The current uaccess code uses a page table walk in some circumstances,
e.g. in case of the in atomic futex operations or if running on old
hardware which doesn't support the mvcos instruction.

However it turned out that the page table walk code does not correctly
lock page tables when accessing page table entries.
In other words: a different cpu may invalidate a page table entry while
the current cpu inspects the pte. This may lead to random data corruption.

Adding correct locking however isn't trivial for all uaccess operations.
Especially copy_in_user() is problematic since that requires to hold at
least two locks, but must be protected against ABBA deadlock when a
different cpu also performs a copy_in_user() operation.

So the solution is a different approach where we change address spaces:

User space runs in primary address mode, or access register mode within
vdso code, like it currently already does.

The kernel usually also runs in home space mode, however when accessing
user space the kernel switches to primary or secondary address mode if
the mvcos instruction is not available or if a compare-and-swap (futex)
instruction on a user space address is performed.
KVM however is special, since that requires the kernel to run in home
address space while implicitly accessing user space with the sie
instruction.

So we end up with:

User space:
- runs in primary or access register mode
- cr1 contains the user asce
- cr7 contains the user asce
- cr13 contains the kernel asce

Kernel space:
- runs in home space mode
- cr1 contains the user or kernel asce
  -> the kernel asce is loaded when a uaccess requires primary or
     secondary address mode
- cr7 contains the user or kernel asce, (changed with set_fs())
- cr13 contains the kernel asce

In case of uaccess the kernel changes to:
- primary space mode in case of a uaccess (copy_to_user) and uses
  e.g. the mvcp instruction to access user space. However the kernel
  will stay in home space mode if the mvcos instruction is available
- secondary space mode in case of futex atomic operations, so that the
  instructions come from primary address space and data from secondary
  space

In case of kvm the kernel runs in home space mode, but cr1 gets switched
to contain the gmap asce before the sie instruction gets executed. When
the sie instruction is finished cr1 will be switched back to contain the
user asce.

A context switch between two processes will always load the kernel asce
for the next process in cr1. So the first exit to user space is a bit
more expensive (one extra load control register instruction) than before,
however keeps the code rather simple.

In sum this means there is no need to perform any error prone page table
walks anymore when accessing user space.

The patch seems to be rather large, however it mainly removes the
the page table walk code and restores the previously deleted "standard"
uaccess code, with a couple of changes.

The uaccess without mvcos mode can be enforced with the "uaccess_primary"
kernel parameter.
Reported-by: NChristian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: NHeiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

The code to use the ECTG instruction to calculate the cputime for the
current thread is currently used only for the per-thread CPU-clock
with the clockid -2 (PID=0, VIRT=1). Use the same code for the clockid
CLOCK_THREAD_CPUTIME_ID to speed up the more common clockid as well.
Reported-by: NHeiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

Switch to the improved update_vsyscall interface that provides
sub-nanosecond precision for gettimeofday and clock_gettime.
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

Copy the interrupt parameters from the lowcore to the pt_regs structure
in entry[64].S and reduce the arguments of the low level interrupt handler
to the pt_regs pointer only. In addition move the test-pending-interrupt
loop from do_IRQ to entry[64].S to make sure that interrupt information
is always delivered via pt_regs.
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

Lets provide functions to prevent KVM from reentering SIE and
to kick cpus out of SIE. We cannot use the common kvm_vcpu_kick code,
since we need to kick out guests in places that hold architecture
specific locks (e.g. pgste lock) which might be necessary on the
other cpus - so no waiting possible.

So lets provide a bit in a private field of the sie control block
that acts as a gate keeper, after we claimed we are in SIE.
Please note that we do not reuse prog0c, since we want to access
that bit without atomic ops.
Signed-off-by: NChristian Borntraeger <borntraeger@de.ibm.com>
Acked-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: NGleb Natapov <gleb@redhat.com>

Lets track in a private bit if the sie control block is active.
We want to track this as closely as possible, so we also have to
instrument the interrupt and program check handler. Lets use the
existing HANDLE_SIE_INTERCEPT macro.
Signed-off-by: NChristian Borntraeger <borntraeger@de.ibm.com>
Acked-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: NGleb Natapov <gleb@redhat.com>

Add a pointer to the system call table to the thread_info structure.
The TIF_31BIT bit is set or cleared by SET_PERSONALITY exactly once
for the lifetime of a process. With the pointer to the correct system
call table in thread_info the system call code in entry64.S path can
drop the check for TIF_31BIT which saves a couple of instructions.
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

Allow user-space processes to use transactional execution (TX).
If the TX facility is available user space programs can use
transactions for fine-grained serialization based on the data
objects that are referenced during a transaction. This is
useful for lockless data structures and speculative compiler
optimizations.
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

The current virtual timer interface is inherently per-cpu and hard to
use. The sole user of the interface is appldata which uses it to execute
a function after a specific amount of cputime has been used over all cpus.

