ppc64le: dynamic ftrace and kgraft support

PATCH In review Torsten Duwe 1 participant 5 messages Mar 19, 2015

Subsystems (7)

Memory management PowerPC Kbuild Library code +3 more subsystems

lore

Share & tools

lore

Torsten Duwe

author

2015-03-19 20:35 UTC #0 lore raw

cover ppc64le: dynamic ftrace and kgraft support

Here's an initial version of dynamic ftrace for ABIv2 (ppc64le), the code maturity is somewhere between proof of concept and pre-alpha. I have split it into 4 parts, for ftrace and kgraft, a configuration enablement and the actual code, respectively.
Please have a look and tell me whether this is the way to go.

Torsten

Torsten Duwe

author

2015-03-19 20:45 UTC #1 lore raw

Re: [PATCH v0 1/4] ppc64le: dynamic ftrace

I'm pretty sure not everything is ifdef'd properly, and the FIXME needs to be solved in order to disable ftracing again. Built upon some original code by Vojtech Pavlik.

arch/powerpc/include/asm/ftrace.h +5 -0

index e366187..a69d47e 100644
@@ -46,6 +46,8 @@
 extern void _mcount(void);
 
 #ifdef CONFIG_DYNAMIC_FTRACE
+# define FTRACE_ADDR ((unsigned long)ftrace_caller+8)
+# 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 */

@@ -57,6 +58,9 @@ struct dyn_arch_ftrace {
 #endif /*  CONFIG_DYNAMIC_FTRACE */
 #endif /* __ASSEMBLY__ */
 
+#ifdef CONFIG_DYNAMIC_FTRACE
+#define ARCH_SUPPORTS_FTRACE_OPS 1
+#endif
 #endif
 
 #if defined(CONFIG_FTRACE_SYSCALLS) && defined(CONFIG_PPC64) && !defined(__ASSEMBLY__)

arch/powerpc/kernel/entry_64.S +92 ~~-20~~

144 lines not on this page · raw message

arch/powerpc/kernel/ftrace.c +60 -9

123 lines not on this page · raw message

arch/powerpc/kernel/module_64.c +30 -3

index d807ee6..05b88d3 100644
@@ -140,12 +140,22 @@ static u32 ppc64_stub_insns[] = {
 	0x4e800420			/* bctr */
 };
 
+/* 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;
+
 #ifdef CONFIG_DYNAMIC_FTRACE
 
 static u32 ppc64_stub_mask[] = {
 	0xffff0000,
 	0xffff0000,
-	0xffffffff,
+	0x00000000,
 	0xffffffff,
 #if !defined(_CALL_ELF) || _CALL_ELF != 2
 	0xffffffff,

@@ -172,6 +182,9 @@ 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;
 }

@@ -477,6 +490,14 @@ static unsigned long stub_for_addr(Elf64_Shdr *sechdrs,
 static int restore_r2(u32 *instruction, struct module *me)
 {
 	if (*instruction != PPC_INST_NOP) {
+
+		/* -mprofile_kernel sequence starting with mflr r0; std r0, LRSAVE(r1) */
+		if (instruction[-3] == 0x7c0802a6 && instruction[-2] == 0xf8010010) {
+			/* Nothing to be done here, it's a _mcount call location
+			   and r2 will have to be restored in the _mcount function */
+			return 2;
+		};
+
 		printk("%s: Expect noop after relocate, got %08x\n",
 		       me->name, *instruction);
 		return 0;

@@ -492,7 +513,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 		       unsigned int relsec,
 		       struct module *me)
 {
-	unsigned int i;
+	unsigned int i, r2;
 	Elf64_Rela *rela = (void *)sechdrs[relsec].sh_addr;
 	Elf64_Sym *sym;
 	unsigned long *location;

@@ -605,8 +626,11 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 				value = stub_for_addr(sechdrs, value, me);
 				if (!value)
 					return -ENOENT;
-				if (!restore_r2((u32 *)location + 1, me))
+				if (!(r2 = 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);

@@ -667,6 +691,9 @@ 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;

Torsten Duwe

author

2015-03-19 20:48 UTC #2 lore raw

PATCH 2/4 ppc64le: dynamic ftrace configuration options

In reply to Torsten Duwe

Switch on -mprofile-kernel, and remove it again from directories involved in exception handling. This needs to be done more fine grained, of course.

