Merge branch 'topic/mprofile-kernel' into next

Merge the ftrace changes to support -mprofile-kernel on ppc64le. This is
a prerequisite for live patching, the support for which will be merged
via the livepatch tree based on this topic branch.

arch/powerpc/Kconfig

@@ -94,6 +94,7 @@ config PPC
 	select OF_RESERVED_MEM
 	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_DYNAMIC_FTRACE
+	select HAVE_DYNAMIC_FTRACE_WITH_REGS if MPROFILE_KERNEL
 	select HAVE_FUNCTION_TRACER
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select SYSCTL_EXCEPTION_TRACE
@@ -373,6 +374,24 @@ config PPC_TRANSACTIONAL_MEM
        ---help---
          Support user-mode Transactional Memory on POWERPC.
 
+config DISABLE_MPROFILE_KERNEL
+	bool "Disable use of mprofile-kernel for kernel tracing"
+	depends on PPC64 && CPU_LITTLE_ENDIAN
+	default y
+	help
+	  Selecting this options disables use of the mprofile-kernel ABI for
+	  kernel tracing. That will cause options such as live patching
+	  (CONFIG_LIVEPATCH) which depend on CONFIG_DYNAMIC_FTRACE_WITH_REGS to
+	  be disabled also.
+
+	  If you have a toolchain which supports mprofile-kernel, then you can
+	  enable this. Otherwise leave it disabled. If you're not sure, say
+	  "N".
+
+config MPROFILE_KERNEL
+	depends on PPC64 && CPU_LITTLE_ENDIAN
+	def_bool !DISABLE_MPROFILE_KERNEL
+
 config IOMMU_HELPER
 	def_bool PPC64
 

arch/powerpc/Makefile

@@ -133,6 +133,21 @@ else
 CFLAGS-$(CONFIG_GENERIC_CPU) += -mcpu=powerpc64
 endif
 
+ifdef CONFIG_MPROFILE_KERNEL
+    ifeq ($(shell $(srctree)/arch/powerpc/scripts/gcc-check-mprofile-kernel.sh $(CC) -I$(srctree)/include -D__KERNEL__),OK)
+        CC_FLAGS_FTRACE := -pg -mprofile-kernel
+        KBUILD_CPPFLAGS += -DCC_USING_MPROFILE_KERNEL
+    else
+        # If the user asked for mprofile-kernel but the toolchain doesn't
+        # support it, emit a warning and deliberately break the build later
+        # with mprofile-kernel-not-supported. We would prefer to make this an
+        # error right here, but then the user would never be able to run
+        # oldconfig to change their configuration.
+        $(warning Compiler does not support mprofile-kernel, set CONFIG_DISABLE_MPROFILE_KERNEL)
+        CC_FLAGS_FTRACE := -mprofile-kernel-not-supported
+    endif
+endif
+
 CFLAGS-$(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)

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

@@ -99,4 +99,25 @@ static inline unsigned long ppc_global_function_entry(void *func)
 #endif
 }
 
+#ifdef CONFIG_PPC64
+/*
+ * Some instruction encodings commonly used in dynamic ftracing
+ * and function live patching.
+ */
+
+/* This must match the definition of STK_GOT in <asm/ppc_asm.h> */
+#if defined(_CALL_ELF) && _CALL_ELF == 2
+#define R2_STACK_OFFSET         24
+#else
+#define R2_STACK_OFFSET         40
+#endif
+
+#define PPC_INST_LD_TOC		(PPC_INST_LD  | ___PPC_RT(__REG_R2) | \
+				 ___PPC_RA(__REG_R1) | R2_STACK_OFFSET)
+
+/* usually preceded by a mflr r0 */
+#define PPC_INST_STD_LR		(PPC_INST_STD | ___PPC_RS(__REG_R0) | \
+				 ___PPC_RA(__REG_R1) | PPC_LR_STKOFF)
+#endif /* CONFIG_PPC64 */
+
 #endif /* _ASM_POWERPC_CODE_PATCHING_H */

arch/powerpc/include/asm/ftrace.h

@@ -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__)

arch/powerpc/include/asm/module.h

@@ -78,10 +78,18 @@ struct mod_arch_specific {
 #    endif	/* MODULE */
 #endif
 
-bool is_module_trampoline(u32 *insns);
-int module_trampoline_target(struct module *mod, u32 *trampoline,
+int module_trampoline_target(struct module *mod, unsigned long trampoline,
 			     unsigned long *target);
 
