linux.git/arch/s390/kernel/entry.S, branch v4.16

s390/entry.S: fix spurious zeroing of r0

2018-03-06T08:19:35+00:00

when a system call is interrupted we might call the critical section
cleanup handler that re-does some of the operations. When we are between
.Lsysc_vtime and .Lsysc_do_svc we might also redo the saving of the
problem state registers r0-r7:

.Lcleanup_system_call:
[...]
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)

The problem is now, that we might have already zeroed out r0.
The fix is to move the zeroing of r0 after sysc_do_svc.

Reported-by: Farhan Ali 
Fixes: 7041d28115e91 ("s390: scrub registers on kernel entry and KVM exit")
Signed-off-by: Christian Borntraeger 
Signed-off-by: Martin Schwidefsky

s390: do not bypass BPENTER for interrupt system calls

2018-02-22T13:08:51+00:00

The system call path can be interrupted before the switch back to the
standard branch prediction with BPENTER has been done. The critical
section cleanup code skips forward to .Lsysc_do_svc and bypasses the
BPENTER. In this case the kernel and all subsequent code will run with
the limited branch prediction.

Fixes: eacf67eb9b32 ("s390: run user space and KVM guests with modified branch prediction")
Signed-off-by: Martin Schwidefsky

s390/clean-up: use CFI_* macros in entry.S

2018-02-22T09:09:20+00:00

Commit f19fbd5ed642 ("s390: introduce execute-trampolines for
branches") introduces .cfi_* assembler directives.  Instead of
using the directives directly, use the macros from asm/dwarf.h.
This also ensures that the dwarf debug information are created
in the .debug_frame section.

Fixes: f19fbd5ed642 ("s390: introduce execute-trampolines for branches")
Signed-off-by: Hendrik Brueckner 
Signed-off-by: Martin Schwidefsky

s390: introduce execute-trampolines for branches

2018-02-07T14:57:02+00:00

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

s390: run user space and KVM guests with modified branch prediction

2018-02-05T13:48:50+00:00

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

s390: add options to change branch prediction behaviour for the kernel

2018-02-05T12:49:17+00:00

Add the PPA instruction to the system entry and exit path to switch
the kernel to a different branch prediction behaviour. The instructions
are added via CPU alternatives and can be disabled with the "nospec"
or the "nobp=0" kernel parameter. If the default behaviour selected
with CONFIG_KERNEL_NOBP is set to "n" then the "nobp=1" parameter can be
used to enable the changed kernel branch prediction.

Acked-by: Cornelia Huck 
Signed-off-by: Martin Schwidefsky

s390: scrub registers on kernel entry and KVM exit

2018-02-05T06:34:54+00:00

Clear all user space registers on entry to the kernel and all KVM guest
registers on KVM guest exit if the register does not contain either a
parameter or a result value.

Reviewed-by: Christian Borntraeger 
Signed-off-by: Martin Schwidefsky

s390/syscalls: use generated syscall_table.h and unistd.h header files

2018-01-23T06:36:52+00:00

Update the uapi/asm/unistd.h to include the generated compat and
64-bit version of the unistd.h and, as well as, the unistd_nr.h
header file.  Also remove the arch/s390/kernel/syscalls.S file
and use the generated system call table, syscall_table.h, instead.

Signed-off-by: Hendrik Brueckner 
Acked-by: Heiko Carstens 
Signed-off-by: Martin Schwidefsky

s390: rework __switch_to() to allow larger task_struct offsets

2017-11-20T07:51:01+00:00

If GCC_PLUGIN_RANDSTRUCT is enabled the members of task_struct will be
shuffled around. The offsets of the "pid" and "stack" members within
task_struct may not necessarily fit into 12 bits anymore, which causes
compile errors within __switch_to, since instructions are used, which
only have a 12 bit displacement field.

Therefore rework __switch_to, to allow for larger offsets.

Signed-off-by: Heiko Carstens 
Signed-off-by: Martin Schwidefsky

s390: remove all code using the access register mode

2017-11-14T10:01:47+00:00

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 
Signed-off-by: Martin Schwidefsky 
Signed-off-by: Heiko Carstens