Makefile +4 -1

index 1a60bdd..72644e6 100644
@@ -732,7 +732,10 @@ ifdef CONFIG_FUNCTION_TRACER
 ifdef CONFIG_HAVE_FENTRY
 CC_USING_FENTRY	:= $(call cc-option, -mfentry -DCC_USING_FENTRY)
 endif
-KBUILD_CFLAGS	+= -pg $(CC_USING_FENTRY)
+ifdef CONFIG_HAVE_MPROFILE_KERNEL
+CC_USING_MPROFILE_KERNEL	:= $(call cc-option, -mprofile-kernel -DCC_USING_MPROFILE_KERNEL)
+endif
+KBUILD_CFLAGS	+= -pg $(CC_USING_FENTRY) $(CC_USING_MPROFILE_KERNEL)
 KBUILD_AFLAGS	+= $(CC_USING_FENTRY)
 ifdef CONFIG_DYNAMIC_FTRACE
 	ifdef CONFIG_HAVE_C_RECORDMCOUNT

arch/powerpc/Kconfig +2 -0

index 4bc7b62..d82d7c8 100644
@@ -93,8 +93,10 @@ config PPC
 	select OF_RESERVED_MEM
 	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_DYNAMIC_FTRACE
+	select HAVE_DYNAMIC_FTRACE_WITH_REGS
 	select HAVE_FUNCTION_TRACER
 	select HAVE_FUNCTION_GRAPH_TRACER
+	select HAVE_MPROFILE_KERNEL
 	select SYSCTL_EXCEPTION_TRACE
 	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select VIRT_TO_BUS if !PPC64

arch/powerpc/kernel/Makefile +6 -6

index 670c312..688e6f9 100644
@@ -17,14 +17,14 @@ 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 \

kernel/Makefile +3 -2

index 8af7403..3c8821d 100644
@@ -13,8 +13,9 @@ obj-y     = fork.o exec_domain.o panic.o \
 
 ifdef CONFIG_FUNCTION_TRACER
 # Do not trace debug files and internal ftrace files
-CFLAGS_REMOVE_cgroup-debug.o = -pg
-CFLAGS_REMOVE_irq_work.o = -pg
+CFLAGS_REMOVE_cgroup-debug.o = -pg -mprofile-kernel
+CFLAGS_REMOVE_irq_work.o = -pg -mprofile-kernel
+CFLAGS_REMOVE_extable.o = -pg -mprofile-kernel
 endif
 
 # cond_syscall is currently not LTO compatible

kernel/locking/Makefile +4 -4

index 8541bfd..1cc57c8 100644
@@ -2,10 +2,10 @@
 obj-y += mutex.o semaphore.o rwsem.o mcs_spinlock.o
 
 ifdef CONFIG_FUNCTION_TRACER
-CFLAGS_REMOVE_lockdep.o = -pg
-CFLAGS_REMOVE_lockdep_proc.o = -pg
-CFLAGS_REMOVE_mutex-debug.o = -pg
-CFLAGS_REMOVE_rtmutex-debug.o = -pg
+CFLAGS_REMOVE_lockdep.o = -pg -mprofile-kernel
+CFLAGS_REMOVE_lockdep_proc.o = -pg -mprofile-kernel
+CFLAGS_REMOVE_mutex-debug.o = -pg -mprofile-kernel
+CFLAGS_REMOVE_rtmutex-debug.o = -pg -mprofile-kernel
 endif
 
 obj-$(CONFIG_DEBUG_MUTEXES) += mutex-debug.o

kernel/trace/Kconfig +5 -0

index a5da09c..dd53f3d 100644
@@ -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

arch/powerpc/lib/Makefile +2 -2

index 59fa2de..b2f5029 100644
@@ -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

arch/powerpc/mm/Makefile +5 -0

index d0130ff..22633af 100644
@@ -6,6 +6,11 @@ subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror
 
 ccflags-$(CONFIG_PPC64)	:= $(NO_MINIMAL_TOC)
 
+# needed for do_page_fault in fault.c :
+KBUILD_CFLAGS := $(filter-out -mprofile-kernel, $(KBUILD_CFLAGS))
+KBUILD_CFLAGS := $(filter-out -pg, $(KBUILD_CFLAGS))
+KBUILD_CFLAGS := $(filter-out -DCC_USING_MPROFILE_KERNEL, $(KBUILD_CFLAGS))
+
 obj-y				:= fault.o mem.o pgtable.o gup.o mmap.o \
 				   init_$(CONFIG_WORD_SIZE).o \
 				   pgtable_$(CONFIG_WORD_SIZE).o

arch/powerpc/kernel/Makefile +3 -0

index 688e6f9..1f08a53 100644
@@ -26,6 +26,9 @@ CFLAGS_REMOVE_ftrace.o = -pg -mno-sched-epilog -mprofile-kernel
 # timers used by tracing
 CFLAGS_REMOVE_time.o = -pg -mno-sched-epilog -mprofile-kernel
 endif
+KBUILD_CFLAGS := $(filter-out -mprofile-kernel, $(KBUILD_CFLAGS))
+KBUILD_CFLAGS := $(filter-out -pg, $(KBUILD_CFLAGS))
+KBUILD_CFLAGS := $(filter-out -DCC_USING_MPROFILE_KERNEL, $(KBUILD_CFLAGS))
 
