4 files changed, 94 insertions, 20 deletions

diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index 86cb51e1ca96..0525a8bdf65d 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -72,4 +72,28 @@ int ftrace_int3_handler(struct pt_regs *regs);
 #endif /* __ASSEMBLY__ */
 #endif /* CONFIG_FUNCTION_TRACER */
 
+
+#if !defined(__ASSEMBLY__) && !defined(COMPILE_OFFSETS)
+
+#if defined(CONFIG_FTRACE_SYSCALLS) && defined(CONFIG_IA32_EMULATION)
+#include <asm/compat.h>
+
+/*
+ * Because ia32 syscalls do not map to x86_64 syscall numbers
+ * this screws up the trace output when tracing a ia32 task.
+ * Instead of reporting bogus syscalls, just do not trace them.
+ *
+ * If the user realy wants these, then they should use the
+ * raw syscall tracepoints with filtering.
+ */
+#define ARCH_TRACE_IGNORE_COMPAT_SYSCALLS 1
+static inline bool arch_trace_is_compat_syscall(struct pt_regs *regs)
+{
+	if (is_compat_task())
+		return true;
+	return false;
+}
+#endif /* CONFIG_FTRACE_SYSCALLS && CONFIG_IA32_EMULATION */
+#endif /* !__ASSEMBLY__  && !COMPILE_OFFSETS */
+
 #endif /* _ASM_X86_FTRACE_H */
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 2d946e63ee82..2cd056e3ada3 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -20,7 +20,6 @@
 struct task_struct;
 struct exec_domain;
 #include <asm/processor.h>
-#include <asm/ftrace.h>
 #include <linux/atomic.h>
 
 struct thread_info {
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index ce8c3d68292f..98ca94a41819 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -3996,37 +3996,51 @@ static void ftrace_init_module(struct module *mod,
 	ftrace_process_locs(mod, start, end);
 }
 
-static int ftrace_module_notify(struct notifier_block *self,
-				unsigned long val, void *data)
+static int ftrace_module_notify_enter(struct notifier_block *self,
+				      unsigned long val, void *data)
 {
 	struct module *mod = data;
 
-	switch (val) {
-	case MODULE_STATE_COMING:
+	if (val == MODULE_STATE_COMING)
 		ftrace_init_module(mod, mod->ftrace_callsites,
 				   mod->ftrace_callsites +
 				   mod->num_ftrace_callsites);
-		break;
-	case MODULE_STATE_GOING:
+	return 0;
+}
+
+static int ftrace_module_notify_exit(struct notifier_block *self,
+				     unsigned long val, void *data)
+{
+	struct module *mod = data;
+
+	if (val == MODULE_STATE_GOING)
 		ftrace_release_mod(mod);
-		break;
-	}
 
 	return 0;
 }
 #else
-static int ftrace_module_notify(struct notifier_block *self,
-				unsigned long val, void *data)
+static int ftrace_module_notify_enter(struct notifier_block *self,
+				      unsigned long val, void *data)
+{
+	return 0;
+}
+static int ftrace_module_notify_exit(struct notifier_block *self,
+				     unsigned long val, void *data)
 {
 	return 0;
 }
 #endif /* CONFIG_MODULES */
 
-struct notifier_block ftrace_module_nb = {
-	.notifier_call = ftrace_module_notify,
+struct notifier_block ftrace_module_enter_nb = {
+	.notifier_call = ftrace_module_notify_enter,
 	.priority = INT_MAX,	/* Run before anything that can use kprobes */
 };
 
+struct notifier_block ftrace_module_exit_nb = {
+	.notifier_call = ftrace_module_notify_exit,
+	.priority = INT_MIN,	/* Run after anything that can remove kprobes */
+};
+
 extern unsigned long __start_mcount_loc[];
 extern unsigned long __stop_mcount_loc[];
 
@@ -4058,9 +4072,13 @@ void __init ftrace_init(void)
 				  __start_mcount_loc,
 				  __stop_mcount_loc);
 
