[PATCH v6 0/9] ftrace with regs + live patching for ppc64 LE (ABI v2)

@@ -1206,7 +1206,12 @@ _GLOBAL(enter_prom)
 #ifdef CONFIG_DYNAMIC_FTRACE
 _GLOBAL(mcount)
 _GLOBAL(_mcount)
-	blr
+	std	r0,LRSAVE(r1) /* gcc6 does this _after_ this call _only_ */
+	mflr	r0
+	mtctr	r0
+	ld	r0,LRSAVE(r1)
+	mtlr	r0
+	bctr
 
 _GLOBAL_TOC(ftrace_caller)
 	/* Taken from output of objdump from lib64/glibc */

@@ -1262,13 +1267,28 @@ _GLOBAL(ftrace_stub)
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 _GLOBAL(ftrace_graph_caller)
+#ifdef CC_USING_MPROFILE_KERNEL
+	/* with -mprofile-kernel, parameter regs are still alive at _mcount */
+	std	r10, 104(r1)
+	std	r9, 96(r1)
+	std	r8, 88(r1)
+	std	r7, 80(r1)
+	std	r6, 72(r1)
+	std	r5, 64(r1)
+	std	r4, 56(r1)
+	std	r3, 48(r1)
+	mfctr	r4		/* ftrace_caller has moved local addr here */
+	std	r4, 40(r1)
+	mflr	r3		/* ftrace_caller has restored LR from stack */
+#else
 	/* load r4 with local address */
 	ld	r4, 128(r1)
-	subi	r4, r4, MCOUNT_INSN_SIZE
 
 	/* Grab the LR out of the caller stack frame */
 	ld	r11, 112(r1)
 	ld	r3, 16(r11)
+#endif
+	subi	r4, r4, MCOUNT_INSN_SIZE
 
 	bl	prepare_ftrace_return
 	nop

@@ -1277,6 +1297,26 @@ _GLOBAL(ftrace_graph_caller)
 	 * prepare_ftrace_return gives us the address we divert to.
 	 * Change the LR in the callers stack frame to this.
 	 */
+
+#ifdef CC_USING_MPROFILE_KERNEL
+	mtlr	r3
+
+	ld	r0, 40(r1)
+	mtctr	r0
+	ld	r10, 104(r1)
+	ld	r9, 96(r1)
+	ld	r8, 88(r1)
+	ld	r7, 80(r1)
+	ld	r6, 72(r1)
+	ld	r5, 64(r1)
+	ld	r4, 56(r1)
+	ld	r3, 48(r1)
+
+	addi	r1, r1, 112
+	mflr	r0
+	std	r0, LRSAVE(r1)
+	bctr
+#else
 	ld	r11, 112(r1)
 	std	r3, 16(r11)
 

@@ -1284,6 +1324,7 @@ _GLOBAL(ftrace_graph_caller)
 	mtlr	r0
 	addi	r1, r1, 112
 	blr
+#endif
 
 _GLOBAL(return_to_handler)
 	/* need to save return values */

@@ -306,11 +306,19 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 	 * The load offset is different depending on the ABI. For simplicity
 	 * just mask it out when doing the compare.
 	 */
+#ifndef CC_USING_MPROFILE_KERNEL
 	if ((op[0] != 0x48000008) || ((op[1] & 0xffff0000) != 0xe8410000)) {
-		pr_err("Unexpected call sequence: %x %x\n", op[0], op[1]);
+		pr_err("Unexpected call sequence at %p: %x %x\n",
+		ip, op[0], op[1]);
 		return -EINVAL;
 	}
-
+#else
+	/* look for patched "NOP" on ppc64 with -mprofile-kernel */
+	if (op[0] != 0x60000000) {
+		pr_err("Unexpected call at %p: %x\n", ip, op[0]);
+		return -EINVAL;
+	}
+#endif
 	/* If we never set up a trampoline to ftrace_caller, then bail */
 	if (!rec->arch.mod->arch.tramp) {
 		pr_err("No ftrace trampoline\n");

