summaryrefslogtreecommitdiffstats
path: root/arch/s390/kernel
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2018-02-09 09:58:37 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2018-02-09 09:58:37 -0800
commitdff839f27dc8d70e191562c8e78b0a9a88028362 (patch)
tree58173c5913ee68e0d8acc8ef31808bbe416d3758 /arch/s390/kernel
parent54ce685cae30c106f062d714c11e644ab1b93b51 (diff)
parent48973df8c9c51612acc870ad1a885b0cf27c3356 (diff)
Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux
Pull s390 updates from Heiko Carstens: "The main thing in this merge is the defense for the Spectre vulnerabilities. But there are other updates as well, the changes in more detail: - An s390 specific implementation of the array_index_mask_nospec function to the defense against spectre v1 - Two patches to utilize the new PPA-12/PPA-13 instructions to run the kernel and/or user space with reduced branch predicton. - The s390 variant of the 'retpoline' spectre v2 defense called 'expoline'. There is no return instruction for s390, instead an indirect branch is used for function return The s390 defense mechanism for indirect branches works by using an execute-type instruction with the indirect branch as the target of the execute. In effect that turns off the prediction for the indirect branch. - Scrub registers in entry.S that contain user controlled values to prevent the speculative use of these values. - Re-add the second parameter for the s390 specific runtime instrumentation system call and move the header file to uapi. The second parameter will continue to do nothing but older kernel versions only accepted valid real-time signal numbers. The details will be documented in the man-page for the system call. - Corrections and improvements for the s390 specific documentation - Add a line to /proc/sysinfo to display the CPU model dependent license-internal-code identifier - A header file include fix for eadm. - An error message fix in the kprobes code. - The removal of an outdated ARCH_xxx select statement" * 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux: s390/kconfig: Remove ARCH_WANTS_PROT_NUMA_PROT_NONE select s390: introduce execute-trampolines for branches s390: run user space and KVM guests with modified branch prediction s390: add options to change branch prediction behaviour for the kernel s390/alternative: use a copy of the facility bit mask s390: add optimized array_index_mask_nospec s390: scrub registers on kernel entry and KVM exit s390/cio: fix kernel-doc usage s390/runtime_instrumentation: re-add signum system call parameter s390/cpum_cf: correct counter number of LAST_HOST_TRANSLATIONS s390/kprobes: Fix %p uses in error messages s390/runtime instrumentation: provide uapi header file s390/sysinfo: add and display licensed internal code identifier s390/docs: reword airq section s390/docs: mention subchannel types s390/cmf: fix kerneldoc s390/eadm: fix CONFIG_BLOCK include dependency
Diffstat (limited to 'arch/s390/kernel')
-rw-r--r--arch/s390/kernel/Makefile4
-rw-r--r--arch/s390/kernel/alternative.c26
-rw-r--r--arch/s390/kernel/early.c5
-rw-r--r--arch/s390/kernel/entry.S249
-rw-r--r--arch/s390/kernel/ipl.c1
-rw-r--r--arch/s390/kernel/kprobes.c2
-rw-r--r--arch/s390/kernel/module.c62
-rw-r--r--arch/s390/kernel/nospec-branch.c100
-rw-r--r--arch/s390/kernel/perf_cpum_cf_events.c2
-rw-r--r--arch/s390/kernel/processor.c18
-rw-r--r--arch/s390/kernel/runtime_instr.c10
-rw-r--r--arch/s390/kernel/setup.c8
-rw-r--r--arch/s390/kernel/smp.c7
-rw-r--r--arch/s390/kernel/sysinfo.c2
-rw-r--r--arch/s390/kernel/vmlinux.lds.S14
15 files changed, 470 insertions, 40 deletions
diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile
index 909bce65cb2b..7f27e3da9709 100644
--- a/arch/s390/kernel/Makefile
+++ b/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
diff --git a/arch/s390/kernel/alternative.c b/arch/s390/kernel/alternative.c
index 574e77622c04..22476135f738 100644
--- a/arch/s390/kernel/alternative.c
+++ b/arch/s390/kernel/alternative.c
@@ -15,6 +15,29 @@ static int __init disable_alternative_instructions(char *str)
early_param("noaltinstr", disable_alternative_instructions);
+static int __init nobp_setup_early(char *str)
+{
+ bool enabled;
+ int rc;
+
+ rc = kstrtobool(str, &enabled);
+ if (rc)
+ return rc;
+ if (enabled && test_facility(82))
+ __set_facility(82, S390_lowcore.alt_stfle_fac_list);
+ else
+ __clear_facility(82, S390_lowcore.alt_stfle_fac_list);
+ return 0;
+}
+early_param("nobp", nobp_setup_early);
+
+static int __init nospec_setup_early(char *str)
+{
+ __clear_facility(82, S390_lowcore.alt_stfle_fac_list);
+ return 0;
+}
+early_param("nospec", nospec_setup_early);
+
struct brcl_insn {
u16 opc;
s32 disp;
@@ -75,7 +98,8 @@ static void __init_or_module __apply_alternatives(struct alt_instr *start,
instr = (u8 *)&a->instr_offset + a->instr_offset;
replacement = (u8 *)&a->repl_offset + a->repl_offset;
- if (!test_facility(a->facility))
+ if (!__test_facility(a->facility,
+ S390_lowcore.alt_stfle_fac_list))
continue;
if (unlikely(a->instrlen % 2 || a->replacementlen % 2)) {
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index 497a92047591..ac707a9f729e 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -193,6 +193,11 @@ static noinline __init void setup_facility_list(void)
{
stfle(S390_lowcore.stfle_fac_list,
ARRAY_SIZE(S390_lowcore.stfle_fac_list));
+ memcpy(S390_lowcore.alt_stfle_fac_list,
+ S390_lowcore.stfle_fac_list,
+ sizeof(S390_lowcore.alt_stfle_fac_list));
+ if (!IS_ENABLED(CONFIG_KERNEL_NOBP))
+ __clear_facility(82, S390_lowcore.alt_stfle_fac_list);
}
static __init void detect_diag9c(void)
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 6cd444d25545..13a133a6015c 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -107,6 +107,7 @@ _PIF_WORK = (_PIF_PER_TRAP | _PIF_SYSCALL_RESTART)
aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
j 3f
1: UPDATE_VTIME %r14,%r15,\timer
+ BPENTER __TI_flags(%r12),_TIF_ISOLATE_BP
2: lg %r15,__LC_ASYNC_STACK # load async stack
3: la %r11,STACK_FRAME_OVERHEAD(%r15)
.endm
@@ -159,6 +160,130 @@ _PIF_WORK = (_PIF_PER_TRAP | _PIF_SYSCALL_RESTART)
tm off+\addr, \mask
.endm
+ .macro BPOFF
+ .pushsection .altinstr_replacement, "ax"
+660: .long 0xb2e8c000
+ .popsection
+661: .long 0x47000000
+ .pushsection .altinstructions, "a"
+ .long 661b - .
+ .long 660b - .
+ .word 82
+ .byte 4
+ .byte 4
+ .popsection
+ .endm
+
+ .macro BPON
+ .pushsection .altinstr_replacement, "ax"
+662: .long 0xb2e8d000
+ .popsection
+663: .long 0x47000000
+ .pushsection .altinstructions, "a"
+ .long 663b - .
+ .long 662b - .
+ .word 82
+ .byte 4
+ .byte 4
+ .popsection
+ .endm
+
+ .macro BPENTER tif_ptr,tif_mask
+ .pushsection .altinstr_replacement, "ax"
+662: .word 0xc004, 0x0000, 0x0000 # 6 byte nop
+ .word 0xc004, 0x0000, 0x0000 # 6 byte nop
+ .popsection
+664: TSTMSK \tif_ptr,\tif_mask
+ jz . + 8
+ .long 0xb2e8d000
+ .pushsection .altinstructions, "a"
+ .long 664b - .
+ .long 662b - .
+ .word 82
+ .byte 12
+ .byte 12
+ .popsection
+ .endm
+
+ .macro BPEXIT tif_ptr,tif_mask
+ TSTMSK \tif_ptr,\tif_mask
+ .pushsection .altinstr_replacement, "ax"
+662: jnz . + 8
+ .long 0xb2e8d000
+ .popsection
+664: jz . + 8
+ .long 0xb2e8c000
+ .pushsection .altinstructions, "a"
+ .long 664b - .
+ .long 662b - .
