The kernel page table splitting code will split page tables even for
features the CPU does not support. E.g. a CPU may not support the NX
feature.
In order to avoid this, remove those bits from the flags parameter
that correlate with unsupported CPU features within __set_memory(). In
addition add an early exit if the flags parameter does not have any
bits set afterwards.
Signed-off-by: NHeiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

With TASK_SIZE now reflecting the maximum size of the address space for
a process the code for arch_get_unmapped_area[_topdown] can be simplified.
Just let the logic pick a suitable address and deal with the page table
upgrade after the address has been selected.
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

The TASK_SIZE for a process should be maximum possible size of the address
space, 2GB for a 31-bit process and 8PB for a 64-bit process. The number
of page table levels required for a given memory layout is a consequence
of the mapped memory areas and their location.
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

The guarded storage interface allows to register a control block for
each thread that is activated with the guarded storage broadcast event.
To retrieve the complete state of a process from the kernel a register
set for the stored broadcast control block is required.
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

Add use_cmma field to mm_context_t, like we do for storage keys.
Signed-off-by: NClaudio Imbrenda <imbrenda@linux.vnet.ibm.com>
Acked-by: NJanosch Frank <frankja@de.ibm.com>
Reviewed-by: NChristian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: NChristian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

Add PGSTE manipulation functions:
* set_pgste_bits sets specific bits in a PGSTE
* get_pgste returns the whole PGSTE
* pgste_perform_essa manipulates a PGSTE to set specific storage states
* ESSA_[SG]ET_* macros used to indicate the action for manipulate_pgste
Signed-off-by: NClaudio Imbrenda <imbrenda@linux.vnet.ibm.com>
Reviewed-by: NJanosch Frank <frankja@de.ibm.com>
Reviewed-by: NChristian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: NChristian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

The CAD instruction never worked quite as expected for the spinlock
code. It has been disabled by default with git commit 61b0b016,
if the "cad" kernel parameter is specified it is enabled for both user
space and the spinlock code. Leave the option to enable the instruction
for user space but remove it from the spinlock code.
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

Add a couple more __atomic_xxx function to atomic_ops.h and use them
to replace the compare-and-swap inlines in the spinlock code. This
changes the type of the lock value from unsigned int to int.
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

There are three different code levels in regard to the identification
of guest samples. They differ in the way the LPP instruction is used.

1) Old kernels without the LPP instruction. The guest program parameter
   is always zero.
2) Newer kernels load the process pid into the program parameter with LPP.
   The guest program parameter is non-zero if the guest executes in a
   process != idle.
3) The latest kernels load ((1UL << 31) | pid) with LPP to make the value
   non-zero even for the idle task. The guest program parameter is non-zero
   if the guest is running.

All kernels load the process pid to CR4 on context switch. The CPU sampling
code uses the value in CR4 to decide between guest and host samples in case
the guest program parameter is zero. The three cases:

1) CR4==pid, gpp==0
2) CR4==pid, gpp==pid
3) CR4==pid, gpp==((1UL << 31) | pid)

The load-control instruction to load the pid into CR4 is expensive and the
goal is to remove it. To distinguish the host CR4 from the guest pid for
the idle process the maximum value 0xffff for the PASN is used.
This adds a fourth case for a guest OS with an updated kernel:

4) CR4==0xffff, gpp=((1UL << 31) | pid)

The host kernel will have CR4==0xffff and will use (gpp!=0 || CR4!==0xffff)
to identify guest samples. This works nicely with all 4 cases, the only
possible issue would be a guest with an old kernel (gpp==0) and a process
pid of 0xffff. Well, don't do that..
Suggested-by: NChristian Borntraeger <borntraeger@de.ibm.com>
Reviewed-by: NChristian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

Move a struct definition to get rid of a forward declaration.
Signed-off-by: NSebastian Ott <sebott@linux.vnet.ibm.com>
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

Users complained that they are hitting the limit of 64 functions (some
physical functions can spawn lots of virtual functions). Double the
default limit. With the latest savings in static data usage this
increases the image size by only 520 bytes.
Signed-off-by: NSebastian Ott <sebott@linux.vnet.ibm.com>
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

Commit c506fff3 ("s390/pci: resize iomap") reduced the iomap
to NR_FUNCTIONS * PCI_BAR_COUNT elements. Since we only support
functions with 64bit BARs we can cut that number in half.
Signed-off-by: NSebastian Ott <sebott@linux.vnet.ibm.com>
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

