powerpc/ftrace: Implement raw syscall tracepoints on PowerPC

This patch implements the raw syscall tracepoints on PowerPC and exports
them for ftrace syscalls to use.

To minimise reworking existing code, I slightly re-ordered the thread
info flags such that the new TIF_SYSCALL_TRACEPOINT bit would still fit
within the 16 bits of the andi. instruction's UI field. The instructions
in question are in /arch/powerpc/kernel/entry_{32,64}.S to and the
_TIF_SYSCALL_T_OR_A with the thread flags to see if system call tracing
is enabled.

In the case of 64bit PowerPC, arch_syscall_addr and
arch_syscall_match_sym_name are overridden to allow ftrace syscalls to
work given the unusual system call table structure and symbol names that
start with a period.

Signed-off-by: Ian Munsie <imunsie@au1.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

arch/powerpc/Kconfig

@@ -141,6 +141,7 @@ config PPC
 	select GENERIC_IRQ_SHOW
 	select GENERIC_IRQ_SHOW_LEVEL
 	select HAVE_RCU_TABLE_FREE if SMP
+	select HAVE_SYSCALL_TRACEPOINTS
 
 config EARLY_PRINTK
 	bool

arch/powerpc/include/asm/ftrace.h

@@ -60,4 +60,18 @@ struct dyn_arch_ftrace {
 
 #endif
 
+#if defined(CONFIG_FTRACE_SYSCALLS) && defined(CONFIG_PPC64) && !defined(__ASSEMBLY__)
+#define ARCH_HAS_SYSCALL_MATCH_SYM_NAME
+static inline bool arch_syscall_match_sym_name(const char *sym, const char *name)
+{
+	/*
+	 * Compare the symbol name with the system call name. Skip the .sys or .SyS
+	 * prefix from the symbol name and the sys prefix from the system call name and
+	 * just match the rest. This is only needed on ppc64 since symbol names on
+	 * 32bit do not start with a period so the generic function will work.
+	 */
+	return !strcmp(sym + 4, name + 3);
+}
+#endif /* CONFIG_FTRACE_SYSCALLS && CONFIG_PPC64 && !__ASSEMBLY__ */
+
 #endif /* _ASM_POWERPC_FTRACE */

arch/powerpc/include/asm/syscall.h

@@ -15,6 +15,11 @@
 
 #include <linux/sched.h>
 
+/* ftrace syscalls requires exporting the sys_call_table */
+#ifdef CONFIG_FTRACE_SYSCALLS
+extern const unsigned long *sys_call_table;
+#endif /* CONFIG_FTRACE_SYSCALLS */
+
 static inline long syscall_get_nr(struct task_struct *task,
 				  struct pt_regs *regs)
 {

arch/powerpc/include/asm/thread_info.h

@@ -110,7 +110,8 @@ static inline struct thread_info *current_thread_info(void)
 #define TIF_NOERROR		12	/* Force successful syscall return */
 #define TIF_NOTIFY_RESUME	13	/* callback before returning to user */
 #define TIF_FREEZE		14	/* Freezing for suspend */
-#define TIF_RUNLATCH		15	/* Is the runlatch enabled? */
+#define TIF_SYSCALL_TRACEPOINT	15	/* syscall tracepoint instrumentation */
+#define TIF_RUNLATCH		16	/* Is the runlatch enabled? */
 
 /* as above, but as bit values */
 #define _TIF_SYSCALL_TRACE	(1<<TIF_SYSCALL_TRACE)
@@ -127,8 +128,10 @@ static inline struct thread_info *current_thread_info(void)
 #define _TIF_NOERROR		(1<<TIF_NOERROR)
 #define _TIF_NOTIFY_RESUME	(1<<TIF_NOTIFY_RESUME)
 #define _TIF_FREEZE		(1<<TIF_FREEZE)
+#define _TIF_SYSCALL_TRACEPOINT	(1<<TIF_SYSCALL_TRACEPOINT)
 #define _TIF_RUNLATCH		(1<<TIF_RUNLATCH)
-#define _TIF_SYSCALL_T_OR_A	(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP)
+#define _TIF_SYSCALL_T_OR_A	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
+				 _TIF_SECCOMP | _TIF_SYSCALL_TRACEPOINT)
 
 #define _TIF_USER_WORK_MASK	(_TIF_SIGPENDING | _TIF_NEED_RESCHED | \
 				 _TIF_NOTIFY_RESUME)

arch/powerpc/kernel/Makefile

@@ -109,6 +109,7 @@ obj-$(CONFIG_PPC_IO_WORKAROUNDS)	+= io-workarounds.o
 
 obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o
 obj-$(CONFIG_FUNCTION_GRAPH_TRACER)	+= ftrace.o
+obj-$(CONFIG_FTRACE_SYSCALLS)	+= ftrace.o
 obj-$(CONFIG_PERF_EVENTS)	+= perf_callchain.o
 
 obj-$(CONFIG_PPC_PERF_CTRS)	+= perf_event.o

arch/powerpc/kernel/ftrace.c

@@ -22,6 +22,7 @@
 #include <asm/cacheflush.h>
 #include <asm/code-patching.h>
 #include <asm/ftrace.h>
+#include <asm/syscall.h>
 
 
 #ifdef CONFIG_DYNAMIC_FTRACE
@@ -600,3 +601,10 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr)
 	}
 }
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
+#if defined(CONFIG_FTRACE_SYSCALLS) && defined(CONFIG_PPC64)
+unsigned long __init arch_syscall_addr(int nr)
+{
+	return sys_call_table[nr*2];
+}
+#endif /* CONFIG_FTRACE_SYSCALLS && CONFIG_PPC64 */

arch/powerpc/kernel/ptrace.c

@@ -29,6 +29,7 @@
 #include <linux/signal.h>
 #include <linux/seccomp.h>
 #include <linux/audit.h>
+#include <trace/syscall.h>
 #ifdef CONFIG_PPC32
 #include <linux/module.h>
 #endif
@@ -40,6 +41,9 @@
 #include <asm/pgtable.h>
 #include <asm/system.h>
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/syscalls.h>
+
 /*
  * The parameter save area on the stack is used to store arguments being passed
  * to callee function and is located at fixed offset from stack pointer.
@@ -1710,6 +1714,9 @@ long do_syscall_trace_enter(struct pt_regs *regs)
 		 */
 		ret = -1L;
 
+	if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
+		trace_sys_enter(regs, regs->gpr[0]);
+
 	if (unlikely(current->audit_context)) {
 #ifdef CONFIG_PPC64
 		if (!is_32bit_task())
@@ -1738,6 +1745,9 @@ void do_syscall_trace_leave(struct pt_regs *regs)
 		audit_syscall_exit((regs->ccr&0x10000000)?AUDITSC_FAILURE:AUDITSC_SUCCESS,
 				   regs->result);
 
+	if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
+		trace_sys_exit(regs, regs->result);
+
 	step = test_thread_flag(TIF_SINGLESTEP);
 	if (step || test_thread_flag(TIF_SYSCALL_TRACE))
 		tracehook_report_syscall_exit(regs, step);