@@ -475,6 +475,20 @@ static unsigned long stub_for_addr(Elf64_Shdr *sechdrs,
 static int restore_r2(u32 *instruction, struct module *me)
 {
 	if (*instruction != PPC_INST_NOP) {
+#ifdef CC_USING_MPROFILE_KERNEL
+		/* -mprofile_kernel sequence starting with
+		 * mflr r0 and maybe std r0, LRSAVE(r1)
+		 */
+		if ((instruction[-3] == 0x7c0802a6 &&
+		    instruction[-2] == 0xf8010010) ||
+		    instruction[-2] == 0x7c0802a6) {
+			/* Nothing to be done here, it's an _mcount
+			 * call location and r2 will have to be
+			 * restored in the _mcount function.
+			 */
+			return 1;
+		};
+#endif
 		pr_err("%s: Expect noop after relocate, got %08x\n",
 		       me->name, *instruction);
 		return 0;

@@ -46,6 +46,8 @@
 extern void _mcount(void);
 
 #ifdef CONFIG_DYNAMIC_FTRACE
+# define FTRACE_ADDR ((unsigned long)ftrace_caller)
+# define FTRACE_REGS_ADDR FTRACE_ADDR
 static inline unsigned long ftrace_call_adjust(unsigned long addr)
 {
        /* reloction of mcount call site is the same as the address */

@@ -58,6 +60,9 @@ struct dyn_arch_ftrace {
 #endif /*  CONFIG_DYNAMIC_FTRACE */
 #endif /* __ASSEMBLY__ */
 
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+#define ARCH_SUPPORTS_FTRACE_OPS 1
+#endif
 #endif
 
 #if defined(CONFIG_FTRACE_SYSCALLS) && defined(CONFIG_PPC64) && !defined(__ASSEMBLY__)

@@ -1213,6 +1213,7 @@ _GLOBAL(_mcount)
 	mtlr	r0
 	bctr
 
+#ifndef CC_USING_MPROFILE_KERNEL
 _GLOBAL_TOC(ftrace_caller)
 	/* Taken from output of objdump from lib64/glibc */
 	mflr	r3

@@ -1234,6 +1235,83 @@ _GLOBAL(ftrace_graph_stub)
 	ld	r0, 128(r1)
 	mtlr	r0
 	addi	r1, r1, 112
+#else
+_GLOBAL(ftrace_caller)
+	std	r0,LRSAVE(r1)
+#if defined(_CALL_ELF) && _CALL_ELF == 2
+	mflr	r0
+	bl	2f
+2:	mflr	r12
+	mtlr	r0
+	mr      r0,r2   /* save callee's TOC */
+	addis	r2,r12,(.TOC.-ftrace_caller-12)@ha
+	addi    r2,r2,(.TOC.-ftrace_caller-12)@l
+#else
+	mr	r0,r2
+#endif
+	ld	r12,LRSAVE(r1)	/* get caller's address */
+
+	stdu	r1,-SWITCH_FRAME_SIZE(r1)
+
+	std     r12, _LINK(r1)
+	SAVE_8GPRS(0,r1)
+	std	r0, 24(r1)	/* save TOC */
+	SAVE_8GPRS(8,r1)
+	SAVE_8GPRS(16,r1)
+	SAVE_8GPRS(24,r1)
+
+	addis	r3,r2,function_trace_op@toc@ha
+	addi	r3,r3,function_trace_op@toc@l
+	ld	r5,0(r3)
+
+	mflr    r3
+	std     r3, _NIP(r1)
+	std	r3, 16(r1)
+	subi    r3, r3, MCOUNT_INSN_SIZE
+	mfmsr   r4
+	std     r4, _MSR(r1)
+	mfctr   r4
+	std     r4, _CTR(r1)
+	mfxer   r4
+	std     r4, _XER(r1)
+	mr	r4, r12
+	addi    r6, r1 ,STACK_FRAME_OVERHEAD
+
+.globl ftrace_call
+ftrace_call:
+	bl	ftrace_stub
+	nop
+
+	ld	r3, _NIP(r1)
+	mtlr	r3
+
+	REST_8GPRS(0,r1)
+	REST_8GPRS(8,r1)
+	REST_8GPRS(16,r1)
+	REST_8GPRS(24,r1)
+
+	addi r1, r1, SWITCH_FRAME_SIZE
+
+	ld	r12, LRSAVE(r1)  /* get caller's address */
+	mtlr	r12
+	mr	r2,r0		/* restore callee's TOC */
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	stdu	r1, -112(r1)
+.globl ftrace_graph_call
+ftrace_graph_call:
+	b	ftrace_graph_stub
+_GLOBAL(ftrace_graph_stub)
+	addi	r1, r1, 112
+#endif
+
+	mflr	r0		/* move this LR to CTR */
+	mtctr	r0
+
+	ld	r0,LRSAVE(r1)	/* restore callee's lr at _mcount site */
+	mtlr	r0
+	bctr			/* jump after _mcount site */
+#endif /* CC_USING_MPROFILE_KERNEL */
 _GLOBAL(ftrace_stub)
 	blr
 #else

