REG(R29)(r1)
 	mtlr	r0
 
 	/*
@@ -447,8 +447,8 @@ _GLOBAL(memcpy_power7)
 	stb	r0,0(r3)
 
 15:	addi	r1,r1,STACKFRAMESIZE
-	ld	r3,48(r1)
-	b	.exit_vmx_copy		/* tail call optimise */
+	ld	r3,-STACKFRAMESIZE+STK_REG(R31)(r1)
+	b	exit_vmx_copy		/* tail call optimise */
 
 .Lvmx_unaligned_copy:
 	/* Get the destination 16B aligned */
@@ -651,6 +651,6 @@ _GLOBAL(memcpy_power7)
 	stb	r0,0(r3)
 
 15:	addi	r1,r1,STACKFRAMESIZE
-	ld	r3,48(r1)
-	b	.exit_vmx_copy		/* tail call optimise */
+	ld	r3,-STACKFRAMESIZE+STK_REG(R31)(r1)
+	b	exit_vmx_copy		/* tail call optimise */
 #endif /* CONFiG_ALTIVEC */

arch/powerpc/mm/hash_low_64.S

@@ -159,7 +159,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
 BEGIN_FTR_SECTION
 	mr	r4,r30
 	mr	r5,r7
-	bl	.hash_page_do_lazy_icache
+	bl	hash_page_do_lazy_icache
 END_FTR_SECTION(CPU_FTR_NOEXECUTE|CPU_FTR_COHERENT_ICACHE, CPU_FTR_NOEXECUTE)
 
 	/* At this point, r3 contains new PP bits, save them in
@@ -201,7 +201,8 @@ htab_insert_pte:
 	li	r8,MMU_PAGE_4K		/* page size */
 	li	r9,MMU_PAGE_4K		/* actual page size */
 	ld	r10,STK_PARAM(R9)(r1)	/* segment size */
-_GLOBAL(htab_call_hpte_insert1)
+.globl htab_call_hpte_insert1
+htab_call_hpte_insert1:
 	bl	.			/* Patched by htab_finish_init() */
 	cmpdi	0,r3,0
 	bge	htab_pte_insert_ok	/* Insertion successful */
@@ -225,7 +226,8 @@ _GLOBAL(htab_call_hpte_insert1)
 	li	r8,MMU_PAGE_4K		/* page size */
 	li	r9,MMU_PAGE_4K		/* actual page size */
 	ld	r10,STK_PARAM(R9)(r1)	/* segment size */
-_GLOBAL(htab_call_hpte_insert2)
+.globl htab_call_hpte_insert2
+htab_call_hpte_insert2:
 	bl	.			/* Patched by htab_finish_init() */
 	cmpdi	0,r3,0
 	bge+	htab_pte_insert_ok	/* Insertion successful */
@@ -242,7 +244,8 @@ _GLOBAL(htab_call_hpte_insert2)
 2:	and	r0,r5,r27
 	rldicr	r3,r0,3,63-3	/* r0 = (hash & mask) << 3 */	
 	/* Call ppc_md.hpte_remove */
-_GLOBAL(htab_call_hpte_remove)
+.globl htab_call_hpte_remove
+htab_call_hpte_remove:
 	bl	.			/* Patched by htab_finish_init() */
 
 	/* Try all again */
@@ -296,7 +299,8 @@ htab_modify_pte:
 	li	r7,MMU_PAGE_4K		/* actual page size */
 	ld	r8,STK_PARAM(R9)(r1)	/* segment size */
 	ld	r9,STK_PARAM(R8)(r1)	/* get "local" param */
-_GLOBAL(htab_call_hpte_updatepp)
+.globl htab_call_hpte_updatepp
+htab_call_hpte_updatepp:
 	bl	.			/* Patched by htab_finish_init() */
 
