s390: introduce execute-trampolines for branches

Add CONFIG_EXPOLINE to enable the use of the new -mindirect-branch= and
-mfunction_return= compiler options to create a kernel fortified against
the specte v2 attack.

With CONFIG_EXPOLINE=y all indirect branches will be issued with an
execute type instruction. For z10 or newer the EXRL instruction will
be used, for older machines the EX instruction. The typical indirect
call

	basr	%r14,%r1

is replaced with a PC relative call to a new thunk

	brasl	%r14,__s390x_indirect_jump_r1

The thunk contains the EXRL/EX instruction to the indirect branch

__s390x_indirect_jump_r1:
	exrl	0,0f
	j	.
0:	br	%r1

The detour via the execute type instruction has a performance impact.
To get rid of the detour the new kernel parameter "nospectre_v2" and
"spectre_v2=[on,off,auto]" can be used. If the parameter is specified
the kernel and module code will be patched at runtime.

Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

arch/s390/kernel/Makefile

@@ -29,6 +29,7 @@ UBSAN_SANITIZE_early.o	:= n
 #
 ifneq ($(CC_FLAGS_MARCH),-march=z900)
 CFLAGS_REMOVE_als.o	+= $(CC_FLAGS_MARCH)
+CFLAGS_REMOVE_als.o	+= $(CC_FLAGS_EXPOLINE)
 CFLAGS_als.o		+= -march=z900
 AFLAGS_REMOVE_head.o	+= $(CC_FLAGS_MARCH)
 AFLAGS_head.o		+= -march=z900
@@ -63,6 +64,9 @@ obj-y	+= entry.o reipl.o relocate_kernel.o kdebugfs.o alternative.o
 
 extra-y				+= head.o head64.o vmlinux.lds
 
+obj-$(CONFIG_EXPOLINE)		+= nospec-branch.o
+CFLAGS_REMOVE_expoline.o	+= $(CC_FLAGS_EXPOLINE)
+
 obj-$(CONFIG_MODULES)		+= module.o
 obj-$(CONFIG_SMP)		+= smp.o
 obj-$(CONFIG_SCHED_TOPOLOGY)	+= topology.o

arch/s390/kernel/entry.S

@@ -222,6 +222,68 @@ _PIF_WORK	= (_PIF_PER_TRAP | _PIF_SYSCALL_RESTART)
 	.popsection
 	.endm
 
+#ifdef CONFIG_EXPOLINE
+
+	.macro GEN_BR_THUNK name,reg,tmp
+	.section .text.\name,"axG",@progbits,\name,comdat
+	.globl \name
+	.hidden \name
+	.type \name,@function
+\name:
+	.cfi_startproc
+#ifdef CONFIG_HAVE_MARCH_Z10_FEATURES
+	exrl	0,0f
+#else
+	larl	\tmp,0f
+	ex	0,0(\tmp)
+#endif
+	j	.
+0:	br	\reg
+	.cfi_endproc
+	.endm
+
+	GEN_BR_THUNK __s390x_indirect_jump_r1use_r9,%r9,%r1
+	GEN_BR_THUNK __s390x_indirect_jump_r1use_r14,%r14,%r1
+	GEN_BR_THUNK __s390x_indirect_jump_r11use_r14,%r14,%r11
+
+	.macro BASR_R14_R9
+0:	brasl	%r14,__s390x_indirect_jump_r1use_r9
+	.pushsection .s390_indirect_branches,"a",@progbits
+	.long	0b-.
+	.popsection
+	.endm
+
+	.macro BR_R1USE_R14
+0:	jg	__s390x_indirect_jump_r1use_r14
+	.pushsection .s390_indirect_branches,"a",@progbits
+	.long	0b-.
+	.popsection
+	.endm
+
+	.macro BR_R11USE_R14
+0:	jg	__s390x_indirect_jump_r11use_r14
+	.pushsection .s390_indirect_branches,"a",@progbits
+	.long	0b-.
+	.popsection
+	.endm
+
+#else	/* CONFIG_EXPOLINE */
+
+	.macro BASR_R14_R9
+	basr	%r14,%r9
+	.endm
+
+	.macro BR_R1USE_R14
+	br	%r14
+	.endm
+
+	.macro BR_R11USE_R14
+	br	%r14
+	.endm
+
+#endif /* CONFIG_EXPOLINE */
+
+
 	.section .kprobes.text, "ax"
 .Ldummy:
 	/*
@@ -237,7 +299,7 @@ _PIF_WORK	= (_PIF_PER_TRAP | _PIF_SYSCALL_RESTART)
 ENTRY(__bpon)
 	.globl __bpon
 	BPON
-	br	%r14
+	BR_R1USE_R14
 