+ .word 82
+ .byte 8
+ .byte 8
+ .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:
/*
@@ -171,6 +296,11 @@ _PIF_WORK = (_PIF_PER_TRAP | _PIF_SYSCALL_RESTART)
*/
nop 0
+ENTRY(__bpon)
+ .globl __bpon
+ BPON
+ BR_R1USE_R14
+
/*
* Scheduler resume function, called by switch_to
* gpr2 = (task_struct *) prev
@@ -193,9 +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:
@@ -207,9 +337,11 @@ ENTRY(__switch_to)
*/
ENTRY(sie64a)
stmg %r6,%r14,__SF_GPRS(%r15) # save kernel registers
+ lg %r12,__LC_CURRENT
stg %r2,__SF_EMPTY(%r15) # save control block pointer
stg %r3,__SF_EMPTY+8(%r15) # save guest register save area
xc __SF_EMPTY+16(8,%r15),__SF_EMPTY+16(%r15) # reason code = 0
+ mvc __SF_EMPTY+24(8,%r15),__TI_flags(%r12) # copy thread flags
TSTMSK __LC_CPU_FLAGS,_CIF_FPU # load guest fp/vx registers ?
jno .Lsie_load_guest_gprs
brasl %r14,load_fpu_regs # load guest fp/vx regs
@@ -226,8 +358,12 @@ ENTRY(sie64a)
jnz .Lsie_skip
TSTMSK __LC_CPU_FLAGS,_CIF_FPU
jo .Lsie_skip # exit if fp/vx regs changed
+ BPEXIT __SF_EMPTY+24(%r15),(_TIF_ISOLATE_BP|_TIF_ISOLATE_BP_GUEST)
.Lsie_entry:
sie 0(%r14)
+.Lsie_exit:
+ BPOFF
+ BPENTER __SF_EMPTY+24(%r15),(_TIF_ISOLATE_BP|_TIF_ISOLATE_BP_GUEST)
.Lsie_skip:
ni __SIE_PROG0C+3(%r14),0xfe # no longer in SIE
lctlg %c1,%c1,__LC_USER_ASCE # load primary asce
@@ -248,9 +384,15 @@ ENTRY(sie64a)
sie_exit:
lg %r14,__SF_EMPTY+8(%r15) # load guest register save area
stmg %r0,%r13,0(%r14) # save guest gprs 0-13
+ xgr %r0,%r0 # clear guest registers to
+ xgr %r1,%r1 # prevent speculative use
+ xgr %r2,%r2
+ xgr %r3,%r3
+ xgr %r4,%r4
+ 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
@@ -273,6 +415,7 @@ ENTRY(system_call)
stpt __LC_SYNC_ENTER_TIMER
.Lsysc_stmg:
stmg %r8,%r15,__LC_SAVE_AREA_SYNC
+ BPOFF
lg %r12,__LC_CURRENT
lghi %r13,__TASK_thread
lghi %r14,_PIF_SYSCALL
@@ -281,7 +424,10 @@ ENTRY(system_call)
la %r11,STACK_FRAME_OVERHEAD(%r15) # pointer to pt_regs
.Lsysc_vtime:
UPDATE_VTIME %r8,%r9,__LC_SYNC_ENTER_TIMER
+ BPENTER __TI_flags(%r12),_TIF_ISOLATE_BP
stmg %r0,%r7,__PT_R0(%r11)
+ # clear user controlled register to prevent speculative use
+ xgr %r0,%r0
mvc __PT_R8(64,%r11),__LC_SAVE_AREA_SYNC
mvc __PT_PSW(16,%r11),__LC_SVC_OLD_PSW
mvc __PT_INT_CODE(4,%r11),__LC_SVC_ILC
@@ -305,7 +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:
@@ -317,6 +463,7 @@ ENTRY(system_call)
jnz .Lsysc_work # check for work
TSTMSK __LC_CPU_FLAGS,_CIF_WORK
jnz .Lsysc_work
+ BPEXIT __TI_flags(%r12),_TIF_ISOLATE_BP
.Lsysc_restore:
lg %r14,__LC_VDSO_PER_CPU
lmg %r0,%r10,__PT_R0(%r11)
@@ -489,7 +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
@@ -513,7 +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
/*
@@ -522,6 +669,7 @@ ENTRY(kernel_thread_starter)
ENTRY(pgm_check_handler)
stpt __LC_SYNC_ENTER_TIMER
+ BPOFF
stmg %r8,%r15,__LC_SAVE_AREA_SYNC
lg %r10,__LC_LAST_BREAK
lg %r12,__LC_CURRENT
@@ -550,6 +698,7 @@ ENTRY(pgm_check_handler)
aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
j 4f
2: UPDATE_VTIME %r14,%r15,__LC_SYNC_ENTER_TIMER
+ BPENTER __TI_flags(%r12),_TIF_ISOLATE_BP
lg %r15,__LC_KERNEL_STACK
lgr %r14,%r12
aghi %r14,__TASK_thread # pointer to thread_struct
@@ -561,6 +710,15 @@ ENTRY(pgm_check_handler)
4: lgr %r13,%r11
la %r11,STACK_FRAME_OVERHEAD(%r15)
stmg %r0,%r7,__PT_R0(%r11)
+ # clear user controlled registers to prevent speculative use
+ xgr %r0,%r0
+ xgr %r1,%r1
+ xgr %r2,%r2
+ xgr %r3,%r3
+ xgr %r4,%r4
+ xgr %r5,%r5
+ xgr %r6,%r6
+ xgr %r7,%r7
mvc __PT_R8(64,%r11),__LC_SAVE_AREA_SYNC
stmg %r8,%r9,__PT_PSW(%r11)
mvc __PT_INT_CODE(4,%r11),__LC_PGM_ILC
@@ -582,9 +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 ?