+#ifdef CONFIG_DYNAMIC_FTRACE
+int module_finalize_ftrace(struct module *mod, const Elf_Shdr *sechdrs);
+#else
+static inline int module_finalize_ftrace(struct module *mod, const Elf_Shdr *sechdrs)
+{
+	return 0;
+}
+#endif
+
 struct exception_table_entry;
 void sort_ex_table(struct exception_table_entry *start,
 		   struct exception_table_entry *finish);

arch/powerpc/include/asm/sections.h

@@ -22,6 +22,18 @@ static inline int in_kernel_text(unsigned long addr)
 	return 0;
 }
 
+static inline unsigned long kernel_toc_addr(void)
+{
+	/* Defined by the linker, see vmlinux.lds.S */
+	extern unsigned long __toc_start;
+
+	/*
+	 * The TOC register (r2) points 32kB into the TOC, so that 64kB of
+	 * the TOC can be addressed using a single machine instruction.
+	 */
+	return (unsigned long)(&__toc_start) + 0x8000UL;
+}
+
 static inline int overlaps_interrupt_vector_text(unsigned long start,
 							unsigned long end)
 {

arch/powerpc/kernel/Makefile

@@ -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 = -mno-sched-epilog $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_prom_init.o = -mno-sched-epilog $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_btext.o = -mno-sched-epilog $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_prom.o = -mno-sched-epilog $(CC_FLAGS_FTRACE)
 # do not trace tracer code
-CFLAGS_REMOVE_ftrace.o = -pg -mno-sched-epilog
+CFLAGS_REMOVE_ftrace.o = -mno-sched-epilog $(CC_FLAGS_FTRACE)
 # timers used by tracing
-CFLAGS_REMOVE_time.o = -pg -mno-sched-epilog
+CFLAGS_REMOVE_time.o = -mno-sched-epilog $(CC_FLAGS_FTRACE)
 endif
 
 obj-y				:= cputable.o ptrace.o syscalls.o \

arch/powerpc/kernel/entry_64.S

@@ -1158,8 +1158,12 @@ _GLOBAL(enter_prom)
 #ifdef CONFIG_DYNAMIC_FTRACE
 _GLOBAL(mcount)
 _GLOBAL(_mcount)
-	blr
+	mflr	r12
+	mtctr	r12
+	mtlr	r0
+	bctr
 