@@ -61,8 +61,11 @@ ftrace_modify_code(unsigned long ip, unsigned int old, unsigned int new)
 		return -EFAULT;
 
 	/* Make sure it is what we expect it to be */
-	if (replaced != old)
+	if (replaced != old) {
+		pr_err("%p: replaced (%#x) != old (%#x)",
+		(void *)ip, replaced, old);
 		return -EINVAL;
+	}
 
 	/* replace the text with the new text */
 	if (patch_instruction((unsigned int *)ip, new))

@@ -106,14 +109,16 @@ static int
 __ftrace_make_nop(struct module *mod,
 		  struct dyn_ftrace *rec, unsigned long addr)
 {
-	unsigned int op;
+	unsigned int op, op0, op1, pop;
 	unsigned long entry, ptr;
 	unsigned long ip = rec->ip;
 	void *tramp;
 
 	/* read where this goes */
-	if (probe_kernel_read(&op, (void *)ip, sizeof(int)))
+	if (probe_kernel_read(&op, (void *)ip, sizeof(int))) {
+		pr_err("Fetching opcode failed.\n");
 		return -EFAULT;
+	}
 
 	/* Make sure that that this is still a 24bit jump */
 	if (!is_bl_op(op)) {

@@ -158,10 +163,46 @@ __ftrace_make_nop(struct module *mod,
 	 *
 	 * Use a b +8 to jump over the load.
 	 */
-	op = 0x48000008;	/* b +8 */
 
-	if (patch_instruction((unsigned int *)ip, op))
+	pop = 0x48000008;	/* b +8 */
+
+	/*
+	 * Check what is in the next instruction. We can see ld r2,40(r1), but
+	 * on first pass after boot we will see mflr r0.
+	 */
+	if (probe_kernel_read(&op, (void *)(ip+4), MCOUNT_INSN_SIZE)) {
+		pr_err("Fetching op failed.\n");
+		return -EFAULT;
+	}
+
+	if (op != 0xe8410028) { /* ld r2,STACK_OFFSET(r1) */
+
+		if (probe_kernel_read(&op0, (void *)(ip-8), MCOUNT_INSN_SIZE)) {
+			pr_err("Fetching op0 failed.\n");
+			return -EFAULT;
+		}
+
+		if (probe_kernel_read(&op1, (void *)(ip-4), MCOUNT_INSN_SIZE)) {
+			pr_err("Fetching op1 failed.\n");
+			return -EFAULT;
+		}
+
+		/* mflr r0 ; std r0,LRSAVE(r1) */
+		if (op0 != 0x7c0802a6 && op1 != 0xf8010010) {
+			pr_err("Unexpected instructions around bl\n"
+				"when enabling dynamic ftrace!\t"
+				"(%08x,%08x,bl,%08x)\n", op0, op1, op);
+			return -EINVAL;
+		}
+
+		/* When using -mkernel_profile there is no load to jump over */
+		pop = PPC_INST_NOP;
+	}
+
+	if (patch_instruction((unsigned int *)ip, pop)) {
+		pr_err("Patching NOP failed.\n");
 		return -EPERM;
+	}
 
 	return 0;
 }

@@ -287,6 +328,13 @@ int ftrace_make_nop(struct module *mod,
 
 #ifdef CONFIG_MODULES
 #ifdef CONFIG_PPC64
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
+			unsigned long addr)
+{
+	return ftrace_make_call(rec, addr);
+}
+#endif
 static int
 __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 {

@@ -338,7 +386,7 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 
 	return 0;
 }
-#else
+#else  /* !CONFIG_PPC64: */
 static int
 __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 {

@@ -138,12 +138,25 @@ static u32 ppc64_stub_insns[] = {
 	0x4e800420			/* bctr */
 };
 
