korg/linux
0
0
Fork 0
mirror of https://mirrors.bfsu.edu.cn/git/linux.git synced 2024-11-19 10:14:23 +08:00
Code Issues Packages Projects Releases Wiki Activity
3d43b981eb
linux/arch/s390/kernel/entry.S
Martin Schwidefsky 0aaba41b58 s390: remove all code using the access register mode 
The vdso code for the getcpu() and the clock_gettime() call use the access
register mode to access the per-CPU vdso data page with the current code.

An alternative to the complicated AR mode is to use the secondary space
mode. This makes the vdso faster and quite a bit simpler. The downside is
that the uaccess code has to be changed quite a bit.

Which instructions are used depends on the machine and what kind of uaccess
operation is requested. The instruction dictates which ASCE value needs
to be loaded into %cr1 and %cr7.

The different cases:

* User copy with MVCOS for z10 and newer machines
  The MVCOS instruction can copy between the primary space (aka user) and
  the home space (aka kernel) directly. For set_fs(KERNEL_DS) the kernel
  ASCE is loaded into %cr1. For set_fs(USER_DS) the user space is already
  loaded in %cr1.

* User copy with MVCP/MVCS for older machines
  To be able to execute the MVCP/MVCS instructions the kernel needs to
  switch to primary mode. The control register %cr1 has to be set to the
  kernel ASCE and %cr7 to either the kernel ASCE or the user ASCE dependent
  on set_fs(KERNEL_DS) vs set_fs(USER_DS).

* Data access in the user address space for strnlen / futex
  To use "normal" instruction with data from the user address space the
  secondary space mode is used. The kernel needs to switch to primary mode,
  %cr1 has to contain the kernel ASCE and %cr7 either the user ASCE or the
  kernel ASCE, dependent on set_fs.

To load a new value into %cr1 or %cr7 is an expensive operation, the kernel
tries to be lazy about it. E.g. for multiple user copies in a row with
MVCP/MVCS the replacement of the vdso ASCE in %cr7 with the user ASCE is
done only once. On return to user space a CPU bit is checked that loads the
vdso ASCE again.

To enable and disable the data access via the secondary space two new
functions are added, enable_sacf_uaccess and disable_sacf_uaccess. The fact
that a context is in secondary space uaccess mode is stored in the
mm_segment_t value for the task. The code of an interrupt may use set_fs
as long as it returns to the previous state it got with get_fs with another
call to set_fs. The code in finish_arch_post_lock_switch simply has to do a
set_fs with the current mm_segment_t value for the task.

For CPUs with MVCOS:

CPU running in                        | %cr1 ASCE | %cr7 ASCE |
--------------------------------------|-----------|-----------|
user space                            |  user     |  vdso     |
kernel, USER_DS, normal-mode          |  user     |  vdso     |
kernel, USER_DS, normal-mode, lazy    |  user     |  user     |
kernel, USER_DS, sacf-mode            |  kernel   |  user     |
kernel, KERNEL_DS, normal-mode        |  kernel   |  vdso     |
kernel, KERNEL_DS, normal-mode, lazy  |  kernel   |  kernel   |
kernel, KERNEL_DS, sacf-mode          |  kernel   |  kernel   |

For CPUs without MVCOS:

CPU running in                        | %cr1 ASCE | %cr7 ASCE |
--------------------------------------|-----------|-----------|
user space                            |  user     |  vdso     |
kernel, USER_DS, normal-mode          |  user     |  vdso     |
kernel, USER_DS, normal-mode lazy     |  kernel   |  user     |
kernel, USER_DS, sacf-mode            |  kernel   |  user     |
kernel, KERNEL_DS, normal-mode        |  kernel   |  vdso     |
kernel, KERNEL_DS, normal-mode, lazy  |  kernel   |  kernel   |
kernel, KERNEL_DS, sacf-mode          |  kernel   |  kernel   |

The lines with "lazy" refer to the state after a copy via the secondary
space with a delayed reload of %cr1 and %cr7.

There are three hardware address spaces that can cause a DAT exception,
primary, secondary and home space. The exception can be related to
four different fault types: user space fault, vdso fault, kernel fault,
and the gmap faults.

Dependent on the set_fs state and normal vs. sacf mode there are a number
of fault combinations:

1) user address space fault via the primary ASCE
2) gmap address space fault via the primary ASCE
3) kernel address space fault via the primary ASCE for machines with
   MVCOS and set_fs(KERNEL_DS)
4) vdso address space faults via the secondary ASCE with an invalid
   address while running in secondary space in problem state
5) user address space fault via the secondary ASCE for user-copy
   based on the secondary space mode, e.g. futex_ops or strnlen_user
6) kernel address space fault via the secondary ASCE for user-copy
   with secondary space mode with set_fs(KERNEL_DS)
7) kernel address space fault via the primary ASCE for user-copy
   with secondary space mode with set_fs(USER_DS) on machines without
   MVCOS.
8) kernel address space fault via the home space ASCE

Replace user_space_fault() with a new function get_fault_type() that
can distinguish all four different fault types.

With these changes the futex atomic ops from the kernel and the
strnlen_user will get a little bit slower, as well as the old style
uaccess with MVCP/MVCS. All user accesses based on MVCOS will be as
fast as before. On the positive side, the user space vdso code is a
lot faster and Linux ceases to use the complicated AR mode.

Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
2017-11-14 11:01:47 +01:00

1407 lines
38 KiB
ArmAsm
Raw Blame History

/* SPDX-License-Identifier: GPL-2.0 */
/*
* S390 low-level entry points.
*
* Copyright IBM Corp. 1999, 2012
* Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com),
* Hartmut Penner (hp@de.ibm.com),
* Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com),
* Heiko Carstens <heiko.carstens@de.ibm.com>
*/
#include <linux/init.h>
#include <linux/linkage.h>
#include <asm/processor.h>
#include <asm/cache.h>
#include <asm/ctl_reg.h>
#include <asm/errno.h>
#include <asm/ptrace.h>
#include <asm/thread_info.h>
#include <asm/asm-offsets.h>
#include <asm/unistd.h>
#include <asm/page.h>
#include <asm/sigp.h>
#include <asm/irq.h>
#include <asm/vx-insn.h>
#include <asm/setup.h>
#include <asm/nmi.h>
#include <asm/export.h>
__PT_R0 = __PT_GPRS
__PT_R1 = __PT_GPRS + 8
__PT_R2 = __PT_GPRS + 16
__PT_R3 = __PT_GPRS + 24
__PT_R4 = __PT_GPRS + 32
__PT_R5 = __PT_GPRS + 40
__PT_R6 = __PT_GPRS + 48
__PT_R7 = __PT_GPRS + 56
__PT_R8 = __PT_GPRS + 64
__PT_R9 = __PT_GPRS + 72
__PT_R10 = __PT_GPRS + 80
__PT_R11 = __PT_GPRS + 88
__PT_R12 = __PT_GPRS + 96
__PT_R13 = __PT_GPRS + 104
__PT_R14 = __PT_GPRS + 112
__PT_R15 = __PT_GPRS + 120
STACK_SHIFT = PAGE_SHIFT + THREAD_SIZE_ORDER
STACK_SIZE = 1 << STACK_SHIFT
STACK_INIT = STACK_SIZE - STACK_FRAME_OVERHEAD - __PT_SIZE
_TIF_WORK = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \
_TIF_UPROBE | _TIF_GUARDED_STORAGE | _TIF_PATCH_PENDING)
_TIF_TRACE = (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | \
_TIF_SYSCALL_TRACEPOINT)
_CIF_WORK = (_CIF_MCCK_PENDING | _CIF_ASCE_PRIMARY | \
_CIF_ASCE_SECONDARY | _CIF_FPU)
_PIF_WORK = (_PIF_PER_TRAP | _PIF_SYSCALL_RESTART)
#define BASED(name) name-cleanup_critical(%r13)
.macro TRACE_IRQS_ON
#ifdef CONFIG_TRACE_IRQFLAGS
basr %r2,%r0
brasl %r14,trace_hardirqs_on_caller
#endif
.endm
.macro TRACE_IRQS_OFF
#ifdef CONFIG_TRACE_IRQFLAGS
basr %r2,%r0
brasl %r14,trace_hardirqs_off_caller
#endif
.endm
.macro LOCKDEP_SYS_EXIT
#ifdef CONFIG_LOCKDEP
tm __PT_PSW+1(%r11),0x01 # returning to user ?
jz .+10
brasl %r14,lockdep_sys_exit
#endif
.endm
.macro CHECK_STACK stacksize,savearea
#ifdef CONFIG_CHECK_STACK
tml %r15,\stacksize - CONFIG_STACK_GUARD
lghi %r14,\savearea
jz stack_overflow
#endif
.endm
.macro SWITCH_ASYNC savearea,timer
tmhh %r8,0x0001 # interrupting from user ?
jnz 1f
lgr %r14,%r9
slg %r14,BASED(.Lcritical_start)
clg %r14,BASED(.Lcritical_length)
jhe 0f
lghi %r11,\savearea # inside critical section, do cleanup
brasl %r14,cleanup_critical
tmhh %r8,0x0001 # retest problem state after cleanup
jnz 1f
0: lg %r14,__LC_ASYNC_STACK # are we already on the async stack?
slgr %r14,%r15
srag %r14,%r14,STACK_SHIFT
jnz 2f
CHECK_STACK 1<<STACK_SHIFT,\savearea
aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
j 3f
1: UPDATE_VTIME %r14,%r15,\timer
2: lg %r15,__LC_ASYNC_STACK # load async stack
3: la %r11,STACK_FRAME_OVERHEAD(%r15)
.endm
.macro UPDATE_VTIME w1,w2,enter_timer
lg \w1,__LC_EXIT_TIMER
lg \w2,__LC_LAST_UPDATE_TIMER
slg \w1,\enter_timer
slg \w2,__LC_EXIT_TIMER
alg \w1,__LC_USER_TIMER
alg \w2,__LC_SYSTEM_TIMER
stg \w1,__LC_USER_TIMER
stg \w2,__LC_SYSTEM_TIMER
mvc __LC_LAST_UPDATE_TIMER(8),\enter_timer
.endm
.macro REENABLE_IRQS
stg %r8,__LC_RETURN_PSW
ni __LC_RETURN_PSW,0xbf
ssm __LC_RETURN_PSW
.endm
.macro STCK savearea
#ifdef CONFIG_HAVE_MARCH_Z9_109_FEATURES
.insn s,0xb27c0000,\savearea # store clock fast
#else
.insn s,0xb2050000,\savearea # store clock
#endif
.endm
/*
* The TSTMSK macro generates a test-under-mask instruction by
* calculating the memory offset for the specified mask value.
* Mask value can be any constant. The macro shifts the mask
* value to calculate the memory offset for the test-under-mask
* instruction.
*/
.macro TSTMSK addr, mask, size=8, bytepos=0
.if (\bytepos < \size) && (\mask >> 8)
.if (\mask & 0xff)
.error "Mask exceeds byte boundary"
.endif
TSTMSK \addr, "(\mask >> 8)", \size, "(\bytepos + 1)"
.exitm
.endif
.ifeq \mask
.error "Mask must not be zero"
.endif
off = \size - \bytepos - 1
tm off+\addr, \mask
.endm
.section .kprobes.text, "ax"
.Ldummy:
/*
* This nop exists only in order to avoid that __switch_to starts at
* the beginning of the kprobes text section. In that case we would
* have several symbols at the same address. E.g. objdump would take
* an arbitrary symbol name when disassembling this code.
* With the added nop in between the __switch_to symbol is unique
* again.
*/
nop 0
/*
* Scheduler resume function, called by switch_to
* gpr2 = (task_struct *) prev
* gpr3 = (task_struct *) next
* Returns:
* gpr2 = prev
*/
ENTRY(__switch_to)
stmg %r6,%r15,__SF_GPRS(%r15) # store gprs of prev task
lgr %r1,%r2
aghi %r1,__TASK_thread # thread_struct of prev task
lg %r5,__TASK_stack(%r3) # start of kernel stack of next
stg %r15,__THREAD_ksp(%r1) # store kernel stack of prev
lgr %r1,%r3
aghi %r1,__TASK_thread # thread_struct of next task
lgr %r15,%r5
aghi %r15,STACK_INIT # end of kernel stack of next
stg %r3,__LC_CURRENT # store task struct of next