Address space identifiers are already defined in <asm/pci_insn.h>.
Signed-off-by: NSebastian Ott <sebott@linux.vnet.ibm.com>
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

barsize was never used. Get rid of it.
Signed-off-by: NSebastian Ott <sebott@linux.vnet.ibm.com>
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

The 32-bit lctl instruction is quite a bit slower than the 64-bit
counter part lctlg. Use the faster instruction.
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

Although Linux does not use format-0 channel command words (CCW0)
these are a non-optional part of the platform spec, and for the sake
of platform compliance, and possibly some non-Linux guests, we have
to support CCW0.

Making the kernel execute a format 0 channel program is too much hassle
because we would need to allocate and use memory which can be addressed
by 24 bit physical addresses (because of CCW0.cda). So we implement CCW0
support by translating the channel program into an equivalent CCW1
program instead.

Based upon an orginal patch by Kai Yue Wang.
Signed-off-by: NDong Jia Shi <bjsdjshi@linux.vnet.ibm.com>
Message-Id: <20170317031743.40128-16-bjsdjshi@linux.vnet.ibm.com>
Signed-off-by: NCornelia Huck <cornelia.huck@de.ibm.com>

To make vfio support subchannel devices, we need to leverage the
mediated device framework to create a mediated device for the
subchannel device.

This registers the subchannel device to the mediated device
framework during probe to enable mediated device creation.
Reviewed-by: NPierre Morel <pmorel@linux.vnet.ibm.com>
Signed-off-by: NDong Jia Shi <bjsdjshi@linux.vnet.ibm.com>
Message-Id: <20170317031743.40128-7-bjsdjshi@linux.vnet.ibm.com>
Signed-off-by: NCornelia Huck <cornelia.huck@de.ibm.com>

To make vfio support subchannel devices, we need a css driver for
the vfio subchannels. This patch adds a basic vfio-ccw subchannel
driver for this purpose.

To enable VFIO for vfio-ccw, enable S390_CCW_IOMMU config option
and configure VFIO as required.
Acked-by: NPierre Morel <pmorel@linux.vnet.ibm.com>
Signed-off-by: NDong Jia Shi <bjsdjshi@linux.vnet.ibm.com>
Message-Id: <20170317031743.40128-5-bjsdjshi@linux.vnet.ibm.com>
Signed-off-by: NCornelia Huck <cornelia.huck@de.ibm.com>

The return code of hw_perf_event_update() is not evaluated by
its callers.  Hence, simplify the function by removing the
return code.
Reported-by: NHeiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: NHendrik Brueckner <brueckner@linux.vnet.ibm.com>
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

Using a register variable for r4 is not necessary.  Let the
compiler decide the register to be used.
Reported-by: NHeiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: NHendrik Brueckner <brueckner@linux.vnet.ibm.com>
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

Make clear that the event definitions relate to the counter
facility (cf) and not to the sampling facility (sf).
Signed-off-by: NHendrik Brueckner <brueckner@linux.vnet.ibm.com>
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

Add the event names for the IBM z13/z13s specific CPU-MF counters.

Also improve the merging of the generic and model specific events
so that their sysfs attribute definitions completely reside in
memory.  Hence, flagging the generic event attribute definitions
as initdata too.
Signed-off-by: NHendrik Brueckner <brueckner@linux.vnet.ibm.com>
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

Complete the IBM z13 support and support counters from the
MT-diagnostic counter set.  Note that this counter set is
available only if SMT is enabled.
Signed-off-by: NHendrik Brueckner <brueckner@linux.vnet.ibm.com>
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

The validate_event() function just checked for reserved counters
in particular CPU-MF counter sets.  Because the number of counters
in counter sets vary among different hardware models, remove the
explicit check to tolerate new models.