 /*
  * Scheduler resume function, called by switch_to
@@ -261,9 +323,9 @@ ENTRY(__switch_to)
 	mvc	__LC_CURRENT_PID(4,%r0),0(%r3)	# store pid of next
 	lmg	%r6,%r15,__SF_GPRS(%r15)	# load gprs of next task
 	TSTMSK	__LC_MACHINE_FLAGS,MACHINE_FLAG_LPP
-	bzr	%r14
+	jz	0f
 	.insn	s,0xb2800000,__LC_LPP		# set program parameter
-	br	%r14
+0:	BR_R1USE_R14
 
 .L__critical_start:
 
@@ -330,7 +392,7 @@ sie_exit:
 	xgr	%r5,%r5
 	lmg	%r6,%r14,__SF_GPRS(%r15)	# restore kernel registers
 	lg	%r2,__SF_EMPTY+16(%r15)		# return exit reason code
-	br	%r14
+	BR_R1USE_R14
 .Lsie_fault:
 	lghi	%r14,-EFAULT
 	stg	%r14,__SF_EMPTY+16(%r15)	# set exit reason code
@@ -389,7 +451,7 @@ ENTRY(system_call)
 	lgf	%r9,0(%r8,%r10)			# get system call add.
 	TSTMSK	__TI_flags(%r12),_TIF_TRACE
 	jnz	.Lsysc_tracesys
-	basr	%r14,%r9			# call sys_xxxx
+	BASR_R14_R9				# call sys_xxxx
 	stg	%r2,__PT_R2(%r11)		# store return value
 
 .Lsysc_return:
@@ -574,7 +636,7 @@ ENTRY(system_call)
 	lmg	%r3,%r7,__PT_R3(%r11)
 	stg	%r7,STACK_FRAME_OVERHEAD(%r15)
 	lg	%r2,__PT_ORIG_GPR2(%r11)
-	basr	%r14,%r9		# call sys_xxx
+	BASR_R14_R9			# call sys_xxx
 	stg	%r2,__PT_R2(%r11)	# store return value
 .Lsysc_tracenogo:
 	TSTMSK	__TI_flags(%r12),_TIF_TRACE
@@ -598,7 +660,7 @@ ENTRY(ret_from_fork)
 	lmg	%r9,%r10,__PT_R9(%r11)	# load gprs
 ENTRY(kernel_thread_starter)
 	la	%r2,0(%r10)
-	basr	%r14,%r9
+	BASR_R14_R9
 	j	.Lsysc_tracenogo
 
 /*
@@ -678,9 +740,9 @@ ENTRY(pgm_check_handler)
 	nill	%r10,0x007f
 	sll	%r10,2
 	je	.Lpgm_return
-	lgf	%r1,0(%r10,%r1)		# load address of handler routine
+	lgf	%r9,0(%r10,%r1)		# load address of handler routine
 	lgr	%r2,%r11		# pass pointer to pt_regs
-	basr	%r14,%r1		# branch to interrupt-handler
+	BASR_R14_R9			# branch to interrupt-handler
 .Lpgm_return:
 	LOCKDEP_SYS_EXIT
 	tm	__PT_PSW+1(%r11),0x01	# returning to user ?
@@ -998,7 +1060,7 @@ ENTRY(psw_idle)
 	stpt	__TIMER_IDLE_ENTER(%r2)
 .Lpsw_idle_lpsw:
 	lpswe	__SF_EMPTY(%r15)
-	br	%r14
+	BR_R1USE_R14
 .Lpsw_idle_end:
 