Rework the virtual timer interface to hook into the cputime accounting.
This makes the interface independent from the CPU timer interrupts, and
makes the virtual timers global as opposed to per-cpu.
Overall the code is greatly simplified. The downside is that the accuracy
is not as good as the original implementation, but it is still good enough
for appldata.
Reviewed-by: NJan Glauber <jang@linux.vnet.ibm.com>
Reviewed-by: NHeiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

Setting the cpu restart parameters is done in three different fashions:
- directly setting the four parameters individually
- copying the four parameters with memcpy (using 4 * sizeof(long))
- copying the four parameters using a private structure

In addition code in entry*.S relies on a certain order of the restart
members of struct _lowcore.

Make all of this more robust to future changes by adding a
mem_absolute_assign(dest, val) define, which assigns val to dest
using absolute addressing mode. Also the load multiple instructions
in entry*.S have been split into separate load instruction so the
order of the struct _lowcore members doesn't matter anymore.

In addition move the prototypes of memcpy_real/absolute from uaccess.h
to processor.h. These memcpy* variants are not related to uaccess at all.
string.h doesn't seem to match as well, so lets use processor.h.

Also replace the eight byte array in struct _lowcore which represents a
misaliged u64 with a u64. The compiler will always create code that
handles the misaligned u64 correctly.
Signed-off-by: NHeiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

Disintegrate asm/system.h for S390.
Signed-off-by: NDavid Howells <dhowells@redhat.com>
cc: linux-s390@vger.kernel.org

Whenever the cpu loads an enabled wait PSW it will appear as idle to the
underlying host system. The code in default_idle calls vtime_stop_cpu
which does the necessary voodoo to get the cpu time accounting right.
The udelay code just loads an enabled wait PSW. To correct this rework
the vtime_stop_cpu/vtime_start_cpu logic and move the difficult parts
to entry[64].S, vtime_stop_cpu can now be called from anywhere and
vtime_start_cpu is gone. The correction of the cpu time during wakeup
from an enabled wait PSW is done with a critical section in entry[64].S.
As vtime_start_cpu is gone, s390_idle_check can be removed as well.
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

Define struct pcpu and merge some of the NR_CPUS arrays into it, including
__cpu_logical_map, current_set and smp_cpu_state. Split smp related
functions to those operating on physical cpus and the functions operating
on a logical cpu number. Make the functions for physical cpus use a
pointer to a struct pcpu. This hides the knowledge about cpu addresses in
smp.c, entry[64].S and swsusp_asm64.S, thus remove the sigp.h header.

The PSW restart mechanism is used to start secondary cpus, calling a
function on an online cpu, calling a function on the ipl cpu, and for
the nmi signal. Replace the different assembler functions with a
single function restart_int_handler. The new entry point calls a function
whose pointer is stored in the lowcore of the target cpu and it can wait
for the source cpu to stop. This covers all existing use cases.

Overall the code is now simpler and there are ~380 lines less code.
Reviewed-by: NHeiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

The 16 bit value at the lowcore location with offset 0x84 is the
cpu address that is associated with an external interrupt. Rename
the field from cpu_addr to ext_cpu_addr to make that clear.
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

Move the program interruption code and the translation exception identifier
to the pt_regs structure as 'int_code' and 'int_parm_long' and make the
first level interrupt handler in entry[64].S store the two values. That
makes it possible to drop 'prot_addr' and 'trap_no' from the thread_struct
and to reduce the number of arguments to a lot of functions. Finally
un-inline do_trap. Overall this saves 5812 bytes in the .text section of
the 64 bit kernel.
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

Another round of cleanup for entry[64].S, in particular the program check
handler looks more reasonable now. The code size for the 31 bit kernel
has been reduced by 616 byte and by 528 byte for the 64 bit version.
Even better the code is a bit faster as well.
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

There is no reason for the cpu-measurement-facility host id constant to
reside in the lowcore where space is precious. Use an entry in the literal
pool in HANDLE_SIE_INTERCEPT and a stack slot in sie64a.
While we are at it replace the id -1 with 0 to indicate host execution.
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

For a ERESTARTNOHAND/ERESTARTSYS/ERESTARTNOINTR restarting system call
do_signal will prepare the restart of the system call with a rewind of
the PSW before calling get_signal_to_deliver (where the debugger might
take control). For A ERESTART_RESTARTBLOCK restarting system call
do_signal will set -EINTR as return code.
There are two issues with this approach:
1) strace never sees ERESTARTNOHAND, ERESTARTSYS, ERESTARTNOINTR or
   ERESTART_RESTARTBLOCK as the rewinding already took place or the
   return code has been changed to -EINTR
2) if get_signal_to_deliver does not return with a signal to deliver
   the restart via the repeat of the svc instruction is left in place.
   This opens a race if another signal is made pending before the
   system call instruction can be reexecuted. The original system call
   will be restarted even if the second signal would have ended the
   system call with -EINTR.

