Increase the initial kernel default page mapping size for SMP kernels to 32MB
and add a runtime check which panics early if the kernel is bigger than the
initial mapping size.

This fixes boot crashes of 32bit SMP kernels. Due to the introduction of huge
page support in kernel 4.4 and it's required initial kernel layout in memory, a
32bit SMP kernel usually got bigger (in layout, not size) than 16MB.

Cc: stable@vger.kernel.org #4.4+
Signed-off-by: NHelge Deller <deller@gmx.de>

Memblock is the standard kernel boot-time memory tracker/allocator. Use it
instead of the bootmem allocator. This allows using kmemleak, CMA and
other features.
Signed-off-by: NHelge Deller <deller@gmx.de>

Add hardened usercopy checks to parisc architecture and clean up
indenting.
Signed-off-by: NHelge Deller <deller@gmx.de>

Early during boot topology_update_package_map() computes
logical_pkg_ids for all present processors.

Later, when processors are brought up, identify_cpu() updates
these values based on phys_pkg_id which is a function of
initial_apicid. On PV guests the latter may point to a
non-existing node, causing logical_pkg_ids to be set to -1.

Intel's RAPL uses logical_pkg_id (as topology_logical_package_id())
to index its arrays and therefore in this case will point to index
65535 (since logical_pkg_id is a u16). This could lead to either a
crash or may actually access random memory location.

As a workaround, we recompute topology during CPU bringup to reset
logical_pkg_id to a valid value.

(The reason for initial_apicid being bogus is because it is
initial_apicid of the processor from which the guest is launched.
This value is CPUID(1).EBX[31:24])
Signed-off-by: NBoris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: stable@vger.kernel.org
Signed-off-by: NDavid Vrabel <david.vrabel@citrix.com>

Commit 215e362d ("ARM: 8306/1: loop_udelay: remove bogomips value
limitation") tried to increase the bogomips limitation, but in doing
so messed up udelay such that it always gives about a 5% error in the
delay, even if we use a timer.

The calculation is:

	loops = UDELAY_MULT * us_delay * ticks_per_jiffy >> UDELAY_SHIFT

Originally, UDELAY_MULT was ((UL(2199023) * HZ) >> 11) and UDELAY_SHIFT
30.  Assuming HZ=100, us_delay of 1000 and ticks_per_jiffy of 1660000
(eg, 166MHz timer, 1ms delay) this would calculate:

	((UL(2199023) * HZ) >> 11) * 1000 * 1660000 >> 30
		=> 165999

With the new values of 2047 * HZ + 483648 * HZ / 1000000 and 31, we get:

	(2047 * HZ + 483648 * HZ / 1000000) * 1000 * 1660000 >> 31
		=> 158269

which is incorrect.  This is due to a typo - correcting it gives:

	(2147 * HZ + 483648 * HZ / 1000000) * 1000 * 1660000 >> 31
		=> 165999

i.o.w, the original value.

Fixes: 215e362d ("ARM: 8306/1: loop_udelay: remove bogomips value limitation")
Cc: <stable@vger.kernel.org>
Reviewed-by: NNicolas Pitre <nico@linaro.org>
Signed-off-by: NRussell King <rmk+kernel@armlinux.org.uk>

Good evening,

Following LinuxCodingStyle documentation and with the help of Sam, fixed
severals identation issues in the code, and few others cosmetic changes

And last and i hope least fixing my name :)

Signed-off-by : Dominique Carrel <netmonk@netmonk.org>
Acked-by: NSam Ravnborg <sam@ravnborg.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Enable relaxed ordering for memory writes in IOMMU TSB entry from
dma_4v_alloc_coherent(), dma_4v_map_page() and dma_4v_map_sg() when
dma_attrs DMA_ATTR_WEAK_ORDERING is set. This requires PCI IOMMU I/O
Translation Services version 2.0 API.

Many PCIe devices allow enabling relaxed-ordering (memory writes bypassing
other memory writes) for various DMA buffers. A notable exception is the
Mellanox mlx4 IB adapter. Due to the nature of x86 HW this appears to have
little performance impact there. On SPARC HW however, this results in major
performance degradation getting only about 3Gbps. Enabling RO in the IOMMU
entries corresponding to mlx4 data buffers increases the throughput to
about 13 Gbps.

Orabug: 19245907
Signed-off-by: NChris Hyser <chris.hyser@oracle.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Enable Version 2 of the PCI IOMMU API needed for advanced features
such as PCI Relaxed Ordering and greater than 2 GB DMA address
space per root complex.
Signed-off-by: NChris Hyser <chris.hyser@oracle.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

These files were only including module.h for exception table
related functions.  We've now separated that content out into its
own file "extable.h" so now move over to that and avoid all the
extra header content in module.h that we don't really need to compile
these files.

