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, 64 insertions, 0 deletions

diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S
index 89c801c2b5d1..3e430590c1e1 100644
--- a/arch/parisc/kernel/entry.S
+++ b/arch/parisc/kernel/entry.S
@@ -2012,6 +2012,70 @@ ftrace_stub:
 #endif
 ENDPROC_CFI(mcount)
 
+#ifdef CONFIG_DYNAMIC_FTRACE
+
+#ifdef CONFIG_64BIT
+#define FTRACE_FRAME_SIZE (2*FRAME_SIZE)
+#else
+#define FTRACE_FRAME_SIZE FRAME_SIZE
+#endif
+ENTRY_CFI(ftrace_caller, caller,frame=FTRACE_FRAME_SIZE,CALLS,SAVE_RP,SAVE_SP)
+ftrace_caller:
+	.global ftrace_caller
+
+	STREG	%r3, -FTRACE_FRAME_SIZE+1*REG_SZ(%sp)
+	ldo	-FTRACE_FRAME_SIZE(%sp), %r3
+	STREG	%rp, -RP_OFFSET(%r3)
+
+	/* Offset 0 is already allocated for %r1 */
+	STREG	%r23, 2*REG_SZ(%r3)
+	STREG	%r24, 3*REG_SZ(%r3)
+	STREG	%r25, 4*REG_SZ(%r3)
+	STREG	%r26, 5*REG_SZ(%r3)
+	STREG	%r28, 6*REG_SZ(%r3)
+	STREG	%r29, 7*REG_SZ(%r3)
+#ifdef CONFIG_64BIT
+	STREG	%r19, 8*REG_SZ(%r3)
+	STREG	%r20, 9*REG_SZ(%r3)
+	STREG	%r21, 10*REG_SZ(%r3)
+	STREG	%r22, 11*REG_SZ(%r3)
+	STREG	%r27, 12*REG_SZ(%r3)
+	STREG	%r31, 13*REG_SZ(%r3)
+	loadgp
+	ldo	-16(%sp),%r29
+#endif
+	LDREG	0(%r3), %r25
+	copy	%rp, %r26
+	ldo	-8(%r25), %r25
+	b,l	ftrace_function_trampoline, %rp
+	copy	%r3, %r24
+
+	LDREG	-RP_OFFSET(%r3), %rp
+	LDREG	2*REG_SZ(%r3), %r23
+	LDREG	3*REG_SZ(%r3), %r24
+	LDREG	4*REG_SZ(%r3), %r25
+	LDREG	5*REG_SZ(%r3), %r26
+	LDREG	6*REG_SZ(%r3), %r28
+	LDREG	7*REG_SZ(%r3), %r29
+#ifdef CONFIG_64BIT
+	LDREG	8*REG_SZ(%r3), %r19
+	LDREG	9*REG_SZ(%r3), %r20
+	LDREG	10*REG_SZ(%r3), %r21
+	LDREG	11*REG_SZ(%r3), %r22
+	LDREG	12*REG_SZ(%r3), %r27
+	LDREG	13*REG_SZ(%r3), %r31
+#endif
+	LDREG	1*REG_SZ(%r3), %r3
+
+	LDREGM	-FTRACE_FRAME_SIZE(%sp), %r1
+	/* Adjust return point to jump back to beginning of traced function */
+	ldo	-4(%r1), %r1
+	bv,n	(%r1)
+
+ENDPROC_CFI(ftrace_caller)
+
+#endif
+
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	.align 8
 ENTRY_CFI(return_to_handler, caller,frame=FRAME_SIZE)