+#ifndef CC_USING_MPROFILE_KERNEL
 _GLOBAL_TOC(ftrace_caller)
 	/* Taken from output of objdump from lib64/glibc */
 	mflr	r3
@@ -1181,6 +1185,115 @@ _GLOBAL(ftrace_graph_stub)
 	ld	r0, 128(r1)
 	mtlr	r0
 	addi	r1, r1, 112
+
+#else /* CC_USING_MPROFILE_KERNEL */
+/*
+ *
+ * ftrace_caller() is the function that replaces _mcount() when ftrace is
+ * active.
+ *
+ * We arrive here after a function A calls function B, and we are the trace
+ * function for B. When we enter r1 points to A's stack frame, B has not yet
+ * had a chance to allocate one yet.
+ *
+ * Additionally r2 may point either to the TOC for A, or B, depending on
+ * whether B did a TOC setup sequence before calling us.
+ *
+ * On entry the LR points back to the _mcount() call site, and r0 holds the
+ * saved LR as it was on entry to B, ie. the original return address at the
+ * call site in A.
+ *
+ * Our job is to save the register state into a struct pt_regs (on the stack)
+ * and then arrange for the ftrace function to be called.
+ */
+_GLOBAL(ftrace_caller)
+	/* Save the original return address in A's stack frame */
+	std	r0,LRSAVE(r1)
+
+	/* Create our stack frame + pt_regs */
+	stdu	r1,-SWITCH_FRAME_SIZE(r1)
+
+	/* Save all gprs to pt_regs */
+	SAVE_8GPRS(0,r1)
+	SAVE_8GPRS(8,r1)
+	SAVE_8GPRS(16,r1)
+	SAVE_8GPRS(24,r1)
+
+	/* Load special regs for save below */
+	mfmsr   r8
+	mfctr   r9
+	mfxer   r10
+	mfcr	r11
+
+	/* Get the _mcount() call site out of LR */
+	mflr	r7
+	/* Save it as pt_regs->nip & pt_regs->link */
+	std     r7, _NIP(r1)
+	std     r7, _LINK(r1)
+
+	/* Save callee's TOC in the ABI compliant location */
+	std	r2, 24(r1)
+	ld	r2,PACATOC(r13)	/* get kernel TOC in r2 */
+
+	addis	r3,r2,function_trace_op@toc@ha
+	addi	r3,r3,function_trace_op@toc@l
+	ld	r5,0(r3)
+
+	/* Calculate ip from nip-4 into r3 for call below */
+	subi    r3, r7, MCOUNT_INSN_SIZE
+
+	/* Put the original return address in r4 as parent_ip */
+	mr	r4, r0
+
+	/* Save special regs */
+	std     r8, _MSR(r1)
+	std     r9, _CTR(r1)
+	std     r10, _XER(r1)
+	std     r11, _CCR(r1)
+
+	/* Load &pt_regs in r6 for call below */
+	addi    r6, r1 ,STACK_FRAME_OVERHEAD
+
+	/* ftrace_call(r3, r4, r5, r6) */
+.globl ftrace_call
+ftrace_call:
+	bl	ftrace_stub
+	nop
+
+	/* Load ctr with the possibly modified NIP */
+	ld	r3, _NIP(r1)
+	mtctr	r3
+
+	/* Restore gprs */
+	REST_8GPRS(0,r1)
+	REST_8GPRS(8,r1)
+	REST_8GPRS(16,r1)
+	REST_8GPRS(24,r1)
+
+	/* Restore callee's TOC */
+	ld	r2, 24(r1)
+
+	/* Pop our stack frame */
+	addi r1, r1, SWITCH_FRAME_SIZE
+
+	/* Restore original LR for return to B */
+	ld	r0, LRSAVE(r1)
+	mtlr	r0
+
+#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
+
+	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
@@ -1213,6 +1326,7 @@ _GLOBAL(ftrace_stub)
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
+#ifndef CC_USING_MPROFILE_KERNEL
 _GLOBAL(ftrace_graph_caller)
 	/* load r4 with local address */
 	ld	r4, 128(r1)
@@ -1237,6 +1351,56 @@ _GLOBAL(ftrace_graph_caller)
 	addi	r1, r1, 112
 	blr
 
+#else /* CC_USING_MPROFILE_KERNEL */
+_GLOBAL(ftrace_graph_caller)
+	/* 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)
+
+	/* Save callee's TOC in the ABI compliant location */
+	std	r2, 24(r1)
+	ld	r2, PACATOC(r13)	/* get kernel TOC in r2 */
+
+	mfctr	r4		/* ftrace_caller has moved local addr here */
+	std	r4, 40(r1)
+	mflr	r3		/* ftrace_caller has restored LR from stack */
+	subi	r4, r4, MCOUNT_INSN_SIZE
+
+	bl	prepare_ftrace_return
+	nop
+
+	/*
+	 * prepare_ftrace_return gives us the address we divert to.
+	 * Change the LR to this.
+	 */
+	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)
+
+	/* Restore callee's TOC */
+	ld	r2, 24(r1)
+
+	addi	r1, r1, 112
+	mflr	r0
+	std	r0, LRSAVE(r1)
+	bctr
+#endif /* CC_USING_MPROFILE_KERNEL */
+
 _GLOBAL(return_to_handler)
 	/* need to save return values */
 	std	r4,  -32(r1)