 	/* if we failed because typically the HPTE wasn't really here
@@ -471,7 +475,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
 BEGIN_FTR_SECTION
 	mr	r4,r30
 	mr	r5,r7
-	bl	.hash_page_do_lazy_icache
+	bl	hash_page_do_lazy_icache
 END_FTR_SECTION(CPU_FTR_NOEXECUTE|CPU_FTR_COHERENT_ICACHE, CPU_FTR_NOEXECUTE)
 
 	/* At this point, r3 contains new PP bits, save them in
@@ -526,7 +530,8 @@ htab_special_pfn:
 	li	r8,MMU_PAGE_4K		/* page size */
 	li	r9,MMU_PAGE_4K		/* actual page size */
 	ld	r10,STK_PARAM(R9)(r1)	/* segment size */
-_GLOBAL(htab_call_hpte_insert1)
+.globl htab_call_hpte_insert1
+htab_call_hpte_insert1:
 	bl	.			/* patched by htab_finish_init() */
 	cmpdi	0,r3,0
 	bge	htab_pte_insert_ok	/* Insertion successful */
@@ -554,7 +559,8 @@ _GLOBAL(htab_call_hpte_insert1)
 	li	r8,MMU_PAGE_4K		/* page size */
 	li	r9,MMU_PAGE_4K		/* actual page size */
 	ld	r10,STK_PARAM(R9)(r1)	/* segment size */
-_GLOBAL(htab_call_hpte_insert2)
+.globl htab_call_hpte_insert2
+htab_call_hpte_insert2:
 	bl	.			/* patched by htab_finish_init() */
 	cmpdi	0,r3,0
 	bge+	htab_pte_insert_ok	/* Insertion successful */
@@ -571,7 +577,8 @@ _GLOBAL(htab_call_hpte_insert2)
 2:	and	r0,r5,r27
 	rldicr	r3,r0,3,63-3		/* r0 = (hash & mask) << 3 */
 	/* Call ppc_md.hpte_remove */
-_GLOBAL(htab_call_hpte_remove)
+.globl htab_call_hpte_remove
+htab_call_hpte_remove:
 	bl	.			/* patched by htab_finish_init() */
 
 	/* Try all again */
@@ -588,7 +595,7 @@ htab_inval_old_hpte:
 	li	r6,MMU_PAGE_64K		/* psize */
 	ld	r7,STK_PARAM(R9)(r1)	/* ssize */
 	ld	r8,STK_PARAM(R8)(r1)	/* local */
-	bl	.flush_hash_page
+	bl	flush_hash_page
 	/* Clear out _PAGE_HPTE_SUB bits in the new linux PTE */
 	lis	r0,_PAGE_HPTE_SUB@h
 	ori	r0,r0,_PAGE_HPTE_SUB@l
@@ -660,7 +667,8 @@ htab_modify_pte:
 	li	r7,MMU_PAGE_4K		/* actual page size */
 	ld	r8,STK_PARAM(R9)(r1)	/* segment size */
 	ld	r9,STK_PARAM(R8)(r1)	/* get "local" param */
-_GLOBAL(htab_call_hpte_updatepp)
+.globl htab_call_hpte_updatepp
+htab_call_hpte_updatepp:
 	bl	.			/* patched by htab_finish_init() */
 
 	/* if we failed because typically the HPTE wasn't really here
@@ -812,7 +820,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
 BEGIN_FTR_SECTION
 	mr	r4,r30
 	mr	r5,r7
-	bl	.hash_page_do_lazy_icache
+	bl	hash_page_do_lazy_icache
 END_FTR_SECTION(CPU_FTR_NOEXECUTE|CPU_FTR_COHERENT_ICACHE, CPU_FTR_NOEXECUTE)
 
