s390/ftrace,kprobes: allow to patch first instruction

If the function tracer is enabled, allow to set kprobes on the first
instruction of a function (which is the function trace caller):

If no kprobe is set handling of enabling and disabling function tracing
of a function simply patches the first instruction. Either it is a nop
(right now it's an unconditional branch, which skips the mcount block),
or it's a branch to the ftrace_caller() function.

If a kprobe is being placed on a function tracer calling instruction
we encode if we actually have a nop or branch in the remaining bytes
after the breakpoint instruction (illegal opcode).
This is possible, since the size of the instruction used for the nop
and branch is six bytes, while the size of the breakpoint is only
two bytes.
Therefore the first two bytes contain the illegal opcode and the last
four bytes contain either "0" for nop or "1" for branch. The kprobes
code will then execute/simulate the correct instruction.

Instruction patching for kprobes and function tracer is always done
with stop_machine(). Therefore we don't have any races where an
instruction is patched concurrently on a different cpu.
Besides that also the program check handler which executes the function
trace caller instruction won't be executed concurrently to any
stop_machine() execution.

This allows to keep full fault based kprobes handling which generates
correct pt_regs contents automatically.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

4 files changed, 62 insertions, 7 deletions

diff --git a/arch/s390/include/asm/ftrace.h b/arch/s390/include/asm/ftrace.h
index 3aef8afec336..785041f1dc77 100644
--- a/arch/s390/include/asm/ftrace.h
+++ b/arch/s390/include/asm/ftrace.h
@@ -1,25 +1,67 @@
 #ifndef _ASM_S390_FTRACE_H
 #define _ASM_S390_FTRACE_H
 
+#define ARCH_SUPPORTS_FTRACE_OPS 1
+
+#define MCOUNT_INSN_SIZE	24
+#define MCOUNT_RETURN_FIXUP	18
+
 #ifndef __ASSEMBLY__
 
-extern void _mcount(void);
+void _mcount(void);
+void ftrace_caller(void);
+
 extern char ftrace_graph_caller_end;
+extern unsigned long ftrace_plt;
 
 struct dyn_arch_ftrace { };
 
-#define MCOUNT_ADDR ((long)_mcount)
+#define MCOUNT_ADDR ((unsigned long)_mcount)
+#define FTRACE_ADDR ((unsigned long)ftrace_caller)
 
+#define KPROBE_ON_FTRACE_NOP	0
+#define KPROBE_ON_FTRACE_CALL	1
 
 static inline unsigned long ftrace_call_adjust(unsigned long addr)
 {
 	return addr;
 }
 
-#endif /* __ASSEMBLY__ */
+struct ftrace_insn {
+	u16 opc;
+	s32 disp;
+} __packed;
 
-#define MCOUNT_INSN_SIZE  18
+static inline void ftrace_generate_nop_insn(struct ftrace_insn *insn)
+{
+#ifdef CONFIG_FUNCTION_TRACER
+	/* jg .+24 */
+	insn->opc = 0xc0f4;
+	insn->disp = MCOUNT_INSN_SIZE / 2;
+#endif
+}
 
-#define ARCH_SUPPORTS_FTRACE_OPS 1
+static inline int is_ftrace_nop(struct ftrace_insn *insn)
+{
+#ifdef CONFIG_FUNCTION_TRACER
+	if (insn->disp == MCOUNT_INSN_SIZE / 2)
+		return 1;
+#endif
+	return 0;
+}
+
+static inline void ftrace_generate_call_insn(struct ftrace_insn *insn,
+					     unsigned long ip)
+{
+#ifdef CONFIG_FUNCTION_TRACER
+	unsigned long target;
 
+	/* brasl r0,ftrace_caller */
+	target = is_module_addr((void *) ip) ? ftrace_plt : FTRACE_ADDR;
+	insn->opc = 0xc005;
+	insn->disp = (target - ip) / 2;
+#endif
+}
+
+#endif /* __ASSEMBLY__ */
 #endif /* _ASM_S390_FTRACE_H */
diff --git a/arch/s390/include/asm/kprobes.h b/arch/s390/include/asm/kprobes.h
index 98629173ce3b..b47ad3b642cc 100644
--- a/arch/s390/include/asm/kprobes.h
+++ b/arch/s390/include/asm/kprobes.h
@@ -60,6 +60,7 @@ typedef u16 kprobe_opcode_t;
 struct arch_specific_insn {
 	/* copy of original instruction */
 	kprobe_opcode_t *insn;
+	unsigned int is_ftrace_insn : 1;
 };
 
 struct prev_kprobe {
diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h
index 6cc51fe84410..34fbcac61133 100644
--- a/arch/s390/include/asm/lowcore.h
+++ b/arch/s390/include/asm/lowcore.h
@@ -147,7 +147,7 @@ struct _lowcore {
 	__u32	softirq_pending;		/* 0x02ec */
 	__u32	percpu_offset;			/* 0x02f0 */
 	__u32	machine_flags;			/* 0x02f4 */
-	__u32	ftrace_func;			/* 0x02f8 */
+	__u8	pad_0x02f8[0x02fc-0x02f8];	/* 0x02f8 */
 	__u32	spinlock_lockval;		/* 0x02fc */
 
 	__u8	pad_0x0300[0x0e00-0x0300];	/* 0x0300 */
@@ -297,7 +297,7 @@ struct _lowcore {
 	__u64	percpu_offset;			/* 0x0378 */
 	__u64	vdso_per_cpu_data;		/* 0x0380 */
 	__u64	machine_flags;			/* 0x0388 */
-	__u64	ftrace_func;			/* 0x0390 */
+	__u8	pad_0x0390[0x0398-0x0390];	/* 0x0390 */
 	__u64	gmap;				/* 0x0398 */
 	__u32	spinlock_lockval;		/* 0x03a0 */
 	__u8	pad_0x03a0[0x0400-0x03a4];	/* 0x03a4 */
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 00d460742e1e..5ef1a266936a 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -133,6 +133,18 @@ extern unsigned long MODULES_END;
 #define MODULES_LEN	(1UL << 31)
 #endif
 
+static inline int is_module_addr(void *addr)
+{
+#ifdef CONFIG_64BIT
+	BUILD_BUG_ON(MODULES_LEN > (1UL << 31));
+	if (addr < (void *)MODULES_VADDR)
+		return 0;
+	if (addr > (void *)MODULES_END)
+		return 0;
+#endif
+	return 1;
+}
+
 /*
  * A 31 bit pagetable entry of S390 has following format:
  *  |   PFRA          |    |  OS  |