At the moment writing new TCE value to the IOMMU table fails with EBUSY
if there is a valid entry already. However PAPR specification allows
the guest to write new TCE value without clearing it first.

Another problem this patch is addressing is the use of pool locks for
external IOMMU users such as VFIO. The pool locks are to protect
DMA page allocator rather than entries and since the host kernel does
not control what pages are in use, there is no point in pool locks and
exchange()+put_page(oldtce) is sufficient to avoid possible races.

This adds an exchange() callback to iommu_table_ops which does the same
thing as set() plus it returns replaced TCE and DMA direction so
the caller can release the pages afterwards. The exchange() receives
a physical address unlike set() which receives linear mapping address;
and returns a physical address as the clear() does.

This implements exchange() for P5IOC2/IODA/IODA2. This adds a requirement
for a platform to have exchange() implemented in order to support VFIO.

This replaces iommu_tce_build() and iommu_clear_tce() with
a single iommu_tce_xchg().

This makes sure that TCE permission bits are not set in TCE passed to
IOMMU API as those are to be calculated by platform code from
DMA direction.

This moves SetPageDirty() to the IOMMU code to make it work for both
VFIO ioctl interface in in-kernel TCE acceleration (when it becomes
available later).
Signed-off-by: NAlexey Kardashevskiy <aik@ozlabs.ru>
[aw: for the vfio related changes]
Acked-by: NAlex Williamson <alex.williamson@redhat.com>
Reviewed-by: NDavid Gibson <david@gibson.dropbear.id.au>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

This adds missing locks in iommu_take_ownership()/
iommu_release_ownership().

This marks all pages busy in iommu_table::it_map in order to catch
errors if there is an attempt to use this table while ownership over it
is taken.

This only clears TCE content if there is no page marked busy in it_map.
Clearing must be done outside of the table locks as iommu_clear_tce()
called from iommu_clear_tces_and_put_pages() does this.

In order to use bitmap_empty(), the existing code clears bit#0 which
is set even in an empty table if it is bus-mapped at 0 as
iommu_init_table() reserves page#0 to prevent buggy drivers
from crashing when allocated page is bus-mapped at zero
(which is correct). This restores the bit in the case of failure
to bring the it_map to the state it was in when we called
iommu_take_ownership().
Signed-off-by: NAlexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: NDavid Gibson <david@gibson.dropbear.id.au>
Reviewed-by: NGavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

This adds tce_iommu_take_ownership() and tce_iommu_release_ownership
which call in a loop iommu_take_ownership()/iommu_release_ownership()
for every table on the group. As there is just one now, no change in
behaviour is expected.

At the moment the iommu_table struct has a set_bypass() which enables/
disables DMA bypass on IODA2 PHB. This is exposed to POWERPC IOMMU code
which calls this callback when external IOMMU users such as VFIO are
about to get over a PHB.

The set_bypass() callback is not really an iommu_table function but
IOMMU/PE function. This introduces a iommu_table_group_ops struct and
adds take_ownership()/release_ownership() callbacks to it which are
called when an external user takes/releases control over the IOMMU.

This replaces set_bypass() with ownership callbacks as it is not
necessarily just bypass enabling, it can be something else/more
so let's give it more generic name.

The callbacks is implemented for IODA2 only. Other platforms (P5IOC2,
IODA1) will use the old iommu_take_ownership/iommu_release_ownership API.
The following patches will replace iommu_take_ownership/
iommu_release_ownership calls in IODA2 with full IOMMU table release/
create.

As we here and touching bypass control, this removes
pnv_pci_ioda2_setup_bypass_pe() as it does not do much
more compared to pnv_pci_ioda2_set_bypass. This moves tce_bypass_base
initialization to pnv_pci_ioda2_setup_dma_pe.
Signed-off-by: NAlexey Kardashevskiy <aik@ozlabs.ru>
[aw: for the vfio related changes]
Acked-by: NAlex Williamson <alex.williamson@redhat.com>
Reviewed-by: NGavin Shan <gwshan@linux.vnet.ibm.com>
Reviewed-by: NDavid Gibson <david@gibson.dropbear.id.au>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

So far one TCE table could only be used by one IOMMU group. However
IODA2 hardware allows programming the same TCE table address to
multiple PE allowing sharing tables.