stg %r15,__LC_KERNEL_STACK # store end of kernel stack
lg %r15,__THREAD_ksp(%r1) # load kernel stack of next
mvc __LC_CURRENT_PID(4,%r0),__TASK_pid(%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
.insn s,0xb2800000,__LC_LPP # set program parameter
br %r14
.L__critical_start:
#if IS_ENABLED(CONFIG_KVM)
/*
* sie64a calling convention:
* %r2 pointer to sie control block
* %r3 guest register save area
*/
ENTRY(sie64a)
stmg %r6,%r14,__SF_GPRS(%r15) # save kernel registers
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
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
.Lsie_load_guest_gprs:
lmg %r0,%r13,0(%r3) # load guest gprs 0-13
lg %r14,__LC_GMAP # get gmap pointer
ltgr %r14,%r14
jz .Lsie_gmap
lctlg %c1,%c1,__GMAP_ASCE(%r14) # load primary asce
.Lsie_gmap:
lg %r14,__SF_EMPTY(%r15) # get control block pointer
oi __SIE_PROG0C+3(%r14),1 # we are going into SIE now
tm __SIE_PROG20+3(%r14),3 # last exit...
jnz .Lsie_skip
TSTMSK __LC_CPU_FLAGS,_CIF_FPU
jo .Lsie_skip # exit if fp/vx regs changed
.Lsie_entry:
sie 0(%r14)
.Lsie_skip:
ni __SIE_PROG0C+3(%r14),0xfe # no longer in SIE
lctlg %c1,%c1,__LC_USER_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
# are some corner cases (e.g. runtime instrumentation) where ILC is unpredictable.
# Other instructions between sie64a and .Lsie_done should not cause program
# interrupts. So lets use 3 nops as a landing pad for all possible rewinds.
# See also .Lcleanup_sie
.Lrewind_pad6:
nopr 7
.Lrewind_pad4:
nopr 7
.Lrewind_pad2:
nopr 7
.globl sie_exit
sie_exit:
lg %r14,__SF_EMPTY+8(%r15) # load guest register save area
stmg %r0,%r13,0(%r14) # save guest gprs 0-13
lmg %r6,%r14,__SF_GPRS(%r15) # restore kernel registers
lg %r2,__SF_EMPTY+16(%r15) # return exit reason code
br %r14
.Lsie_fault:
lghi %r14,-EFAULT
stg %r14,__SF_EMPTY+16(%r15) # set exit reason code
j sie_exit
EX_TABLE(.Lrewind_pad6,.Lsie_fault)
EX_TABLE(.Lrewind_pad4,.Lsie_fault)
EX_TABLE(.Lrewind_pad2,.Lsie_fault)
EX_TABLE(sie_exit,.Lsie_fault)
EXPORT_SYMBOL(sie64a)
EXPORT_SYMBOL(sie_exit)
#endif
/*
* SVC interrupt handler routine. System calls are synchronous events and
* are executed with interrupts enabled.
*/
ENTRY(system_call)
stpt __LC_SYNC_ENTER_TIMER
.Lsysc_stmg:
stmg %r8,%r15,__LC_SAVE_AREA_SYNC
lg %r12,__LC_CURRENT
lghi %r13,__TASK_thread
lghi %r14,_PIF_SYSCALL
.Lsysc_per:
lg %r15,__LC_KERNEL_STACK
la %r11,STACK_FRAME_OVERHEAD(%r15) # pointer to pt_regs
.Lsysc_vtime:
UPDATE_VTIME %r8,%r9,__LC_SYNC_ENTER_TIMER
stmg %r0,%r7,__PT_R0(%r11)
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
stg %r14,__PT_FLAGS(%r11)
.Lsysc_do_svc:
# load address of system call table
lg %r10,__THREAD_sysc_table(%r13,%r12)
llgh %r8,__PT_INT_CODE+2(%r11)
slag %r8,%r8,2 # shift and test for svc 0
jnz .Lsysc_nr_ok
# svc 0: system call number in %r1
llgfr %r1,%r1 # clear high word in r1
cghi %r1,NR_syscalls
jnl .Lsysc_nr_ok
sth %r1,__PT_INT_CODE+2(%r11)
slag %r8,%r1,2
.Lsysc_nr_ok:
xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
stg %r2,__PT_ORIG_GPR2(%r11)
stg %r7,STACK_FRAME_OVERHEAD(%r15)
lgf %r9,0(%r8,%r10) # get system call add.
TSTMSK __TI_flags(%r12),_TIF_TRACE
jnz .Lsysc_tracesys
basr %r14,%r9 # call sys_xxxx
stg %r2,__PT_R2(%r11) # store return value
.Lsysc_return:
LOCKDEP_SYS_EXIT
.Lsysc_tif:
TSTMSK __PT_FLAGS(%r11),_PIF_WORK
jnz .Lsysc_work
TSTMSK __TI_flags(%r12),_TIF_WORK
jnz .Lsysc_work # check for work
TSTMSK __LC_CPU_FLAGS,_CIF_WORK
jnz .Lsysc_work
.Lsysc_restore:
lg %r14,__LC_VDSO_PER_CPU
lmg %r0,%r10,__PT_R0(%r11)
mvc __LC_RETURN_PSW(16),__PT_PSW(%r11)
.Lsysc_exit_timer:
stpt __LC_EXIT_TIMER
mvc __VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER
lmg %r11,%r15,__PT_R11(%r11)
lpswe __LC_RETURN_PSW
.Lsysc_done:
#
# One of the work bits is on. Find out which one.
#
.Lsysc_work:
TSTMSK __LC_CPU_FLAGS,_CIF_MCCK_PENDING
jo .Lsysc_mcck_pending
TSTMSK __TI_flags(%r12),_TIF_NEED_RESCHED
jo .Lsysc_reschedule
TSTMSK __PT_FLAGS(%r11),_PIF_SYSCALL_RESTART
jo .Lsysc_syscall_restart
#ifdef CONFIG_UPROBES
TSTMSK __TI_flags(%r12),_TIF_UPROBE
jo .Lsysc_uprobe_notify
#endif
TSTMSK __TI_flags(%r12),_TIF_GUARDED_STORAGE
jo .Lsysc_guarded_storage
TSTMSK __PT_FLAGS(%r11),_PIF_PER_TRAP
jo .Lsysc_singlestep
#ifdef CONFIG_LIVEPATCH
TSTMSK __TI_flags(%r12),_TIF_PATCH_PENDING
jo .Lsysc_patch_pending # handle live patching just before
# signals and possible syscall restart
#endif
TSTMSK __PT_FLAGS(%r11),_PIF_SYSCALL_RESTART
jo .Lsysc_syscall_restart
TSTMSK __TI_flags(%r12),_TIF_SIGPENDING
jo .Lsysc_sigpending
TSTMSK __TI_flags(%r12),_TIF_NOTIFY_RESUME
jo .Lsysc_notify_resume
TSTMSK __LC_CPU_FLAGS,_CIF_FPU
jo .Lsysc_vxrs
TSTMSK __LC_CPU_FLAGS,(_CIF_ASCE_PRIMARY|_CIF_ASCE_SECONDARY)
jnz .Lsysc_asce
j .Lsysc_return # beware of critical section cleanup
#
# _TIF_NEED_RESCHED is set, call schedule
#
.Lsysc_reschedule:
larl %r14,.Lsysc_return
jg schedule
#
# _CIF_MCCK_PENDING is set, call handler
#
.Lsysc_mcck_pending:
larl %r14,.Lsysc_return
jg s390_handle_mcck # TIF bit will be cleared by handler
