s390/mm: remove set_fs / rework address space handling
Remove set_fs support from s390. With doing this rework address space
handling and simplify it. As a result address spaces are now setup
like this:
CPU running in | %cr1 ASCE | %cr7 ASCE | %cr13 ASCE
----------------------------|-----------|-----------|-----------
user space | user | user | kernel
kernel, normal execution | kernel | user | kernel
kernel, kvm guest execution | gmap | user | kernel
To achieve this the getcpu vdso syscall is removed in order to avoid
secondary address mode and a separate vdso address space in for user
space. The getcpu vdso syscall will be implemented differently with a
subsequent patch.
The kernel accesses user space always via secondary address space.
This happens in different ways:
- with mvcos in home space mode and directly read/write to secondary
address space
- with mvcs/mvcp in primary space mode and copy from primary space to
secondary space or vice versa
- with e.g. cs in secondary space mode and access secondary space
Switching translation modes happens with sacf before and after
instructions which access user space, like before.
Lazy handling of control register reloading is removed in the hope to
make everything simpler, but at the cost of making kernel entry and
exit a bit slower. That is: on kernel entry the primary asce is always
changed to contain the kernel asce, and on kernel exit the primary
asce is changed again so it contains the user asce.
In kernel mode there is only one exception to the primary asce: when
kvm guests are executed the primary asce contains the gmap asce (which
describes the guest address space). The primary asce is reset to
kernel asce whenever kvm guest execution is interrupted, so that this
doesn't has to be taken into account for any user space accesses.
Reviewed-by: Sven Schnelle <svens@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index b454654..d43ef46 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -55,7 +55,7 @@
_TIF_UPROBE | _TIF_GUARDED_STORAGE | _TIF_PATCH_PENDING)
_TIF_TRACE = (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | \
_TIF_SYSCALL_TRACEPOINT)
-_CIF_WORK = (_CIF_ASCE_PRIMARY | _CIF_ASCE_SECONDARY | _CIF_FPU)
+_CIF_WORK = (_CIF_FPU)
_PIF_WORK = (_PIF_PER_TRAP | _PIF_SYSCALL_RESTART)
_LPP_OFFSET = __LC_LPP
@@ -327,7 +327,7 @@
BPENTER __SF_SIE_FLAGS(%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
+ lctlg %c1,%c1,__LC_KERNEL_ASCE # load primary asce
.Lsie_done:
# some program checks are suppressing. C code (e.g. do_protection_exception)
# will rewind the PSW by the ILC, which is often 4 bytes in case of SIE. There
@@ -380,6 +380,7 @@
lg %r12,__LC_CURRENT
lghi %r14,_PIF_SYSCALL
.Lsysc_per:
+ lctlg %c1,%c1,__LC_KERNEL_ASCE
lghi %r13,__TASK_thread
lg %r15,__LC_KERNEL_STACK
la %r11,STACK_FRAME_OVERHEAD(%r15) # pointer to pt_regs
@@ -427,8 +428,7 @@
jnz .Lsysc_work
TSTMSK __TI_flags(%r12),_TIF_WORK
jnz .Lsysc_work # check for work
- TSTMSK __LC_CPU_FLAGS,(_CIF_WORK-_CIF_FPU)
- jnz .Lsysc_work
+ lctlg %c1,%c1,__LC_USER_ASCE
BPEXIT __TI_flags(%r12),_TIF_ISOLATE_BP
TSTMSK __LC_CPU_FLAGS, _CIF_FPU
jz .Lsysc_skip_fpu
@@ -467,8 +467,6 @@
jo .Lsysc_sigpending
TSTMSK __TI_flags(%r12),_TIF_NOTIFY_RESUME
jo .Lsysc_notify_resume
- TSTMSK __LC_CPU_FLAGS,(_CIF_ASCE_PRIMARY|_CIF_ASCE_SECONDARY)
- jnz .Lsysc_asce
j .Lsysc_return
#
@@ -479,26 +477,6 @@
jg schedule
#
-# _CIF_ASCE_PRIMARY and/or _CIF_ASCE_SECONDARY set, load user space asce
-#
-.Lsysc_asce:
- ni __LC_CPU_FLAGS+7,255-_CIF_ASCE_SECONDARY
- lctlg %c7,%c7,__LC_VDSO_ASCE # load secondary asce
- TSTMSK __LC_CPU_FLAGS,_CIF_ASCE_PRIMARY
- jz .Lsysc_return
-#ifndef CONFIG_HAVE_MARCH_Z10_FEATURES
- tm __LC_STFLE_FAC_LIST+3,0x10 # has MVCOS ?
- jnz .Lsysc_set_fs_fixup
- ni __LC_CPU_FLAGS+7,255-_CIF_ASCE_PRIMARY
- lctlg %c1,%c1,__LC_USER_ASCE # load primary asce
- j .Lsysc_return
-.Lsysc_set_fs_fixup:
-#endif
- larl %r14,.Lsysc_return
- jg set_fs_fixup
-
-
-#
# _TIF_SIGPENDING is set, call do_signal
#
.Lsysc_sigpending:
@@ -634,8 +612,11 @@
0: lg %r12,__LC_CURRENT
lghi %r11,0
lmg %r8,%r9,__LC_PGM_OLD_PSW
- tmhh %r8,0x0001 # test problem state bit
- jnz 3f # -> fault in user space
+ tmhh %r8,0x0001 # coming from user space?