arch/powerpc/kernel/ftrace.c

@@ -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 +109,15 @@ static int
 __ftrace_make_nop(struct module *mod,
 		  struct dyn_ftrace *rec, unsigned long addr)
 {
-	unsigned int op;
-	unsigned long entry, ptr;
+	unsigned long entry, ptr, tramp;
 	unsigned long ip = rec->ip;
-	void *tramp;
+	unsigned int op, pop;
 
 	/* 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)) {
@@ -122,14 +126,9 @@ __ftrace_make_nop(struct module *mod,
 	}
 
 	/* lets find where the pointer goes */
-	tramp = (void *)find_bl_target(ip, op);
-
-	pr_devel("ip:%lx jumps to %p", ip, tramp);
+	tramp = find_bl_target(ip, op);
 
-	if (!is_module_trampoline(tramp)) {
-		pr_err("Not a trampoline\n");
-		return -EINVAL;
-	}
+	pr_devel("ip:%lx jumps to %lx", ip, tramp);
 
 	if (module_trampoline_target(mod, tramp, &ptr)) {
 		pr_err("Failed to get trampoline target\n");
@@ -158,10 +157,42 @@ __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 = PPC_INST_BRANCH | 8;	/* 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 != PPC_INST_LD_TOC) {
+		unsigned int inst;
+
+		if (probe_kernel_read(&inst, (void *)(ip - 4), 4)) {
+			pr_err("Fetching instruction at %lx failed.\n", ip - 4);
+			return -EFAULT;
+		}
+
+		/* We expect either a mlfr r0, or a std r0, LRSAVE(r1) */
+		if (inst != PPC_INST_MFLR && inst != PPC_INST_STD_LR) {
+			pr_err("Unexpected instructions around bl _mcount\n"
+			       "when enabling dynamic ftrace!\t"
+			       "(%08x,bl,%08x)\n", inst, 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;
 }
@@ -287,16 +318,15 @@ int ftrace_make_nop(struct module *mod,
 
 #ifdef CONFIG_MODULES
 #ifdef CONFIG_PPC64
+/*
+ * Examine the existing instructions for __ftrace_make_call.
+ * They should effectively be a NOP, and follow formal constraints,
+ * depending on the ABI. Return false if they don't.
+ */
+#ifndef CC_USING_MPROFILE_KERNEL
 static int
-__ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+expected_nop_sequence(void *ip, unsigned int op0, unsigned int op1)
 {
-	unsigned int op[2];
-	void *ip = (void *)rec->ip;
-
-	/* read where this goes */
-	if (probe_kernel_read(op, ip, sizeof(op)))
-		return -EFAULT;
-
 	/*
 	 * We expect to see:
 	 *
@@ -306,8 +336,34 @@ __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.
 	 */
-	if ((op[0] != 0x48000008) || ((op[1] & 0xffff0000) != 0xe8410000)) {
-		pr_err("Unexpected call sequence: %x %x\n", op[0], op[1]);
+	if ((op0 != 0x48000008) || ((op1 & 0xffff0000) != 0xe8410000))
+		return 0;
+	return 1;
+}
+#else
+static int
+expected_nop_sequence(void *ip, unsigned int op0, unsigned int op1)
+{
+	/* look for patched "NOP" on ppc64 with -mprofile-kernel */
+	if (op0 != PPC_INST_NOP)
+		return 0;
+	return 1;
+}
+#endif
+
+static int
+__ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned int op[2];
+	void *ip = (void *)rec->ip;
+
+	/* read where this goes */
+	if (probe_kernel_read(op, ip, sizeof(op)))
+		return -EFAULT;
+
+	if (!expected_nop_sequence(ip, op[0], op[1])) {
+		pr_err("Unexpected call sequence at %p: %x %x\n",
+		ip, op[0], op[1]);
 		return -EINVAL;
 	}
 