+#ifdef CC_USING_MPROFILE_KERNEL
+/* In case of _mcount calls or dynamic ftracing, Do not save the
+ * current callee's TOC (in R2) again into the original caller's stack
+ * frame during this trampoline hop. The stack frame already holds
+ * that of the original caller.  _mcount and ftrace_caller will take
+ * care of this TOC value themselves.
+ */
+#define SQUASH_TOC_SAVE_INSN(trampoline_addr) \
+	(((struct ppc64_stub_entry *)(trampoline_addr))->jump[2] = PPC_INST_NOP)
+#else
+#define SQUASH_TOC_SAVE_INSN(trampoline_addr)
+#endif
+
 #ifdef CONFIG_DYNAMIC_FTRACE
 
 static u32 ppc64_stub_mask[] = {
 	0xffff0000,
 	0xffff0000,
-	0xffffffff,
+	0x00000000,
 	0xffffffff,
 #if !defined(_CALL_ELF) || _CALL_ELF != 2
 	0xffffffff,

@@ -170,6 +183,9 @@ bool is_module_trampoline(u32 *p)
 		if ((insna & mask) != (insnb & mask))
 			return false;
 	}
+	if (insns[2] != ppc64_stub_insns[2] &&
+	    insns[2] != PPC_INST_NOP)
+		return false;
 
 	return true;
 }

@@ -619,6 +635,9 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 					return -ENOENT;
 				if (!restore_r2((u32 *)location + 1, me))
 					return -ENOEXEC;
+				/* Squash the TOC saver for profiler calls */
+				if (!strcmp("_mcount", strtab+sym->st_name))
+					SQUASH_TOC_SAVE_INSN(value);
 			} else
 				value += local_entry_offset(sym);
 

@@ -679,6 +698,10 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 	me->arch.tramp = stub_for_addr(sechdrs,
 				       (unsigned long)ftrace_caller,
 				       me);
+	/* ftrace_caller will take care of the TOC;
+	 * do not clobber original caller's value.
+	 */
+	SQUASH_TOC_SAVE_INSN(me->arch.tramp);
 #endif
 
 	return 0;

@@ -511,20 +511,12 @@ void ftrace_replace_code(int enable)
 	}
 }
 
+/* Use the default ftrace_modify_all_code, but without
+ * stop_machine().
+ */
 void arch_ftrace_update_code(int command)
 {
-	if (command & FTRACE_UPDATE_CALLS)
-		ftrace_replace_code(1);
-	else if (command & FTRACE_DISABLE_CALLS)
-		ftrace_replace_code(0);
-
-	if (command & FTRACE_UPDATE_TRACE_FUNC)
-		ftrace_update_ftrace_func(ftrace_trace_function);
-
-	if (command & FTRACE_START_FUNC_RET)
-		ftrace_enable_ftrace_graph_caller();
-	else if (command & FTRACE_STOP_FUNC_RET)
-		ftrace_disable_ftrace_graph_caller();
+	ftrace_modify_all_code(command);
 }
 
 int __init ftrace_dyn_arch_init(void)

@@ -97,8 +97,10 @@ config PPC
 	select OF_RESERVED_MEM
 	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_DYNAMIC_FTRACE
+	select HAVE_DYNAMIC_FTRACE_WITH_REGS if PPC64 && CPU_LITTLE_ENDIAN
 	select HAVE_FUNCTION_TRACER
 	select HAVE_FUNCTION_GRAPH_TRACER
+	select HAVE_MPROFILE_KERNEL if PPC64 && CPU_LITTLE_ENDIAN
 	select SYSCTL_EXCEPTION_TRACE
 	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select VIRT_TO_BUS if !PPC64

@@ -133,6 +133,16 @@ else
 CFLAGS-$(CONFIG_GENERIC_CPU) += -mcpu=powerpc64
 endif
 
+ifeq ($(CONFIG_PPC64),y)
+ifdef CONFIG_HAVE_MPROFILE_KERNEL
+CC_USING_MPROFILE_KERNEL := $(call cc-option,-mprofile-kernel)
+ifdef CC_USING_MPROFILE_KERNEL
+CC_FLAGS_FTRACE	:= -pg $(CC_USING_MPROFILE_KERNEL)
+KBUILD_CPPFLAGS	+= -DCC_USING_MPROFILE_KERNEL
+endif
+endif
+endif
+
 CFLAGS-$(CONFIG_CELL_CPU) += $(call cc-option,-mcpu=cell)
 CFLAGS-$(CONFIG_POWER4_CPU) += $(call cc-option,-mcpu=power4)
 CFLAGS-$(CONFIG_POWER5_CPU) += $(call cc-option,-mcpu=power5)

