s390/ftrace: use expoline for indirect branches

The return from the ftrace_stub, _mcount, ftrace_caller and
return_to_handler functions is done with "br %r14" and "br %r1".
These are indirect branches as well and need to use execute
trampolines for CONFIG_EXPOLINE=y.

The ftrace_caller function is a special case as it returns to the
start of a function and may only use %r0 and %r1. For a pre z10
machine the standard execute trampoline uses a LARL + EX to do
this, but this requires *two* registers in the range %r1..%r15.
To get around this the 'br %r1' located in the lowcore is used,
then the EX instruction does not need an address register.
But the lowcore trick may only be used for pre z14 machines,
with noexec=on the mapping for the first page may not contain
instructions. The solution for that is an ALTERNATIVE in the
expoline THUNK generated by 'GEN_BR_THUNK %r1' to switch to
EXRL, this relies on the fact that a machine that supports
noexec=on has EXRL as well.

Cc: stable@vger.kernel.org # 4.16
Fixes: f19fbd5ed6 ("s390: introduce execute-trampolines for branches")
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

arch/s390/include/asm/nospec-insn.h

@@ -2,12 +2,16 @@
 #ifndef _ASM_S390_NOSPEC_ASM_H
 #define _ASM_S390_NOSPEC_ASM_H
 
+#include <asm/alternative-asm.h>
+#include <asm/asm-offsets.h>
 #include <asm/dwarf.h>
 
 #ifdef __ASSEMBLY__
 
 #ifdef CONFIG_EXPOLINE
 
+_LC_BR_R1 = __LC_BR_R1
+
 /*
  * The expoline macros are used to create thunks in the same format
  * as gcc generates them. The 'comdat' section flag makes sure that
@@ -78,13 +82,21 @@
 	.endm
 
 	.macro __THUNK_EX_BR reg,ruse
+	# Be very careful when adding instructions to this macro!
+	# The ALTERNATIVE replacement code has a .+10 which targets
+	# the "br \reg" after the code has been patched.
 #ifdef CONFIG_HAVE_MARCH_Z10_FEATURES
 	exrl	0,555f
 	j	.
 #else
+	.ifc \reg,%r1
+	ALTERNATIVE "ex %r0,_LC_BR_R1", ".insn ril,0xc60000000000,0,.+10", 35
+	j	.
+	.else
 	larl	\ruse,555f
 	ex	0,0(\ruse)
 	j	.
+	.endif
 #endif
 555:	br	\reg
 	.endm

arch/s390/kernel/asm-offsets.c

@@ -181,6 +181,7 @@ int main(void)
 	OFFSET(__LC_MACHINE_FLAGS, lowcore, machine_flags);
 	OFFSET(__LC_PREEMPT_COUNT, lowcore, preempt_count);
 	OFFSET(__LC_GMAP, lowcore, gmap);
+	OFFSET(__LC_BR_R1, lowcore, br_r1_trampoline);
 	/* software defined ABI-relevant lowcore locations 0xe00 - 0xe20 */
 	OFFSET(__LC_DUMP_REIPL, lowcore, ipib);
 	/* hardware defined lowcore locations 0x1000 - 0x18ff */

arch/s390/kernel/mcount.S

@@ -9,13 +9,17 @@
 #include <linux/linkage.h>
 #include <asm/asm-offsets.h>
 #include <asm/ftrace.h>
+#include <asm/nospec-insn.h>
 #include <asm/ptrace.h>
 #include <asm/export.h>
 
+	GEN_BR_THUNK %r1
+	GEN_BR_THUNK %r14
+
 	.section .kprobes.text, "ax"
 
 ENTRY(ftrace_stub)
-	br	%r14
+	BR_EX	%r14
 
 #define STACK_FRAME_SIZE  (STACK_FRAME_OVERHEAD + __PT_SIZE)
 #define STACK_PTREGS	  (STACK_FRAME_OVERHEAD)
@@ -23,7 +27,7 @@ ENTRY(ftrace_stub)
 #define STACK_PTREGS_PSW  (STACK_PTREGS + __PT_PSW)
 
 ENTRY(_mcount)
-	br	%r14
+	BR_EX	%r14
 
 EXPORT_SYMBOL(_mcount)
 
@@ -53,7 +57,7 @@ ENTRY(ftrace_caller)
 #endif
 	lgr	%r3,%r14
 	la	%r5,STACK_PTREGS(%r15)
-	basr	%r14,%r1
+	BASR_EX	%r14,%r1
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 # The j instruction gets runtime patched to a nop instruction.
 # See ftrace_enable_ftrace_graph_caller.
@@ -68,7 +72,7 @@ ftrace_graph_caller_end:
 #endif
 	lg	%r1,(STACK_PTREGS_PSW+8)(%r15)
 	lmg	%r2,%r15,(STACK_PTREGS_GPRS+2*8)(%r15)
-	br	%r1
+	BR_EX	%r1
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 
@@ -81,6 +85,6 @@ ENTRY(return_to_handler)
 	aghi	%r15,STACK_FRAME_OVERHEAD
 	lgr	%r14,%r2
 	lmg	%r2,%r5,32(%r15)
-	br	%r14
+	BR_EX	%r14
 
 #endif