MIPS: Tracing: Add function graph tracer support for MIPS

The implementation of function graph tracer for MIPS is a little
different from X86.

in MIPS, gcc(with -pg) only transfer the caller's return address(at) and
the _mcount's return address(ra) to us.

For the kernel part without -mlong-calls:

move at, ra
jal _mcount

For the module part with -mlong-calls:

lui v1, hi16bit_of_mcount
addiu v1, v1, low16bit_of_mcount
move at, ra
jal _mcount

Without -mlong-calls,

if the function is a leaf, it will not save the return address(ra):

ffffffff80101298 <au1k_wait>:
ffffffff80101298:       67bdfff0        daddiu  sp,sp,-16
ffffffff8010129c:       ffbe0008        sd      s8,8(sp)
ffffffff801012a0:       03a0f02d        move    s8,sp
ffffffff801012a4:       03e0082d        move    at,ra
ffffffff801012a8:       0c042930        jal     ffffffff8010a4c0 <_mcount>
ffffffff801012ac:       00020021        nop

so, we can hijack it directly in _mcount, but if the function is non-leaf, the
return address is saved in the stack.

ffffffff80133030 <copy_process>:
ffffffff80133030:       67bdff50        daddiu  sp,sp,-176
ffffffff80133034:       ffbe00a0        sd      s8,160(sp)
ffffffff80133038:       03a0f02d        move    s8,sp
ffffffff8013303c:       ffbf00a8        sd      ra,168(sp)
ffffffff80133040:       ffb70098        sd      s7,152(sp)
ffffffff80133044:       ffb60090        sd      s6,144(sp)
ffffffff80133048:       ffb50088        sd      s5,136(sp)
ffffffff8013304c:       ffb40080        sd      s4,128(sp)
ffffffff80133050:       ffb30078        sd      s3,120(sp)
ffffffff80133054:       ffb20070        sd      s2,112(sp)
ffffffff80133058:       ffb10068        sd      s1,104(sp)
ffffffff8013305c:       ffb00060        sd      s0,96(sp)
ffffffff80133060:       03e0082d        move    at,ra
ffffffff80133064:       0c042930        jal     ffffffff8010a4c0 <_mcount>
ffffffff80133068:       00020021        nop

but we can not get the exact stack address(which saved ra) directly in
_mcount, we need to search the content of at register in the stack space
or search the "s{d,w} ra, offset(sp)" instruction in the text. 'Cause we
can not prove there is only a match in the stack space, so, we search
the text instead.

as we can see, if the first instruction above "move at, ra" is not a
store instruction, there should be a leaf function, so we hijack the at
register directly via putting &return_to_handler into it, otherwise, we
search the "s{d,w} ra, offset(sp)" instruction to get the stack offset,
and then the stack address. we use the above copy_process() as an
example, we at last find "ffbf00a8", 0xa8 is the stack offset, we plus
it with s8(fp), that is the stack address, we hijack the content via
writing the &return_to_handler in.

If with -mlong-calls, since there are two more instructions above "move
at, ra", so, we can move the pointer to the position above "lui v1,
hi16bit_of_mcount".

Signed-off-by: Wu Zhangjin <wuzhangjin@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Nicholas Mc Guire <der.herr@hofr.at>
Cc: zhangfx@lemote.com
Cc: Wu Zhangjin <wuzhangjin@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: linux-kernel@vger.kernel.org
Cc: linux-mips@linux-mips.org
Patchwork: http://patchwork.linux-mips.org/patch/677/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>

1 files changed, 106 insertions, 0 deletions

diff --git a/arch/mips/kernel/ftrace.c b/arch/mips/kernel/ftrace.c
index 5459a7838370..65a3f8a89927 100644
--- a/arch/mips/kernel/ftrace.c
+++ b/arch/mips/kernel/ftrace.c
@@ -13,6 +13,8 @@
 #include <linux/ftrace.h>
 
 #include <asm/cacheflush.h>
+#include <asm/asm.h>
+#include <asm/asm-offsets.h>
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 
@@ -110,3 +112,107 @@ int __init ftrace_dyn_arch_init(void *data)
         return 0;
 }
 #endif                          /* CONFIG_DYNAMIC_FTRACE */
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+
+#define S_RA_SP (0xafbf << 16)  /* s{d,w} ra, offset(sp) */
+#define S_R_SP  (0xafb0 << 16)  /* s{d,w} R, offset(sp) */
+#define OFFSET_MASK     0xffff  /* stack offset range: 0 ~ PT_SIZE */
+
+unsigned long ftrace_get_parent_addr(unsigned long self_addr,
+                                     unsigned long parent,
+                                     unsigned long parent_addr,
+                                     unsigned long fp)
+{
+        unsigned long sp, ip, ra;
+        unsigned int code;
+
+        /* in module or kernel? */
+        if (self_addr & 0x40000000) {
+                /* module: move to the instruction "lui v1, HI_16BIT_OF_MCOUNT" */
+                ip = self_addr - 20;
+        } else {
+                /* kernel: move to the instruction "move ra, at" */
+                ip = self_addr - 12;
+        }
+
+        /* search the text until finding the non-store instruction or "s{d,w}
+         * ra, offset(sp)" instruction */
+        do {
+                ip -= 4;
+
+                /* get the code at "ip" */
+                code = *(unsigned int *)ip;
+
+                /* If we hit the non-store instruction before finding where the
+                 * ra is stored, then this is a leaf function and it does not
+                 * store the ra on the stack. */
+                if ((code & S_R_SP) != S_R_SP)
+                        return parent_addr;
+
+        } while (((code & S_RA_SP) != S_RA_SP));
+
+        sp = fp + (code & OFFSET_MASK);
+        ra = *(unsigned long *)sp;
+
+        if (ra == parent)
+                return sp;
+
+        return 0;
+}
+
+/*
+ * Hook the return address and push it in the stack of return addrs
+ * in current thread info.
+ */
+void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
+                           unsigned long fp)
+{
+        unsigned long old;
+        struct ftrace_graph_ent trace;
+        unsigned long return_hooker = (unsigned long)
+            &return_to_handler;
+
+        if (unlikely(atomic_read(&current->tracing_graph_pause)))
+                return;
+
+        /* "parent" is the stack address saved the return address of the caller
+         * of _mcount, for a leaf function not save the return address in the
+         * stack address, so, we "emulate" one in _mcount's stack space, and
+         * hijack it directly, but for a non-leaf function, it will save the
+         * return address to the its stack space, so, we can not hijack the
+         * "parent" directly, but need to find the real stack address,
+         * ftrace_get_parent_addr() does it!
+         */
+
+        old = *parent;
+
+        parent = (unsigned long *)ftrace_get_parent_addr(self_addr, old,
+                                                         (unsigned long)parent,
+                                                         fp);
+
+        /* If fails when getting the stack address of the non-leaf function's
+         * ra, stop function graph tracer and return */
+        if (parent == 0) {
+                ftrace_graph_stop();
+                WARN_ON(1);
+                return;
+        }
+
+        *parent = return_hooker;
+
+        if (ftrace_push_return_trace(old, self_addr, &trace.depth, fp) ==
+            -EBUSY) {
+                *parent = old;
+                return;
+        }
+
+        trace.func = self_addr;
+
+        /* Only trace if the calling function expects to */
+        if (!ftrace_graph_entry(&trace)) {
+                current->curr_ret_stack--;
+                *parent = old;
+        }
+}
+#endif                          /* CONFIG_FUNCTION_GRAPH_TRACER */