Merge in some commits we're sharing with the KVM tree.

I manually propagated the change from commit d3d4ffaa
("powerpc/powernv/ioda2: Reduce upper limit for DMA window size") into
pci-ioda-tce.c.

Conflicts:
        arch/powerpc/include/asm/cputable.h
        arch/powerpc/platforms/powernv/pci-ioda.c
        arch/powerpc/platforms/powernv/pci.h

At the moment we allocate the entire TCE table, twice (hardware part and
userspace translation cache). This normally works as we normally have
contigous memory and the guest will map entire RAM for 64bit DMA.

However if we have sparse RAM (one example is a memory device), then
we will allocate TCEs which will never be used as the guest only maps
actual memory for DMA. If it is a single level TCE table, there is nothing
we can really do but if it a multilevel table, we can skip allocating
TCEs we know we won't need.

This adds ability to allocate only first level, saving memory.

This changes iommu_table::free() to avoid allocating of an extra level;
iommu_table::set() will do this when needed.

This adds @alloc parameter to iommu_table::exchange() to tell the callback
if it can allocate an extra level; the flag is set to "false" for
the realmode KVM handlers of H_PUT_TCE hcalls and the callback returns
H_TOO_HARD.

This still requires the entire table to be counted in mm::locked_vm.

To be conservative, this only does on-demand allocation when
the usespace cache table is requested which is the case of VFIO.

The example math for a system replicating a powernv setup with NVLink2
in a guest:
16GB RAM mapped at 0x0
128GB GPU RAM window (16GB of actual RAM) mapped at 0x244000000000

the table to cover that all with 64K pages takes:
(((0x244000000000 + 0x2000000000) >> 16)*8)>>20 = 4556MB

If we allocate only necessary TCE levels, we will only need:
(((0x400000000 + 0x400000000) >> 16)*8)>>20 = 4MB (plus some for indirect
levels).
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

This moves actual pages allocation to a separate function which is going
to be reused later in on-demand TCE allocation.

While we are at it, remove unnecessary level size round up as the caller
does this already.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

We want to support sparse memory and therefore huge chunks of DMA windows
do not need to be mapped. If a DMA window big enough to require 2 or more
indirect levels, and a DMA window is used to map all RAM (which is
a default case for 64bit window), we can actually save some memory by
not allocation TCE for regions which we are not going to map anyway.

The hardware tables alreary support indirect levels but we also keep
host-physical-to-userspace translation array which is allocated by
vmalloc() and is a flat array which might use quite some memory.

This converts it_userspace from vmalloc'ed array to a multi level table.

As the format becomes platform dependend, this replaces the direct access
to it_usespace with a iommu_table_ops::useraddrptr hook which returns
a pointer to the userspace copy of a TCE; future extension will return
NULL if the level was not allocated.

This should not change non-KVM handling of TCE tables and it_userspace
will not be allocated for non-KVM tables.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

We are going to reuse multilevel TCE code for the userspace copy of
the TCE table and since it is big endian, let's make the copy big endian
too.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Acked-by: Paul Mackerras <paulus@ozlabs.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

Right now we have allocation code in pci-ioda.c and traversing code in
pci.c, let's keep them toghether. However both files are big enough
already so let's move this business to a new file.

While we at it, move the code which links IOMMU table groups to
IOMMU tables as it is not specific to any PNV PHB model.

These puts exported symbols from the new file together.

This fixes several warnings from checkpatch.pl like this:
"WARNING: Prefer 'unsigned int' to bare use of 'unsigned'".

As this is almost cut-n-paste, there should be no behavioral change.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

This gets rid of a useless wrapper around
pnv_pci_ioda2_table_free_pages().
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

POWER9 DD1 was never a product. It is no longer supported by upstream
firmware, and it is not effectively supported in Linux due to lack of
testing.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Reviewed-by: Michael Ellerman <mpe@ellerman.id.au>
[mpe: Remove arch_make_huge_pte() entirely]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

Replace msleep(x) with with msleep(OPAL_BUSY_DELAY_MS) to document
these sleeps are to wait for opal (firmware).
Signed-off-by: Daniel Klamt <eleon@ele0n.de>
Signed-off-by: Bjoern Noetel <bjoern@br3ak3r.de>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

When we take an SLB multi-hit on bare metal, we see both the multi-hit
and parity error bits set in DSISR. The user manuals indicates this is
expected to always happen on Power8, whereas on Power9 it says a
multi-hit will "usually" also cause a parity error.

We decide what to do based on the various error tables in mce_power.c,
and because we process them in order and only report the first, we
currently always report a parity error but not the multi-hit, eg:

  Severe Machine check interrupt [Recovered]
    Initiator: CPU
    Error type: SLB [Parity]
      Effective address: c000000ffffd4300

Although this is correct, it leaves the user wondering why they got a
parity error. It would be clearer instead if we reported the
multi-hit because that is more likely to be simply a software bug,
whereas a true parity error is possibly an indication of a bad core.