This replaces a single pointer to a group in a iommu_table struct
with a linked list of groups which provides the way of invalidating
TCE cache for every PE when an actual TCE table is updated. This adds
pnv_pci_link_table_and_group() and pnv_pci_unlink_table_and_group()
helpers to manage the list. However without VFIO, it is still going
to be a single IOMMU group per iommu_table.

This changes iommu_add_device() to add a device to a first group
from the group list of a table as it is only called from the platform
init code or PCI bus notifier and at these moments there is only
one group per table.

This does not change TCE invalidation code to loop through all
attached groups in order to simplify this patch and because
it is not really needed in most cases. IODA2 is fixed in a later
patch.

This should cause no behavioural change.
Signed-off-by: NAlexey Kardashevskiy <aik@ozlabs.ru>
[aw: for the vfio related changes]
Acked-by: NAlex Williamson <alex.williamson@redhat.com>
Reviewed-by: NGavin Shan <gwshan@linux.vnet.ibm.com>
Reviewed-by: NDavid Gibson <david@gibson.dropbear.id.au>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

Modern IBM POWERPC systems support multiple (currently two) TCE tables
per IOMMU group (a.k.a. PE). This adds a iommu_table_group container
for TCE tables. Right now just one table is supported.

This defines iommu_table_group struct which stores pointers to
iommu_group and iommu_table(s). This replaces iommu_table with
iommu_table_group where iommu_table was used to identify a group:
- iommu_register_group();
- iommudata of generic iommu_group;

This removes @data from iommu_table as it_table_group provides
same access to pnv_ioda_pe.

For IODA, instead of embedding iommu_table, the new iommu_table_group
keeps pointers to those. The iommu_table structs are allocated
dynamically.

For P5IOC2, both iommu_table_group and iommu_table are embedded into
PE struct. As there is no EEH and SRIOV support for P5IOC2,
iommu_free_table() should not be called on iommu_table struct pointers
so we can keep it embedded in pnv_phb::p5ioc2.

For pSeries, this replaces multiple calls of kzalloc_node() with a new
iommu_pseries_alloc_group() helper and stores the table group struct
pointer into the pci_dn struct. For release, a iommu_table_free_group()
helper is added.

This moves iommu_table struct allocation from SR-IOV code to
the generic DMA initialization code in pnv_pci_ioda_setup_dma_pe and
pnv_pci_ioda2_setup_dma_pe as this is where DMA is actually initialized.
This change is here because those lines had to be changed anyway.

This should cause no behavioural change.
Signed-off-by: NAlexey Kardashevskiy <aik@ozlabs.ru>
[aw: for the vfio related changes]
Acked-by: NAlex Williamson <alex.williamson@redhat.com>
Reviewed-by: NDavid Gibson <david@gibson.dropbear.id.au>
Reviewed-by: NGavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

This adds a iommu_table_ops struct and puts pointer to it into
the iommu_table struct. This moves tce_build/tce_free/tce_get/tce_flush
callbacks from ppc_md to the new struct where they really belong to.

This adds the requirement for @it_ops to be initialized before calling
iommu_init_table() to make sure that we do not leave any IOMMU table
with iommu_table_ops uninitialized. This is not a parameter of
iommu_init_table() though as there will be cases when iommu_init_table()
will not be called on TCE tables, for example - VFIO.

This does s/tce_build/set/, s/tce_free/clear/ and removes "tce_"
redundant prefixes.

This removes tce_xxx_rm handlers from ppc_md but does not add
them to iommu_table_ops as this will be done later if we decide to
support TCE hypercalls in real mode. This removes _vm callbacks as
only virtual mode is supported by now so this also removes @rm parameter.

For pSeries, this always uses tce_buildmulti_pSeriesLP/
tce_buildmulti_pSeriesLP. This changes multi callback to fall back to
tce_build_pSeriesLP/tce_free_pSeriesLP if FW_FEATURE_MULTITCE is not
present. The reason for this is we still have to support "multitce=off"
boot parameter in disable_multitce() and we do not want to walk through
all IOMMU tables in the system and replace "multi" callbacks with single
ones.