@@ -620,12 +778,23 @@ ENTRY(pgm_check_handler)
ENTRY(io_int_handler)
STCK __LC_INT_CLOCK
stpt __LC_ASYNC_ENTER_TIMER
+ BPOFF
stmg %r8,%r15,__LC_SAVE_AREA_ASYNC
lg %r12,__LC_CURRENT
larl %r13,cleanup_critical
lmg %r8,%r9,__LC_IO_OLD_PSW
SWITCH_ASYNC __LC_SAVE_AREA_ASYNC,__LC_ASYNC_ENTER_TIMER
stmg %r0,%r7,__PT_R0(%r11)
+ # clear user controlled registers to prevent speculative use
+ xgr %r0,%r0
+ xgr %r1,%r1
+ xgr %r2,%r2
+ xgr %r3,%r3
+ xgr %r4,%r4
+ xgr %r5,%r5
+ xgr %r6,%r6
+ xgr %r7,%r7
+ xgr %r10,%r10
mvc __PT_R8(64,%r11),__LC_SAVE_AREA_ASYNC
stmg %r8,%r9,__PT_PSW(%r11)
mvc __PT_INT_CODE(12,%r11),__LC_SUBCHANNEL_ID
@@ -660,9 +829,13 @@ ENTRY(io_int_handler)
lg %r14,__LC_VDSO_PER_CPU
lmg %r0,%r10,__PT_R0(%r11)
mvc __LC_RETURN_PSW(16),__PT_PSW(%r11)
+ tm __PT_PSW+1(%r11),0x01 # returning to user ?
+ jno .Lio_exit_kernel
+ BPEXIT __TI_flags(%r12),_TIF_ISOLATE_BP
.Lio_exit_timer:
stpt __LC_EXIT_TIMER
mvc __VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER
+.Lio_exit_kernel:
lmg %r11,%r15,__PT_R11(%r11)
lpswe __LC_RETURN_PSW
.Lio_done:
@@ -833,12 +1006,23 @@ ENTRY(io_int_handler)
ENTRY(ext_int_handler)
STCK __LC_INT_CLOCK
stpt __LC_ASYNC_ENTER_TIMER
+ BPOFF
stmg %r8,%r15,__LC_SAVE_AREA_ASYNC
lg %r12,__LC_CURRENT
larl %r13,cleanup_critical
lmg %r8,%r9,__LC_EXT_OLD_PSW
SWITCH_ASYNC __LC_SAVE_AREA_ASYNC,__LC_ASYNC_ENTER_TIMER
stmg %r0,%r7,__PT_R0(%r11)
+ # clear user controlled registers to prevent speculative use
+ xgr %r0,%r0
+ xgr %r1,%r1
+ xgr %r2,%r2
+ xgr %r3,%r3
+ xgr %r4,%r4
+ xgr %r5,%r5
+ xgr %r6,%r6
+ xgr %r7,%r7
+ xgr %r10,%r10
mvc __PT_R8(64,%r11),__LC_SAVE_AREA_ASYNC
stmg %r8,%r9,__PT_PSW(%r11)
lghi %r1,__LC_EXT_PARAMS2
@@ -871,11 +1055,12 @@ ENTRY(psw_idle)
.Lpsw_idle_stcctm:
#endif
oi __LC_CPU_FLAGS+7,_CIF_ENABLED_WAIT
+ BPON
STCK __CLOCK_IDLE_ENTER(%r2)
stpt __TIMER_IDLE_ENTER(%r2)
.Lpsw_idle_lpsw:
lpswe __SF_EMPTY(%r15)
- br %r14
+ BR_R1USE_R14
.Lpsw_idle_end:
/*
@@ -889,7 +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
@@ -916,7 +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)
@@ -934,7 +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
@@ -961,7 +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:
@@ -971,6 +1158,7 @@ load_fpu_regs:
*/
ENTRY(mcck_int_handler)
STCK __LC_MCCK_CLOCK
+ BPOFF
la %r1,4095 # validate r1
spt __LC_CPU_TIMER_SAVE_AREA-4095(%r1) # validate cpu timer