@@ -52,6 +52,11 @@ config HAVE_FENTRY
 	help
 	  Arch supports the gcc options -pg with -mfentry
 
+config HAVE_MPROFILE_KERNEL
+	bool
+	help
+	  Arch supports the gcc options -pg with -mprofile-kernel
+
 config HAVE_C_RECORDMCOUNT
 	bool
 	help

@@ -16,14 +16,14 @@ endif
 
 ifdef CONFIG_FUNCTION_TRACER
 # Do not trace early boot code
-CFLAGS_REMOVE_cputable.o = -pg -mno-sched-epilog
-CFLAGS_REMOVE_prom_init.o = -pg -mno-sched-epilog
-CFLAGS_REMOVE_btext.o = -pg -mno-sched-epilog
-CFLAGS_REMOVE_prom.o = -pg -mno-sched-epilog
+CFLAGS_REMOVE_cputable.o = -pg -mno-sched-epilog -mprofile-kernel
+CFLAGS_REMOVE_prom_init.o = -pg -mno-sched-epilog -mprofile-kernel
+CFLAGS_REMOVE_btext.o = -pg -mno-sched-epilog -mprofile-kernel
+CFLAGS_REMOVE_prom.o = -pg -mno-sched-epilog -mprofile-kernel
 # do not trace tracer code
-CFLAGS_REMOVE_ftrace.o = -pg -mno-sched-epilog
+CFLAGS_REMOVE_ftrace.o = -pg -mno-sched-epilog -mprofile-kernel
 # timers used by tracing
-CFLAGS_REMOVE_time.o = -pg -mno-sched-epilog
+CFLAGS_REMOVE_time.o = -pg -mno-sched-epilog -mprofile-kernel
 endif
 
 obj-y				:= cputable.o ptrace.o syscalls.o \

@@ -733,7 +733,7 @@ static inline void __switch_to_tm(struct task_struct *prev)
  * don't know which of the checkpointed state and the transactional
  * state to use.
  */
-void restore_tm_state(struct pt_regs *regs)
+notrace void restore_tm_state(struct pt_regs *regs)
 {
 	unsigned long msr_diff;
 

@@ -205,7 +205,7 @@ static int mm_fault_error(struct pt_regs *regs, unsigned long addr, int fault)
  * The return value is 0 if the fault was handled, or the signal
  * number if this is a kernel fault that can't be handled here.
  */
-int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,
+notrace int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,
 			    unsigned long error_code)
 {
 	enum ctx_state prev_state = exception_enter();

@@ -849,7 +849,7 @@ void early_init_mmu_secondary(void)
 /*
  * Called by asm hashtable.S for doing lazy icache flush
  */
-unsigned int hash_page_do_lazy_icache(unsigned int pp, pte_t pte, int trap)
+notrace unsigned int hash_page_do_lazy_icache(unsigned int pp, pte_t pte, int trap)
 {
 	struct page *page;
 

@@ -870,7 +870,7 @@ unsigned int hash_page_do_lazy_icache(unsigned int pp, pte_t pte, int trap)
 }
 
 #ifdef CONFIG_PPC_MM_SLICES
-static unsigned int get_paca_psize(unsigned long addr)
+static notrace unsigned int get_paca_psize(unsigned long addr)
 {
 	u64 lpsizes;
 	unsigned char *hpsizes;

@@ -899,7 +899,7 @@ unsigned int get_paca_psize(unsigned long addr)
  * For now this makes the whole process use 4k pages.
  */
 #ifdef CONFIG_PPC_64K_PAGES
-void demote_segment_4k(struct mm_struct *mm, unsigned long addr)
+notrace void demote_segment_4k(struct mm_struct *mm, unsigned long addr)
 {
 	if (get_slice_psize(mm, addr) == MMU_PAGE_4K)
 		return;

@@ -920,7 +920,7 @@ void demote_segment_4k(struct mm_struct *mm, unsigned long addr)
  * Result is 0: full permissions, _PAGE_RW: read-only,
  * _PAGE_USER or _PAGE_USER|_PAGE_RW: no access.
  */
-static int subpage_protection(struct mm_struct *mm, unsigned long ea)
+static notrace int subpage_protection(struct mm_struct *mm, unsigned long ea)
 {
 	struct subpage_prot_table *spt = &mm->context.spt;
 	u32 spp = 0;

@@ -968,7 +968,7 @@ void hash_failure_debug(unsigned long ea, unsigned long access,
 		trap, vsid, ssize, psize, lpsize, pte);
 }
 
