tracing/syscalls: core infrastructure for syscalls tracing, enhancements

Impact: new feature

This adds the generic support for syscalls tracing. This is
currently exploited through a devoted tracer but other tracing
engines can use it. (They just have to play with
{start,stop}_ftrace_syscalls() and use the display callbacks
unless they want to override them.)

The syscalls prototypes definitions are abused here to steal
some metadata informations:

- syscall name, param types, param names, number of params

The syscall addr is not directly saved during this definition
because we don't know if its prototype is available in the
namespace. But we don't really need it. The arch has just to
build a function able to resolve the syscall number to its
metadata struct.

The current tracer prints the syscall names, parameters names
and values (and their types optionally). Currently the value is
a raw hex but higher level values diplaying is on my TODO list.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
LKML-Reference: <1236955332-10133-2-git-send-email-fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

3 files changed, 79 insertions, 6 deletions

diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 0e0f39be6c8b..d3bc3c86df6a 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -77,6 +77,14 @@
 #define TRACE_PRINTKS()
 #endif
 
+#ifdef CONFIG_FTRACE_SYSCALLS
+#define TRACE_SYSCALLS() VMLINUX_SYMBOL(__start_syscalls_metadata) = .; \
+                         *(__syscalls_metadata)                         \
+                         VMLINUX_SYMBOL(__stop_syscalls_metadata) = .;
+#else
+#define TRACE_SYSCALLS()
+#endif
+
 /* .data section */
 #define DATA_DATA                                                       \
         *(.data)                                                        \
@@ -99,7 +107,8 @@
         LIKELY_PROFILE()                                                \
         BRANCH_PROFILE()                                                \
         TRACE_PRINTKS()                                                 \
-        FTRACE_EVENTS()
+        FTRACE_EVENTS()                                                 \
+        TRACE_SYSCALLS()
 
 #define RO_DATA(align)                                                  \
         . = ALIGN((align));                                             \
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index c146c1021a29..6dc1c652447e 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -506,13 +506,21 @@ static inline void trace_hw_branch_oops(void) {}
 /*
  * A syscall entry in the ftrace syscalls array.
  *
- * @syscall_nr: syscall number
+ * @name: name of the syscall
+ * @nb_args: number of parameters it takes
+ * @types: list of types as strings
+ * @args: list of args as strings (args[i] matches types[i])
  */
-struct syscall_trace_entry {
-        int             syscall_nr;
+struct syscall_metadata {
+        const char      *name;
+        int             nb_args;
+        const char      **types;
+        const char      **args;
 };
 
 #ifdef CONFIG_FTRACE_SYSCALLS
+extern void arch_init_ftrace_syscalls(void);
+extern struct syscall_metadata *syscall_nr_to_meta(int nr);
 extern void start_ftrace_syscalls(void);
 extern void stop_ftrace_syscalls(void);
 extern void ftrace_syscall_enter(struct pt_regs *regs);
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index f9f900cfd066..0cff9bb80b02 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -65,6 +65,7 @@ struct old_linux_dirent;
 #include <asm/signal.h>
 #include <linux/quota.h>
 #include <linux/key.h>
+#include <linux/ftrace.h>
 
 #define __SC_DECL1(t1, a1)      t1 a1
 #define __SC_DECL2(t2, a2, ...) t2 a2, __SC_DECL1(__VA_ARGS__)
@@ -95,7 +96,46 @@ struct old_linux_dirent;
 #define __SC_TEST5(t5, a5, ...) __SC_TEST(t5); __SC_TEST4(__VA_ARGS__)
 #define __SC_TEST6(t6, a6, ...) __SC_TEST(t6); __SC_TEST5(__VA_ARGS__)
 