These two issues can be solved by dropping the early rewind of the
system call before get_signal_to_deliver has been called and by using
the TIF_RESTART_SVC magic to do the restart if no signal has to be
delivered. The only situation where the system call restart via the
repeat of the svc instruction is appropriate is when a SA_RESTART
signal is delivered to user space.

Unfortunately this breaks inferior calls by the debugger again. The
system call number and the length of the system call instruction is
lost over the inferior call and user space will see ERESTARTNOHAND/
ERESTARTSYS/ERESTARTNOINTR/ERESTART_RESTARTBLOCK. To correct this a
new ptrace interface is added to save/restore the system call number
and system call instruction length.
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

Remove the save_area_64 field from the 0xe00 - 0xf00 area in the lowcore.
Use a free slot in the save_area array instead.
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

598841ca ([S390] use gmap address
spaces for kvm guest images) changed kvm to use a separate address
space for kvm guests. This address space was switched in __vcpu_run
In some cases (preemption, page fault) there is the possibility that
this address space switch is lost.
The typical symptom was a huge amount of validity intercepts or
random guest addressing exceptions.
Fix this by doing the switch in sie_loop and sie_exit and saving the
address space in the gmap structure itself. Also use the preempt
notifier.
Signed-off-by: NChristian Borntraeger <borntraeger@de.ibm.com>
Acked-by: NAvi Kivity <avi@redhat.com>
Signed-off-by: NHeiko Carstens <heiko.carstens@de.ibm.com>

Because of readability reasons we ignore the 80 character line limit
in asm offsets. Just one line per define, nothing else.
Signed-off-by: NHeiko Carstens <heiko.carstens@de.ibm.com>

With this patch a new S390 shutdown trigger "restart" is added. If under
z/VM "systerm restart" is entered or under the HMC the "PSW restart" button
is pressed, the PSW located at 0 (31 bit) or 0x1a0 (64 bit) bit is loaded.
Now we execute do_restart() that processes the restart action that is
defined under /sys/firmware/shutdown_actions/on_restart. Currently the
following actions are possible: reipl (default), stop, vmcmd, dump, and
dump_reipl.
Signed-off-by: NMichael Holzheu <holzheu@linux.vnet.ibm.com>
Signed-off-by: NHeiko Carstens <heiko.carstens@de.ibm.com>

Add code that allows KVM to control the virtual memory layout that
is seen by a guest. The guest address space uses a second page table
that shares the last level pte-tables with the process page table.
If a page is unmapped from the process page table it is automatically
unmapped from the guest page table as well.

The guest address space mapping starts out empty, KVM can map any
individual 1MB segments from the process virtual memory to any 1MB
aligned location in the guest virtual memory. If a target segment in
the process virtual memory does not exist or is unmapped while a
guest mapping exists the desired target address is stored as an
invalid segment table entry in the guest page table.
The population of the guest page table is fault driven.
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

On cpu hot remove a PFAULT CANCEL command is sent to the hypervisor
which in turn will cancel all outstanding pfault requests that have
been issued on that cpu (the same happens with a SIGP cpu reset).

The result is that we end up with uninterruptible processes where
the interrupt that would wake up these processes never arrives.

In order to solve this all processes which wait for a pfault
completion interrupt get woken up after a cpu hot remove. The worst
case that could happen is that they fault again and in turn need to
wait again.
Signed-off-by: NHeiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

The noexec support on s390 does not rely on a bit in the page table
entry but utilizes the secondary space mode to distinguish between
memory accesses for instructions vs. data. The noexec code relies
on the assumption that the cpu will always use the secondary space
page table for data accesses while it is running in the secondary
space mode. Up to the z9-109 class machines this has been the case.
Unfortunately this is not true anymore with z10 and later machines.
The load-relative-long instructions lrl, lgrl and lgfrl access the
memory operand using the same addressing-space mode that has been
used to fetch the instruction.
This breaks the noexec mode for all user space binaries compiled
with march=z10 or later. The only option is to remove the current
noexec support.
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

Overhaul program event recording and the code dealing with the ptrace
user space interface.
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

