parisc: add dynamic ftrace

This patch implements dynamic ftrace for PA-RISC. The required mcount
call sequences can get pretty long, so instead of patching the
whole call sequence out of the functions, we are using
-fpatchable-function-entry from gcc. This puts a configurable amount of
NOPS before/at the start of the function. Taking do_sys_open() as example,
which would look like this when the call is patched out:

1036b248:       08 00 02 40     nop
1036b24c:       08 00 02 40     nop
1036b250:       08 00 02 40     nop
1036b254:       08 00 02 40     nop

1036b258 <do_sys_open>:
1036b258:       08 00 02 40     nop
1036b25c:       08 03 02 41     copy r3,r1
1036b260:       6b c2 3f d9     stw rp,-14(sp)
1036b264:       08 1e 02 43     copy sp,r3
1036b268:       6f c1 01 00     stw,ma r1,80(sp)

When ftrace gets enabled for this function the kernel will patch these
NOPs to:

1036b248:       10 19 57 20     <address of ftrace>
1036b24c:       6f c1 00 80     stw,ma r1,40(sp)
1036b250:       48 21 3f d1     ldw -18(r1),r1
1036b254:       e8 20 c0 02     bv,n r0(r1)

1036b258 <do_sys_open>:
1036b258:       e8 3f 1f df     b,l,n .-c,r1
1036b25c:       08 03 02 41     copy r3,r1
1036b260:       6b c2 3f d9     stw rp,-14(sp)
1036b264:       08 1e 02 43     copy sp,r3
1036b268:       6f c1 01 00     stw,ma r1,80(sp)

So the first NOP in do_sys_open() will be patched to jump backwards into
some minimal trampoline code which pushes a stackframe, saves r1 which
holds the return address, loads the address of the real ftrace function,
and branches to that location. For 64 Bit things are getting a bit more
complicated (and longer) because we must make sure that the address of
ftrace location is 8 byte aligned, and the offset passed to ldd for
fetching the address is 8 byte aligned as well.

Note that gcc has a bug which misplaces the function label, and needs a
patch to make dynamic ftrace work. See
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=90751 for details.

Signed-off-by: Sven Schnelle <svens@stackframe.org>
Signed-off-by: Helge Deller <deller@gmx.de>

1 files changed, 120 insertions, 9 deletions

diff --git a/arch/parisc/kernel/ftrace.c b/arch/parisc/kernel/ftrace.c
index a28f915993b1..d784ccdd8fef 100644
--- a/arch/parisc/kernel/ftrace.c
+++ b/arch/parisc/kernel/ftrace.c
@@ -7,17 +7,17 @@
  * Copyright (C) 2007-2008 Steven Rostedt <srostedt@redhat.com>
  *
  * future possible enhancements:
- * 	- add CONFIG_DYNAMIC_FTRACE
  *	- add CONFIG_STACK_TRACER
  */
 
 #include <linux/init.h>
 #include <linux/ftrace.h>
+#include <linux/uaccess.h>
 
 #include <asm/assembly.h>
 #include <asm/sections.h>
 #include <asm/ftrace.h>
-
+#include <asm/patch.h>
 
 #define __hot __attribute__ ((__section__ (".text.hot")))
 
@@ -50,13 +50,11 @@ void notrace __hot ftrace_function_trampoline(unsigned long parent,
 				unsigned long self_addr,
 				unsigned long org_sp_gr3)
 {
-	extern ftrace_func_t ftrace_trace_function;  /* depends on CONFIG_DYNAMIC_FTRACE */
-
-	if (ftrace_trace_function != ftrace_stub) {
-		/* struct ftrace_ops *op, struct pt_regs *regs); */
-		ftrace_trace_function(parent, self_addr, NULL, NULL);
-		return;
-	}
+#ifndef CONFIG_DYNAMIC_FTRACE
+	extern ftrace_func_t ftrace_trace_function;
+#endif
+	if (ftrace_trace_function != ftrace_stub)
+		ftrace_trace_function(self_addr, parent, NULL, NULL);
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	if (ftrace_graph_return != (trace_func_graph_ret_t) ftrace_stub ||
@@ -75,3 +73,116 @@ void notrace __hot ftrace_function_trampoline(unsigned long parent,
 #endif
 }
 