 	/* At this point, r3 contains new PP bits, save them in
@@ -857,7 +865,8 @@ ht64_insert_pte:
 	li	r8,MMU_PAGE_64K
 	li	r9,MMU_PAGE_64K		/* actual page size */
 	ld	r10,STK_PARAM(R9)(r1)	/* segment size */
-_GLOBAL(ht64_call_hpte_insert1)
+.globl ht64_call_hpte_insert1
+ht64_call_hpte_insert1:
 	bl	.			/* patched by htab_finish_init() */
 	cmpdi	0,r3,0
 	bge	ht64_pte_insert_ok	/* Insertion successful */
@@ -881,7 +890,8 @@ _GLOBAL(ht64_call_hpte_insert1)
 	li	r8,MMU_PAGE_64K
 	li	r9,MMU_PAGE_64K		/* actual page size */
 	ld	r10,STK_PARAM(R9)(r1)	/* segment size */
-_GLOBAL(ht64_call_hpte_insert2)
+.globl ht64_call_hpte_insert2
+ht64_call_hpte_insert2:
 	bl	.			/* patched by htab_finish_init() */
 	cmpdi	0,r3,0
 	bge+	ht64_pte_insert_ok	/* Insertion successful */
@@ -898,7 +908,8 @@ _GLOBAL(ht64_call_hpte_insert2)
 2:	and	r0,r5,r27
 	rldicr	r3,r0,3,63-3	/* r0 = (hash & mask) << 3 */
 	/* Call ppc_md.hpte_remove */
-_GLOBAL(ht64_call_hpte_remove)
+.globl ht64_call_hpte_remove
+ht64_call_hpte_remove:
 	bl	.			/* patched by htab_finish_init() */
 
 	/* Try all again */
@@ -952,7 +963,8 @@ ht64_modify_pte:
 	li	r7,MMU_PAGE_64K		/* actual page size */
 	ld	r8,STK_PARAM(R9)(r1)	/* segment size */
 	ld	r9,STK_PARAM(R8)(r1)	/* get "local" param */
-_GLOBAL(ht64_call_hpte_updatepp)
+.globl ht64_call_hpte_updatepp
+ht64_call_hpte_updatepp:
 	bl	.			/* patched by htab_finish_init() */
 
 	/* if we failed because typically the HPTE wasn't really here

arch/powerpc/mm/hash_utils_64.c

@@ -622,47 +622,43 @@ int remove_section_mapping(unsigned long start, unsigned long end)
 }
 #endif /* CONFIG_MEMORY_HOTPLUG */
 
-#define FUNCTION_TEXT(A)	((*(unsigned long *)(A)))
+extern u32 htab_call_hpte_insert1[];
+extern u32 htab_call_hpte_insert2[];
+extern u32 htab_call_hpte_remove[];
+extern u32 htab_call_hpte_updatepp[];
+extern u32 ht64_call_hpte_insert1[];
+extern u32 ht64_call_hpte_insert2[];
+extern u32 ht64_call_hpte_remove[];
+extern u32 ht64_call_hpte_updatepp[];
 
 static void __init htab_finish_init(void)
 {
-	extern unsigned int *htab_call_hpte_insert1;
-	extern unsigned int *htab_call_hpte_insert2;
-	extern unsigned int *htab_call_hpte_remove;
-	extern unsigned int *htab_call_hpte_updatepp;
-
 #ifdef CONFIG_PPC_HAS_HASH_64K
-	extern unsigned int *ht64_call_hpte_insert1;
-	extern unsigned int *ht64_call_hpte_insert2;
-	extern unsigned int *ht64_call_hpte_remove;
-	extern unsigned int *ht64_call_hpte_updatepp;
-
 	patch_branch(ht64_call_hpte_insert1,
-		FUNCTION_TEXT(ppc_md.hpte_insert),
+		ppc_function_entry(ppc_md.hpte_insert),
 		BRANCH_SET_LINK);
 	patch_branch(ht64_call_hpte_insert2,
-		FUNCTION_TEXT(ppc_md.hpte_insert),
+		ppc_function_entry(ppc_md.hpte_insert),
 		BRANCH_SET_LINK);
 	patch_branch(ht64_call_hpte_remove,
-		FUNCTION_TEXT(ppc_md.hpte_remove),
+		ppc_function_entry(ppc_md.hpte_remove),
 		BRANCH_SET_LINK);
 	patch_branch(ht64_call_hpte_updatepp,
-		FUNCTION_TEXT(ppc_md.hpte_updatepp),
+		ppc_function_entry(ppc_md.hpte_updatepp),
 		BRANCH_SET_LINK);
-
 #endif /* CONFIG_PPC_HAS_HASH_64K */
 