@@ -330,7 +386,16 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 
 	return 0;
 }
-#else
+
+#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
+
+#else  /* !CONFIG_PPC64: */
 static int
 __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 {
@@ -455,20 +520,13 @@ 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)

arch/powerpc/kernel/module.c

@@ -47,6 +47,11 @@ int module_finalize(const Elf_Ehdr *hdr,
 		const Elf_Shdr *sechdrs, struct module *me)
 {
 	const Elf_Shdr *sect;
+	int rc;
+
+	rc = module_finalize_ftrace(me, sechdrs);
+	if (rc)
+		return rc;
 
 	/* Apply feature fixups */
 	sect = find_section(hdr, sechdrs, "__ftr_fixup");

arch/powerpc/kernel/module_32.c

@@ -181,7 +181,7 @@ static inline int entry_matches(struct ppc_plt_entry *entry, Elf32_Addr val)
 /* Set up a trampoline in the PLT to bounce us to the distant function */
 static uint32_t do_plt_call(void *location,
 			    Elf32_Addr val,
-			    Elf32_Shdr *sechdrs,
+			    const Elf32_Shdr *sechdrs,
 			    struct module *mod)
 {
 	struct ppc_plt_entry *entry;
@@ -294,11 +294,19 @@ int apply_relocate_add(Elf32_Shdr *sechdrs,
 			return -ENOEXEC;
 		}
 	}
+
+	return 0;
+}
+
 #ifdef CONFIG_DYNAMIC_FTRACE
-	module->arch.tramp =
-		do_plt_call(module->core_layout.base,
-			    (unsigned long)ftrace_caller,
-			    sechdrs, module);
-#endif
+int module_finalize_ftrace(struct module *module, const Elf_Shdr *sechdrs)
+{
+	module->arch.tramp = do_plt_call(module->core_layout.base,
+					 (unsigned long)ftrace_caller,
+					 sechdrs, module);
+	if (!module->arch.tramp)
+		return -ENOENT;
+
 	return 0;
 }
+#endif

arch/powerpc/kernel/module_64.c

@@ -31,6 +31,7 @@
 #include <asm/code-patching.h>
 #include <linux/sort.h>
 #include <asm/setup.h>
+#include <asm/sections.h>
 
 /* FIXME: We don't do .init separately.  To do this, we'd need to have
    a separate r2 value in the init and core section, and stub between
@@ -41,7 +42,6 @@
    --RR.  */
 
 #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;
@@ -73,7 +73,6 @@ static unsigned int local_entry_offset(const Elf64_Sym *sym)
 	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;
@@ -96,6 +95,8 @@ static unsigned int local_entry_offset(const Elf64_Sym *sym)
 }
 #endif
 
+#define STUB_MAGIC 0x73747562 /* stub */
+
 /* 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). */
@@ -105,7 +106,8 @@ struct ppc64_stub_entry
 	 * 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;
+	/* Used by ftrace to identify stubs */
+	u32 magic;
 	/* Data for the above code */
 	func_desc_t funcdata;
 };
@@ -139,70 +141,39 @@ static u32 ppc64_stub_insns[] = {
 };
 
 #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)
+int module_trampoline_target(struct module *mod, unsigned long addr,
+			     unsigned long *target)
 {
-	unsigned int i;
-	u32 insns[ARRAY_SIZE(ppc64_stub_insns)];
-
-	BUILD_BUG_ON(sizeof(ppc64_stub_insns) != sizeof(ppc64_stub_mask));
+	struct ppc64_stub_entry *stub;
+	func_desc_t funcdata;
+	u32 magic;
 
-	if (probe_kernel_read(insns, p, sizeof(insns)))
+	if (!within_module_core(addr, mod)) {
+		pr_err("%s: stub %lx not in module %s\n", __func__, addr, mod->name);
 		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;
+	stub = (struct ppc64_stub_entry *)addr;
 