sckc __LC_CLOCK_COMPARATOR # validate comparator
@@ -1046,6 +1234,16 @@ ENTRY(mcck_int_handler)
.Lmcck_skip:
lghi %r14,__LC_GPREGS_SAVE_AREA+64
stmg %r0,%r7,__PT_R0(%r11)
+ # clear user controlled registers to prevent speculative use
+ xgr %r0,%r0
+ xgr %r1,%r1
+ xgr %r2,%r2
+ xgr %r3,%r3
+ xgr %r4,%r4
+ xgr %r5,%r5
+ xgr %r6,%r6
+ xgr %r7,%r7
+ xgr %r10,%r10
mvc __PT_R8(64,%r11),0(%r14)
stmg %r8,%r9,__PT_PSW(%r11)
xc __PT_FLAGS(8,%r11),__PT_FLAGS(%r11)
@@ -1071,6 +1269,7 @@ ENTRY(mcck_int_handler)
mvc __LC_RETURN_MCCK_PSW(16),__PT_PSW(%r11) # move return PSW
tm __LC_RETURN_MCCK_PSW+1,0x01 # returning to user ?
jno 0f
+ BPEXIT __TI_flags(%r12),_TIF_ISOLATE_BP
stpt __LC_EXIT_TIMER
mvc __VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER
0: lmg %r11,%r15,__PT_R11(%r11)
@@ -1166,7 +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:
@@ -1197,11 +1396,12 @@ cleanup_critical:
clg %r9,BASED(.Lsie_crit_mcck_length)
jh 1f
oi __LC_CPU_FLAGS+7, _CIF_MCCK_GUEST
-1: lg %r9,__SF_EMPTY(%r15) # get control block pointer
+1: BPENTER __SF_EMPTY+24(%r15),(_TIF_ISOLATE_BP|_TIF_ISOLATE_BP_GUEST)
+ lg %r9,__SF_EMPTY(%r15) # get control block pointer
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:
@@ -1254,7 +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
@@ -1266,7 +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
@@ -1283,14 +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
@@ -1304,7 +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
@@ -1357,17 +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
@@ -1387,7 +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
diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index da5cc3b469aa..34477c1aee6d 100644
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -543,6 +543,7 @@ static struct kset *ipl_kset;
static void __ipl_run(void *unused)
{
+ __bpon();
diag308(DIAG308_LOAD_CLEAR, NULL);
if (MACHINE_IS_VM)
__cpcmd("IPL", NULL, 0, NULL);
diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c
index 943d13e90c98..60f60afa645c 100644
--- a/arch/s390/kernel/kprobes.c
+++ b/arch/s390/kernel/kprobes.c
@@ -281,7 +281,7 @@ static void kprobe_reenter_check(struct kprobe_ctlblk *kcb, struct kprobe *p)
* is a BUG. The code path resides in the .kprobes.text
* section and is executed with interrupts disabled.