 /*
@@ -1012,7 +1074,7 @@ ENTRY(save_fpu_regs)
 	lg	%r2,__LC_CURRENT
 	aghi	%r2,__TASK_thread
 	TSTMSK	__LC_CPU_FLAGS,_CIF_FPU
-	bor	%r14
+	jo	.Lsave_fpu_regs_exit
 	stfpc	__THREAD_FPU_fpc(%r2)
 	lg	%r3,__THREAD_FPU_regs(%r2)
 	TSTMSK	__LC_MACHINE_FLAGS,MACHINE_FLAG_VX
@@ -1039,7 +1101,8 @@ ENTRY(save_fpu_regs)
 	std	15,120(%r3)
 .Lsave_fpu_regs_done:
 	oi	__LC_CPU_FLAGS+7,_CIF_FPU
-	br	%r14
+.Lsave_fpu_regs_exit:
+	BR_R1USE_R14
 .Lsave_fpu_regs_end:
 EXPORT_SYMBOL(save_fpu_regs)
 
@@ -1057,7 +1120,7 @@ load_fpu_regs:
 	lg	%r4,__LC_CURRENT
 	aghi	%r4,__TASK_thread
 	TSTMSK	__LC_CPU_FLAGS,_CIF_FPU
-	bnor	%r14
+	jno	.Lload_fpu_regs_exit
 	lfpc	__THREAD_FPU_fpc(%r4)
 	TSTMSK	__LC_MACHINE_FLAGS,MACHINE_FLAG_VX
 	lg	%r4,__THREAD_FPU_regs(%r4)	# %r4 <- reg save area
@@ -1084,7 +1147,8 @@ load_fpu_regs:
 	ld	15,120(%r4)
 .Lload_fpu_regs_done:
 	ni	__LC_CPU_FLAGS+7,255-_CIF_FPU
-	br	%r14
+.Lload_fpu_regs_exit:
+	BR_R1USE_R14
 .Lload_fpu_regs_end:
 
 .L__critical_end:
@@ -1301,7 +1365,7 @@ cleanup_critical:
 	jl	0f
 	clg	%r9,BASED(.Lcleanup_table+104)	# .Lload_fpu_regs_end
 	jl	.Lcleanup_load_fpu_regs
-0:	br	%r14
+0:	BR_R11USE_R14
 
 	.align	8
 .Lcleanup_table:
@@ -1337,7 +1401,7 @@ cleanup_critical:
 	ni	__SIE_PROG0C+3(%r9),0xfe	# no longer in SIE
 	lctlg	%c1,%c1,__LC_USER_ASCE		# load primary asce
 	larl	%r9,sie_exit			# skip forward to sie_exit
-	br	%r14
+	BR_R11USE_R14
 #endif
 
 .Lcleanup_system_call:
@@ -1390,7 +1454,7 @@ cleanup_critical:
 	stg	%r15,56(%r11)		# r15 stack pointer
 	# set new psw address and exit
 	larl	%r9,.Lsysc_do_svc
-	br	%r14
+	BR_R11USE_R14
 .Lcleanup_system_call_insn:
 	.quad	system_call
 	.quad	.Lsysc_stmg
@@ -1402,7 +1466,7 @@ cleanup_critical:
 
 .Lcleanup_sysc_tif:
 	larl	%r9,.Lsysc_tif
-	br	%r14
+	BR_R11USE_R14
 
 .Lcleanup_sysc_restore:
 	# check if stpt has been executed
@@ -1419,14 +1483,14 @@ cleanup_critical:
 	mvc	0(64,%r11),__PT_R8(%r9)
 	lmg	%r0,%r7,__PT_R0(%r9)
 1:	lmg	%r8,%r9,__LC_RETURN_PSW
-	br	%r14
+	BR_R11USE_R14
 .Lcleanup_sysc_restore_insn:
 	.quad	.Lsysc_exit_timer
 	.quad	.Lsysc_done - 4
 