+ jno .Lpgm_skip_asce
+ lctlg %c1,%c1,__LC_KERNEL_ASCE
+ j 3f
+.Lpgm_skip_asce:
#if IS_ENABLED(CONFIG_KVM)
# cleanup critical section for program checks in sie64a
lgr %r14,%r9
@@ -646,7 +627,7 @@
jhe 1f
lg %r14,__SF_SIE_CONTROL(%r15) # get control block pointer
ni __SIE_PROG0C+3(%r14),0xfe # no longer in SIE
- lctlg %c1,%c1,__LC_USER_ASCE # load primary asce
+ lctlg %c1,%c1,__LC_KERNEL_ASCE # load primary asce
larl %r9,sie_exit # skip forward to sie_exit
lghi %r11,_PIF_GUEST_FAULT
#endif
@@ -767,6 +748,10 @@
xgr %r10,%r10
mvc __PT_R8(64,%r11),__LC_SAVE_AREA_ASYNC
stmg %r8,%r9,__PT_PSW(%r11)
+ tm __PT_PSW+1(%r11),0x01 # coming from user space?
+ jno .Lio_skip_asce
+ lctlg %c1,%c1,__LC_KERNEL_ASCE
+.Lio_skip_asce:
mvc __PT_INT_CODE(12,%r11),__LC_SUBCHANNEL_ID
xc __PT_FLAGS(8,%r11),__PT_FLAGS(%r11)
TSTMSK __LC_CPU_FLAGS,_CIF_IGNORE_IRQ
@@ -808,6 +793,7 @@
mvc __LC_RETURN_PSW(16),__PT_PSW(%r11)
tm __PT_PSW+1(%r11),0x01 # returning to user ?
jno .Lio_exit_kernel
+ lctlg %c1,%c1,__LC_USER_ASCE
BPEXIT __TI_flags(%r12),_TIF_ISOLATE_BP
stpt __LC_EXIT_TIMER
.Lio_exit_kernel:
@@ -873,30 +859,9 @@
jo .Lio_guarded_storage
TSTMSK __LC_CPU_FLAGS,_CIF_FPU
jo .Lio_vxrs
- TSTMSK __LC_CPU_FLAGS,(_CIF_ASCE_PRIMARY|_CIF_ASCE_SECONDARY)
- jnz .Lio_asce
j .Lio_return
#
-# _CIF_ASCE_PRIMARY and/or CIF_ASCE_SECONDARY set, load user space asce
-#
-.Lio_asce:
- ni __LC_CPU_FLAGS+7,255-_CIF_ASCE_SECONDARY
- lctlg %c7,%c7,__LC_VDSO_ASCE # load secondary asce
- TSTMSK __LC_CPU_FLAGS,_CIF_ASCE_PRIMARY
- jz .Lio_return
-#ifndef CONFIG_HAVE_MARCH_Z10_FEATURES
- tm __LC_STFLE_FAC_LIST+3,0x10 # has MVCOS ?
- jnz .Lio_set_fs_fixup
- ni __LC_CPU_FLAGS+7,255-_CIF_ASCE_PRIMARY
- lctlg %c1,%c1,__LC_USER_ASCE # load primary asce
- j .Lio_return
-.Lio_set_fs_fixup:
-#endif
- larl %r14,.Lio_return
- jg set_fs_fixup
-
-#
# CIF_FPU is set, restore floating-point controls and floating-point registers.
#
.Lio_vxrs:
@@ -977,6 +942,10 @@
xgr %r10,%r10
mvc __PT_R8(64,%r11),__LC_SAVE_AREA_ASYNC
stmg %r8,%r9,__PT_PSW(%r11)
+ tm __PT_PSW+1(%r11),0x01 # coming from user space?
+ jno .Lext_skip_asce
+ lctlg %c1,%c1,__LC_KERNEL_ASCE
+.Lext_skip_asce:
lghi %r1,__LC_EXT_PARAMS2
mvc __PT_INT_CODE(4,%r11),__LC_EXT_CPU_ADDR
mvc __PT_INT_PARM(4,%r11),__LC_EXT_PARAMS
@@ -1206,6 +1175,9 @@
xgr %r10,%r10
mvc __PT_R8(64,%r11),0(%r14)
stmg %r8,%r9,__PT_PSW(%r11)
+ la %r14,4095
+ mvc __PT_CR1(8,%r11),__LC_CREGS_SAVE_AREA-4095+8(%r14)
+ lctlg %c1,%c1,__LC_KERNEL_ASCE
xc __PT_FLAGS(8,%r11),__PT_FLAGS(%r11)
xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
lgr %r2,%r11 # pass pointer to pt_regs
@@ -1221,6 +1193,7 @@
brasl %r14,s390_handle_mcck
TRACE_IRQS_ON
.Lmcck_return:
+ lctlg %c1,%c1,__PT_CR1(%r11)
lmg %r0,%r10,__PT_R0(%r11)
mvc __LC_RETURN_MCCK_PSW(16),__PT_PSW(%r11) # move return PSW
tm __LC_RETURN_MCCK_PSW+1,0x01 # returning to user ?
@@ -1297,7 +1270,7 @@
1: BPENTER __SF_SIE_FLAGS(%r15),(_TIF_ISOLATE_BP|_TIF_ISOLATE_BP_GUEST)
lg %r9,__SF_SIE_CONTROL(%r15) # get control block pointer
ni __SIE_PROG0C+3(%r9),0xfe # no longer in SIE
- lctlg %c1,%c1,__LC_USER_ASCE # load primary asce
+ lctlg %c1,%c1,__LC_KERNEL_ASCE
larl %r9,sie_exit # skip forward to sie_exit
BR_EX %r14,%r11