-static void check_paca_psize(unsigned long ea, struct mm_struct *mm,
+static notrace void check_paca_psize(unsigned long ea, struct mm_struct *mm,
 			     int psize, bool user_region)
 {
 	if (user_region) {

@@ -990,7 +990,7 @@ static void check_paca_psize(unsigned long ea, struct mm_struct *mm,
  * -1 - critical hash insertion error
  * -2 - access not permitted by subpage protection mechanism
  */
-int hash_page_mm(struct mm_struct *mm, unsigned long ea,
+notrace int hash_page_mm(struct mm_struct *mm, unsigned long ea,
 		 unsigned long access, unsigned long trap,
 		 unsigned long flags)
 {

@@ -1187,7 +1187,7 @@ bail:
 }
 EXPORT_SYMBOL_GPL(hash_page_mm);
 
-int hash_page(unsigned long ea, unsigned long access, unsigned long trap,
+notrace int hash_page(unsigned long ea, unsigned long access, unsigned long trap,
 	      unsigned long dsisr)
 {
 	unsigned long flags = 0;

@@ -1289,7 +1289,7 @@ out_exit:
 /* WARNING: This is called from hash_low_64.S, if you change this prototype,
  *          do not forget to update the assembly call site !
  */
-void flush_hash_page(unsigned long vpn, real_pte_t pte, int psize, int ssize,
+notrace void flush_hash_page(unsigned long vpn, real_pte_t pte, int psize, int ssize,
 		     unsigned long flags)
 {
 	unsigned long hash, index, shift, hidx, slot;

@@ -1437,7 +1437,7 @@ void low_hash_fault(struct pt_regs *regs, unsigned long address, int rc)
 	exception_exit(prev_state);
 }
 
-long hpte_insert_repeating(unsigned long hash, unsigned long vpn,
+notrace long hpte_insert_repeating(unsigned long hash, unsigned long vpn,
 			   unsigned long pa, unsigned long rflags,
 			   unsigned long vflags, int psize, int ssize)
 {

@@ -18,7 +18,7 @@ extern long hpte_insert_repeating(unsigned long hash, unsigned long vpn,
 				  unsigned long pa, unsigned long rlags,
 				  unsigned long vflags, int psize, int ssize);
 
-int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
+notrace int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
 		     pte_t *ptep, unsigned long trap, unsigned long flags,
 		     int ssize, unsigned int shift, unsigned int mmu_psize)
 {

@@ -942,7 +942,7 @@ static int __init hugetlbpage_init(void)
 #endif
 arch_initcall(hugetlbpage_init);
 
-void flush_dcache_icache_hugepage(struct page *page)
+notrace void flush_dcache_icache_hugepage(struct page *page)
 {
 	int i;
 	void *start;

@@ -975,7 +975,7 @@ void flush_dcache_icache_hugepage(struct page *page)
  * when we have MSR[EE] = 0 but the paca->soft_enabled = 1
  */
 
-pte_t *__find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea,
+notrace pte_t *__find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea,
 				   bool *is_thp, unsigned *shift)
 {
 	pgd_t pgd, *pgdp;

@@ -406,7 +406,7 @@ void flush_dcache_page(struct page *page)
 }
 EXPORT_SYMBOL(flush_dcache_page);
 
-void flush_dcache_icache_page(struct page *page)
+notrace void flush_dcache_icache_page(struct page *page)
 {
 #ifdef CONFIG_HUGETLB_PAGE
 	if (PageCompound(page)) {

@@ -442,7 +442,7 @@ static void page_table_free_rcu(void *table)
 	}
 }
 
-void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift)
+notrace void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift)
 {
 	unsigned long pgf = (unsigned long)table;
 

@@ -96,7 +96,7 @@ static inline void create_shadowed_slbe(unsigned long ea, int ssize,
 		     : "memory" );
 }
 
-static void __slb_flush_and_rebolt(void)
+static notrace void __slb_flush_and_rebolt(void)
 {
 	/* If you change this make sure you change SLB_NUM_BOLTED
 	 * and PR KVM appropriately too. */

@@ -136,7 +136,7 @@ static void __slb_flush_and_rebolt(void)
 		     : "memory");
 }
 
-void slb_flush_and_rebolt(void)
+notrace void slb_flush_and_rebolt(void)
 {
 
 	WARN_ON(!irqs_disabled());