For powernv, this defines _ops per PHB type which are P5IOC2/IODA1/IODA2.
This makes the callbacks for them public. Later patches will extend
callbacks for IODA1/2.

No change in behaviour is expected.
Signed-off-by: NAlexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: NDavid Gibson <david@gibson.dropbear.id.au>
Reviewed-by: NGavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

Normally a bitmap from the iommu_table is used to track what TCE entry
is in use. Since we are going to use iommu_table without its locks and
do xchg() instead, it becomes essential not to put bits which are not
implied in the direction flag as the old TCE value (more precisely -
the permission bits) will be used to decide whether to put the page or not.

This adds iommu_direction_to_tce_perm() (its counterpart is there already)
and uses it for powernv's pnv_tce_build().
Signed-off-by: NAlexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: NDavid Gibson <david@gibson.dropbear.id.au>
Reviewed-by: NGavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

This moves page pinning (get_user_pages_fast()/put_page()) code out of
the platform IOMMU code and puts it to VFIO IOMMU driver where it belongs
to as the platform code does not deal with page pinning.

This makes iommu_take_ownership()/iommu_release_ownership() deal with
the IOMMU table bitmap only.

This removes page unpinning from iommu_take_ownership() as the actual
TCE table might contain garbage and doing put_page() on it is undefined
behaviour.

Besides the last part, the rest of the patch is mechanical.
Signed-off-by: NAlexey Kardashevskiy <aik@ozlabs.ru>
[aw: for the vfio related changes]
Acked-by: NAlex Williamson <alex.williamson@redhat.com>
Reviewed-by: NDavid Gibson <david@gibson.dropbear.id.au>
Reviewed-by: NGavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

At the moment iommu_free_table() only releases memory if
the table was initialized for the platform code use, i.e. it had
it_map initialized (which purpose is to track DMA memory space use).

With dynamic DMA windows, we will need to be able to release
iommu_table even if it was used for VFIO in which case it_map is NULL
so does the patch.
Signed-off-by: NAlexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: NDavid Gibson <david@gibson.dropbear.id.au>
Reviewed-by: NGavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

So far an iommu_table lifetime was the same as PE. Dynamic DMA windows
will change this and iommu_free_table() will not always require
the group to be released.

This moves iommu_group_put() out of iommu_free_table().

This adds a iommu_pseries_free_table() helper which does
iommu_group_put() and iommu_free_table(). Later it will be
changed to receive a table_group and we will have to change less
lines then.

This should cause no behavioural change.
Signed-off-by: NAlexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: NGavin Shan <gwshan@linux.vnet.ibm.com>
Reviewed-by: NDavid Gibson <david@gibson.dropbear.id.au>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

After d905c5df ("PPC: POWERNV: move iommu_add_device earlier"), the
refcnt on the kobject backing the IOMMU group for a PCI device is
elevated by each call to pci_dma_dev_setup_pSeriesLP() (via
set_iommu_table_base_and_group). When we go to dlpar a multi-function
PCI device out:

        iommu_reconfig_notifier ->
                iommu_free_table ->
                        iommu_group_put
                        BUG_ON(tbl->it_group)

We trip this BUG_ON, because there are still references on the table, so
it is not freed. Fix this by moving the powernv bus notifier to common
code and calling it for both powernv and pseries.

Fixes: d905c5df ("PPC: POWERNV: move iommu_add_device earlier")
Signed-off-by: NNishanth Aravamudan <nacc@linux.vnet.ibm.com>
Tested-by: NNishanth Aravamudan <nacc@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

The IOMMU-API gained support for a new iommu_map_sg
function. This causes compile failures on powerpc because
the function name is already globally used there.
This patch renames adds a ppc_ prefix to these functions to
solve the compile problem.
Signed-off-by: NJoerg Roedel <jroedel@suse.de>

This still has not been merged and now powerpc is the only arch that does
not have this change. Sorry about missing linuxppc-dev before.