+#ifdef CONFIG_FTRACE_SYSCALLS
+#define __SC_STR_ADECL1(t, a)           #a
+#define __SC_STR_ADECL2(t, a, ...)      #a, __SC_STR_ADECL1(__VA_ARGS__)
+#define __SC_STR_ADECL3(t, a, ...)      #a, __SC_STR_ADECL2(__VA_ARGS__)
+#define __SC_STR_ADECL4(t, a, ...)      #a, __SC_STR_ADECL3(__VA_ARGS__)
+#define __SC_STR_ADECL5(t, a, ...)      #a, __SC_STR_ADECL4(__VA_ARGS__)
+#define __SC_STR_ADECL6(t, a, ...)      #a, __SC_STR_ADECL5(__VA_ARGS__)
+
+#define __SC_STR_TDECL1(t, a)           #t
+#define __SC_STR_TDECL2(t, a, ...)      #t, __SC_STR_TDECL1(__VA_ARGS__)
+#define __SC_STR_TDECL3(t, a, ...)      #t, __SC_STR_TDECL2(__VA_ARGS__)
+#define __SC_STR_TDECL4(t, a, ...)      #t, __SC_STR_TDECL3(__VA_ARGS__)
+#define __SC_STR_TDECL5(t, a, ...)      #t, __SC_STR_TDECL4(__VA_ARGS__)
+#define __SC_STR_TDECL6(t, a, ...)      #t, __SC_STR_TDECL5(__VA_ARGS__)
+
+#define SYSCALL_METADATA(sname, nb)                             \
+        static const struct syscall_metadata __used             \
+          __attribute__((__aligned__(4)))                       \
+          __attribute__((section("__syscalls_metadata")))       \
+          __syscall_meta_##sname = {                            \
+                .name           = "sys"#sname,                  \
+                .nb_args        = nb,                           \
+                .types          = types_##sname,                \
+                .args           = args_##sname,                 \
+        }
+
+#define SYSCALL_DEFINE0(sname)                                  \
+        static const struct syscall_metadata __used             \
+          __attribute__((__aligned__(4)))                       \
+          __attribute__((section("__syscalls_metadata")))       \
+          __syscall_meta_##sname = {                            \
+                .name           = "sys_"#sname,                 \
+                .nb_args        = 0,                            \
+        };                                                      \
+        asmlinkage long sys_##sname(void)
+
+#else
 #define SYSCALL_DEFINE0(name)      asmlinkage long sys_##name(void)
+#endif
+
 #define SYSCALL_DEFINE1(name, ...) SYSCALL_DEFINEx(1, _##name, __VA_ARGS__)
 #define SYSCALL_DEFINE2(name, ...) SYSCALL_DEFINEx(2, _##name, __VA_ARGS__)
 #define SYSCALL_DEFINE3(name, ...) SYSCALL_DEFINEx(3, _##name, __VA_ARGS__)
@@ -117,10 +157,26 @@ struct old_linux_dirent;
 #endif
 #endif
 
+#ifdef CONFIG_FTRACE_SYSCALLS
+#define SYSCALL_DEFINEx(x, sname, ...)                          \
+        static const char *types_##sname[] = {                  \
+                __SC_STR_TDECL##x(__VA_ARGS__)                  \
+        };                                                      \
+        static const char *args_##sname[] = {                   \
+                __SC_STR_ADECL##x(__VA_ARGS__)                  \
+        };                                                      \
+        SYSCALL_METADATA(sname, x);                             \
+        __SYSCALL_DEFINEx(x, sname, __VA_ARGS__)
+#else
+#define SYSCALL_DEFINEx(x, sname, ...)                          \
+        __SYSCALL_DEFINEx(x, sname, __VA_ARGS__)
+#endif
+
 #ifdef CONFIG_HAVE_SYSCALL_WRAPPERS
 
 #define SYSCALL_DEFINE(name) static inline long SYSC_##name
-#define SYSCALL_DEFINEx(x, name, ...)                                   \
+
+#define __SYSCALL_DEFINEx(x, name, ...)                                 \
         asmlinkage long sys##name(__SC_DECL##x(__VA_ARGS__));           \
         static inline long SYSC##name(__SC_DECL##x(__VA_ARGS__));       \
         asmlinkage long SyS##name(__SC_LONG##x(__VA_ARGS__))            \
@@ -134,7 +190,7 @@ struct old_linux_dirent;
 #else /* CONFIG_HAVE_SYSCALL_WRAPPERS */
 
 #define SYSCALL_DEFINE(name) asmlinkage long sys_##name
-#define SYSCALL_DEFINEx(x, name, ...)                                   \
+#define __SYSCALL_DEFINEx(x, name, ...)                                 \
         asmlinkage long sys##name(__SC_DECL##x(__VA_ARGS__))
 
 #endif /* CONFIG_HAVE_SYSCALL_WRAPPERS */