@@ -151,7 +151,7 @@ void slb_flush_and_rebolt(void)
 	get_paca()->slb_cache_ptr = 0;
 }
 
-void slb_vmalloc_update(void)
+notrace void slb_vmalloc_update(void)
 {
 	unsigned long vflags;
 

@@ -76,8 +76,8 @@ static void slice_print_mask(const char *label, struct slice_mask mask) {}
 
 #endif
 
-static struct slice_mask slice_range_to_mask(unsigned long start,
-					     unsigned long len)
+static notrace struct slice_mask slice_range_to_mask(unsigned long start,
+						     unsigned long len)
 {
 	unsigned long end = start + len - 1;
 	struct slice_mask ret = { 0, 0 };

@@ -564,7 +564,7 @@ unsigned long arch_get_unmapped_area_topdown(struct file *filp,
 				       current->mm->context.user_psize, 1);
 }
 
-unsigned int get_slice_psize(struct mm_struct *mm, unsigned long addr)
+notrace unsigned int get_slice_psize(struct mm_struct *mm, unsigned long addr)
 {
 	unsigned char *hpsizes;
 	int index, mask_index;

@@ -645,7 +645,7 @@ void slice_set_user_psize(struct mm_struct *mm, unsigned int psize)
 	spin_unlock_irqrestore(&slice_convert_lock, flags);
 }
 
-void slice_set_range_psize(struct mm_struct *mm, unsigned long start,
+notrace void slice_set_range_psize(struct mm_struct *mm, unsigned long start,
 			   unsigned long len, unsigned int psize)
 {
 	struct slice_mask mask = slice_range_to_mask(start, len);

@@ -0,0 +1,45 @@
+/*
+ * livepatch.h - powerpc-specific Kernel Live Patching Core
+ *
+ * Copyright (C) 2015 SUSE
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef _ASM_POWERPC64_LIVEPATCH_H
+#define _ASM_POWERPC64_LIVEPATCH_H
+
+#include <linux/module.h>
+#include <linux/ftrace.h>
+
+#ifdef CONFIG_LIVEPATCH
+static inline int klp_check_compiler_support(void)
+{
+#if !defined(_CALL_ELF) || _CALL_ELF != 2 || !defined(CC_USING_MPROFILE_KERNEL)
+	return 1;
+#endif
+	return 0;
+}
+
+extern int klp_write_module_reloc(struct module *mod, unsigned long type,
+				   unsigned long loc, unsigned long value);
+
+static inline void klp_arch_set_pc(struct pt_regs *regs, unsigned long ip)
+{
+	regs->nip = ip;
+}
+#else
+#error Live patching support is disabled; check CONFIG_LIVEPATCH
+#endif
+
+#endif /* _ASM_POWERPC64_LIVEPATCH_H */

@@ -1267,6 +1267,9 @@ _GLOBAL(ftrace_caller)
 	mflr    r3
 	std     r3, _NIP(r1)
 	std	r3, 16(r1)
+#ifdef CONFIG_LIVEPATCH
+	mr	r14,r3		/* remember old NIP */
+#endif
 	subi    r3, r3, MCOUNT_INSN_SIZE
 	mfmsr   r4
 	std     r4, _MSR(r1)

@@ -1283,7 +1286,10 @@ ftrace_call:
 	nop
 
 	ld	r3, _NIP(r1)
-	mtlr	r3
+	mtctr	r3		/* prepare to jump there */
+#ifdef CONFIG_LIVEPATCH
+	cmpd	r14,r3		/* has NIP been altered? */
+#endif
 
 	REST_8GPRS(0,r1)
 	REST_8GPRS(8,r1)

@@ -1296,6 +1302,27 @@ ftrace_call:
 	mtlr	r12
 	mr	r2,r0		/* restore callee's TOC */
 
+#ifdef CONFIG_LIVEPATCH
+	beq+	4f		/* likely(old_NIP == new_NIP) */
+
+	/* For a local call, restore this TOC after calling the patch function.
+	 * For a global call, it does not matter what we restore here,
+	 * since the global caller does its own restore right afterwards,
+	 * anyway. Just insert a KLP_return_helper frame in any case,
+	 * so a patch function can always count on the changed stack offsets.
+	 */
+	stdu	r1,-32(r1)	/* open new mini stack frame */
+	std	r0,24(r1)	/* save TOC now, unconditionally. */
+	bl	5f
+5:	mflr	r12
+	addi	r12,r12,(KLP_return_helper+4-.)@l
+	std	r12,LRSAVE(r1)
+	mtlr	r12
+	mfctr	r12		/* allow for TOC calculation in newfunc */
+	bctr
+4:
+#endif
+
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	stdu	r1, -112(r1)
 .globl ftrace_graph_call