 	patch_branch(htab_call_hpte_insert1,
-		FUNCTION_TEXT(ppc_md.hpte_insert),
+		ppc_function_entry(ppc_md.hpte_insert),
 		BRANCH_SET_LINK);
 	patch_branch(htab_call_hpte_insert2,
-		FUNCTION_TEXT(ppc_md.hpte_insert),
+		ppc_function_entry(ppc_md.hpte_insert),
 		BRANCH_SET_LINK);
 	patch_branch(htab_call_hpte_remove,
-		FUNCTION_TEXT(ppc_md.hpte_remove),
+		ppc_function_entry(ppc_md.hpte_remove),
 		BRANCH_SET_LINK);
 	patch_branch(htab_call_hpte_updatepp,
-		FUNCTION_TEXT(ppc_md.hpte_updatepp),
+		ppc_function_entry(ppc_md.hpte_updatepp),
 		BRANCH_SET_LINK);
 }
 

arch/powerpc/mm/slb.c

@@ -256,10 +256,14 @@ static inline void patch_slb_encoding(unsigned int *insn_addr,
 	patch_instruction(insn_addr, insn);
 }
 
+extern u32 slb_compare_rr_to_size[];
+extern u32 slb_miss_kernel_load_linear[];
+extern u32 slb_miss_kernel_load_io[];
+extern u32 slb_compare_rr_to_size[];
+extern u32 slb_miss_kernel_load_vmemmap[];
+
 void slb_set_size(u16 size)
 {
-	extern unsigned int *slb_compare_rr_to_size;
-
 	if (mmu_slb_size == size)
 		return;
 
@@ -272,11 +276,7 @@ void slb_initialize(void)
 	unsigned long linear_llp, vmalloc_llp, io_llp;
 	unsigned long lflags, vflags;
 	static int slb_encoding_inited;
-	extern unsigned int *slb_miss_kernel_load_linear;
-	extern unsigned int *slb_miss_kernel_load_io;
-	extern unsigned int *slb_compare_rr_to_size;
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
-	extern unsigned int *slb_miss_kernel_load_vmemmap;
 	unsigned long vmemmap_llp;
 #endif
 

arch/powerpc/mm/slb_low.S

@@ -59,7 +59,8 @@ _GLOBAL(slb_allocate_realmode)
 	/* Linear mapping encoding bits, the "li" instruction below will
 	 * be patched by the kernel at boot
 	 */
-_GLOBAL(slb_miss_kernel_load_linear)
+.globl slb_miss_kernel_load_linear
+slb_miss_kernel_load_linear:
 	li	r11,0
 	/*
 	 * context = (MAX_USER_CONTEXT) + ((ea >> 60) - 0xc) + 1
@@ -79,7 +80,8 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_1T_SEGMENT)
 	/* Check virtual memmap region. To be patches at kernel boot */
 	cmpldi	cr0,r9,0xf
 	bne	1f
-_GLOBAL(slb_miss_kernel_load_vmemmap)
+.globl slb_miss_kernel_load_vmemmap
+slb_miss_kernel_load_vmemmap:
 	li	r11,0
 	b	6f
 1:
@@ -95,7 +97,8 @@ _GLOBAL(slb_miss_kernel_load_vmemmap)
 	b	6f
 5:
 	/* IO mapping */
-	_GLOBAL(slb_miss_kernel_load_io)
+.globl slb_miss_kernel_load_io
+slb_miss_kernel_load_io:
 	li	r11,0
 6:
 	/*
@@ -250,7 +253,8 @@ slb_finish_load:
 7:	ld	r10,PACASTABRR(r13)
 	addi	r10,r10,1
 	/* This gets soft patched on boot. */
-_GLOBAL(slb_compare_rr_to_size)
+.globl slb_compare_rr_to_size
+slb_compare_rr_to_size:
 	cmpldi	r10,0
 
 	blt+	4f

arch/powerpc/platforms/85xx/smp.c

@@ -27,6 +27,7 @@
 #include <asm/cacheflush.h>
 #include <asm/dbell.h>
 #include <asm/fsl_guts.h>
+#include <asm/code-patching.h>
 