The CLOCK_* defines in asm-offsets.c are only used for the vdso code
however in the meantime they cause other trouble.
Just rename them to get permanently rid of this:

In file included from /home2/heicarst/linux-2.6/arch/s390/include/asm/asm-offsets.h:1:0,
                 from arch/s390/mm/fault.c:33:
include/generated/asm-offsets.h:53:0: warning: "CLOCK_REALTIME" redefined
include/linux/time.h:286:0: note: this is the location of the previous definition
include/generated/asm-offsets.h:54:0: warning: "CLOCK_MONOTONIC" redefined
include/linux/time.h:287:0: note: this is the location of the previous definition
Signed-off-by: NHeiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

Read external interrupts parameters from the lowcore in the first
level interrupt handler in entry[64].S.
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

Read all required fields for program checks from the lowcore in the
first level interrupt handler in entry[64].S. If the context that
caused the fault was enabled for interrupts we can now re-enable the
irqs in entry[64].S.
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

Fix build breakage for CONFIG_32BIT caused by cd3b70f5
"[S390] virtualization aware cpu measurement"
Signed-off-by: NHeiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

Copy the last breaking event address from the lowcore to a new
field in the thread_struct on each system entry. Add a new
ptrace request PTRACE_GET_LAST_BREAK and a new utrace regset
REGSET_LAST_BREAK to query the last breaking event.

This is useful for debugging wild branches in user space code.
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

Use the SPP instruction to set a tag on entry to / exit of the virtual
machine context. This allows the cpu measurement facility to distinguish
the samples from the host and the different guests.
Signed-off-by: NCarsten Otte <cotte@de.ibm.com>

A machine check can interrupt the i/o and external interrupt handler
anytime. If the machine check occurs while the interrupt handler is
waking up from idle vtime_start_cpu can get executed a second time
and the int_clock / async_enter_timer values in the lowcore get
clobbered. This can confuse the cpu time accounting.
To fix this problem two changes are needed. First the machine check
handler has to use its own copies of int_clock and async_enter_timer,
named mcck_clock and mcck_enter_timer. Second the nested execution
of vtime_start_cpu has to be prevented. This is done in s390_idle_check
by checking the wait bit in the program status word.
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

Remove cpu_id from lowcore and replace addr_t with __u64.
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

Commit "timekeeping: Fix clock_gettime vsyscall time warp" (0696b711)
introduced the new parameter "mult" to update_vsyscall(). This parameter
contains the internal NTP adjusted clock multiplier.

The s390x vdso did not use this adjusted multiplier.  Instead, it used
the constant clock multiplier for gettimeofday() and clock_gettime()
variants.  This may result in observable time warps as explained in
commit 0696b711.

Make the NTP adjusted clock multiplier available to the s390x vdso
implementation and use it for time calculations.

Cc: <stable@kernel.org>
Signed-off-by: NHendrik Brueckner <brueckner@linux.vnet.ibm.com>
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

Use asm offsets to make sure the offset defines to struct _lowcore and
its layout don't get out of sync.
Also add a BUILD_BUG_ON() which checks that the size of the structure
is sane.
And while being at it change those sites which use odd casts to access
the current lowcore. These should use S390_lowcore instead.
Signed-off-by: NHeiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

Drop support to compile the kernel with gcc versions older than 3.3.3.
This allows us to use the "Q" inline assembly contraint on some more
inline assemblies without duplicating a lot of complex code (e.g. __xchg
and __cmpxchg). The distinction for older gcc versions can be removed
which saves a few lines and simplifies the code.
Reviewed-by: NHeiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

Currently, when the physical resume CPU is not equal to the physical suspend
CPU, we swap the CPUs logically, by modifying the logical/physical CPU mapping.
This has two major drawbacks: First the change is visible from user space (e.g.
CPU sysfs files) and second it is hard to ensure that nowhere in the kernel
the physical CPU ID is stored before suspend.
To fix this, we now really swap the physical CPUs, if the resume CPU is not
the pysical suspend CPU. We restart the suspend CPU and stop the resume CPU
using SIGP restart and SIGP stop. If the suspend CPU is no longer available,
we write a message and load a disabled wait PSW.
Signed-off-by: NMichael Holzheu <michael.holzheu@linux.vnet.ibm.com>
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

Reset the cpu timer to the maximum value and correctly initialize the
cpu accounting values in the lowcore when the cpu is started.
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

The extract cpu time instruction (ectg) instruction allows the user
process to get the current thread cputime without calling into the
kernel. The code that uses the instruction needs to switch to the
access registers mode to get access to the per-cpu info page that
contains the two base values that are needed to calculate the current
cputime from the CPU timer with the ectg instruction.
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>