We can do that simply by reordering the error tables so that multi-hit
appears before parity. That doesn't affect the error recovery at all,
because we flush the SLB either way.
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

This was added to support an early version of Power8 that did not have
working doorbells. These machines were not publicly available, and all of
the internal users have long since upgraded.
Signed-off-by: Joel Stanley <joel@jms.id.au>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

Using 'at24' as fallback is now deprecated - use the full
'atmel,<model>' string.
Signed-off-by: Bartosz Golaszewski <brgl@bgdev.pl>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

Using compatible strings without the <manufacturer> part for at24 is
now deprecated. Use a correct 'atmel,<model>' value.
Signed-off-by: Bartosz Golaszewski <brgl@bgdev.pl>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

Using 'at' as the <manufacturer> part of the compatible string is now
deprecated. Use a correct string: 'atmel,<model>'.
Signed-off-by: Bartosz Golaszewski <brgl@bgdev.pl>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

POWER9 does not support global pstate requests for the chip. So remove
the timer logic which slowly ramps down the global pstate in P9
platforms.
Signed-off-by: Shilpasri G Bhat <shilpa.bhat@linux.vnet.ibm.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
[mpe: Drop NULL check before kfree(policy->driver_data)]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

Enable kernel XZ compression option on BOOK3S_32. Tested on G4
PowerBook.
Signed-off-by: Aaro Koskinen <aaro.koskinen@iki.fi>
[mpe: Use one select under the PPC symbol guarded by if PPC_BOOK3S]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

In the quest to remove all stack VLA usage from the kernel[1], this
switches from an unchanging variable to a constant expression to
eliminate the VLA generation.

[1] https://lkml.kernel.org/r/CA+55aFzCG-zNmZwX4A2FQpadafLfEzK6CC=qPXydAacU1RqZWA@mail.gmail.comSigned-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

The sketchy bypass uses 256M pages so add this page size as well.

This should cause no behavioral change but will be used later.

Fixes: 477afd6ea6 "powerpc/ioda: Use ibm,supported-tce-sizes for IOMMU page size mask"
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

Memory reservation for crashkernel could fail if there are holes around
kdump kernel offset (128M). Fail gracefully in such cases and print an
error message.
Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
Tested-by: David Gibson <dgibson@redhat.com>
Reviewed-by: Dave Young <dyoung@redhat.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

In the quest to remove all stack VLA usage from the kernel[1], this
switches to using a stack size large enough for the saved routine and
adds a sanity check making sure the routine doesn't overflow into the
0x600 exception handler.

[1] https://lkml.kernel.org/r/CA+55aFzCG-zNmZwX4A2FQpadafLfEzK6CC=qPXydAacU1RqZWA@mail.gmail.comSigned-off-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

If a process exits without doing proper cleanup, there's a window
where an opencapi device can try to access the memory of the dying
process and may trigger a page fault. That's an expected scenario and
the ocxl driver holds a reference on the mm_struct of the process
until the opencapi device is notified of the process exiting.
However, if mm_users is already at 0, i.e. the address space of the
process has already been destroyed, the driver shouldn't try resolving
the page fault, as it will fail, but it can also try accessing already
freed data.

It is fixed by only calling the bottom half of the page fault handler
if mm_users is greater than 0 and get a reference on mm_users instead
of mm_count. Otherwise, we can safely return a translation fault to
the device, as its associated memory context is being removed. The
opencapi device will be properly cleaned up shortly after when closing
the file descriptors.

Fixes: 5ef3166e ("ocxl: Driver code for 'generic' opencapi devices")
Cc: stable@vger.kernel.org # v4.16+
Signed-off-by: Frederic Barrat <fbarrat@linux.ibm.com>
Reviewed-By: Alastair D'Silva <alastair@d-silva.org>
Acked-by: Andrew Donnellan <andrew.donnellan@au1.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

Fix two typos in the file header. Replacing the word 'priviledged'
by 'privileged' and 'exuecuted' by 'executed'.
Signed-off-by: Breno Leitao <leitao@debian.org>
Signed-off-by: Gustavo Romero <gromero@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

There is a buffer overflow in dscr_inherit_test.c test. In main(), strncpy()'s
third argument is the length of the source, not the size of the destination
buffer, which makes strncpy() behaves like strcpy(), causing a buffer overflow
if argv[0] is bigger than LEN_MAX (100).

