Commits · aaa2245ed836824f21f8e42e0ab63b1637d1cb20 · nexedi / linux

04 Oct, 2016 40 commits

cxl: Flush PSL cache before resetting the adapter · aaa2245e

Frederic Barrat authored Oct 03, 2016

If the capi link is going down while the PSL owns a dirty cache line,
any access from the host for that data could lead to an Uncorrectable
Error.

So when resetting the capi adapter through sysfs, make sure the PSL
cache is flushed. It won't help if there are any active Process
Elements on the card, as the cache would likely get new dirty cache
lines immediately, but if resetting an idle adapter, it should avoid
any bad surprises from data left over from terminated Process Elements.
Signed-off-by: Frederic Barrat <fbarrat@linux.vnet.ibm.com>
Reviewed-by: Andrew Donnellan <andrew.donnellan@au1.ibm.com>
Acked-by: Ian Munsie <imunsie@au1.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

aaa2245e

powerpc: Set default CPU type to POWER8 for little endian builds · e2ad477c

Anton Blanchard authored Sep 25, 2016

We supported POWER7 CPUs for bootstrapping little endian, but the
target was always POWER8. Now that POWER7 specific issues are
impacting performance, change the default target to POWER8.
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

e2ad477c

powerpc: Only disable HAVE_EFFICIENT_UNALIGNED_ACCESS on POWER7 little endian · 8a18cc0c

Anton Blanchard authored Sep 25, 2016

POWER8 handles unaligned accesses in little endian mode, but commit
0b5e6661 ("powerpc: Don't set HAVE_EFFICIENT_UNALIGNED_ACCESS on
little endian builds") disabled it for all.

The issue with unaligned little endian accesses is specific to POWER7,
so update the Kconfig check to match. Using the stat() testcase from
commit a75c380c ("powerpc: Enable DCACHE_WORD_ACCESS on ppc64le"),
performance improves 15% on POWER8.
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

8a18cc0c

powerpc: Remove static branch prediction in atomic{, 64}_add_unless · 61e98ebf

Anton Blanchard authored Oct 03, 2016

I see quite a lot of static branch mispredictions on a simple
web serving workload. The issue is in __atomic_add_unless(), called
from _atomic_dec_and_lock(). There is no obvious common case, so it
is better to let the hardware predict the branch.
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

61e98ebf

powerpc: During context switch, check before setting mm_cpumask · bb85fb58

Anton Blanchard authored Oct 03, 2016

During context switch, switch_mm() sets our current CPU in mm_cpumask.
We can avoid this atomic sequence in most cases by checking before
setting the bit.

Testing on a POWER8 using our context switch microbenchmark:

tools/testing/selftests/powerpc/benchmarks/context_switch \
	--process --no-fp --no-altivec --no-vector

Performance improves 2%.
Signed-off-by: Anton Blanchard <anton@samba.org>
Acked-by: Balbir Singh <bsingharora@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

bb85fb58

powerpc/eeh: Quieten EEH message when no adapters are found · 91ac730b

Anton Blanchard authored Oct 02, 2016

No real need for this to be pr_warn(), reduce it to pr_info().
Signed-off-by: Anton Blanchard <anton@samba.org>
Acked-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

91ac730b

powerpc/configs: Enable Intel i40e on 64 bit configs · 9eda65fb

Anton Blanchard authored Sep 30, 2016

We are starting to see i40e adapters in recent machines, so enable
it in our configs.
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

9eda65fb

powerpc/configs: Change a few things from built in to modules · d3eb34a3

Anton Blanchard authored Sep 30, 2016

Change a few devices and filesystems that are seldom used any more
from built in to modules. This reduces our vmlinux about 500kB.
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

d3eb34a3

powerpc/configs: Bump kernel ring buffer size on 64 bit configs · 32eab6c9

Anton Blanchard authored Sep 30, 2016

When we issue a system reset, every CPU in the box prints an Oops,
including a backtrace. Each of these can be quite large (over 4kB)
and we may end up wrapping the ring buffer and losing important
information.

Bump the base size from 128kB to 256kB and the per CPU size from
4kB to 8kB.
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

32eab6c9

powerpc/configs: Enable VMX crypto · 43c2394f

Anton Blanchard authored Sep 30, 2016

We see big improvements with the VMX crypto functions (often 10x or more),
so enable it as a module.
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

43c2394f

powerpc/64: Align hot loops of memset() and backwards_memcpy() · 12ab11a2

Anton Blanchard authored Aug 04, 2016

Align the hot loops in our assembly implementation of memset()
and backwards_memcpy().

backwards_memcpy() is called from tcp_v4_rcv(), so we might
want to optimise this a little more.
Signed-off-by: Anton Blanchard <anton@samba.org>
Reviewed-by: Nick Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

12ab11a2

powerpc/64s: Remove unused exception code, small cleanups · e0319829

Nicholas Piggin authored Sep 21, 2016

This was not done before the big patches because I only noticed
them afterwards. It has become much easier to see which handlers
are branched to from which exception vectors now, and to see
exactly what vector space is being used for what.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

e0319829

powerpc/64s: Use a single macro for both parts of OOL exception · a33532af

Nicholas Piggin authored Sep 21, 2016

Simple substitution. This is possible now that both parts of the OOL
initial handler get linked into their correct location.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

a33532af

powerpc/64s: Move __replay_interrupt function below handlers · 0f0c6ca1

Nicholas Piggin authored Sep 21, 2016

This is not an exception handler as such, it's called from
local_irq_enable(), not exception entry.