-	if (probe_kernel_read(buf, trampoline, sizeof(buf)))
+	if (probe_kernel_read(&magic, &stub->magic, sizeof(magic))) {
+		pr_err("%s: fault reading magic for stub %lx for %s\n", __func__, addr, mod->name);
 		return -EFAULT;
+	}
 
-	upper = buf[0] & 0xffff;
-	lower = buf[1] & 0xffff;
-
-	/* perform the addis/addi, both signed */
-	offset = ((short)upper << 16) + (short)lower;
+	if (magic != STUB_MAGIC) {
+		pr_err("%s: bad magic for stub %lx for %s\n", __func__, addr, mod->name);
+		return -EFAULT;
+	}
 
-	/*
-	 * 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(&funcdata, &stub->funcdata, sizeof(funcdata))) {
+		pr_err("%s: fault reading funcdata for stub %lx for %s\n", __func__, addr, mod->name);
+                return -EFAULT;
+	}
 
-	if (probe_kernel_read(target, toc_entry, sizeof(*target)))
-		return -EFAULT;
+	*target = stub_func_addr(funcdata);
 
 	return 0;
 }
-
 #endif
 
 /* Count how many different 24-bit relocations (different symbol,
@@ -413,7 +384,7 @@ int module_frob_arch_sections(Elf64_Ehdr *hdr,
 /* r2 is the TOC pointer: it actually points 0x8000 into the TOC (this
    gives the value maximum span in an instruction which uses a signed
    offset) */
-static inline unsigned long my_r2(Elf64_Shdr *sechdrs, struct module *me)
+static inline unsigned long my_r2(const Elf64_Shdr *sechdrs, struct module *me)
 {
 	return sechdrs[me->arch.toc_section].sh_addr + 0x8000;
 }
@@ -426,7 +397,7 @@ static inline unsigned long my_r2(Elf64_Shdr *sechdrs, struct module *me)
 #define PPC_HA(v) PPC_HI ((v) + 0x8000)
 
 /* Patch stub to reference function and correct r2 value. */
-static inline int create_stub(Elf64_Shdr *sechdrs,
+static inline int create_stub(const Elf64_Shdr *sechdrs,
 			      struct ppc64_stub_entry *entry,
 			      unsigned long addr,
 			      struct module *me)
@@ -447,12 +418,14 @@ static inline int create_stub(Elf64_Shdr *sechdrs,
 	entry->jump[0] |= PPC_HA(reladdr);
 	entry->jump[1] |= PPC_LO(reladdr);
 	entry->funcdata = func_desc(addr);
+	entry->magic = STUB_MAGIC;
+
 	return 1;
 }
 
 /* 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,
+static unsigned long stub_for_addr(const Elf64_Shdr *sechdrs,
 				   unsigned long addr,
 				   struct module *me)
 {
@@ -476,17 +449,60 @@ static unsigned long stub_for_addr(Elf64_Shdr *sechdrs,
 	return (unsigned long)&stubs[i];
 }
 
+#ifdef CC_USING_MPROFILE_KERNEL
+static bool is_early_mcount_callsite(u32 *instruction)
+{
+	/*
+	 * Check if this is one of the -mprofile-kernel sequences.
+	 */
+	if (instruction[-1] == PPC_INST_STD_LR &&
+	    instruction[-2] == PPC_INST_MFLR)
+		return true;
+
+	if (instruction[-1] == PPC_INST_MFLR)
+		return true;
+
+	return false;
+}
+
+/*
+ * In case of _mcount calls, do not save the current callee's TOC (in r2) into
+ * the original caller's stack frame. If we did we would clobber the saved TOC
+ * value of the original caller.
+ */
+static void squash_toc_save_inst(const char *name, unsigned long addr)
+{
+	struct ppc64_stub_entry *stub = (struct ppc64_stub_entry *)addr;
+
+	/* Only for calls to _mcount */
+	if (strcmp("_mcount", name) != 0)
+		return;
+
+	stub->jump[2] = PPC_INST_NOP;
+}
+#else
+static void squash_toc_save_inst(const char *name, unsigned long addr) { }
+
+/* without -mprofile-kernel, mcount calls are never early */
+static bool is_early_mcount_callsite(u32 *instruction)
+{
+	return false;
+}
+#endif
+
 /* We expect a noop next: if it is, replace it with instruction to
    restore r2. */
 static int restore_r2(u32 *instruction, struct module *me)
 {
 	if (*instruction != PPC_INST_NOP) {
+		if (is_early_mcount_callsite(instruction - 1))
+			return 1;
 		pr_err("%s: Expect noop after relocate, got %08x\n",
 		       me->name, *instruction);
 		return 0;
 	}
 	/* ld r2,R2_STACK_OFFSET(r1) */
-	*instruction = 0xe8410000 | R2_STACK_OFFSET;
+	*instruction = PPC_INST_LD_TOC;
 	return 1;
 }
 