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+int ftrace_enable_ftrace_graph_caller(void)
+{
+	return 0;
+}
+
+int ftrace_disable_ftrace_graph_caller(void)
+{
+	return 0;
+}
+#endif
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+
+int __init ftrace_dyn_arch_init(void)
+{
+	return 0;
+}
+int ftrace_update_ftrace_func(ftrace_func_t func)
+{
+	return 0;
+}
+
+unsigned long ftrace_call_adjust(unsigned long addr)
+{
+	return addr+(FTRACE_PATCHABLE_FUNCTION_SIZE-1)*4;
+}
+
+int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+	u32 insn[FTRACE_PATCHABLE_FUNCTION_SIZE];
+	u32 *tramp;
+	int size, ret, i;
+	void *ip;
+
+#ifdef CONFIG_64BIT
+	unsigned long addr2 =
+		(unsigned long)dereference_function_descriptor((void *)addr);
+
+	u32 ftrace_trampoline[] = {
+		0x73c10208, /* std,ma r1,100(sp) */
+		0x0c2110c1, /* ldd -10(r1),r1 */
+		0xe820d002, /* bve,n (r1) */
+		addr2 >> 32,
+		addr2 & 0xffffffff,
+		0xe83f1fd7, /* b,l,n .-14,r1 */
+	};
+
+	u32 ftrace_trampoline_unaligned[] = {
+		addr2 >> 32,
+		addr2 & 0xffffffff,
+		0x37de0200, /* ldo 100(sp),sp */
+		0x73c13e01, /* std r1,-100(sp) */
+		0x34213ff9, /* ldo -4(r1),r1 */
+		0x50213fc1, /* ldd -20(r1),r1 */
+		0xe820d002, /* bve,n (r1) */
+		0xe83f1fcf, /* b,l,n .-20,r1 */
+	};
+
+	BUILD_BUG_ON(ARRAY_SIZE(ftrace_trampoline_unaligned) >
+				FTRACE_PATCHABLE_FUNCTION_SIZE);
+#else
+	u32 ftrace_trampoline[] = {
+		(u32)addr,
+		0x6fc10080, /* stw,ma r1,40(sp) */
+		0x48213fd1, /* ldw -18(r1),r1 */
+		0xe820c002, /* bv,n r0(r1) */
+		0xe83f1fdf, /* b,l,n .-c,r1 */
+	};
+#endif
+
+	BUILD_BUG_ON(ARRAY_SIZE(ftrace_trampoline) >
+				FTRACE_PATCHABLE_FUNCTION_SIZE);
+
+	size = sizeof(ftrace_trampoline);
+	tramp = ftrace_trampoline;
+
+#ifdef CONFIG_64BIT
+	if (rec->ip & 0x4) {
+		size = sizeof(ftrace_trampoline_unaligned);
+		tramp = ftrace_trampoline_unaligned;
+	}
+#endif
+
+	ip = (void *)(rec->ip + 4 - size);
+
+	ret = probe_kernel_read(insn, ip, size);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < size / 4; i++) {
+		if (insn[i] != INSN_NOP)
+			return -EINVAL;
+	}
+
+	__patch_text_multiple(ip, tramp, size);
+	return 0;
+}
+
+int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec,
+		    unsigned long addr)
+{
+	u32 insn[FTRACE_PATCHABLE_FUNCTION_SIZE];
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(insn); i++)
+		insn[i] = INSN_NOP;
+
+	__patch_text_multiple((void *)rec->ip + 4 - sizeof(insn),
+			      insn, sizeof(insn));
+	return 0;
+}
+#endif