 #include <sysdev/fsl_soc.h>
 #include <sysdev/mpic.h>
@@ -267,7 +268,7 @@ static int smp_85xx_kick_cpu(int nr)
 	flush_spin_table(spin_table);
 	out_be32(&spin_table->pir, hw_cpu);
 	out_be64((u64 *)(&spin_table->addr_h),
-	  __pa((u64)*((unsigned long long *)generic_secondary_smp_init)));
+		__pa(ppc_function_entry(generic_secondary_smp_init)));
 	flush_spin_table(spin_table);
 #endif
 

arch/powerpc/platforms/cell/smp.c

@@ -40,6 +40,7 @@
 #include <asm/firmware.h>
 #include <asm/rtas.h>
 #include <asm/cputhreads.h>
+#include <asm/code-patching.h>
 
 #include "interrupt.h"
 #include <asm/udbg.h>
@@ -70,8 +71,8 @@ static cpumask_t of_spin_map;
 static inline int smp_startup_cpu(unsigned int lcpu)
 {
 	int status;
-	unsigned long start_here = __pa((u32)*((unsigned long *)
-					       generic_secondary_smp_init));
+	unsigned long start_here =
+			__pa(ppc_function_entry(generic_secondary_smp_init));
 	unsigned int pcpu;
 	int start_cpu;
 

arch/powerpc/platforms/pasemi/powersave.S

@@ -66,7 +66,7 @@ sleep_common:
 	std	r3, 48(r1)
 
 	/* Only do power savings when in astate 0 */
-	bl	.check_astate
+	bl	check_astate
 	cmpwi	r3,0
 	bne	1f
 

arch/powerpc/platforms/powernv/opal-takeover.S

@@ -21,11 +21,13 @@
 _GLOBAL(opal_query_takeover)
 	mfcr	r0
 	stw	r0,8(r1)
+	stdu	r1,-STACKFRAMESIZE(r1)
 	std	r3,STK_PARAM(R3)(r1)
 	std	r4,STK_PARAM(R4)(r1)
 	li	r3,H_HAL_TAKEOVER
 	li	r4,H_HAL_TAKEOVER_QUERY_MAGIC
 	HVSC
+	addi	r1,r1,STACKFRAMESIZE
 	ld	r10,STK_PARAM(R3)(r1)
 	std	r4,0(r10)
 	ld	r10,STK_PARAM(R4)(r1)

arch/powerpc/platforms/powernv/opal-wrappers.S

@@ -32,7 +32,7 @@
 	std	r12,PACASAVEDMSR(r13);	\
 	andc	r12,r12,r0;		\
 	mtmsrd	r12,1;			\
-	LOAD_REG_ADDR(r0,.opal_return);	\
+	LOAD_REG_ADDR(r0,opal_return);	\
 	mtlr	r0;			\
 	li	r0,MSR_DR|MSR_IR|MSR_LE;\
 	andc	r12,r12,r0;		\
@@ -44,7 +44,7 @@
 	mtspr	SPRN_HSRR0,r12;		\
 	hrfid
 
-_STATIC(opal_return)
+opal_return:
 	/*
 	 * Fixup endian on OPAL return... we should be able to simplify
 	 * this by instead converting the below trampoline to a set of

arch/powerpc/platforms/powernv/smp.c

@@ -31,6 +31,7 @@
 #include <asm/xics.h>
 #include <asm/opal.h>
 #include <asm/runlatch.h>
+#include <asm/code-patching.h>
 
