linux.git/arch/powerpc/platforms/pseries, branch v3.0

powerpc/mm: Fix memory_block_size_bytes() for non-pseries

2011-07-12T01:16:45+00:00

Just compiling pseries in the kernel causes it to override
memory_block_size_bytes() regardless of what is the runtime
platform.

This cleans up the implementation of that function, fixing
a bug or two while at it, so that it's harmless (and potentially
useful) for other platforms. Without this, bugs in that code
would trigger a WARN_ON() in drivers/base/memory.c when
booting some different platforms.

If/when we have another platform supporting memory hotplug we
might want to either move that out to a generic place or
make it a ppc_md. callback.

Signed-off-by: Benjamin Herrenschmidt

powerpc/pseries/iommu: Cleanup ddw naming

2011-05-19T07:25:28+00:00

When using a property refering to the availibily of dynamic dma windows
call it ddw_avail not ddr_avail.

dupe_ddw_if_already_created does not dupilcate anything, it only finds
and reuses the windows we already created, so rename it to
find_existing_ddw.  Also, it does not need the pci device node, so
remove that argument.

Signed-off-by: Milton Miller 
Signed-off-by: Nishanth Aravamudan 
Signed-off-by: Benjamin Herrenschmidt

powerpc/pseries/iommu: Find windows after kexec during boot

2011-05-19T07:25:28+00:00

Move the discovery of windows previously setup from when the pci driver
calls set_dma_mask to an arch_initcall.

When kexecing into a kernel with dynamic dma windows allocated, we need
to find the windows early so that memory hot remove will be able to
delete the tces mapping the to be removed memory and memory hotplug add
will map the new memory into the window.  We should not wait for the
driver to be loaded and the device to be probed.  The iommu init hooks
are before kmalloc is setup, so defer to arch_initcall.

Signed-off-by: Milton Miller 
Signed-off-by: Nishanth Aravamudan 
Signed-off-by: Benjamin Herrenschmidt

powerpc/pseries/iommu: Remove ddw property when destroying window

2011-05-19T07:25:27+00:00

If we destroy the window, we need to remove the property recording that
we setup the window.  Otherwise the next kernel we kexec will be
confused.

Also we should remove the property if even if we don't find the
ibm,ddw-applicable window or if one of the property sizes is unexpected;
presumably these came from a prior kernel via kexec, and we will not be
maintaining the window with respect to memory hotplug.

Signed-off-by: Milton Miller 
Signed-off-by: Nishanth Aravamudan 
Signed-off-by: Benjamin Herrenschmidt

powerpc/pseries/iommu: Add additional checks when changing iommu mask

2011-05-19T07:25:27+00:00

Do not check dma supported until we have chosen the right dma ops.
Check that the device is pci before treating it as such.

Check the mask is supported by the selected dma ops before
committing it.

We only need to set iommu ops if it is not the current ops; this
avoids searching the tree for the iommu table unnecessarily.

Signed-off-by: Milton Miller 
Signed-off-by: Nishanth Aravamudan 
Signed-off-by: Benjamin Herrenschmidt

powerpc/pseries/iommu: Use correct return type in dupe_ddw_if_already_created

2011-05-19T07:25:27+00:00

Otherwise we get silent truncations.

Signed-off-by: Nishanth Aravamudan 
Cc: Anton Blanchard 
Cc: Milton Miller 
Cc: linuxppc-dev@ozlabs.org
Signed-off-by: Benjamin Herrenschmidt

powerpc: Consolidate ipi message mux and demux

2011-05-19T05:31:03+00:00

Consolidate the mux and demux of ipi messages into smp.c and call
a new smp_ops callback to actually trigger the ipi.

The powerpc architecture code is optimised for having 4 distinct
ipi triggers, which are mapped to 4 distinct messages (ipi many, ipi
single, scheduler ipi, and enter debugger).  However, several interrupt
controllers only provide a single software triggered interrupt that
can be delivered to each cpu.  To resolve this limitation, each smp_ops
implementation created a per-cpu variable that is manipulated with atomic
bitops.  Since these lines will be contended they are optimialy marked as
shared_aligned and take a full cache line for each cpu.  Distro kernels
may have 2 or 3 of these in their config, each taking per-cpu space
even though at most one will be in use.