#
# _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
#
# CIF_FPU is set, restore floating-point controls and floating-point registers.
#
.Lsysc_vxrs:
larl %r14,.Lsysc_return
jg load_fpu_regs
#
# _TIF_SIGPENDING is set, call do_signal
#
.Lsysc_sigpending:
lgr %r2,%r11 # pass pointer to pt_regs
brasl %r14,do_signal
TSTMSK __PT_FLAGS(%r11),_PIF_SYSCALL
jno .Lsysc_return
.Lsysc_do_syscall:
lghi %r13,__TASK_thread
lmg %r2,%r7,__PT_R2(%r11) # load svc arguments
lghi %r1,0 # svc 0 returns -ENOSYS
j .Lsysc_do_svc
#
# _TIF_NOTIFY_RESUME is set, call do_notify_resume
#
.Lsysc_notify_resume:
lgr %r2,%r11 # pass pointer to pt_regs
larl %r14,.Lsysc_return
jg do_notify_resume
#
# _TIF_UPROBE is set, call uprobe_notify_resume
#
#ifdef CONFIG_UPROBES
.Lsysc_uprobe_notify:
lgr %r2,%r11 # pass pointer to pt_regs
larl %r14,.Lsysc_return
jg uprobe_notify_resume
#endif
#
# _TIF_GUARDED_STORAGE is set, call guarded_storage_load
#
.Lsysc_guarded_storage:
lgr %r2,%r11 # pass pointer to pt_regs
larl %r14,.Lsysc_return
jg gs_load_bc_cb
#
# _TIF_PATCH_PENDING is set, call klp_update_patch_state
#
#ifdef CONFIG_LIVEPATCH
.Lsysc_patch_pending:
lg %r2,__LC_CURRENT # pass pointer to task struct
larl %r14,.Lsysc_return
jg klp_update_patch_state
#endif
#
# _PIF_PER_TRAP is set, call do_per_trap
#
.Lsysc_singlestep:
ni __PT_FLAGS+7(%r11),255-_PIF_PER_TRAP
lgr %r2,%r11 # pass pointer to pt_regs
larl %r14,.Lsysc_return
jg do_per_trap
#
# _PIF_SYSCALL_RESTART is set, repeat the current system call
#
.Lsysc_syscall_restart:
ni __PT_FLAGS+7(%r11),255-_PIF_SYSCALL_RESTART
lmg %r1,%r7,__PT_R1(%r11) # load svc arguments
lg %r2,__PT_ORIG_GPR2(%r11)
j .Lsysc_do_svc
#
# call tracehook_report_syscall_entry/tracehook_report_syscall_exit before
# and after the system call
#
.Lsysc_tracesys:
lgr %r2,%r11 # pass pointer to pt_regs
la %r3,0
llgh %r0,__PT_INT_CODE+2(%r11)
stg %r0,__PT_R2(%r11)
brasl %r14,do_syscall_trace_enter
lghi %r0,NR_syscalls
clgr %r0,%r2
jnh .Lsysc_tracenogo
sllg %r8,%r2,2
lgf %r9,0(%r8,%r10)
.Lsysc_tracego:
lmg %r3,%r7,__PT_R3(%r11)
stg %r7,STACK_FRAME_OVERHEAD(%r15)
lg %r2,__PT_ORIG_GPR2(%r11)
basr %r14,%r9 # call sys_xxx
stg %r2,__PT_R2(%r11) # store return value
.Lsysc_tracenogo:
TSTMSK __TI_flags(%r12),_TIF_TRACE
jz .Lsysc_return
lgr %r2,%r11 # pass pointer to pt_regs
larl %r14,.Lsysc_return
jg do_syscall_trace_exit
#
# a new process exits the kernel with ret_from_fork
#
ENTRY(ret_from_fork)
la %r11,STACK_FRAME_OVERHEAD(%r15)
lg %r12,__LC_CURRENT
brasl %r14,schedule_tail
TRACE_IRQS_ON
ssm __LC_SVC_NEW_PSW # reenable interrupts
tm __PT_PSW+1(%r11),0x01 # forking a kernel thread ?
jne .Lsysc_tracenogo
# it's a kernel thread
lmg %r9,%r10,__PT_R9(%r11) # load gprs
ENTRY(kernel_thread_starter)
la %r2,0(%r10)
basr %r14,%r9
j .Lsysc_tracenogo
/*
* Program check handler routine
*/
ENTRY(pgm_check_handler)
stpt __LC_SYNC_ENTER_TIMER
stmg %r8,%r15,__LC_SAVE_AREA_SYNC
lg %r10,__LC_LAST_BREAK
lg %r12,__LC_CURRENT
lghi %r11,0
larl %r13,cleanup_critical
lmg %r8,%r9,__LC_PGM_OLD_PSW
tmhh %r8,0x0001 # test problem state bit
jnz 2f # -> fault in user space
#if IS_ENABLED(CONFIG_KVM)
# cleanup critical section for program checks in sie64a
lgr %r14,%r9
slg %r14,BASED(.Lsie_critical_start)
clg %r14,BASED(.Lsie_critical_length)
jhe 0f
lg %r14,__SF_EMPTY(%r15) # get control block pointer
ni __SIE_PROG0C+3(%r14),0xfe # no longer in SIE
lctlg %c1,%c1,__LC_USER_ASCE # load primary asce
larl %r9,sie_exit # skip forward to sie_exit
lghi %r11,_PIF_GUEST_FAULT
#endif
0: tmhh %r8,0x4000 # PER bit set in old PSW ?
jnz 1f # -> enabled, can't be a double fault
tm __LC_PGM_ILC+3,0x80 # check for per exception
jnz .Lpgm_svcper # -> single stepped svc
1: CHECK_STACK STACK_SIZE,__LC_SAVE_AREA_SYNC
aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
j 4f
2: UPDATE_VTIME %r14,%r15,__LC_SYNC_ENTER_TIMER
lg %r15,__LC_KERNEL_STACK
lgr %r14,%r12
aghi %r14,__TASK_thread # pointer to thread_struct
lghi %r13,__LC_PGM_TDB
tm __LC_PGM_ILC+2,0x02 # check for transaction abort
jz 3f
mvc __THREAD_trap_tdb(256,%r14),0(%r13)
3: stg %r10,__THREAD_last_break(%r14)
4: lgr %r13,%r11
la %r11,STACK_FRAME_OVERHEAD(%r15)
stmg %r0,%r7,__PT_R0(%r11)
mvc __PT_R8(64,%r11),__LC_SAVE_AREA_SYNC
stmg %r8,%r9,__PT_PSW(%r11)
mvc __PT_INT_CODE(4,%r11),__LC_PGM_ILC
mvc __PT_INT_PARM_LONG(8,%r11),__LC_TRANS_EXC_CODE
stg %r13,__PT_FLAGS(%r11)
stg %r10,__PT_ARGS(%r11)
tm __LC_PGM_ILC+3,0x80 # check for per exception
jz 5f
tmhh %r8,0x0001 # kernel per event ?
jz .Lpgm_kprobe
oi __PT_FLAGS+7(%r11),_PIF_PER_TRAP
mvc __THREAD_per_address(8,%r14),__LC_PER_ADDRESS
mvc __THREAD_per_cause(2,%r14),__LC_PER_CODE
mvc __THREAD_per_paid(1,%r14),__LC_PER_ACCESS_ID
5: REENABLE_IRQS
xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
larl %r1,pgm_check_table
llgh %r10,__PT_INT_CODE+2(%r11)
nill %r10,0x007f
sll %r10,2
je .Lpgm_return
lgf %r1,0(%r10,%r1) # load address of handler routine
lgr %r2,%r11 # pass pointer to pt_regs
basr %r14,%r1 # branch to interrupt-handler
.Lpgm_return:
LOCKDEP_SYS_EXIT
tm __PT_PSW+1(%r11),0x01 # returning to user ?
jno .Lsysc_restore
TSTMSK __PT_FLAGS(%r11),_PIF_SYSCALL
jo .Lsysc_do_syscall
j .Lsysc_tif