V2->V2
  - Fix up to work against 3.18-rc1

__get_cpu_var() is used for multiple purposes in the kernel source. One of
them is address calculation via the form &__get_cpu_var(x).  This calculates
the address for the instance of the percpu variable of the current processor
based on an offset.

Other use cases are for storing and retrieving data from the current
processors percpu area.  __get_cpu_var() can be used as an lvalue when
writing data or on the right side of an assignment.

__get_cpu_var() is defined as :

__get_cpu_var() always only does an address determination. However, store
and retrieve operations could use a segment prefix (or global register on
other platforms) to avoid the address calculation.

this_cpu_write() and this_cpu_read() can directly take an offset into a
percpu area and use optimized assembly code to read and write per cpu
variables.

This patch converts __get_cpu_var into either an explicit address
calculation using this_cpu_ptr() or into a use of this_cpu operations that
use the offset.  Thereby address calculations are avoided and less registers
are used when code is generated.

At the end of the patch set all uses of __get_cpu_var have been removed so
the macro is removed too.

The patch set includes passes over all arches as well. Once these operations
are used throughout then specialized macros can be defined in non -x86
arches as well in order to optimize per cpu access by f.e.  using a global
register that may be set to the per cpu base.

Transformations done to __get_cpu_var()

1. Determine the address of the percpu instance of the current processor.

	DEFINE_PER_CPU(int, y);
	int *x = &__get_cpu_var(y);

    Converts to

	int *x = this_cpu_ptr(&y);

2. Same as #1 but this time an array structure is involved.

	DEFINE_PER_CPU(int, y[20]);
	int *x = __get_cpu_var(y);

    Converts to

	int *x = this_cpu_ptr(y);

3. Retrieve the content of the current processors instance of a per cpu
variable.

	DEFINE_PER_CPU(int, y);
	int x = __get_cpu_var(y)

   Converts to

	int x = __this_cpu_read(y);

4. Retrieve the content of a percpu struct

	DEFINE_PER_CPU(struct mystruct, y);
	struct mystruct x = __get_cpu_var(y);

   Converts to

	memcpy(&x, this_cpu_ptr(&y), sizeof(x));

5. Assignment to a per cpu variable

	DEFINE_PER_CPU(int, y)
	__get_cpu_var(y) = x;

   Converts to

	__this_cpu_write(y, x);

6. Increment/Decrement etc of a per cpu variable

	DEFINE_PER_CPU(int, y);
	__get_cpu_var(y)++

   Converts to

	__this_cpu_inc(y)

Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
CC: Paul Mackerras <paulus@samba.org>
Signed-off-by: NChristoph Lameter <cl@linux.com>
[mpe: Fix build errors caused by set/or_softirq_pending(), and rework
      assignment in __set_breakpoint() to use memcpy().]
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

This reverts commit 5828f666 due to
build failure after merging with pending powerpc changes.

Link: http://lkml.kernel.org/g/20140827142243.6277eaff@canb.auug.org.auSigned-off-by: NTejun Heo <tj@kernel.org>
Reported-by: NStephen Rothwell <sfr@canb.auug.org.au>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>

__get_cpu_var() is used for multiple purposes in the kernel source. One of
them is address calculation via the form &__get_cpu_var(x).  This calculates
the address for the instance of the percpu variable of the current processor
based on an offset.

Other use cases are for storing and retrieving data from the current
processors percpu area.  __get_cpu_var() can be used as an lvalue when
writing data or on the right side of an assignment.

__get_cpu_var() is defined as :

#define __get_cpu_var(var) (*this_cpu_ptr(&(var)))

__get_cpu_var() always only does an address determination. However, store
and retrieve operations could use a segment prefix (or global register on
other platforms) to avoid the address calculation.

this_cpu_write() and this_cpu_read() can directly take an offset into a
percpu area and use optimized assembly code to read and write per cpu
variables.

This patch converts __get_cpu_var into either an explicit address
calculation using this_cpu_ptr() or into a use of this_cpu operations that
use the offset.  Thereby address calculations are avoided and less registers
are used when code is generated.

At the end of the patch set all uses of __get_cpu_var have been removed so
the macro is removed too.