@@ -1305,15 +1332,31 @@ _GLOBAL(ftrace_graph_stub)
 	addi	r1, r1, 112
 #endif
 
-	mflr	r0		/* move this LR to CTR */
-	mtctr	r0
-
 	ld	r0,LRSAVE(r1)	/* restore callee's lr at _mcount site */
 	mtlr	r0
 	bctr			/* jump after _mcount site */
 #endif /* CC_USING_MPROFILE_KERNEL */
 _GLOBAL(ftrace_stub)
 	blr
+
+#ifdef CONFIG_LIVEPATCH
+/* Helper function for local calls that are becoming global
+   due to live patching.
+   We can't simply patch the NOP after the original call,
+   because, depending on the consistency model, some kernel
+   threads may still have called the original, local function
+   *without* saving their TOC in the respective stack frame slot,
+   so the decision is made per-thread during function return by
+   maybe inserting a KLP_return_helper frame or not.
+*/
+KLP_return_helper:
+	ld	r2,24(r1)	/* restore TOC (saved by ftrace_caller) */
+	addi r1, r1, 32		/* destroy mini stack frame */
+	ld	r0,LRSAVE(r1)	/* get the real return address */
+	mtlr	r0
+	blr
+#endif
+
 #else
 _GLOBAL_TOC(_mcount)
 	/* Taken from output of objdump from lib64/glibc */

@@ -0,0 +1,38 @@
+/*
+ * livepatch.c - powerpc-specific Kernel Live Patching Core
+ *
+ * Copyright (C) 2015 SUSE
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+#include <linux/module.h>
+#include <asm/livepatch.h>
+
+/**
+ * klp_write_module_reloc() - write a relocation in a module
+ * @mod:       module in which the section to be modified is found
+ * @type:      ELF relocation type (see asm/elf.h)
+ * @loc:       address that the relocation should be written to
+ * @value:     relocation value (sym address + addend)
+ *
+ * This function writes a relocation to the specified location for
+ * a particular module.
+ */
+int klp_write_module_reloc(struct module *mod, unsigned long type,
+			    unsigned long loc, unsigned long value)
+{
+	/* This requires infrastructure changes; we need the loadinfos. */
+	pr_err("lpc_write_module_reloc not yet supported\n");
+	return -ENOSYS;
+}

@@ -162,6 +162,7 @@ config PPC
 	select EDAC_ATOMIC_SCRUB
 	select ARCH_HAS_DMA_SET_COHERENT_MASK
 	select HAVE_ARCH_SECCOMP_FILTER
+	select HAVE_LIVEPATCH if PPC64 && CPU_LITTLE_ENDIAN
 
 config GENERIC_CSUM
 	def_bool CPU_LITTLE_ENDIAN

@@ -1095,3 +1098,5 @@ config PPC_LIB_RHEAP
 	bool
 
 source "arch/powerpc/kvm/Kconfig"
+
+source "kernel/livepatch/Kconfig"

@@ -119,6 +119,7 @@ obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o
 obj-$(CONFIG_FUNCTION_GRAPH_TRACER)	+= ftrace.o
 obj-$(CONFIG_FTRACE_SYSCALLS)	+= ftrace.o
 obj-$(CONFIG_TRACING)		+= trace_clock.o
+obj-$(CONFIG_LIVEPATCH)		+= livepatch.o
 
 ifneq ($(CONFIG_PPC_INDIRECT_PIO),y)
 obj-y				+= iomap.o

@@ -6,8 +6,8 @@ subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror
 
 ccflags-$(CONFIG_PPC64)	:= $(NO_MINIMAL_TOC)
 
-CFLAGS_REMOVE_code-patching.o = -pg
-CFLAGS_REMOVE_feature-fixups.o = -pg
+CFLAGS_REMOVE_code-patching.o = -pg -mprofile-kernel
+CFLAGS_REMOVE_feature-fixups.o = -pg -mprofile-kernel
 
 obj-y += string.o alloc.o crtsavres.o ppc_ksyms.o code-patching.o \
 	 feature-fixups.o