*/
- printk(KERN_EMERG "Invalid kprobe detected at %p.\n", p->addr);
+ pr_err("Invalid kprobe detected.\n");
dump_kprobe(p);
BUG();
}
diff --git a/arch/s390/kernel/module.c b/arch/s390/kernel/module.c
index b7abfad4fd7d..1fc6d1ff92d3 100644
--- a/arch/s390/kernel/module.c
+++ b/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);
diff --git a/arch/s390/kernel/nospec-branch.c b/arch/s390/kernel/nospec-branch.c
new file mode 100644
index 000000000000..69d7fcf48158
--- /dev/null
+++ b/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);
+}
diff --git a/arch/s390/kernel/perf_cpum_cf_events.c b/arch/s390/kernel/perf_cpum_cf_events.c
index 94f90cefbffc..c5bc3f209652 100644
--- a/arch/s390/kernel/perf_cpum_cf_events.c
+++ b/arch/s390/kernel/perf_cpum_cf_events.c
@@ -226,7 +226,7 @@ CPUMF_EVENT_ATTR(cf_z14, L1I_OFFDRAWER_L4_SOURCED_WRITES, 0x00af);
CPUMF_EVENT_ATTR(cf_z14, BCD_DFP_EXECUTION_SLOTS, 0x00e0);
CPUMF_EVENT_ATTR(cf_z14, VX_BCD_EXECUTION_SLOTS, 0x00e1);
CPUMF_EVENT_ATTR(cf_z14, DECIMAL_INSTRUCTIONS, 0x00e2);
-CPUMF_EVENT_ATTR(cf_z14, LAST_HOST_TRANSLATIONS, 0x00e9);
+CPUMF_EVENT_ATTR(cf_z14, LAST_HOST_TRANSLATIONS, 0x00e8);
CPUMF_EVENT_ATTR(cf_z14, TX_NC_TABORT, 0x00f3);
CPUMF_EVENT_ATTR(cf_z14, TX_C_TABORT_NO_SPECIAL, 0x00f4);
CPUMF_EVENT_ATTR(cf_z14, TX_C_TABORT_SPECIAL, 0x00f5);
diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c
index 5362fd868d0d..6fe2e1875058 100644
--- a/arch/s390/kernel/processor.c
+++ b/arch/s390/kernel/processor.c
@@ -197,3 +197,21 @@ const struct seq_operations cpuinfo_op = {
.stop = c_stop,
.show = show_cpuinfo,
};
+
+int s390_isolate_bp(void)
+{
+ if (!test_facility(82))
+ return -EOPNOTSUPP;
+ set_thread_flag(TIF_ISOLATE_BP);
+ return 0;
+}
+EXPORT_SYMBOL(s390_isolate_bp);
+
+int s390_isolate_bp_guest(void)
+{
+ if (!test_facility(82))
+ return -EOPNOTSUPP;
+ set_thread_flag(TIF_ISOLATE_BP_GUEST);
+ return 0;
+}
+EXPORT_SYMBOL(s390_isolate_bp_guest);
diff --git a/arch/s390/kernel/runtime_instr.c b/arch/s390/kernel/runtime_instr.c
index 09f5bf0d5c0c..125c7f6e8715 100644
--- a/arch/s390/kernel/runtime_instr.c
+++ b/arch/s390/kernel/runtime_instr.c
@@ -18,6 +18,8 @@
#include <asm/cpu_mf.h>
#include <asm/irq.h>
+#include "entry.h"
+
/* empty control block to disable RI by loading it */
struct runtime_instr_cb runtime_instr_empty_cb;
@@ -59,7 +61,13 @@ static void init_runtime_instr_cb(struct runtime_instr_cb *cb)
cb->v = 1;
}
-SYSCALL_DEFINE1(s390_runtime_instr, int, command)
+/*
+ * The signum argument is unused. In older kernels it was used to
+ * specify a real-time signal. For backwards compatibility user space
+ * should pass a valid real-time signal number (the signum argument
+ * was checked in older kernels).
+ */
+SYSCALL_DEFINE2(s390_runtime_instr, int, command, int, signum)
{
struct runtime_instr_cb *cb;
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 793da97f9a6e..a6a91f01a17a 100644
--- a/arch/s390/kernel/setup.c
+++ b/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"
/*
@@ -340,7 +341,9 @@ static void __init setup_lowcore(void)
lc->preempt_count = S390_lowcore.preempt_count;
lc->stfl_fac_list = S390_lowcore.stfl_fac_list;
memcpy(lc->stfle_fac_list, S390_lowcore.stfle_fac_list,
- MAX_FACILITY_BIT/8);
+ sizeof(lc->stfle_fac_list));
+ memcpy(lc->alt_stfle_fac_list, S390_lowcore.alt_stfle_fac_list,
+ sizeof(lc->alt_stfle_fac_list));
nmi_alloc_boot_cpu(lc);
vdso_alloc_boot_cpu(lc);
lc->sync_enter_timer = S390_lowcore.s