This consolidation removes smp_message_recv and replaces the single call
actions cases with direct calls from the common message recognition loop.
The complicated debugger ipi case with its muxed crash handling code is
moved to debug_ipi_action which is now called from the demux code (instead
of the multi-message action calling smp_message_recv).

I put a call to reschedule_action to increase the likelyhood of correctly
merging the anticipated scheduler_ipi() hook coming from the scheduler
tree; that single required call can be inlined later.

The actual message decode is a copy of the old pseries xics code with its
memory barriers and cache line spacing, augmented with a per-cpu unsigned
long based on the book-e doorbell code.  The optional data is set via a
callback from the implementation and is passed to the new cause-ipi hook
along with the logical cpu number.  While currently only the doorbell
implemntation uses this data it should be almost zero cost to retrieve and
pass it -- it adds a single register load for the argument from the same
cache line to which we just completed a store and the register is dead
on return from the call.  I extended the data element from unsigned int
to unsigned long in case some other code wanted to associate a pointer.

The doorbell check_self is replaced by a call to smp_muxed_ipi_resend,
conditioned on the CPU_DBELL feature.  The ifdef guard could be relaxed
to CONFIG_SMP but I left it with BOOKE for now.

Also, the doorbell interrupt vector for book-e was not calling irq_enter
and irq_exit, which throws off cpu accounting and causes code to not
realize it is running in interrupt context.  Add the missing calls.

Signed-off-by: Milton Miller 
Signed-off-by: Benjamin Herrenschmidt

powerpc/pseries: Print corrupt r3 in FWNMI code

2011-05-19T04:30:43+00:00

I have a report of an FWNMI with an r3 value that we think is
corrupt, but since we don't print r3 we have no idea what was
wrong with it.

Signed-off-by: Anton Blanchard 
Signed-off-by: Benjamin Herrenschmidt

pseries/iommu: Restore iommu table pointer when restoring iommu ops

2011-05-19T04:30:43+00:00

When we swtich to direct dma ops, we set the dma data union to have the
dma offset.  When we switch back to iommu table ops because of a later
dma_set_mask, we need to restore the iommu table pointer. Without this
change, crashes have been observed on kexec where (for reasons still
being investigated) we fall back to a 32-bit dma mask on a particular
device and then panic because the table pointer is not valid.

The easiset way to find this value is to call
pci_dma_dev_setup_pSeriesLP which will search up the pci tree until it
finds the node with the table.

Signed-off-by: Nishanth Aravamudan 
Cc: Milton Miller 
Cc: Paul Mackerras 
Cc: Anton Blanchard 
Cc: linuxppc-dev@lists.ozlabs.org
Signed-off-by: Benjamin Herrenschmidt

powerpc: Ensure dtl buffers do not cross 4k boundary

2011-05-19T04:30:41+00:00

Future releases of fimrware will enforce a requirement that DTL buffers
do not cross a 4k boundary. Commit
127493d5dc73589cbe00ea5ec8357cc2a4c0d82a satisfies this requirement for
CONFIG_VIRT_CPU_ACCOUNTING=y kernels, but if !CONFIG_VIRT_CPU_ACCOUNTING
&& CONFIG_DTL=y, the current code will fail at dtl registration time.
Fix this by making the kmem cache from
127493d5dc73589cbe00ea5ec8357cc2a4c0d82a visible outside of setup.c and
using the same cache in both dtl.c and setup.c. This requires a bit of
reorganization to ensure ordering of the kmem cache and buffer
allocations.

Note: Since firmware now limits the size of the buffer, I made
dtl_buf_entries read-only in debugfs.

Tested with upcoming firmware with the 4 combinations of
CONFIG_VIRT_CPU_ACCOUNTING and CONFIG_DTL.

Signed-off-by: Nishanth Aravamudan 
Cc: Paul Mackerras 
Cc: Anton Blanchard 
Cc: linuxppc-dev@lists.ozlabs.org
Signed-off-by: Benjamin Herrenschmidt