[PATCH 5/6] trace, powerpc: Implement raw syscall tracepoints on PowerPC

[PATCH 5/6] trace, powerpc: Implement raw syscall tracepoints on PowerPC

[Ian Munsie]

From: Ian Munsie <imunsie@au.ibm.com>

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>
---
 arch/powerpc/Kconfig                   |    1 +
 arch/powerpc/include/asm/syscall.h     |    5 +++++
 arch/powerpc/include/asm/thread_info.h |    7 +++++--
 arch/powerpc/kernel/Makefile           |    1 +
 arch/powerpc/kernel/ftrace.c           |   19 +++++++++++++++++++
 arch/powerpc/kernel/ptrace.c           |   10 ++++++++++
 6 files changed, 41 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index e625e9e..6614b69 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -140,6 +140,7 @@ config PPC
 	select HAVE_PERF_EVENTS
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_HW_BREAKPOINT if PERF_EVENTS && PPC_BOOK3S_64
+	select HAVE_SYSCALL_TRACEPOINTS
 
 config EARLY_PRINTK
 	bool
diff --git a/arch/powerpc/include/asm/syscall.h b/arch/powerpc/include/asm/syscall.h
index 23913e9..b54b2ad 100644
--- a/arch/powerpc/include/asm/syscall.h
+++ b/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)
 {
diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h
index 65eb859..4403f09 100644
--- a/arch/powerpc/include/asm/thread_info.h
+++ b/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)
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 36c30f3..13d6eb0 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -106,6 +106,7 @@ obj64-$(CONFIG_AUDIT)		+= compat_audit.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
diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c
index ce1f3e4..f5fadbb 100644
--- a/arch/powerpc/kernel/ftrace.c
+++ b/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 +601,21 @@ 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];
+}
+
+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. 32bit can use the generic
+	 * function since their symbol names don't start with a period.
+	 */
+	return (!strcmp(sym + 4, name + 3));
+}
+#endif /* CONFIG_FTRACE_SYSCALLS && CONFIG_PPC64 */
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index a9b3296..f70d144 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/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.
@@ -1681,6 +1685,9 @@ 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())
@@ -1709,6 +1716,9 @@ 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);
-- 
1.7.2.3

PowerPC, ftrace: Add PPC raw syscall tracepoints & ftrace fixes (subset from v2)

[Ian Munsie]

Oops, It seems that I missed LKML in the to address of the cover email
for this set. Guess I shouldn't send a patch set just as the fire alarm
goes off.  Resending:


Hi all,

This is a partial version of my 'ftrace syscalls, PowerPC: Various fixes,
Compat Syscall support and PowerPC implementation'.

I've been tied up with other work and haven't had time to complete the
work on the v3 of the full set, but the patches I'm including here are
pretty stable and there has been a request for the raw syscall
tracepoints in PowerPC.

The actual patches included here have not been changed from the v2 other than
rebasing them on tip/master. They add support for *raw* syscall tracepoints on
PowerPC, while fixing ftrace syscalls to ensure that events will only be created
for syscalls that successfully map their metadata to a syscall number,
so that non-working phantom events are not created.

Patch #2 and #6 in this series are not strictly necessary for this, they just
optimise ftrace syscalls a bit.


What's missing from this series that was in the v2 is the conversion of
all the syscalls implemented under /arch/powerpc, Jason Baron's compat
syscall support and the conversion of the remaining native and compat
syscalls to this infrastructure.

Cheers,
-Ian

GIT: [PATCH 1/6] ftrace syscalls: don't add events for unmapped syscalls
GIT: [PATCH 2/6] trace syscalls: Remove redundant syscall_nr checks
GIT: [PATCH 3/6] ftrace syscalls: Make arch_syscall_addr weak
GIT: [PATCH 4/6] ftrace syscalls: Allow arch specific syscall symbol matching
GIT: [PATCH 5/6] trace, powerpc: Implement raw syscall tracepoints on PowerPC
GIT: [PATCH 6/6] trace syscalls: Early terminate search for sys_ni_syscall

[PATCH 5/6] trace, powerpc: Implement raw syscall tracepoints on PowerPC

[Ian Munsie]

From: Ian Munsie <imunsie@au.ibm.com>

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>
---
 arch/powerpc/Kconfig                   |    1 +
 arch/powerpc/include/asm/ftrace.h      |   10 ++++++++++
 arch/powerpc/include/asm/syscall.h     |    5 +++++
 arch/powerpc/include/asm/thread_info.h |    7 +++++--
 arch/powerpc/kernel/Makefile           |    1 +
 arch/powerpc/kernel/ftrace.c           |    8 ++++++++
 arch/powerpc/kernel/ptrace.c           |   10 ++++++++++
 7 files changed, 40 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 7d69e9b..a0e8e02 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -134,6 +134,7 @@ config PPC
 	select HAVE_GENERIC_HARDIRQS
 	select HAVE_SPARSE_IRQ
 	select IRQ_PER_CPU
+	select HAVE_SYSCALL_TRACEPOINTS
 
 config EARLY_PRINTK
 	bool
diff --git a/arch/powerpc/include/asm/ftrace.h b/arch/powerpc/include/asm/ftrace.h
index dde1296..0a08902 100644
--- a/arch/powerpc/include/asm/ftrace.h
+++ b/arch/powerpc/include/asm/ftrace.h
@@ -60,4 +60,14 @@ struct dyn_arch_ftrace {
 
 #endif
 
+#if defined(CONFIG_FTRACE_SYSCALLS) && defined(CONFIG_PPC64)
+/*
+ * 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.
+ */
+#define arch_syscall_match_sym_name(sym, name) !strcmp(sym + 4, name + 3)
+#endif /* CONFIG_FTRACE_SYSCALLS && CONFIG_PPC64 */
+
 #endif /* _ASM_POWERPC_FTRACE */
diff --git a/arch/powerpc/include/asm/syscall.h b/arch/powerpc/include/asm/syscall.h
index 23913e9..b54b2ad 100644
--- a/arch/powerpc/include/asm/syscall.h
+++ b/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)
 {
diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h
index 65eb859..4403f09 100644
--- a/arch/powerpc/include/asm/thread_info.h
+++ b/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)
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 3bb2a3e..fe1ac47 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -105,6 +105,7 @@ obj64-$(CONFIG_AUDIT)		+= compat_audit.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
diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c
index ce1f3e4..bf99cfa 100644
--- a/arch/powerpc/kernel/ftrace.c
+++ b/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 */
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index 9065369..b6ff0cb 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/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.
@@ -1691,6 +1695,9 @@ 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())
@@ -1719,6 +1726,9 @@ 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);
-- 
1.7.2.3