The patch set includes passes over all arches as well. Once these operations
are used throughout then specialized macros can be defined in non -x86
arches as well in order to optimize per cpu access by f.e.  using a global
register that may be set to the per cpu base.

Transformations done to __get_cpu_var()

1. Determine the address of the percpu instance of the current processor.

	DEFINE_PER_CPU(int, y);
	int *x = &__get_cpu_var(y);

    Converts to

	int *x = this_cpu_ptr(&y);

2. Same as #1 but this time an array structure is involved.

	DEFINE_PER_CPU(int, y[20]);
	int *x = __get_cpu_var(y);

    Converts to

	int *x = this_cpu_ptr(y);

3. Retrieve the content of the current processors instance of a per cpu
variable.

	DEFINE_PER_CPU(int, y);
	int x = __get_cpu_var(y)

   Converts to

	int x = __this_cpu_read(y);

4. Retrieve the content of a percpu struct

	DEFINE_PER_CPU(struct mystruct, y);
	struct mystruct x = __get_cpu_var(y);

   Converts to

	memcpy(&x, this_cpu_ptr(&y), sizeof(x));

5. Assignment to a per cpu variable

	DEFINE_PER_CPU(int, y)
	__get_cpu_var(y) = x;

   Converts to

	__this_cpu_write(y, x);

6. Increment/Decrement etc of a per cpu variable

	DEFINE_PER_CPU(int, y);
	__get_cpu_var(y)++

   Converts to

	__this_cpu_inc(y)

tj: Folded a fix patch.
    http://lkml.kernel.org/g/alpine.DEB.2.11.1408172143020.9652@gentwo.org

Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
CC: Paul Mackerras <paulus@samba.org>
Signed-off-by: NChristoph Lameter <cl@linux.com>
Signed-off-by: NTejun Heo <tj@kernel.org>

When we take full hotplug to recover from EEH errors, PCI buses
could be involved. For the case, the child devices of involved
PCI buses can't be attached to IOMMU group properly, which is
caused by commit 3f28c5af ("powerpc/powernv: Reduce multi-hit of
iommu_add_device()").

When adding the PCI devices of the newly created PCI buses to
the system, the IOMMU group is expected to be added in (C).
(A) fails to bind the IOMMU group because bus->is_added is
false. (B) fails because the device doesn't have binding IOMMU
table yet. bus->is_added is set to true at end of (C) and
pdev->is_added is set to true at (D).

   pcibios_add_pci_devices()
      pci_scan_bridge()
         pci_scan_child_bus()
            pci_scan_slot()
               pci_scan_single_device()
                  pci_scan_device()
                  pci_device_add()
                     pcibios_add_device()           A: Ignore
                     device_add()                   B: Ignore
                  pcibios_fixup_bus()
                     pcibios_setup_bus_devices()
                        pcibios_setup_device()      C: Hit
      pcibios_finish_adding_to_bus()
         pci_bus_add_devices()
            pci_bus_add_device()                    D: Add device

If the parent PCI bus isn't involved in hotplug, the IOMMU
group is expected to be bound in (B). (A) should fail as the
sysfs entries aren't populated.

The patch fixes the issue by reverting commit 3f28c5af and remove
WARN_ON() in iommu_add_device() to allow calling the function
even the specified device already has associated IOMMU group.

Cc: <stable@vger.kernel.org>  # 3.16+
Reported-by: NThadeu Lima de Souza Cascardo <cascardo@linux.vnet.ibm.com>
Signed-off-by: NGavin Shan <gwshan@linux.vnet.ibm.com>
Acked-by: NWei Yang <weiyang@linux.vnet.ibm.com>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

There is a couple of commented debug prints which still use
IOMMU_PAGE_SHIFT() which is not defined for POWERPC anymore, replace
them with it_page_shift.
Signed-off-by: NAlexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

This patch adds the support for to create a direct iommu "bypass"
window on IODA2 bridges (such as Power8) allowing to bypass iommu
page translation completely for 64-bit DMA capable devices, thus
significantly improving DMA performances.