#
# PER event in supervisor state, must be kprobes
#
.Lpgm_kprobe:
REENABLE_IRQS
xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
lgr %r2,%r11 # pass pointer to pt_regs
brasl %r14,do_per_trap
j .Lpgm_return
#
# single stepped system call
#
.Lpgm_svcper:
mvc __LC_RETURN_PSW(8),__LC_SVC_NEW_PSW
lghi %r13,__TASK_thread
larl %r14,.Lsysc_per
stg %r14,__LC_RETURN_PSW+8
lghi %r14,_PIF_SYSCALL | _PIF_PER_TRAP
lpswe __LC_RETURN_PSW # branch to .Lsysc_per and enable irqs
/*
* IO interrupt handler routine
*/
ENTRY(io_int_handler)
STCK __LC_INT_CLOCK
stpt __LC_ASYNC_ENTER_TIMER
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)
mvc __PT_R8(64,%r11),__LC_SAVE_AREA_ASYNC
stmg %r8,%r9,__PT_PSW(%r11)
mvc __PT_INT_CODE(12,%r11),__LC_SUBCHANNEL_ID
xc __PT_FLAGS(8,%r11),__PT_FLAGS(%r11)
TSTMSK __LC_CPU_FLAGS,_CIF_IGNORE_IRQ
jo .Lio_restore
TRACE_IRQS_OFF
xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
.Lio_loop:
lgr %r2,%r11 # pass pointer to pt_regs
lghi %r3,IO_INTERRUPT
tm __PT_INT_CODE+8(%r11),0x80 # adapter interrupt ?
jz .Lio_call
lghi %r3,THIN_INTERRUPT
.Lio_call:
brasl %r14,do_IRQ
TSTMSK __LC_MACHINE_FLAGS,MACHINE_FLAG_LPAR
jz .Lio_return
tpi 0
jz .Lio_return
mvc __PT_INT_CODE(12,%r11),__LC_SUBCHANNEL_ID
j .Lio_loop
.Lio_return:
LOCKDEP_SYS_EXIT
TRACE_IRQS_ON
.Lio_tif:
TSTMSK __TI_flags(%r12),_TIF_WORK
jnz .Lio_work # there is work to do (signals etc.)
TSTMSK __LC_CPU_FLAGS,_CIF_WORK
jnz .Lio_work
.Lio_restore:
lg %r14,__LC_VDSO_PER_CPU
lmg %r0,%r10,__PT_R0(%r11)
mvc __LC_RETURN_PSW(16),__PT_PSW(%r11)
.Lio_exit_timer:
stpt __LC_EXIT_TIMER
mvc __VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER
lmg %r11,%r15,__PT_R11(%r11)
lpswe __LC_RETURN_PSW
.Lio_done:
#
# There is work todo, find out in which context we have been interrupted:
# 1) if we return to user space we can do all _TIF_WORK work
# 2) if we return to kernel code and kvm is enabled check if we need to
# modify the psw to leave SIE
# 3) if we return to kernel code and preemptive scheduling is enabled check
# the preemption counter and if it is zero call preempt_schedule_irq
# Before any work can be done, a switch to the kernel stack is required.
#
.Lio_work:
tm __PT_PSW+1(%r11),0x01 # returning to user ?
jo .Lio_work_user # yes -> do resched & signal
#ifdef CONFIG_PREEMPT
# check for preemptive scheduling
icm %r0,15,__LC_PREEMPT_COUNT
jnz .Lio_restore # preemption is disabled
TSTMSK __TI_flags(%r12),_TIF_NEED_RESCHED
jno .Lio_restore
# switch to kernel stack
lg %r1,__PT_R15(%r11)
aghi %r1,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
mvc STACK_FRAME_OVERHEAD(__PT_SIZE,%r1),0(%r11)
xc __SF_BACKCHAIN(8,%r1),__SF_BACKCHAIN(%r1)
la %r11,STACK_FRAME_OVERHEAD(%r1)
lgr %r15,%r1
# TRACE_IRQS_ON already done at .Lio_return, call
# TRACE_IRQS_OFF to keep things symmetrical
TRACE_IRQS_OFF
brasl %r14,preempt_schedule_irq
j .Lio_return
#else
j .Lio_restore
#endif
#
# Need to do work before returning to userspace, switch to kernel stack
#
.Lio_work_user:
lg %r1,__LC_KERNEL_STACK
mvc STACK_FRAME_OVERHEAD(__PT_SIZE,%r1),0(%r11)
xc __SF_BACKCHAIN(8,%r1),__SF_BACKCHAIN(%r1)
la %r11,STACK_FRAME_OVERHEAD(%r1)
lgr %r15,%r1
#
# One of the work bits is on. Find out which one.
#
.Lio_work_tif:
TSTMSK __LC_CPU_FLAGS,_CIF_MCCK_PENDING
jo .Lio_mcck_pending
TSTMSK __TI_flags(%r12),_TIF_NEED_RESCHED
jo .Lio_reschedule
#ifdef CONFIG_LIVEPATCH
TSTMSK __TI_flags(%r12),_TIF_PATCH_PENDING
jo .Lio_patch_pending
#endif
TSTMSK __TI_flags(%r12),_TIF_SIGPENDING
jo .Lio_sigpending
TSTMSK __TI_flags(%r12),_TIF_NOTIFY_RESUME
jo .Lio_notify_resume
TSTMSK __TI_flags(%r12),_TIF_GUARDED_STORAGE
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 # beware of critical section cleanup
#
# _CIF_MCCK_PENDING is set, call handler
#
.Lio_mcck_pending:
# TRACE_IRQS_ON already done at .Lio_return
brasl %r14,s390_handle_mcck # TIF bit will be cleared by handler
TRACE_IRQS_OFF
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:
larl %r14,.Lio_return
jg load_fpu_regs
#
# _TIF_GUARDED_STORAGE is set, call guarded_storage_load
#
.Lio_guarded_storage:
# TRACE_IRQS_ON already done at .Lio_return
ssm __LC_SVC_NEW_PSW # reenable interrupts
lgr %r2,%r11 # pass pointer to pt_regs
brasl %r14,gs_load_bc_cb
ssm __LC_PGM_NEW_PSW # disable I/O and ext. interrupts
TRACE_IRQS_OFF
j .Lio_return
#
# _TIF_NEED_RESCHED is set, call schedule
#
.Lio_reschedule:
# TRACE_IRQS_ON already done at .Lio_return
ssm __LC_SVC_NEW_PSW # reenable interrupts
brasl %r14,schedule # call scheduler
ssm __LC_PGM_NEW_PSW # disable I/O and ext. interrupts
TRACE_IRQS_OFF
j .Lio_return
#
# _TIF_PATCH_PENDING is set, call klp_update_patch_state
#
#ifdef CONFIG_LIVEPATCH
.Lio_patch_pending:
lg %r2,__LC_CURRENT # pass pointer to task struct
larl %r14,.Lio_return
jg klp_update_patch_state
#endif
#
# _TIF_SIGPENDING or is set, call do_signal
#
.Lio_sigpending:
# TRACE_IRQS_ON already done at .Lio_return
ssm __LC_SVC_NEW_PSW # reenable interrupts
lgr %r2,%r11 # pass pointer to pt_regs
brasl %r14,do_signal
ssm __LC_PGM_NEW_PSW # disable I/O and ext. interrupts
TRACE_IRQS_OFF
j .Lio_return