Reserved counters are not accounted and, thus, will return zero.
Signed-off-by: NHendrik Brueckner <brueckner@linux.vnet.ibm.com>
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

Use the highest counter number that can be specified for the
ecctr (extract CPU counter) instruction for perf.
Signed-off-by: NHendrik Brueckner <brueckner@linux.vnet.ibm.com>
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

Signed-off-by: NHeiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

Signed-off-by: NHeiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

Signed-off-by: NHeiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

Deferred struct page initialization works on s390. However it makes
only sense for the fake numa case, since the kthreads that initialize
struct pages are started per node. Without fake numa there is just a
single node and therefore no gain.
However there is no reason to not enable this feature. Therefore
select the config option and enable the feature in all config files.
Signed-off-by: NHeiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

Since linux v3.14 with commit 38dfac84 ("vmcore: prevent PT_NOTE
p_memsz overflow during header update") on s390 we get the following
message in the kdump kernel:

  Warning: Exceeded p_memsz, dropping PT_NOTE entry n_namesz=0x6b6b6b6b,
  n_descsz=0x6b6b6b6b

The reason for this is that we don't create a final zero note in
the ELF header which the proc/vmcore code uses to find out the end
of the notes section (see also kernel/kexec_core.c:final_note()).

It still worked on s390 by chance because we (most of the time?) have the
byte pattern 0x6b6b6b6b after the notes section which also makes the notes
parsing code stop in update_note_header_size_elf64() because 0x6b6b6b6b is
interpreded as note size:

  if ((real_sz + sz) > max_sz) {
          pr_warn("Warning: Exceeded p_memsz, dropping P ...);
          break;
  }

So fix this and add the missing final note to the ELF header.
We don't have to adjust the memory size for ELF header ("alloc_size")
because the new ELF note still fits into the 0x1000 base memory.

Cc: stable@vger.kernel.org # v4.4+
Signed-off-by: NMichael Holzheu <holzheu@linux.vnet.ibm.com>
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

HAVE_ARCH_EARLY_PFN_TO_NID selects a not present Kconfig
option. Therefore remove it.
Given that the first call of early_pfn_to_nid() happens after
numa_setup() finished to establish the memory to node mapping, there
is no need to implement an architecture private version of
__early_pfn_to_nid() like (only) ia64 does.
Signed-off-by: NHeiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

ptep_notify and gmap_shadow_notify both need a guest address and
therefore retrieve them from the available virtual host address.

As they operate on the same guest address, we can calculate it once
and then pass it on. As a gmap normally has more than one shadow gmap,
we also do not recalculate for each of them any more.
Signed-off-by: NJanosch Frank <frankja@linux.vnet.ibm.com>
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

There is no need for the __ASSEMBLY__ ifdefery anymore since the
architecture level set code that deals with facility bits was
converted to C in the meantime.
Signed-off-by: NHeiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

Use the actual size of the facility list array within the lowcore
structure for the MAX_FACILITY_BIT define instead of a comment which
states what this is good for. This makes it a bit harder to break
things.
Signed-off-by: NHeiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

Provide the remaining stsi information via debugfs files. This also
might be useful for debugging purposes.
Suggested-by: NChristian Borntraeger <borntraeger@de.ibm.com>
Acked-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>

Provide the raw stsi 15,1,x data contents via debugfs. This makes it
much easier to debug unexpected scheduling domains on machines that
provide cpu topology information.

Therefore this file adds a new 's390/stsi' debugfs directory with a
file for each possible topology nesting level that is allowed by the
architecture. The files will be created regardless if the machine
supports all, or any, level.  If a level is not supported, or no data
is available, user space can recognize this with a -EINVAL error code
when trying to read such data.
In addition a 'topology' symlink is created that points to the file
that contains the data that is used to create the scheduling domains.
Acked-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>

Introduce a top-level 's390' directory which should be used when
adding new s390 specific debug feature files and/or directories.

This makes hopefully sure that the contents of the s390 directory will
be a bit more structured. Right now we have a couple of top-level
files where it is not easy to tell to which subsystem they belong to.
Acked-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>

User space needs some information about the secure key(s)
before actually invoking the pkey and/or paes funcionality.
This patch introduces a new ioctl API and in kernel API to
verify the the secure key blob and give back some
information about the key (type, bitsize, old MKVP).
Both APIs are described in detail in the header files
arch/s390/include/asm/pkey.h and arch/s390/include/uapi/asm/pkey.h.
Signed-off-by: NHarald Freudenberger <freude@linux.vnet.ibm.com>
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

Signed-off-by: NMichael Holzheu <holzheu@linux.vnet.ibm.com>
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

If running within a level 3 hypervisor, the hypervisor provides a
SYSIB block which contains a control program indentifier string. Use
this string instead of the simple KVM and z/VM strings only. In case
of z/VM this provides addtional information: the z/VM version.

The new string looks similar to this:

Hardware name: IBM 2964 N96 702 (z/VM 6.4.0)
Signed-off-by: NHeiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>