 obj-y				:= cputable.o ptrace.o syscalls.o \
 				   irq.o align.o signal_32.o pmc.o vdso.o \

kernel/Makefile +3 -0

index f2f8537..f84c784 100644
@@ -17,6 +17,9 @@ CFLAGS_REMOVE_cgroup-debug.o = -pg -mprofile-kernel
 CFLAGS_REMOVE_irq_work.o = -pg -mprofile-kernel
 CFLAGS_REMOVE_extable.o = -pg -mprofile-kernel
 endif
+KBUILD_CFLAGS := $(filter-out -mprofile-kernel, $(KBUILD_CFLAGS))
+KBUILD_CFLAGS := $(filter-out -pg, $(KBUILD_CFLAGS))
+KBUILD_CFLAGS := $(filter-out -DCC_USING_MPROFILE_KERNEL, $(KBUILD_CFLAGS))
 
 # cond_syscall is currently not LTO compatible
 CFLAGS_sys_ni.o = $(DISABLE_LTO)

lib/Makefile +3 -0

index d6b4bc4..186cf9b 100644
@@ -6,6 +6,9 @@ ifdef CONFIG_FUNCTION_TRACER
 ORIG_CFLAGS := $(KBUILD_CFLAGS)
 KBUILD_CFLAGS = $(subst -pg,,$(ORIG_CFLAGS))
 endif
+KBUILD_CFLAGS := $(filter-out -mprofile-kernel, $(KBUILD_CFLAGS))
+KBUILD_CFLAGS := $(filter-out -pg, $(KBUILD_CFLAGS))
+KBUILD_CFLAGS := $(filter-out -DCC_USING_MPROFILE_KERNEL, $(KBUILD_CFLAGS))
 
 lib-y := ctype.o string.o vsprintf.o cmdline.o \
 	 rbtree.o radix-tree.o dump_stack.o timerqueue.o\

mm/Makefile +4 -0

index 632ae77..07be08f 100644
@@ -20,6 +20,10 @@ obj-y			:= filemap.o mempool.o oom_kill.o fadvise.o \
 			   interval_tree.o list_lru.o workingset.o \
 			   iov_iter.o $(mmu-y)
 
+KBUILD_CFLAGS := $(filter-out -mprofile-kernel, $(KBUILD_CFLAGS))
+KBUILD_CFLAGS := $(filter-out -pg, $(KBUILD_CFLAGS))
+KBUILD_CFLAGS := $(filter-out -DCC_USING_MPROFILE_KERNEL, $(KBUILD_CFLAGS))
+
 obj-y += init-mm.o
 
 ifdef CONFIG_NO_BOOTMEM

Torsten Duwe

author

2015-03-19 20:51 UTC #3 lore raw

PATCH 3/4 ppc64le: kgraft support

In reply to Torsten Duwe

The kgraft hooks for ppc64. Just massaged a bit to get them to compile and not interfere. Feel free to test them if you're daring ;)

arch/powerpc/include/asm/kgraft.h new file +33 -0

new file mode 100644
index 0000000..7f8600d
@@ -0,0 +1,33 @@
+/*
+ * kGraft Online Kernel Patching
+ *
+ *  Copyright (c) 2013-2014 SUSE
+ *   Authors: Jiri Kosina
+ *	      Vojtech Pavlik
+ *	      Jiri Slaby
+ */
+
+/*
+ * 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.
+ */
+
+#ifndef ASM_KGR_H
+#define ASM_KGR_H
+
+#include <asm/ptrace.h>
+#include <linux/stacktrace.h>
+
+static inline void kgr_set_regs_ip(struct pt_regs *regs, unsigned long ip)
+{
+	regs->link = ip;
+}
+
+static inline bool kgr_needs_lazy_migration(struct task_struct *p)
+{
+	return true;
+}
+
+#endif

arch/powerpc/include/asm/thread_info.h +6 -2

index b034ecd..aa6a084 100644
@@ -92,6 +92,7 @@ static inline struct thread_info *current_thread_info(void)
 					   TIF_NEED_RESCHED */
 #define TIF_32BIT		4	/* 32 bit binary */
 #define TIF_RESTORE_TM		5	/* need to restore TM FP/VEC/VSX */
+#define TIF_KGR_IN_PROGRESS	6	/* kGraft patching in progress */
 #define TIF_SYSCALL_AUDIT	7	/* syscall auditing active */
 #define TIF_SINGLESTEP		8	/* singlestepping active */
 #define TIF_NOHZ		9	/* in adaptive nohz mode */