@@ -611,6 +627,8 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 					return -ENOENT;
 				if (!restore_r2((u32 *)location + 1, me))
 					return -ENOEXEC;
+
+				squash_toc_save_inst(strtab + sym->st_name, value);
 			} else
 				value += local_entry_offset(sym);
 
@@ -693,12 +711,84 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 		}
 	}
 
+	return 0;
+}
+
 #ifdef CONFIG_DYNAMIC_FTRACE
-	me->arch.toc = my_r2(sechdrs, me);
-	me->arch.tramp = stub_for_addr(sechdrs,
-				       (unsigned long)ftrace_caller,
-				       me);
+
+#ifdef CC_USING_MPROFILE_KERNEL
+
+#define PACATOC offsetof(struct paca_struct, kernel_toc)
+
+/*
+ * For mprofile-kernel we use a special stub for ftrace_caller() because we
+ * can't rely on r2 containing this module's TOC when we enter the stub.
+ *
+ * That can happen if the function calling us didn't need to use the toc. In
+ * that case it won't have setup r2, and the r2 value will be either the
+ * kernel's toc, or possibly another modules toc.
+ *
+ * To deal with that this stub uses the kernel toc, which is always accessible
+ * via the paca (in r13). The target (ftrace_caller()) is responsible for
+ * saving and restoring the toc before returning.
+ */
+static unsigned long create_ftrace_stub(const Elf64_Shdr *sechdrs, struct module *me)
+{
+	struct ppc64_stub_entry *entry;
+	unsigned int i, num_stubs;
+	static u32 stub_insns[] = {
+		0xe98d0000 | PACATOC, 	/* ld      r12,PACATOC(r13)	*/
+		0x3d8c0000,		/* addis   r12,r12,<high>	*/
+		0x398c0000, 		/* addi    r12,r12,<low>	*/
+		0x7d8903a6, 		/* mtctr   r12			*/
+		0x4e800420, 		/* bctr				*/
+	};
+	long reladdr;
+
+	num_stubs = sechdrs[me->arch.stubs_section].sh_size / sizeof(*entry);
+
+	/* Find the next available stub entry */
+	entry = (void *)sechdrs[me->arch.stubs_section].sh_addr;
+	for (i = 0; i < num_stubs && stub_func_addr(entry->funcdata); i++, entry++);
+
+	if (i >= num_stubs) {
+		pr_err("%s: Unable to find a free slot for ftrace stub.\n", me->name);
+		return 0;
+	}
+
+	memcpy(entry->jump, stub_insns, sizeof(stub_insns));
+
+	/* Stub uses address relative to kernel toc (from the paca) */
+	reladdr = (unsigned long)ftrace_caller - kernel_toc_addr();
+	if (reladdr > 0x7FFFFFFF || reladdr < -(0x80000000L)) {
+		pr_err("%s: Address of ftrace_caller out of range of kernel_toc.\n", me->name);
+		return 0;
+	}
+
+	entry->jump[1] |= PPC_HA(reladdr);
+	entry->jump[2] |= PPC_LO(reladdr);
+
+	/* Eventhough we don't use funcdata in the stub, it's needed elsewhere. */
+	entry->funcdata = func_desc((unsigned long)ftrace_caller);
+	entry->magic = STUB_MAGIC;
+
+	return (unsigned long)entry;
+}
+#else
+static unsigned long create_ftrace_stub(const Elf64_Shdr *sechdrs, struct module *me)
+{
+	return stub_for_addr(sechdrs, (unsigned long)ftrace_caller, me);
+}
 #endif
 