Additionally, this adds a hook to the struct iommu_table so that
the IOMMU API / VFIO can disable the bypass when external ownership
is requested, since in that case, the device will be used by an
environment such as userspace or a KVM guest which must not be
allowed to bypass translations.
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

Some devices, for example PCI root port, don't have IOMMU table and
group. We needn't detach them from their IOMMU group. Otherwise, it
potentially incurs kernel crash because of referring NULL IOMMU group
as following backtrace indicates:

  .iommu_group_remove_device+0x74/0x1b0
  .iommu_bus_notifier+0x94/0xb4
  .notifier_call_chain+0x78/0xe8
  .__blocking_notifier_call_chain+0x7c/0xbc
  .blocking_notifier_call_chain+0x38/0x48
  .device_del+0x50/0x234
  .pci_remove_bus_device+0x88/0x138
  .pci_stop_and_remove_bus_device+0x2c/0x40
  .pcibios_remove_pci_devices+0xcc/0xfc
  .pcibios_remove_pci_devices+0x3c/0xfc
Signed-off-by: NGavin Shan <shangw@linux.vnet.ibm.com>
Reviewed-by: NAlexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

This patch updates the generic iommu backend code to use the
it_page_shift field to determine the iommu page size instead of
using hardcoded values.
Signed-off-by: NAlistair Popple <alistair@popple.id.au>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

The powerpc iommu uses a hardcoded page size of 4K. This patch changes
the name of the IOMMU_PAGE_* macros to reflect the hardcoded values. A
future patch will use the existing names to support dynamic page
sizes.
Signed-off-by: NAlistair Popple <alistair@popple.id.au>
Signed-off-by: NAlexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

The current implementation of IOMMU on sPAPR does not use iommu_ops
and therefore does not call IOMMU API's bus_set_iommu() which
1) sets iommu_ops for a bus
2) registers a bus notifier
Instead, PCI devices are added to IOMMU groups from
subsys_initcall_sync(tce_iommu_init) which does basically the same
thing without using iommu_ops callbacks.

However Freescale PAMU driver (https://lkml.org/lkml/2013/7/1/158)
implements iommu_ops and when tce_iommu_init is called, every PCI device
is already added to some group so there is a conflict.

This patch does 2 things:
1. removes the loop in which PCI devices were added to groups and
adds explicit iommu_add_device() calls to add devices as soon as they get
the iommu_table pointer assigned to them.
2. moves a bus notifier to powernv code in order to avoid conflict with
the notifier from Freescale driver.

iommu_add_device() and iommu_del_device() are public now.
Signed-off-by: NAlexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

Under heavy (DLPAR?) stress, we tripped this panic() in
arch/powerpc/kernel/iommu.c::iommu_init_table():

	page = alloc_pages_node(nid, GFP_ATOMIC, get_order(sz));
	if (!page)
		panic("iommu_init_table: Can't allocate %ld bytes\n", sz);

Before the panic() we got a page allocation failure for an order-2
allocation. There appears to be memory free, but perhaps not in the
ATOMIC context. I looked through all the call-sites of
iommu_init_table() and didn't see any obvious reason to need an ATOMIC
allocation. Most call-sites in fact have an explicit GFP_KERNEL
allocation shortly before the call to iommu_init_table(), indicating we
are not in an atomic context. There is some indirection for some paths,
but I didn't see any locks indicating that GFP_KERNEL is inappropriate.

With this change under the same conditions, we have not been able to
reproduce the panic.
Signed-off-by: NNishanth Aravamudan <nacc@us.ibm.com>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>
CC: <stable@vger.kernel.org>

Sweep of the simple cases.

Cc: netdev@vger.kernel.org
Cc: linuxppc-dev@lists.ozlabs.org
Cc: linux-arm-kernel@lists.infradead.org
Cc: Julia Lawall <julia.lawall@lip6.fr>
Signed-off-by: NRusty Russell <rusty@rustcorp.com.au>
Acked-by: NDavid S. Miller <davem@davemloft.net>
Acked-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

This initializes IOMMU groups based on the IOMMU configuration
discovered during the PCI scan on POWERNV (POWER non virtualized)
platform.  The IOMMU groups are to be used later by the VFIO driver,
which is used for PCI pass through.