 .Lcleanup_io_tif:
 	larl	%r9,.Lio_tif
-	br	%r14
+	BR_R11USE_R14
 
 .Lcleanup_io_restore:
 	# check if stpt has been executed
@@ -1440,7 +1504,7 @@ cleanup_critical:
 	mvc	0(64,%r11),__PT_R8(%r9)
 	lmg	%r0,%r7,__PT_R0(%r9)
 1:	lmg	%r8,%r9,__LC_RETURN_PSW
-	br	%r14
+	BR_R11USE_R14
 .Lcleanup_io_restore_insn:
 	.quad	.Lio_exit_timer
 	.quad	.Lio_done - 4
@@ -1493,17 +1557,17 @@ cleanup_critical:
 	# prepare return psw
 	nihh	%r8,0xfcfd		# clear irq & wait state bits
 	lg	%r9,48(%r11)		# return from psw_idle
-	br	%r14
+	BR_R11USE_R14
 .Lcleanup_idle_insn:
 	.quad	.Lpsw_idle_lpsw
 
 .Lcleanup_save_fpu_regs:
 	larl	%r9,save_fpu_regs
-	br	%r14
+	BR_R11USE_R14
 
 .Lcleanup_load_fpu_regs:
 	larl	%r9,load_fpu_regs
-	br	%r14
+	BR_R11USE_R14
 
 /*
  * Integer constants
@@ -1523,7 +1587,6 @@ cleanup_critical:
 .Lsie_crit_mcck_length:
 	.quad   .Lsie_skip - .Lsie_entry
 #endif
-
 	.section .rodata, "a"
 #define SYSCALL(esame,emu)	.long esame
 	.globl	sys_call_table

arch/s390/kernel/module.c

@@ -19,6 +19,8 @@
 #include <linux/moduleloader.h>
 #include <linux/bug.h>
 #include <asm/alternative.h>
+#include <asm/nospec-branch.h>
+#include <asm/facility.h>
 
 #if 0
 #define DEBUGP printk
@@ -156,7 +158,11 @@ int module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs,
 	me->arch.got_offset = me->core_layout.size;
 	me->core_layout.size += me->arch.got_size;
 	me->arch.plt_offset = me->core_layout.size;
-	me->core_layout.size += me->arch.plt_size;
+	if (me->arch.plt_size) {
+		if (IS_ENABLED(CONFIG_EXPOLINE) && !nospec_call_disable)
+			me->arch.plt_size += PLT_ENTRY_SIZE;
+		me->core_layout.size += me->arch.plt_size;
+	}
 	return 0;
 }
 
@@ -310,9 +316,21 @@ static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab,
 			unsigned int *ip;
 			ip = me->core_layout.base + me->arch.plt_offset +
 				info->plt_offset;
-			ip[0] = 0x0d10e310; /* basr 1,0; lg 1,10(1); br 1 */
-			ip[1] = 0x100a0004;
-			ip[2] = 0x07f10000;
+			ip[0] = 0x0d10e310;	/* basr 1,0  */
+			ip[1] = 0x100a0004;	/* lg	1,10(1) */
+			if (IS_ENABLED(CONFIG_EXPOLINE) &&
+			    !nospec_call_disable) {
+				unsigned int *ij;
+				ij = me->core_layout.base +
+					me->arch.plt_offset +
+					me->arch.plt_size - PLT_ENTRY_SIZE;
+				ip[2] = 0xa7f40000 +	/* j __jump_r1 */
+					(unsigned int)(u16)
+					(((unsigned long) ij - 8 -
+					  (unsigned long) ip) / 2);
+			} else {
+				ip[2] = 0x07f10000;	/* br %r1 */
+			}
 			ip[3] = (unsigned int) (val >> 32);
 			ip[4] = (unsigned int) val;
 			info->plt_initialized = 1;
@@ -418,16 +436,42 @@ int module_finalize(const Elf_Ehdr *hdr,
 		    struct module *me)
 {
 	const Elf_Shdr *s;
-	char *secstrings;
+	char *secstrings, *secname;
+	void *aseg;
+
+	if (IS_ENABLED(CONFIG_EXPOLINE) &&
+	    !nospec_call_disable && me->arch.plt_size) {
+		unsigned int *ij;
+
+		ij = me->core_layout.base + me->arch.plt_offset +
+			me->arch.plt_size - PLT_ENTRY_SIZE;
+		if (test_facility(35)) {
+			ij[0] = 0xc6000000;	/* exrl	%r0,.+10	*/
+			ij[1] = 0x0005a7f4;	/* j	.		*/
+			ij[2] = 0x000007f1;	/* br	%r1		*/
+		} else {
+			ij[0] = 0x44000000 | (unsigned int)
+				offsetof(struct lowcore, br_r1_trampoline);
+			ij[1] = 0xa7f40000;	/* j	.		*/
+		}
+	}
 