+int module_finalize_ftrace(struct module *mod, const Elf_Shdr *sechdrs)
+{
+	mod->arch.toc = my_r2(sechdrs, mod);
+	mod->arch.tramp = create_ftrace_stub(sechdrs, mod);
+
+	if (!mod->arch.tramp)
+		return -ENOENT;
+
 	return 0;
 }
+#endif

arch/powerpc/kernel/paca.c

@@ -17,10 +17,6 @@
 #include <asm/pgtable.h>
 #include <asm/kexec.h>
 
-/* This symbol is provided by the linker - let it fill in the paca
- * field correctly */
-extern unsigned long __toc_start;
-
 #ifdef CONFIG_PPC_BOOK3S
 
 /*
@@ -149,11 +145,6 @@ EXPORT_SYMBOL(paca);
 
 void __init initialise_paca(struct paca_struct *new_paca, int cpu)
 {
-       /* The TOC register (GPR2) points 32kB into the TOC, so that 64kB
-	* of the TOC can be addressed using a single machine instruction.
-	*/
-	unsigned long kernel_toc = (unsigned long)(&__toc_start) + 0x8000UL;
-
 #ifdef CONFIG_PPC_BOOK3S
 	new_paca->lppaca_ptr = new_lppaca(cpu);
 #else
@@ -161,7 +152,7 @@ void __init initialise_paca(struct paca_struct *new_paca, int cpu)
 #endif
 	new_paca->lock_token = 0x8000;
 	new_paca->paca_index = cpu;
-	new_paca->kernel_toc = kernel_toc;
+	new_paca->kernel_toc = kernel_toc_addr();
 	new_paca->kernelbase = (unsigned long) _stext;
 	/* Only set MSR:IR/DR when MMU is initialized */
 	new_paca->kernel_msr = MSR_KERNEL & ~(MSR_IR | MSR_DR);

arch/powerpc/lib/Makefile

@@ -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 = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_feature-fixups.o = $(CC_FLAGS_FTRACE)
 
 obj-y += string.o alloc.o crtsavres.o ppc_ksyms.o code-patching.o \
 	 feature-fixups.o

arch/powerpc/platforms/powermac/Makefile

@@ -2,7 +2,7 @@ CFLAGS_bootx_init.o  		+= -fPIC
 
 ifdef CONFIG_FUNCTION_TRACER
 # Do not trace early boot code
-CFLAGS_REMOVE_bootx_init.o = -pg -mno-sched-epilog
+CFLAGS_REMOVE_bootx_init.o = -mno-sched-epilog $(CC_FLAGS_FTRACE)
 endif
 
 obj-y				+= pic.o setup.o time.o feature.o pci.o \

arch/powerpc/scripts/gcc-check-mprofile-kernel.sh

+#!/bin/bash
+
+set -e
+set -o pipefail
+
+# To debug, uncomment the following line
+# set -x
+
+# Test whether the compile option -mprofile-kernel exists and generates
+# profiling code (ie. a call to _mcount()).
+echo "int func() { return 0; }" | \
+    $* -S -x c -O2 -p -mprofile-kernel - -o - 2> /dev/null | \
+    grep -q "_mcount"
+
+# Test whether the notrace attribute correctly suppresses calls to _mcount().
+
+echo -e "#include <linux/compiler.h>\nnotrace int func() { return 0; }" | \
+    $* -S -x c -O2 -p -mprofile-kernel - -o - 2> /dev/null | \
+    grep -q "_mcount" && \
+    exit 1
+
+echo "OK"
+exit 0