It also implements an API for mapping/unmapping pages for
guest PCI drivers and providing DMA window properties.
This API is going to be used later by QEMU-VFIO to handle
h_put_tce hypercalls from the KVM guest.

The iommu_put_tce_user_mode() does only a single page mapping
as an API for adding many mappings at once is going to be
added later.

Although this driver has been tested only on the POWERNV
platform, it should work on any platform which supports
TCE tables.  As h_put_tce hypercall is received by the host
kernel and processed by the QEMU (what involves calling
the host kernel again), performance is not the best -
circa 220MB/s on 10Gb ethernet network.

To enable VFIO on POWER, enable SPAPR_TCE_IOMMU config
option and configure VFIO as required.

Cc: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: NAlexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: NPaul Mackerras <paulus@samba.org>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

Signed-off-by: NAdrian-Leonard Radu <ady8radu@gmail.com>
Acked-by: NGeoff Levand <geoff@infradead.org>
Signed-off-by: NMichael Ellerman <michael@ellerman.id.au>

When a device DMA window includes the address 0, it's reserved in the
TCE bitmap to avoid returning that address to drivers.

When the device is removed, the bitmap is checked for any mappings not
removed by the driver, indicating a possible DMA mapping leak. Since the
reserved address is not cleared, a message is printed, warning of such a
leak.

Check for the reservation, and clear it before checking for any other
standing mappings.
Signed-off-by: NThadeu Lima de Souza Cascardo <cascardo@linux.vnet.ibm.com>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

- Caluculate the bitmap size with BITS_TO_LONGS()
 - Use bitmap_empty() to verify that all bits are cleared

This also includes a printk to pr_warn() conversion.
Signed-off-by: NAkinobu Mita <akinobu.mita@gmail.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: linuxppc-dev@lists.ozlabs.org
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

There are a number of issues in the recent IOMMU pools code:

- On a preempt kernel we might switch CPUs in the middle of building
  a scatter gather list. When this happens the handle hint passed in
  no longer falls within the local CPU's pool. Check for this and
  fall back to the pool hint.

- We were missing a spin_unlock/spin_lock in one spot where we
  switch pools.

- We need to provide locking around dart_tlb_invalidate_all and
  dart_tlb_invalidate_one now that the global lock is gone.
Reported-by: NAlexander Graf <agraf@suse.de>
Signed-off-by: NAnton Blanchard <anton@samba.org>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>
CC: <stable@kernel.org> [v3.6]

The iommu pool patch has a bug where it would cause a crash when using
only one pool (based on the size of the DMA window).
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

Add the ability to inject IOMMU faults. We enable this per device
via a fail_iommu sysfs property, similar to fault injection on other
subsystems.

An example:

...
0003:01:00.1 Ethernet controller: Emulex Corporation OneConnect 10Gb NIC (be3) (rev 02)

To inject one error to this device:

echo 1 > /sys/bus/pci/devices/0003:01:00.1/fail_iommu
echo 1 > /sys/kernel/debug/fail_iommu/probability
echo 1 > /sys/kernel/debug/fail_iommu/times

As feared, the first failure injected on the be3 results in an
unrecoverable error, taking down both functions of the card
permanently:

be2net 0003:01:00.1: Unrecoverable error in the card
Signed-off-by: NAnton Blanchard <anton@samba.org>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

At the moment all queues in a multiqueue adapter will serialise
against the IOMMU table lock. This is proving to be a big issue,
especially with 10Gbit ethernet.

This patch creates 4 pools and tries to spread the load across
them. If the table is under 1GB in size we revert back to the
original behaviour of 1 pool and 1 largealloc pool.

We create a hash to map CPUs to pools. Since we prefer interrupts to
be affinitised to primary CPUs, without some form of hashing we are
very likely to end up using the same pool. As an example, POWER7
has 4 way SMT and with 4 pools all primary threads will map to the
same pool.

The largealloc pool is reduced from 1/2 to 1/4 of the space to
partially offset the overhead of breaking the table up into pools.

Some performance numbers were obtained with a Chelsio T3 adapter on
two POWER7 boxes, running a 100 session TCP round robin test.