 #include "powernv.h"
 
@@ -50,8 +51,8 @@ static void pnv_smp_setup_cpu(int cpu)
 int pnv_smp_kick_cpu(int nr)
 {
 	unsigned int pcpu = get_hard_smp_processor_id(nr);
-	unsigned long start_here = __pa(*((unsigned long *)
-					  generic_secondary_smp_init));
+	unsigned long start_here =
+			__pa(ppc_function_entry(generic_secondary_smp_init));
 	long rc;
 
 	BUG_ON(nr < 0 || nr >= NR_CPUS);

arch/powerpc/platforms/pseries/hvCall.S

@@ -49,7 +49,7 @@ END_FTR_SECTION(0, 1);						\
 	std	r0,16(r1);					\
 	addi	r4,r1,STK_PARAM(FIRST_REG);			\
 	stdu	r1,-STACK_FRAME_OVERHEAD(r1);			\
-	bl	.__trace_hcall_entry;				\
+	bl	__trace_hcall_entry;				\
 	addi	r1,r1,STACK_FRAME_OVERHEAD;			\
 	ld	r0,16(r1);					\
 	ld	r3,STK_PARAM(R3)(r1);				\
@@ -83,7 +83,7 @@ END_FTR_SECTION(0, 1);						\
 	mr	r3,r6;						\
 	std	r0,16(r1);					\
 	stdu	r1,-STACK_FRAME_OVERHEAD(r1);			\
-	bl	.__trace_hcall_exit;				\
+	bl	__trace_hcall_exit;				\
 	addi	r1,r1,STACK_FRAME_OVERHEAD;			\
 	ld	r0,16(r1);					\
 	ld	r3,STK_PARAM(R3)(r1);				\

arch/powerpc/platforms/pseries/smp.c

@@ -44,6 +44,7 @@
 #include <asm/xics.h>
 #include <asm/dbell.h>
 #include <asm/plpar_wrappers.h>
+#include <asm/code-patching.h>
 
 #include "pseries.h"
 #include "offline_states.h"
@@ -96,8 +97,8 @@ int smp_query_cpu_stopped(unsigned int pcpu)
 static inline int smp_startup_cpu(unsigned int lcpu)
 {
 	int status;
-	unsigned long start_here = __pa((u32)*((unsigned long *)
-					       generic_secondary_smp_init));
+	unsigned long start_here =
+			__pa(ppc_function_entry(generic_secondary_smp_init));
 	unsigned int pcpu;
 	int start_cpu;
 

arch/powerpc/platforms/wsp/scom_smp.c

@@ -20,6 +20,7 @@
 #include <asm/reg_a2.h>
 #include <asm/scom.h>
 #include <asm/udbg.h>
+#include <asm/code-patching.h>
 
 #include "wsp.h"
 
@@ -405,7 +406,7 @@ int a2_scom_startup_cpu(unsigned int lcpu, int thr_idx, struct device_node *np)
 			goto fail;
 	}
 
-	start_here = *(unsigned long *)(core_setup ? generic_secondary_smp_init
+	start_here = ppc_function_entry(core_setup ? generic_secondary_smp_init
 					: generic_secondary_thread_init);
 	pr_devel("CPU%d entry point at 0x%lx...\n", lcpu, start_here);
 

tools/testing/selftests/powerpc/copyloops/asm/ppc_asm.h

@@ -46,12 +46,15 @@
 #define R20 r20
 #define R21 r21
 #define R22 r22
+#define R29 r29
+#define R30 r30
+#define R31 r31
 
 #define STACKFRAMESIZE	256
-#define STK_PARAM(i)	(48 + ((i)-3)*8)
 #define STK_REG(i)	(112 + ((i)-14)*8)
 
 #define _GLOBAL(A) FUNC_START(test_ ## A)
+#define _GLOBAL_TOC(A) _GLOBAL(A)
 
 #define PPC_MTOCRF(A, B)	mtocrf A, B