This patch maps 'prog' to the argv[0] memory region, removing the static
allocation and the LEN_MAX size restriction.
Signed-off-by: Breno Leitao <leitao@debian.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

Remove a few XSL/CX4 oddities which are no longer needed. A simple
revert of the initial commits was not possible (or not worth it) due
to the history of the code.
Signed-off-by: Frederic Barrat <fbarrat@linux.ibm.com>
Acked-by: Andrew Donnellan <andrew.donnellan@au1.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

Remove abandonned capi support for the Mellanox CX4.

This reverts commit a19bd79e.
Signed-off-by: Frederic Barrat <fbarrat@linux.ibm.com>
Acked-by: Andrew Donnellan <andrew.donnellan@au1.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

Remove abandonned capi support for the Mellanox CX4.

This reverts commit 4e56f858.
Signed-off-by: Frederic Barrat <fbarrat@linux.ibm.com>
Acked-by: Andrew Donnellan <andrew.donnellan@au1.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

Remove abandonned capi support for the Mellanox CX4.

This reverts commit 4361b034.
Signed-off-by: Alastair D'Silva <alastair@d-silva.org>
Acked-by: Andrew Donnellan <andrew.donnellan@au1.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

Remove abandonned capi support for the Mellanox CX4.

This reverts commit 317f5ef1.
Signed-off-by: Alastair D'Silva <alastair@d-silva.org>
Acked-by: Andrew Donnellan <andrew.donnellan@au1.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

Remove abandonned capi support for the Mellanox CX4.

This reverts commit b0b5e591.
Signed-off-by: Alastair D'Silva <alastair@d-silva.org>
Acked-by: Andrew Donnellan <andrew.donnellan@au1.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

Remove abandonned capi support for the Mellanox CX4.

This reverts commit 79384e4b.
Signed-off-by: Alastair D'Silva <alastair@d-silva.org>
Acked-by: Andrew Donnellan <andrew.donnellan@au1.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

Remove abandonned capi support for the Mellanox CX4.

This reverts commit cbce0917.
Signed-off-by: Alastair D'Silva <alastair@d-silva.org>
Acked-by: Andrew Donnellan <andrew.donnellan@au1.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

Remove abandonned capi support for the Mellanox CX4.

This reverts commit a2f67d5e.
Signed-off-by: Alastair D'Silva <alastair@d-silva.org>
Acked-by: Andrew Donnellan <andrew.donnellan@au1.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

Remove abandonned capi support for the Mellanox CX4.
The symbol 'cxl_set_translation_mode' is never called, so
ctx->real_mode is always false.

This reverts commit 7a0d85d3.
Signed-off-by: Alastair D'Silva <alastair@d-silva.org>
Acked-by: Andrew Donnellan <andrew.donnellan@au1.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

debugfs doesn't support mmap(), so this code is never used.
Signed-off-by: Michael Neuling <mikey@neuling.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

We use PHB in mode1 which uses bit 59 to select a correct DMA window.
However there is mode2 which uses bits 59:55 and allows up to 32 DMA
windows per a PE.

Even though documentation does not clearly specify that, it seems that
the actual hardware does not support bits 59:55 even in mode1, in other
words we can create a window as big as 1<<58 but DMA simply won't work.

This reduces the upper limit from 59 to 55 bits to let the userspace know
about the hardware limits.

Fixes: 7aafac11 "powerpc/powernv/ioda2: Gracefully fail if too many TCE levels requested"
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

Signed-off-by: Michael Neuling <mikey@neuling.org>
Acked-by: Stewart Smith <stewart@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

Signed-off-by: Michael Neuling <mikey@neuling.org>
Acked-by: Stewart Smith <stewart@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

Commit 59f47eff ("powerpc/pci: Use of_irq_parse_and_map_pci() helper")
removed the 'oirq' variable, but kept memsetting it when the DEBUG macro is
defined.

When setting DEBUG macro for debugging purpose, the kernel fails to build since
'oirq' is not defined anymore.

This patch simply remove the debug block, since it does not seem to sense
now.

Fixes: 59f47eff ("powerpc/pci: Use of_irq_parse_and_map_pci() helper")
Signed-off-by: Breno Leitao <leitao@debian.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

64-bit ELF v2 ABI specification for POWER describes, on section "General
Stack Frame Requirements", that the stack should use the following
instructions when compiled with backchain:

  mflr r0
  std  r0, 16(r1)
  stdu r1, -XX(r1)

Where XX is the frame size for that function, and this is the value
checkstack.pl will find the stack size for each function.

This patch also simplifies the entire Powerpc section, since just two
type of instructions are used, 'stdu' for 64 bits and 'stwu' for 32 bits
platform.
Signed-off-by: Breno Leitao <leitao@debian.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

The workaround has been removed. What stays is just code to find the
memory hole so the BATs can be configured properly in the function below.

Fixes: 57deb8fe ("powerpc/wii: Don't rely on the reserved memory hack")
Signed-off-by: Jonathan Neuschäfer <j.neuschaefer@gmx.net>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>