Performance improved 69% with this patch applied.
Signed-off-by: NAnton Blanchard <anton@samba.org>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

In preparation for IOMMU pools, push the spinlock into
iommu_range_alloc and __iommu_free.
Signed-off-by: NAnton Blanchard <anton@samba.org>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

This patch moves tce_free outside of the lock in iommu_free.

Some performance numbers were obtained with a Chelsio T3 adapter on
two POWER7 boxes, running a 100 session TCP round robin test.

Performance improved 25% with this patch applied.
Signed-off-by: NAnton Blanchard <anton@samba.org>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

We currently hold the IOMMU spinlock around tce_build and tce_flush.
This causes our spinlock hold times to be much higher than required
and can impact multiqueue adapters.

This patch moves tce_build and tce_flush outside of the lock in
iommu_alloc, and tce_flush outside of the lock in iommu_free.

Some performance numbers were obtained with a Chelsio T3 adapter on
two POWER7 boxes, running a 100 session TCP round robin test.

Performance improved 32% with this patch applied.
Signed-off-by: NAnton Blanchard <anton@samba.org>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

On 2012-02-20 11:02:51 Mon, Paul Mackerras wrote:
> On Thu, Feb 16, 2012 at 04:44:30PM +0530, Mahesh J Salgaonkar wrote:
>
> If I have read the code correctly, we are going to get this printk on
> non-pSeries machines or on older pSeries machines, even if the user
> has not put the fadump=on option on the kernel command line.  The
> printk will be annoying since there is no actual error condition.  It
> seems to me that the condition for the printk should include
> fw_dump.fadump_enabled.  In other words you should probably add
>
> 	if (!fw_dump.fadump_enabled)
> 		return 0;
>
> at the beginning of the function.

Hi Paul,

Thanks for pointing it out. Please find the updated patch below.

The existing patches above this (4/10 through 10/10) cleanly applies
on this update.

Thanks,
-Mahesh.
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

Some devices have a dma-window that starts at the address 0. This allows
DMA addresses to be mapped to this address and returned to drivers as a
valid DMA address. Some drivers may not behave well in this case, since
the address 0 is considered an error or not allocated.

The solution to avoid this kind of error from happening is reserve the
page addressed as 0 so it cannot be allocated for a DMA mapping.
Signed-off-by: NThadeu Lima de Souza Cascardo <cascardo@linux.vnet.ibm.com>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

Right now its difficult to see which device is running out of iommu space:

iommu_alloc failed, tbl c00000076e096660 vaddr c000000768806600 npages 1

Use dev_info() so we get the device name and location:

ipr 0000:00:01.0: iommu_alloc failed, tbl c00000076e096660 vaddr c000000768806600 npages 1
Signed-off-by: NAnton Blanchard <anton@samba.org>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

'protect4gb' boot parameter was introduced to avoid allocating dma
space acrossing 4GB boundary in 2007 (the commit
56997559).

In 2008, the IOMMU was fixed to use the boundary_mask parameter per
device properly. So 'protect4gb' workaround was removed (the
383af952). But somehow I messed the
'protect4gb' boot parameter that was used to enable the
workaround.
Signed-off-by: NFUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

The description says:

 Cause IO segments sent to a device for DMA to be merged virtually
 by the IOMMU when they happen to have been allocated contiguously.
 This doesn't add pressure to the IOMMU allocator. However, some
 drivers don't support getting large merged segments coming back
 from *_map_sg().

 Most drivers don't have this problem; it is safe to say Y here.

It's out of date. Long ago, drivers didn't have a way to tell IOMMUs
about their segment length limit (that is, the maximum segment length
that they can handle). So IOMMUs merged as many segments as possible
and gave too large segments to drivers.

dma_get_max_seg_size() was introduced to solve the above
problem. Device drives can use the API to tell IOMMU about the maximum
segment length that they can handle. In addition, the default limit
(64K) should be safe for everyone.

So this config option seems to be unnecessary.

Note that this config option just enables users to disable the virtual
merging by default. Users can still disable the virtual merging by the
boot parameter.
Signed-off-by: NFUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>