[PATCH 5/6] s390: run user space and KVM guests with modified branch prediction

From: Martin Schwidefsky
Date: Wed Feb 07 2018 - 02:01:00 EST

Next message: Martin Schwidefsky: "[PATCH 6/6] s390: introduce execute-trampolines for branches"
Previous message: Huang, Ying: "[PATCH -mm -v2] mm, swap, frontswap: Fix THP swap if frontswap enabled"
In reply to: Martin Schwidefsky: "Re: [PATCH 4/6] s390: add options to change branch prediction behaviour for the kernel"
Next in thread: Martin Schwidefsky: "[PATCH 6/6] s390: introduce execute-trampolines for branches"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

Define TIF_ISOLATE_BP and TIF_ISOLATE_BP_GUEST and add the necessary
plumbing in entry.S to be able to run user space and KVM guests with
limited branch prediction.

To switch a user space process to limited branch prediction the
s390_isolate_bp() function has to be call, and to run a vCPU of a KVM
guest associated with the current task with limited branch prediction
call s390_isolate_bp_guest().

Signed-off-by: Martin Schwidefsky <schwidefsky@xxxxxxxxxx>
---
arch/s390/include/asm/processor.h | 3 +++
arch/s390/include/asm/thread_info.h | 4 +++
arch/s390/kernel/entry.S | 51 +++++++++++++++++++++++++++++++++----
arch/s390/kernel/processor.c | 18 +++++++++++++
4 files changed, 71 insertions(+), 5 deletions(-)

diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index 5f37f9c..7f2953c 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -378,6 +378,9 @@ extern void memcpy_absolute(void *, void *, size_t);
memcpy_absolute(&(dest), &__tmp, sizeof(__tmp)); \
} while (0)

+extern int s390_isolate_bp(void);
+extern int s390_isolate_bp_guest(void);
+
#endif /* __ASSEMBLY__ */

#endif /* __ASM_S390_PROCESSOR_H */
diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h
index 25d6ec3..83ba575 100644
--- a/arch/s390/include/asm/thread_info.h
+++ b/arch/s390/include/asm/thread_info.h
@@ -58,6 +58,8 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src);
#define TIF_GUARDED_STORAGE 4 /* load guarded storage control block */
#define TIF_PATCH_PENDING 5 /* pending live patching update */
#define TIF_PGSTE 6 /* New mm's will use 4K page tables */
+#define TIF_ISOLATE_BP 8 /* Run process with isolated BP */
+#define TIF_ISOLATE_BP_GUEST 9 /* Run KVM guests with isolated BP */

#define TIF_31BIT 16 /* 32bit process */
#define TIF_MEMDIE 17 /* is terminating due to OOM killer */
@@ -78,6 +80,8 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src);
#define _TIF_UPROBE _BITUL(TIF_UPROBE)
#define _TIF_GUARDED_STORAGE _BITUL(TIF_GUARDED_STORAGE)
#define _TIF_PATCH_PENDING _BITUL(TIF_PATCH_PENDING)
+#define _TIF_ISOLATE_BP _BITUL(TIF_ISOLATE_BP)
+#define _TIF_ISOLATE_BP_GUEST _BITUL(TIF_ISOLATE_BP_GUEST)

#define _TIF_31BIT _BITUL(TIF_31BIT)
#define _TIF_SINGLE_STEP _BITUL(TIF_SINGLE_STEP)
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index e6d7550..53145b5 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
@@ -187,6 +188,40 @@ _PIF_WORK = (_PIF_PER_TRAP | _PIF_SYSCALL_RESTART)
.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
+
.section .kprobes.text, "ax"
.Ldummy:
/*
@@ -240,9 +275,11 @@ 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
@@ -259,11 +296,12 @@ ENTRY(sie64a)
jnz .Lsie_skip
TSTMSK __LC_CPU_FLAGS,_CIF_FPU
jo .Lsie_skip # exit if fp/vx regs changed
- BPON
+ 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
@@ -324,6 +362,7 @@ 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
@@ -362,7 +401,7 @@ ENTRY(system_call)
jnz .Lsysc_work # check for work
TSTMSK __LC_CPU_FLAGS,_CIF_WORK
jnz .Lsysc_work
- BPON
+ BPEXIT __TI_flags(%r12),_TIF_ISOLATE_BP
.Lsysc_restore:
lg %r14,__LC_VDSO_PER_CPU
lmg %r0,%r10,__PT_R0(%r11)
@@ -597,6 +636,7 @@ 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
@@ -729,7 +769,7 @@ ENTRY(io_int_handler)
mvc __LC_RETURN_PSW(16),__PT_PSW(%r11)
tm __PT_PSW+1(%r11),0x01 # returning to user ?
jno .Lio_exit_kernel
- BPON
+ BPEXIT __TI_flags(%r12),_TIF_ISOLATE_BP
.Lio_exit_timer:
stpt __LC_EXIT_TIMER
mvc __VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER
@@ -1165,7 +1205,7 @@ 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
- BPON
+ 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)
@@ -1292,7 +1332,8 @@ 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
diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c
index 5362fd8..6fe2e18 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);
--
2.7.4

Next message: Martin Schwidefsky: "[PATCH 6/6] s390: introduce execute-trampolines for branches"
Previous message: Huang, Ying: "[PATCH -mm -v2] mm, swap, frontswap: Fix THP swap if frontswap enabled"
In reply to: Martin Schwidefsky: "Re: [PATCH 4/6] s390: add options to change branch prediction behaviour for the kernel"
Next in thread: Martin Schwidefsky: "[PATCH 6/6] s390: introduce execute-trampolines for branches"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]