#
# _TIF_NOTIFY_RESUME or is set, call do_notify_resume
#
.Lio_notify_resume:
# TRACE_IRQS_ON already done at .Lio_return
ssm __LC_SVC_NEW_PSW # reenable interrupts
lgr %r2,%r11 # pass pointer to pt_regs
brasl %r14,do_notify_resume
ssm __LC_PGM_NEW_PSW # disable I/O and ext. interrupts
TRACE_IRQS_OFF
j .Lio_return
/*
* External interrupt handler routine
*/
ENTRY(ext_int_handler)
STCK __LC_INT_CLOCK
stpt __LC_ASYNC_ENTER_TIMER
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)
mvc __PT_R8(64,%r11),__LC_SAVE_AREA_ASYNC
stmg %r8,%r9,__PT_PSW(%r11)
lghi %r1,__LC_EXT_PARAMS2
mvc __PT_INT_CODE(4,%r11),__LC_EXT_CPU_ADDR
mvc __PT_INT_PARM(4,%r11),__LC_EXT_PARAMS
mvc __PT_INT_PARM_LONG(8,%r11),0(%r1)
xc __PT_FLAGS(8,%r11),__PT_FLAGS(%r11)
TSTMSK __LC_CPU_FLAGS,_CIF_IGNORE_IRQ
jo .Lio_restore
TRACE_IRQS_OFF
xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
lgr %r2,%r11 # pass pointer to pt_regs
lghi %r3,EXT_INTERRUPT
brasl %r14,do_IRQ
j .Lio_return
/*
* Load idle PSW. The second "half" of this function is in .Lcleanup_idle.
*/
ENTRY(psw_idle)
stg %r3,__SF_EMPTY(%r15)
larl %r1,.Lpsw_idle_lpsw+4
stg %r1,__SF_EMPTY+8(%r15)
#ifdef CONFIG_SMP
larl %r1,smp_cpu_mtid
llgf %r1,0(%r1)
ltgr %r1,%r1
jz .Lpsw_idle_stcctm
.insn rsy,0xeb0000000017,%r1,5,__SF_EMPTY+16(%r15)
.Lpsw_idle_stcctm:
#endif
oi __LC_CPU_FLAGS+7,_CIF_ENABLED_WAIT
STCK __CLOCK_IDLE_ENTER(%r2)
stpt __TIMER_IDLE_ENTER(%r2)
.Lpsw_idle_lpsw:
lpswe __SF_EMPTY(%r15)
br %r14
.Lpsw_idle_end:
/*
* Store floating-point controls and floating-point or vector register
* depending whether the vector facility is available. A critical section
* cleanup assures that the registers are stored even if interrupted for
* some other work. The CIF_FPU flag is set to trigger a lazy restore
* of the register contents at return from io or a system call.
*/
ENTRY(save_fpu_regs)
lg %r2,__LC_CURRENT
aghi %r2,__TASK_thread
TSTMSK __LC_CPU_FLAGS,_CIF_FPU
bor %r14
stfpc __THREAD_FPU_fpc(%r2)
lg %r3,__THREAD_FPU_regs(%r2)
TSTMSK __LC_MACHINE_FLAGS,MACHINE_FLAG_VX
jz .Lsave_fpu_regs_fp # no -> store FP regs
VSTM %v0,%v15,0,%r3 # vstm 0,15,0(3)
VSTM %v16,%v31,256,%r3 # vstm 16,31,256(3)
j .Lsave_fpu_regs_done # -> set CIF_FPU flag
.Lsave_fpu_regs_fp:
std 0,0(%r3)
std 1,8(%r3)
std 2,16(%r3)
std 3,24(%r3)
std 4,32(%r3)
std 5,40(%r3)
std 6,48(%r3)
std 7,56(%r3)
std 8,64(%r3)
std 9,72(%r3)
std 10,80(%r3)
std 11,88(%r3)
std 12,96(%r3)
std 13,104(%r3)
std 14,112(%r3)
std 15,120(%r3)
.Lsave_fpu_regs_done:
oi __LC_CPU_FLAGS+7,_CIF_FPU
br %r14
.Lsave_fpu_regs_end:
EXPORT_SYMBOL(save_fpu_regs)
/*
* Load floating-point controls and floating-point or vector registers.
* A critical section cleanup assures that the register contents are
* loaded even if interrupted for some other work.
*
* There are special calling conventions to fit into sysc and io return work:
* %r15: <kernel stack>
* The function requires:
* %r4
*/
load_fpu_regs:
lg %r4,__LC_CURRENT
aghi %r4,__TASK_thread
TSTMSK __LC_CPU_FLAGS,_CIF_FPU
bnor %r14
lfpc __THREAD_FPU_fpc(%r4)
TSTMSK __LC_MACHINE_FLAGS,MACHINE_FLAG_VX
lg %r4,__THREAD_FPU_regs(%r4) # %r4 <- reg save area
jz .Lload_fpu_regs_fp # -> no VX, load FP regs
VLM %v0,%v15,0,%r4
VLM %v16,%v31,256,%r4
j .Lload_fpu_regs_done
.Lload_fpu_regs_fp:
ld 0,0(%r4)
ld 1,8(%r4)
ld 2,16(%r4)
ld 3,24(%r4)
ld 4,32(%r4)
ld 5,40(%r4)
ld 6,48(%r4)
ld 7,56(%r4)
ld 8,64(%r4)
ld 9,72(%r4)
ld 10,80(%r4)
ld 11,88(%r4)
ld 12,96(%r4)
ld 13,104(%r4)
ld 14,112(%r4)
ld 15,120(%r4)
.Lload_fpu_regs_done:
ni __LC_CPU_FLAGS+7,255-_CIF_FPU
br %r14
.Lload_fpu_regs_end:
.L__critical_end:
/*
* Machine check handler routines
*/
ENTRY(mcck_int_handler)
STCK __LC_MCCK_CLOCK
la %r1,4095 # validate r1
spt __LC_CPU_TIMER_SAVE_AREA-4095(%r1) # validate cpu timer
sckc __LC_CLOCK_COMPARATOR # validate comparator
lam %a0,%a15,__LC_AREGS_SAVE_AREA-4095(%r1) # validate acrs
lmg %r0,%r15,__LC_GPREGS_SAVE_AREA-4095(%r1)# validate gprs
lg %r12,__LC_CURRENT
larl %r13,cleanup_critical
lmg %r8,%r9,__LC_MCK_OLD_PSW
TSTMSK __LC_MCCK_CODE,MCCK_CODE_SYSTEM_DAMAGE
jo .Lmcck_panic # yes -> rest of mcck code invalid
TSTMSK __LC_MCCK_CODE,MCCK_CODE_CR_VALID
jno .Lmcck_panic # control registers invalid -> panic
la %r14,4095
lctlg %c0,%c15,__LC_CREGS_SAVE_AREA-4095(%r14) # validate ctl regs
ptlb
lg %r11,__LC_MCESAD-4095(%r14) # extended machine check save area
nill %r11,0xfc00 # MCESA_ORIGIN_MASK
TSTMSK __LC_CREGS_SAVE_AREA+16-4095(%r14),CR2_GUARDED_STORAGE
jno 0f
TSTMSK __LC_MCCK_CODE,MCCK_CODE_GS_VALID
jno 0f
.insn rxy,0xe3000000004d,0,__MCESA_GS_SAVE_AREA(%r11) # LGSC
0: l %r14,__LC_FP_CREG_SAVE_AREA-4095(%r14)
TSTMSK __LC_MCCK_CODE,MCCK_CODE_FC_VALID
jo 0f
sr %r14,%r14
0: sfpc %r14
TSTMSK __LC_MACHINE_FLAGS,MACHINE_FLAG_VX
jo 0f
lghi %r14,__LC_FPREGS_SAVE_AREA
ld %f0,0(%r14)
ld %f1,8(%r14)
ld %f2,16(%r14)
ld %f3,24(%r14)
ld %f4,32(%r14)
ld %f5,40(%r14)
ld %f6,48(%r14)
ld %f7,56(%r14)
ld %f8,64(%r14)
ld %f9,72(%r14)
ld %f10,80(%r14)
ld %f11,88(%r14)
ld %f12,96(%r14)
ld %f13,104(%r14)
ld %f14,112(%r14)
ld %f15,120(%r14)
j 1f
0: VLM %v0,%v15,0,%r11
VLM %v16,%v31,256,%r11
1: lghi %r14,__LC_CPU_TIMER_SAVE_AREA