-	ret = register_module_notifier(&ftrace_module_nb);
+	ret = register_module_notifier(&ftrace_module_enter_nb);
+	if (ret)
+		pr_warning("Failed to register trace ftrace module enter notifier\n");
+
+	ret = register_module_notifier(&ftrace_module_exit_nb);
 	if (ret)
-		pr_warning("Failed to register trace ftrace module notifier\n");
+		pr_warning("Failed to register trace ftrace module exit notifier\n");
 
 	set_ftrace_early_filters();
 
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 5329e13e74a1..7a809e321058 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -1,5 +1,6 @@
 #include <trace/syscall.h>
 #include <trace/events/syscalls.h>
+#include <linux/syscalls.h>
 #include <linux/slab.h>
 #include <linux/kernel.h>
 #include <linux/module.h>	/* for MODULE_NAME_LEN via KSYM_SYMBOL_LEN */
@@ -47,6 +48,38 @@ static inline bool arch_syscall_match_sym_name(const char *sym, const char *name
 }
 #endif
 
+#ifdef ARCH_TRACE_IGNORE_COMPAT_SYSCALLS
+/*
+ * Some architectures that allow for 32bit applications
+ * to run on a 64bit kernel, do not map the syscalls for
+ * the 32bit tasks the same as they do for 64bit tasks.
+ *
+ *     *cough*x86*cough*
+ *
+ * In such a case, instead of reporting the wrong syscalls,
+ * simply ignore them.
+ *
+ * For an arch to ignore the compat syscalls it needs to
+ * define ARCH_TRACE_IGNORE_COMPAT_SYSCALLS as well as
+ * define the function arch_trace_is_compat_syscall() to let
+ * the tracing system know that it should ignore it.
+ */
+static int
+trace_get_syscall_nr(struct task_struct *task, struct pt_regs *regs)
+{
+	if (unlikely(arch_trace_is_compat_syscall(regs)))
+		return -1;
+
+	return syscall_get_nr(task, regs);
+}
+#else
+static inline int
+trace_get_syscall_nr(struct task_struct *task, struct pt_regs *regs)
+{
+	return syscall_get_nr(task, regs);
+}
+#endif /* ARCH_TRACE_IGNORE_COMPAT_SYSCALLS */
+
 static __init struct syscall_metadata *
 find_syscall_meta(unsigned long syscall)
 {
@@ -276,10 +309,10 @@ static void ftrace_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 	struct syscall_metadata *sys_data;
 	struct ring_buffer_event *event;
 	struct ring_buffer *buffer;
-	int size;
 	int syscall_nr;
+	int size;
 
-	syscall_nr = syscall_get_nr(current, regs);
+	syscall_nr = trace_get_syscall_nr(current, regs);
 	if (syscall_nr < 0)
 		return;
 	if (!test_bit(syscall_nr, enabled_enter_syscalls))
@@ -313,7 +346,7 @@ static void ftrace_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 	struct ring_buffer *buffer;
 	int syscall_nr;
 
-	syscall_nr = syscall_get_nr(current, regs);
+	syscall_nr = trace_get_syscall_nr(current, regs);
 	if (syscall_nr < 0)
 		return;
 	if (!test_bit(syscall_nr, enabled_exit_syscalls))
@@ -502,7 +535,7 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 	int rctx;
 	int size;
 
-	syscall_nr = syscall_get_nr(current, regs);
+	syscall_nr = trace_get_syscall_nr(current, regs);
 	if (syscall_nr < 0)
 		return;
 	if (!test_bit(syscall_nr, enabled_perf_enter_syscalls))
@@ -578,7 +611,7 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 	int rctx;
 	int size;
 
-	syscall_nr = syscall_get_nr(current, regs);
+	syscall_nr = trace_get_syscall_nr(current, regs);
 	if (syscall_nr < 0)
 		return;
 	if (!test_bit(syscall_nr, enabled_perf_exit_syscalls))