 	secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
 	for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) {
-		if (!strcmp(".altinstructions", secstrings + s->sh_name)) {
-			/* patch .altinstructions */
-			void *aseg = (void *)s->sh_addr;
+		aseg = (void *) s->sh_addr;
+		secname = secstrings + s->sh_name;
 
+		if (!strcmp(".altinstructions", secname))
+			/* patch .altinstructions */
 			apply_alternatives(aseg, aseg + s->sh_size);
-		}
+
+		if (IS_ENABLED(CONFIG_EXPOLINE) &&
+		    (!strcmp(".nospec_call_table", secname)))
+			nospec_call_revert(aseg, aseg + s->sh_size);
+
+		if (IS_ENABLED(CONFIG_EXPOLINE) &&
+		    (!strcmp(".nospec_return_table", secname)))
+			nospec_return_revert(aseg, aseg + s->sh_size);
 	}
 
 	jump_label_apply_nops(me);

arch/s390/kernel/nospec-branch.c

@@ -0,0 +1,100 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/module.h>
+#include <asm/nospec-branch.h>
+
+int nospec_call_disable = IS_ENABLED(EXPOLINE_OFF);
+int nospec_return_disable = !IS_ENABLED(EXPOLINE_FULL);
+
+static int __init nospectre_v2_setup_early(char *str)
+{
+	nospec_call_disable = 1;
+	nospec_return_disable = 1;
+	return 0;
+}
+early_param("nospectre_v2", nospectre_v2_setup_early);
+
+static int __init spectre_v2_setup_early(char *str)
+{
+	if (str && !strncmp(str, "on", 2)) {
+		nospec_call_disable = 0;
+		nospec_return_disable = 0;
+	}
+	if (str && !strncmp(str, "off", 3)) {
+		nospec_call_disable = 1;
+		nospec_return_disable = 1;
+	}
+	if (str && !strncmp(str, "auto", 4)) {
+		nospec_call_disable = 0;
+		nospec_return_disable = 1;
+	}
+	return 0;
+}
+early_param("spectre_v2", spectre_v2_setup_early);
+
+static void __init_or_module __nospec_revert(s32 *start, s32 *end)
+{
+	enum { BRCL_EXPOLINE, BRASL_EXPOLINE } type;
+	u8 *instr, *thunk, *br;
+	u8 insnbuf[6];
+	s32 *epo;
+
+	/* Second part of the instruction replace is always a nop */
+	memcpy(insnbuf + 2, (char[]) { 0x47, 0x00, 0x00, 0x00 }, 4);
+	for (epo = start; epo < end; epo++) {
+		instr = (u8 *) epo + *epo;
+		if (instr[0] == 0xc0 && (instr[1] & 0x0f) == 0x04)
+			type = BRCL_EXPOLINE;	/* brcl instruction */
+		else if (instr[0] == 0xc0 && (instr[1] & 0x0f) == 0x05)
+			type = BRASL_EXPOLINE;	/* brasl instruction */
+		else
+			continue;
+		thunk = instr + (*(int *)(instr + 2)) * 2;
+		if (thunk[0] == 0xc6 && thunk[1] == 0x00)
+			/* exrl %r0,<target-br> */
+			br = thunk + (*(int *)(thunk + 2)) * 2;
+		else if (thunk[0] == 0xc0 && (thunk[1] & 0x0f) == 0x00 &&
+			 thunk[6] == 0x44 && thunk[7] == 0x00 &&
+			 (thunk[8] & 0x0f) == 0x00 && thunk[9] == 0x00 &&
+			 (thunk[1] & 0xf0) == (thunk[8] & 0xf0))
+			/* larl %rx,<target br> + ex %r0,0(%rx) */
+			br = thunk + (*(int *)(thunk + 2)) * 2;
+		else
+			continue;
+		if (br[0] != 0x07 || (br[1] & 0xf0) != 0xf0)
+			continue;
+		switch (type) {
+		case BRCL_EXPOLINE:
+			/* brcl to thunk, replace with br + nop */
+			insnbuf[0] = br[0];
+			insnbuf[1] = (instr[1] & 0xf0) | (br[1] & 0x0f);
+			break;
+		case BRASL_EXPOLINE:
+			/* brasl to thunk, replace with basr + nop */
+			insnbuf[0] = 0x0d;
+			insnbuf[1] = (instr[1] & 0xf0) | (br[1] & 0x0f);
+			break;
+		}
+
+		s390_kernel_write(instr, insnbuf, 6);
+	}
+}
+
+void __init_or_module nospec_call_revert(s32 *start, s32 *end)
+{
+	if (nospec_call_disable)
+		__nospec_revert(start, end);
+}
+
+void __init_or_module nospec_return_revert(s32 *start, s32 *end)
+{
+	if (nospec_return_disable)
+		__nospec_revert(start, end);
+}
+
+extern s32 __nospec_call_start[], __nospec_call_end[];
+extern s32 __nospec_return_start[], __nospec_return_end[];
+void __init nospec_init_branches(void)
+{
+	nospec_call_revert(__nospec_call_start, __nospec_call_end);
+	nospec_return_revert(__nospec_return_start, __nospec_return_end);
+}