mvc __LC_MCCK_ENTER_TIMER(8),0(%r14)
TSTMSK __LC_MCCK_CODE,MCCK_CODE_CPU_TIMER_VALID
jo 3f
la %r14,__LC_SYNC_ENTER_TIMER
clc 0(8,%r14),__LC_ASYNC_ENTER_TIMER
jl 0f
la %r14,__LC_ASYNC_ENTER_TIMER
0: clc 0(8,%r14),__LC_EXIT_TIMER
jl 1f
la %r14,__LC_EXIT_TIMER
1: clc 0(8,%r14),__LC_LAST_UPDATE_TIMER
jl 2f
la %r14,__LC_LAST_UPDATE_TIMER
2: spt 0(%r14)
mvc __LC_MCCK_ENTER_TIMER(8),0(%r14)
3: TSTMSK __LC_MCCK_CODE,MCCK_CODE_PSW_MWP_VALID
jno .Lmcck_panic
tmhh %r8,0x0001 # interrupting from user ?
jnz 4f
TSTMSK __LC_MCCK_CODE,MCCK_CODE_PSW_IA_VALID
jno .Lmcck_panic
4: SWITCH_ASYNC __LC_GPREGS_SAVE_AREA+64,__LC_MCCK_ENTER_TIMER
.Lmcck_skip:
lghi %r14,__LC_GPREGS_SAVE_AREA+64
stmg %r0,%r7,__PT_R0(%r11)
mvc __PT_R8(64,%r11),0(%r14)
stmg %r8,%r9,__PT_PSW(%r11)
xc __PT_FLAGS(8,%r11),__PT_FLAGS(%r11)
xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
lgr %r2,%r11 # pass pointer to pt_regs
brasl %r14,s390_do_machine_check
tm __PT_PSW+1(%r11),0x01 # returning to user ?
jno .Lmcck_return
lg %r1,__LC_KERNEL_STACK # switch to kernel stack
mvc STACK_FRAME_OVERHEAD(__PT_SIZE,%r1),0(%r11)
xc __SF_BACKCHAIN(8,%r1),__SF_BACKCHAIN(%r1)
la %r11,STACK_FRAME_OVERHEAD(%r1)
lgr %r15,%r1
ssm __LC_PGM_NEW_PSW # turn dat on, keep irqs off
TSTMSK __LC_CPU_FLAGS,_CIF_MCCK_PENDING
jno .Lmcck_return
TRACE_IRQS_OFF
brasl %r14,s390_handle_mcck
TRACE_IRQS_ON
.Lmcck_return:
lg %r14,__LC_VDSO_PER_CPU
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 ?
jno 0f
stpt __LC_EXIT_TIMER
mvc __VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER
0: lmg %r11,%r15,__PT_R11(%r11)
lpswe __LC_RETURN_MCCK_PSW
.Lmcck_panic:
lg %r15,__LC_PANIC_STACK
la %r11,STACK_FRAME_OVERHEAD(%r15)
j .Lmcck_skip
#
# PSW restart interrupt handler
#
ENTRY(restart_int_handler)
TSTMSK __LC_MACHINE_FLAGS,MACHINE_FLAG_LPP
jz 0f
.insn s,0xb2800000,__LC_LPP
0: stg %r15,__LC_SAVE_AREA_RESTART
lg %r15,__LC_RESTART_STACK
aghi %r15,-__PT_SIZE # create pt_regs on stack
xc 0(__PT_SIZE,%r15),0(%r15)
stmg %r0,%r14,__PT_R0(%r15)
mvc __PT_R15(8,%r15),__LC_SAVE_AREA_RESTART
mvc __PT_PSW(16,%r15),__LC_RST_OLD_PSW # store restart old psw
aghi %r15,-STACK_FRAME_OVERHEAD # create stack frame on stack
xc 0(STACK_FRAME_OVERHEAD,%r15),0(%r15)
lg %r1,__LC_RESTART_FN # load fn, parm & source cpu
lg %r2,__LC_RESTART_DATA
lg %r3,__LC_RESTART_SOURCE
ltgr %r3,%r3 # test source cpu address
jm 1f # negative -> skip source stop
0: sigp %r4,%r3,SIGP_SENSE # sigp sense to source cpu
brc 10,0b # wait for status stored
1: basr %r14,%r1 # call function
stap __SF_EMPTY(%r15) # store cpu address
llgh %r3,__SF_EMPTY(%r15)
2: sigp %r4,%r3,SIGP_STOP # sigp stop to current cpu
brc 2,2b
3: j 3b
.section .kprobes.text, "ax"
#ifdef CONFIG_CHECK_STACK
/*
* The synchronous or the asynchronous stack overflowed. We are dead.
* No need to properly save the registers, we are going to panic anyway.
* Setup a pt_regs so that show_trace can provide a good call trace.
*/
stack_overflow:
lg %r15,__LC_PANIC_STACK # change to panic stack
la %r11,STACK_FRAME_OVERHEAD(%r15)
stmg %r0,%r7,__PT_R0(%r11)
stmg %r8,%r9,__PT_PSW(%r11)
mvc __PT_R8(64,%r11),0(%r14)
stg %r10,__PT_ORIG_GPR2(%r11) # store last break to orig_gpr2
xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
lgr %r2,%r11 # pass pointer to pt_regs
jg kernel_stack_overflow
#endif
cleanup_critical:
#if IS_ENABLED(CONFIG_KVM)
clg %r9,BASED(.Lcleanup_table_sie) # .Lsie_gmap
jl 0f
clg %r9,BASED(.Lcleanup_table_sie+8)# .Lsie_done
jl .Lcleanup_sie
#endif
clg %r9,BASED(.Lcleanup_table) # system_call
jl 0f
clg %r9,BASED(.Lcleanup_table+8) # .Lsysc_do_svc
jl .Lcleanup_system_call
clg %r9,BASED(.Lcleanup_table+16) # .Lsysc_tif
jl 0f
clg %r9,BASED(.Lcleanup_table+24) # .Lsysc_restore
jl .Lcleanup_sysc_tif
clg %r9,BASED(.Lcleanup_table+32) # .Lsysc_done
jl .Lcleanup_sysc_restore
clg %r9,BASED(.Lcleanup_table+40) # .Lio_tif
jl 0f
clg %r9,BASED(.Lcleanup_table+48) # .Lio_restore
jl .Lcleanup_io_tif
clg %r9,BASED(.Lcleanup_table+56) # .Lio_done
jl .Lcleanup_io_restore
clg %r9,BASED(.Lcleanup_table+64) # psw_idle
jl 0f
clg %r9,BASED(.Lcleanup_table+72) # .Lpsw_idle_end
jl .Lcleanup_idle
clg %r9,BASED(.Lcleanup_table+80) # save_fpu_regs
jl 0f
clg %r9,BASED(.Lcleanup_table+88) # .Lsave_fpu_regs_end
jl .Lcleanup_save_fpu_regs
clg %r9,BASED(.Lcleanup_table+96) # load_fpu_regs
jl 0f
clg %r9,BASED(.Lcleanup_table+104) # .Lload_fpu_regs_end
jl .Lcleanup_load_fpu_regs
0: br %r14
.align 8
.Lcleanup_table:
.quad system_call
.quad .Lsysc_do_svc
.quad .Lsysc_tif
.quad .Lsysc_restore
.quad .Lsysc_done
.quad .Lio_tif
.quad .Lio_restore
.quad .Lio_done
.quad psw_idle
.quad .Lpsw_idle_end
.quad save_fpu_regs
.quad .Lsave_fpu_regs_end
.quad load_fpu_regs
.quad .Lload_fpu_regs_end
#if IS_ENABLED(CONFIG_KVM)
.Lcleanup_table_sie:
.quad .Lsie_gmap
.quad .Lsie_done
.Lcleanup_sie:
cghi %r11,__LC_SAVE_AREA_ASYNC #Is this in normal interrupt?
je 1f
slg %r9,BASED(.Lsie_crit_mcck_start)
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
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
#endif
.Lcleanup_system_call:
