linux-stable.git/arch/s390/kernel/entry.S, branch linux-4.4.y

s390/entry: save the caller of psw_idle

2021-04-28T10:05:47+00:00

[ Upstream commit a994eddb947ea9ebb7b14d9a1267001699f0a136 ]

Currently psw_idle does not allocate a stack frame and does not
save its r14 and r15 into the save area. Even though this is valid from
call ABI point of view, because psw_idle does not make any calls
explicitly, in reality psw_idle is an entry point for controlled
transition into serving interrupts. So, in practice, psw_idle stack
frame is analyzed during stack unwinding. Depending on build options
that r14 slot in the save area of psw_idle might either contain a value
saved by previous sibling call or complete garbage.

  [task    0000038000003c28] do_ext_irq+0xd6/0x160
  [task    0000038000003c78] ext_int_handler+0xba/0xe8
  [task   *0000038000003dd8] psw_idle_exit+0x0/0x8 <-- pt_regs
 ([task    0000038000003dd8] 0x0)
  [task    0000038000003e10] default_idle_call+0x42/0x148
  [task    0000038000003e30] do_idle+0xce/0x160
  [task    0000038000003e70] cpu_startup_entry+0x36/0x40
  [task    0000038000003ea0] arch_call_rest_init+0x76/0x80

So, to make a stacktrace nicer and actually point for the real caller of
psw_idle in this frequently occurring case, make psw_idle save its r14.

  [task    0000038000003c28] do_ext_irq+0xd6/0x160
  [task    0000038000003c78] ext_int_handler+0xba/0xe8
  [task   *0000038000003dd8] psw_idle_exit+0x0/0x6 <-- pt_regs
 ([task    0000038000003dd8] arch_cpu_idle+0x3c/0xd0)
  [task    0000038000003e10] default_idle_call+0x42/0x148
  [task    0000038000003e30] do_idle+0xce/0x160
  [task    0000038000003e70] cpu_startup_entry+0x36/0x40
  [task    0000038000003ea0] arch_call_rest_init+0x76/0x80

Reviewed-by: Sven Schnelle 
Signed-off-by: Vasily Gorbik 
Signed-off-by: Heiko Carstens 
Signed-off-by: Sasha Levin

s390: Correct register corruption in critical section cleanup

2018-07-11T14:03:48+00:00

commit 891f6a726cacbb87e5b06076693ffab53bd378d7 upstream.

In the critical section cleanup we must not mess with r1.  For march=z9
or older, larl + ex (instead of exrl) are used with r1 as a temporary
register. This can clobber r1 in several interrupt handlers. Fix this by
using r11 as a temp register.  r11 is being saved by all callers of
cleanup_critical.

Fixes: 6dd85fbb87 ("s390: move expoline assembler macros to a header")
Cc: stable@vger.kernel.org #v4.16
Reported-by: Oliver Kurz 
Reported-by: Petr Tesařík 
Signed-off-by: Christian Borntraeger 
Reviewed-by: Hendrik Brueckner 
Signed-off-by: Martin Schwidefsky 
Signed-off-by: Greg Kroah-Hartman

s390: move expoline assembler macros to a header

2018-05-26T06:48:58+00:00

[ Upstream commit 6dd85fbb87d1d6b87a3b1f02ca28d7b2abd2e7ba ]

To be able to use the expoline branches in different assembler
files move the associated macros from entry.S to a new header
nospec-insn.h.

While we are at it make the macros a bit nicer to use.

Cc: stable@vger.kernel.org # 4.16
Fixes: f19fbd5ed6 ("s390: introduce execute-trampolines for branches")
Signed-off-by: Martin Schwidefsky 
Signed-off-by: Greg Kroah-Hartman

s390/entry.S: fix spurious zeroing of r0

2018-04-29T05:50:03+00:00

[ Upstream commit d3f468963cd6fd6d2aa5e26aed8b24232096d0e1 ]

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 

Signed-off-by: Martin Schwidefsky 

Signed-off-by: Martin Schwidefsky 

Signed-off-by: Martin Schwidefsky 

Signed-off-by: Martin Schwidefsky 

Signed-off-by: Martin Schwidefsky 
Signed-off-by: Greg Kroah-Hartman

s390: do not bypass BPENTER for interrupt system calls

2018-04-29T05:50:03+00:00

[ Upstream commit d5feec04fe578c8dbd9e2e1439afc2f0af761ed4 ]

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 
Signed-off-by: Greg Kroah-Hartman

s390: introduce execute-trampolines for branches

2018-04-29T05:50:03+00:00

[ Upstream commit f19fbd5ed642dc31c809596412dab1ed56f2f156 ]

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 
Signed-off-by: Greg Kroah-Hartman

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

2018-04-29T05:50:03+00:00

[ Upstream commit 6b73044b2b0081ee3dd1cd6eaab7dee552601efb ]

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 
Signed-off-by: Greg Kroah-Hartman

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

2018-04-29T05:50:03+00:00

[ Upstream commit d768bd892fc8f066cd3aa000eb1867bcf32db0ee ]

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 
Signed-off-by: Greg Kroah-Hartman

s390: scrub registers on kernel entry and KVM exit

2018-04-29T05:50:02+00:00

[ Upstream commit 7041d28115e91f2144f811ffe8a195c696b1e1d0 ]

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 
Signed-off-by: Greg Kroah-Hartman

s390/kvm: do not rely on the ILC on kvm host protection fauls

2017-06-17T04:39:38+00:00

commit c0e7bb38c07cbd8269549ee0a0566021a3c729de upstream.

For most cases a protection exception in the host (e.g. copy
on write or dirty tracking) on the sie instruction will indicate
an instruction length of 4. Turns out that there are some corner
cases (e.g. runtime instrumentation) where this is not necessarily
true and the ILC is unpredictable.

Let's replace our 4 byte rewind_pad with 3 byte nops to prepare for
all possible ILCs.

Signed-off-by: Christian Borntraeger 
Signed-off-by: Martin Schwidefsky 
Signed-off-by: Greg Kroah-Hartman