@@ -115,8 +117,10 @@ static inline struct thread_info *current_thread_info(void)
 #define _TIF_POLLING_NRFLAG	(1<<TIF_POLLING_NRFLAG)
 #define _TIF_32BIT		(1<<TIF_32BIT)
 #define _TIF_RESTORE_TM		(1<<TIF_RESTORE_TM)
+#define _TIF_KGR_IN_PROGRESS	(1<<TIF_KGR_IN_PROGRESS)
 #define _TIF_SYSCALL_AUDIT	(1<<TIF_SYSCALL_AUDIT)
 #define _TIF_SINGLESTEP		(1<<TIF_SINGLESTEP)
+#define _TIF_NOHZ		(1<<TIF_NOHZ)
 #define _TIF_SECCOMP		(1<<TIF_SECCOMP)
 #define _TIF_RESTOREALL		(1<<TIF_RESTOREALL)
 #define _TIF_NOERROR		(1<<TIF_NOERROR)

@@ -124,7 +128,7 @@ static inline struct thread_info *current_thread_info(void)
 #define _TIF_UPROBE		(1<<TIF_UPROBE)
 #define _TIF_SYSCALL_TRACEPOINT	(1<<TIF_SYSCALL_TRACEPOINT)
 #define _TIF_EMULATE_STACK_STORE	(1<<TIF_EMULATE_STACK_STORE)
-#define _TIF_NOHZ		(1<<TIF_NOHZ)
+
 #define _TIF_SYSCALL_T_OR_A	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
 				 _TIF_SECCOMP | _TIF_SYSCALL_TRACEPOINT | \
 				 _TIF_NOHZ)

@@ -132,7 +136,8 @@ static inline struct thread_info *current_thread_info(void)
 #define _TIF_USER_WORK_MASK	(_TIF_SIGPENDING | _TIF_NEED_RESCHED | \
 				 _TIF_NOTIFY_RESUME | _TIF_UPROBE | \
 				 _TIF_RESTORE_TM)
-#define _TIF_PERSYSCALL_MASK	(_TIF_RESTOREALL|_TIF_NOERROR)
+
+#define _TIF_PERSYSCALL_MASK	(_TIF_RESTOREALL|_TIF_NOERROR|_TIF_KGR_IN_PROGRESS)
 
 /* Bits in local_flags */
 /* Don't move TLF_NAPPING without adjusting the code in entry_32.S */

arch/powerpc/kernel/entry_64.S +13 -2

index 5bbd1bc..569acd4 100644
@@ -151,8 +151,8 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR)
 #endif
 	CURRENT_THREAD_INFO(r11, r1)
 	ld	r10,TI_FLAGS(r11)
-	andi.	r11,r10,_TIF_SYSCALL_T_OR_A
-	bne	syscall_dotrace
+	andi.	r10,r10,(_TIF_SYSCALL_T_OR_A|_TIF_KGR_IN_PROGRESS)
+	bne-	syscall_precall
 .Lsyscall_dotrace_cont:
 	cmpldi	0,r0,NR_syscalls
 	bge-	syscall_enosys

@@ -245,6 +245,17 @@ syscall_error:
 	neg	r3,r3
 	std	r5,_CCR(r1)
 	b	.Lsyscall_error_cont
+
+syscall_precall:
+	andi.	r10,r10,(_TIF_KGR_IN_PROGRESS)
+	beq+	syscall_dotrace
+
+	addi	r11,r11,TI_FLAGS
+1:	ldarx	r12,0,r11
+	andc	r12,r12,r10
+	stdcx.	r12,0,r11
+	bne-	1b
+	subi	r11,r11,TI_FLAGS
 	
 /* Traced system call support */
 syscall_dotrace:

Torsten Duwe

author

2015-03-19 20:54 UTC #4 lore raw

PATCH 4/4 ppc64le: kgraft config options

In reply to Torsten Duwe

Enable kgraft on ppc, fairly trivial.

arch/powerpc/Kconfig +3 -0

index 4bc7b62..d82d7c8 100644
@@ -102,6 +104,7 @@ config PPC
 	select HAVE_IOREMAP_PROT
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS if !CPU_LITTLE_ENDIAN
 	select HAVE_KPROBES
+	select HAVE_KGRAFT
 	select HAVE_ARCH_KGDB
 	select HAVE_KRETPROBES
 	select HAVE_ARCH_TRACEHOOK

@@ -291,6 +294,8 @@ source "init/Kconfig"
 
 source "kernel/Kconfig.freezer"
 
+source "kernel/Kconfig.kgraft"
+
 source "arch/powerpc/sysdev/Kconfig"
 source "arch/powerpc/platforms/Kconfig"