arch/s390/kernel/setup.c

@@ -68,6 +68,7 @@
 #include <asm/sysinfo.h>
 #include <asm/numa.h>
 #include <asm/alternative.h>
+#include <asm/nospec-branch.h>
 #include "entry.h"
 
 /*
@@ -379,6 +380,7 @@ static void __init setup_lowcore(void)
 	lc->spinlock_index = 0;
 	arch_spin_lock_setup(0);
 #endif
+	lc->br_r1_trampoline = 0x07f1;	/* br %r1 */
 
 	set_prefix((u32)(unsigned long) lc);
 	lowcore_ptr[0] = lc;
@@ -954,6 +956,8 @@ void __init setup_arch(char **cmdline_p)
 	set_preferred_console();
 
 	apply_alternative_instructions();
+	if (IS_ENABLED(CONFIG_EXPOLINE))
+		nospec_init_branches();
 
 	/* Setup zfcpdump support */
 	setup_zfcpdump();

arch/s390/kernel/smp.c

@@ -214,6 +214,7 @@ static int pcpu_alloc_lowcore(struct pcpu *pcpu, int cpu)
 	lc->cpu_nr = cpu;
 	lc->spinlock_lockval = arch_spin_lockval(cpu);
 	lc->spinlock_index = 0;
+	lc->br_r1_trampoline = 0x07f1;	/* br %r1 */
 	if (nmi_alloc_per_cpu(lc))
 		goto out;
 	if (vdso_alloc_per_cpu(lc))

arch/s390/kernel/vmlinux.lds.S

@@ -123,6 +123,20 @@ SECTIONS
 		*(.altinstr_replacement)
 	}
 
+	/*
+	 * Table with the patch locations to undo expolines
+	*/
+	.nospec_call_table : {
+		__nospec_call_start = . ;
+		*(.s390_indirect*)
+		__nospec_call_end = . ;
+	}
+	.nospec_return_table : {
+		__nospec_return_start = . ;
+		*(.s390_return*)
+		__nospec_return_end = . ;
+	}
+
 	/* early.c uses stsi, which requires page aligned data. */
 	. = ALIGN(PAGE_SIZE);
 	INIT_DATA_SECTION(0x100)