# check if stpt has been executed
clg %r9,BASED(.Lcleanup_system_call_insn)
jh 0f
mvc __LC_SYNC_ENTER_TIMER(8),__LC_ASYNC_ENTER_TIMER
cghi %r11,__LC_SAVE_AREA_ASYNC
je 0f
mvc __LC_SYNC_ENTER_TIMER(8),__LC_MCCK_ENTER_TIMER
0: # check if stmg has been executed
clg %r9,BASED(.Lcleanup_system_call_insn+8)
jh 0f
mvc __LC_SAVE_AREA_SYNC(64),0(%r11)
0: # check if base register setup + TIF bit load has been done
clg %r9,BASED(.Lcleanup_system_call_insn+16)
jhe 0f
# set up saved register r12 task struct pointer
stg %r12,32(%r11)
# set up saved register r13 __TASK_thread offset
mvc 40(8,%r11),BASED(.Lcleanup_system_call_const)
0: # check if the user time update has been done
clg %r9,BASED(.Lcleanup_system_call_insn+24)
jh 0f
lg %r15,__LC_EXIT_TIMER
slg %r15,__LC_SYNC_ENTER_TIMER
alg %r15,__LC_USER_TIMER
stg %r15,__LC_USER_TIMER
0: # check if the system time update has been done
clg %r9,BASED(.Lcleanup_system_call_insn+32)
jh 0f
lg %r15,__LC_LAST_UPDATE_TIMER
slg %r15,__LC_EXIT_TIMER
alg %r15,__LC_SYSTEM_TIMER
stg %r15,__LC_SYSTEM_TIMER
0: # update accounting time stamp
mvc __LC_LAST_UPDATE_TIMER(8),__LC_SYNC_ENTER_TIMER
# set up saved register r11
lg %r15,__LC_KERNEL_STACK
la %r9,STACK_FRAME_OVERHEAD(%r15)
stg %r9,24(%r11) # r11 pt_regs pointer
# fill pt_regs
mvc __PT_R8(64,%r9),__LC_SAVE_AREA_SYNC
stmg %r0,%r7,__PT_R0(%r9)
mvc __PT_PSW(16,%r9),__LC_SVC_OLD_PSW
mvc __PT_INT_CODE(4,%r9),__LC_SVC_ILC
xc __PT_FLAGS(8,%r9),__PT_FLAGS(%r9)
mvi __PT_FLAGS+7(%r9),_PIF_SYSCALL
# setup saved register r15
stg %r15,56(%r11) # r15 stack pointer
# set new psw address and exit
larl %r9,.Lsysc_do_svc
br %r14
.Lcleanup_system_call_insn:
.quad system_call
.quad .Lsysc_stmg
.quad .Lsysc_per
.quad .Lsysc_vtime+36
.quad .Lsysc_vtime+42
.Lcleanup_system_call_const:
.quad __TASK_thread
.Lcleanup_sysc_tif:
larl %r9,.Lsysc_tif
br %r14
.Lcleanup_sysc_restore:
# check if stpt has been executed
clg %r9,BASED(.Lcleanup_sysc_restore_insn)
jh 0f
mvc __LC_EXIT_TIMER(8),__LC_ASYNC_ENTER_TIMER
cghi %r11,__LC_SAVE_AREA_ASYNC
je 0f
mvc __LC_EXIT_TIMER(8),__LC_MCCK_ENTER_TIMER
0: clg %r9,BASED(.Lcleanup_sysc_restore_insn+8)
je 1f
lg %r9,24(%r11) # get saved pointer to pt_regs
mvc __LC_RETURN_PSW(16),__PT_PSW(%r9)
mvc 0(64,%r11),__PT_R8(%r9)
lmg %r0,%r7,__PT_R0(%r9)
1: lmg %r8,%r9,__LC_RETURN_PSW
br %r14
.Lcleanup_sysc_restore_insn:
.quad .Lsysc_exit_timer
.quad .Lsysc_done - 4
.Lcleanup_io_tif:
larl %r9,.Lio_tif
br %r14
.Lcleanup_io_restore:
# check if stpt has been executed
clg %r9,BASED(.Lcleanup_io_restore_insn)
jh 0f
mvc __LC_EXIT_TIMER(8),__LC_MCCK_ENTER_TIMER
0: clg %r9,BASED(.Lcleanup_io_restore_insn+8)
je 1f
lg %r9,24(%r11) # get saved r11 pointer to pt_regs
mvc __LC_RETURN_PSW(16),__PT_PSW(%r9)
mvc 0(64,%r11),__PT_R8(%r9)
lmg %r0,%r7,__PT_R0(%r9)
1: lmg %r8,%r9,__LC_RETURN_PSW
br %r14
.Lcleanup_io_restore_insn:
.quad .Lio_exit_timer
.quad .Lio_done - 4
.Lcleanup_idle:
ni __LC_CPU_FLAGS+7,255-_CIF_ENABLED_WAIT
# copy interrupt clock & cpu timer
mvc __CLOCK_IDLE_EXIT(8,%r2),__LC_INT_CLOCK
mvc __TIMER_IDLE_EXIT(8,%r2),__LC_ASYNC_ENTER_TIMER
cghi %r11,__LC_SAVE_AREA_ASYNC
je 0f
mvc __CLOCK_IDLE_EXIT(8,%r2),__LC_MCCK_CLOCK
mvc __TIMER_IDLE_EXIT(8,%r2),__LC_MCCK_ENTER_TIMER
0: # check if stck & stpt have been executed
clg %r9,BASED(.Lcleanup_idle_insn)
jhe 1f
mvc __CLOCK_IDLE_ENTER(8,%r2),__CLOCK_IDLE_EXIT(%r2)
mvc __TIMER_IDLE_ENTER(8,%r2),__TIMER_IDLE_EXIT(%r2)
1: # calculate idle cycles
#ifdef CONFIG_SMP
clg %r9,BASED(.Lcleanup_idle_insn)
jl 3f
larl %r1,smp_cpu_mtid
llgf %r1,0(%r1)
ltgr %r1,%r1
jz 3f
.insn rsy,0xeb0000000017,%r1,5,__SF_EMPTY+80(%r15)
larl %r3,mt_cycles
ag %r3,__LC_PERCPU_OFFSET
la %r4,__SF_EMPTY+16(%r15)
2: lg %r0,0(%r3)
slg %r0,0(%r4)
alg %r0,64(%r4)
stg %r0,0(%r3)
la %r3,8(%r3)
la %r4,8(%r4)
brct %r1,2b
#endif
3: # account system time going idle
lg %r9,__LC_STEAL_TIMER
alg %r9,__CLOCK_IDLE_ENTER(%r2)
slg %r9,__LC_LAST_UPDATE_CLOCK
stg %r9,__LC_STEAL_TIMER
mvc __LC_LAST_UPDATE_CLOCK(8),__CLOCK_IDLE_EXIT(%r2)
lg %r9,__LC_SYSTEM_TIMER
alg %r9,__LC_LAST_UPDATE_TIMER
slg %r9,__TIMER_IDLE_ENTER(%r2)
stg %r9,__LC_SYSTEM_TIMER
mvc __LC_LAST_UPDATE_TIMER(8),__TIMER_IDLE_EXIT(%r2)
# prepare return psw
nihh %r8,0xfcfd # clear irq & wait state bits
lg %r9,48(%r11) # return from psw_idle
br %r14
.Lcleanup_idle_insn:
.quad .Lpsw_idle_lpsw
.Lcleanup_save_fpu_regs:
larl %r9,save_fpu_regs
br %r14
.Lcleanup_load_fpu_regs:
larl %r9,load_fpu_regs
br %r14
/*
* Integer constants
*/
.align 8
.Lcritical_start:
.quad .L__critical_start
.Lcritical_length:
.quad .L__critical_end - .L__critical_start
#if IS_ENABLED(CONFIG_KVM)
.Lsie_critical_start:
.quad .Lsie_gmap
.Lsie_critical_length:
.quad .Lsie_done - .Lsie_gmap
.Lsie_crit_mcck_start:
.quad .Lsie_entry
.Lsie_crit_mcck_length:
.quad .Lsie_skip - .Lsie_entry
#endif
.section .rodata, "a"
#define SYSCALL(esame,emu) .long esame
.globl sys_call_table
sys_call_table:
#include "syscalls.S"
#undef SYSCALL
#ifdef CONFIG_COMPAT
#define SYSCALL(esame,emu) .long emu
.globl sys_call_table_emu
sys_call_table_emu:
#include "syscalls.S"
#undef SYSCALL
#endif
Reference in New Issue View Git Blame Copy Permalink