Also clean up some now redundant comments at the end of the
consolidation series.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

0f0c6ca1

powerpc/64s: Consolidate CBE Thermal 0x1800 interrupt · 3965f8ab

Nicholas Piggin authored Sep 21, 2016

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

3965f8ab

powerpc/64s: Consolidate Altivec 0x1700 interrupt · b51c079e

Nicholas Piggin authored Sep 21, 2016

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

b51c079e

powerpc/64s: Consolidate Debug 0x1600 interrupt · 69a79344

Nicholas Piggin authored Sep 21, 2016

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

69a79344

powerpc/64s: Consolidate Softpatch 0x1500 interrupt · d7e89849

Nicholas Piggin authored Sep 21, 2016

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

d7e89849

powerpc/64s: Consolidate Instruction Breakpoint 0x1300 interrupt · 4e96dbbf
Nicholas Piggin authored Sep 21, 2016
```
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
```
4e96dbbf
powerpc/64s: Consolidate CBE System Error 0x1200 interrupt · ff1b3206
Nicholas Piggin authored Sep 21, 2016
```
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
```
ff1b3206
powerpc/64s: Consolidate Reserved 0xfa0-0x1200 interrupts · e46b964c
Nicholas Piggin authored Sep 21, 2016
```
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
```
e46b964c
powerpc/64s: Consolidate Hypervisor Facility Unavailable 0xf80 interrupt · 14b0072c
Nicholas Piggin authored Sep 21, 2016
```
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
```
14b0072c
powerpc/64s: Consolidate Facility Unavailable 0xf60 interrupt · 1134713c
Nicholas Piggin authored Sep 21, 2016
```
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
```
1134713c
powerpc/64s: Consolidate VSX Unavailable 0xf40 interrupt · 792cbddd
Nicholas Piggin authored Sep 21, 2016
```
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
```
792cbddd
powerpc/64s: Consolidate Vector Unavailable 0xf20 interrupt · d1a0ca9c
Nicholas Piggin authored Sep 21, 2016
```
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
```
d1a0ca9c
powerpc/64s: Consolidate Performance Monitor 0xf00 interrupt · b1c7f150
Nicholas Piggin authored Sep 21, 2016
```
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
```
b1c7f150
powerpc/64s: Consolidate Reserved 0xec0, 0xee0 interrupts · bda7fea2
Nicholas Piggin authored Sep 21, 2016
```
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
```
bda7fea2
powerpc/64s: Consolidate Hypervisor Virtualization 0xea0 interrupt · 74408776
Nicholas Piggin authored Sep 21, 2016
```
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
```
74408776
powerpc/64s: Consolidate Directed Hypervisor Doorbell 0xe80 interrupt · 9bcb81bf
Nicholas Piggin authored Sep 21, 2016
```
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
```
9bcb81bf
powerpc/64s: Consolidate Hypervisor Maintenance 0xe60 interrupt · 62f9b03b
Nicholas Piggin authored Sep 21, 2016
```
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
```
62f9b03b
powerpc/64s: Consolidate Hypervisor Emulation Assistance 0xe40 interrupt · 031b4026
Nicholas Piggin authored Sep 21, 2016
```
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
```
031b4026
powerpc/64s: Consolidate Hypervisor Instruction Storage 0xe20 interrupt · 82517cab
Nicholas Piggin authored Sep 21, 2016
```
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
```
82517cab
powerpc/64s: Consolidate Hypervisor Data Storage 0xe00 interrupt · f5c32c1d
Nicholas Piggin authored Sep 21, 2016
```
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
```
f5c32c1d

powerpc/64s: Consolidate Trace 0xd00 interrupt · bc6675c6

Nicholas Piggin authored Sep 21, 2016

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

bc6675c6

powerpc/64s: Consolidate System Call 0xc00 interrupt · d807ad37

Nicholas Piggin authored Sep 21, 2016

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

d807ad37

powerpc/64s: Consolidate Reserved 0xb00 interrupt · 341215dc

Nicholas Piggin authored Sep 21, 2016

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

341215dc

powerpc/64s: Consolidate Directed Privileged Doorbell 0xa00 interrupt · ca243163
Nicholas Piggin authored Sep 21, 2016
```
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
```
ca243163
powerpc/64s: Consolidate Hypervisor Decrementer 0x980 interrupt · facc6d74
Nicholas Piggin authored Sep 21, 2016
```
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
```
facc6d74

powerpc/64s: Consolidate Decrementer 0x900 interrupt · 39c0da57

Nicholas Piggin authored Sep 21, 2016

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

39c0da57

powerpc/64s: Consolidate FP Unavailable 0x800 interrupt · c78d9b97
Nicholas Piggin authored Sep 21, 2016
```
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
```
c78d9b97