Cc: "David S. Miller" <davem@davemloft.net>
Cc: sparclinux@vger.kernel.org
Signed-off-by: NPaul Gortmaker <paul.gortmaker@windriver.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add ENTRY_CFI() and ENDPROC_CFI() macros for dwarf debug info and
convert assembly users to new macros.
Signed-off-by: NHelge Deller <deller@gmx.de>

Do not reserve space in data section for hpmc stack, instead move it
into the page aligned bss section.
Signed-off-by: NHelge Deller <deller@gmx.de>

xen_cpuhp_setup() calls mutex_lock() which, when CONFIG_DEBUG_MUTEXES
is defined, ends up calling xen_save_fl(). That routine expects
per_cpu(xen_vcpu, 0) to be already initialized.
Signed-off-by: NBoris Ostrovsky <boris.ostrovsky@oracle.com>
Reported-by: NSander Eikelenboom <linux@eikelenboom.it>
Signed-off-by: NDavid Vrabel <david.vrabel@citrix.com>

Move the driver source and Kconfig to the PCI host bridge drivers directory
and move the config option to a more appropriate sub-menu instead of
occupying the top-level location.

Update the Kconfig option with the X86_64 dependency that was implicitly
included from the previous location, and add information about the module
name when built as a loadable module.
Signed-off-by: NKeith Busch <keith.busch@intel.com>
Signed-off-by: NBjorn Helgaas <bhelgaas@google.com>
CC: Jon Derrick <jonathan.derrick@intel.com>

In line with similar support for other architectures by Daniel Borkmann.

'MOD Default X' from test_bpf without constant blinding:
84 bytes emitted from JIT compiler (pass:3, flen:7)
d0000000058a4688 + <x>:
   0:	nop
   4:	nop
   8:	std     r27,-40(r1)
   c:	std     r28,-32(r1)
  10:	xor     r8,r8,r8
  14:	xor     r28,r28,r28
  18:	mr      r27,r3
  1c:	li      r8,66
  20:	cmpwi   r28,0
  24:	bne     0x0000000000000030
  28:	li      r8,0
  2c:	b       0x0000000000000044
  30:	divwu   r9,r8,r28
  34:	mullw   r9,r28,r9
  38:	subf    r8,r9,r8
  3c:	rotlwi  r8,r8,0
  40:	li      r8,66
  44:	ld      r27,-40(r1)
  48:	ld      r28,-32(r1)
  4c:	mr      r3,r8
  50:	blr

... and with constant blinding:
140 bytes emitted from JIT compiler (pass:3, flen:11)
d00000000bd6ab24 + <x>:
   0:	nop
   4:	nop
   8:	std     r27,-40(r1)
   c:	std     r28,-32(r1)
  10:	xor     r8,r8,r8
  14:	xor     r28,r28,r28
  18:	mr      r27,r3
  1c:	lis     r2,-22834
  20:	ori     r2,r2,36083
  24:	rotlwi  r2,r2,0
  28:	xori    r2,r2,36017
  2c:	xoris   r2,r2,42702
  30:	rotlwi  r2,r2,0
  34:	mr      r8,r2
  38:	rotlwi  r8,r8,0
  3c:	cmpwi   r28,0
  40:	bne     0x000000000000004c
  44:	li      r8,0
  48:	b       0x000000000000007c
  4c:	divwu   r9,r8,r28
  50:	mullw   r9,r28,r9
  54:	subf    r8,r9,r8
  58:	rotlwi  r8,r8,0
  5c:	lis     r2,-17137
  60:	ori     r2,r2,39065
  64:	rotlwi  r2,r2,0
  68:	xori    r2,r2,39131
  6c:	xoris   r2,r2,48399
  70:	rotlwi  r2,r2,0
  74:	mr      r8,r2
  78:	rotlwi  r8,r8,0
  7c:	ld      r27,-40(r1)
  80:	ld      r28,-32(r1)
  84:	mr      r3,r8
  88:	blr
Signed-off-by: NNaveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Acked-by: NDaniel Borkmann <daniel@iogearbox.net>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

Tail calls allow JIT'ed eBPF programs to call into other JIT'ed eBPF
programs. This can be achieved either by:
(1) retaining the stack setup by the first eBPF program and having all
subsequent eBPF programs re-using it, or,
(2) by unwinding/tearing down the stack and having each eBPF program
deal with its own stack as it sees fit.

To ensure that this does not create loops, there is a limit to how many
tail calls can be done (currently 32). This requires the JIT'ed code to
maintain a count of the number of tail calls done so far.

Approach (1) is simple, but requires every eBPF program to have (almost)
the same prologue/epilogue, regardless of whether they need it. This is
inefficient for small eBPF programs which may not sometimes need a
prologue at all. As such, to minimize impact of tail call
implementation, we use approach (2) here which needs each eBPF program
in the chain to use its own prologue/epilogue. This is not ideal when
many tail calls are involved and when all the eBPF programs in the chain
have similar prologue/epilogue. However, the impact is restricted to
programs that do tail calls. Individual eBPF programs are not affected.

We maintain the tail call count in a fixed location on the stack and
updated tail call count values are passed in through this. The very
first eBPF program in a chain sets this up to 0 (the first 2
instructions). Subsequent tail calls skip the first two eBPF JIT
instructions to maintain the count. For programs that don't do tail
calls themselves, the first two instructions are NOPs.
Signed-off-by: NNaveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

While at it, ensure that the location of the local save area is
consistent whether or not we setup our own stackframe. This property is
utilised in the next patch that adds support for tail calls.
Signed-off-by: NNaveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

The fadump code calls vmcore_cleanup() which only exists if
CONFIG_PROC_VMCORE=y. We don't want to depend on CONFIG_PROC_VMCORE,
because it's user selectable, so just wrap the call in an #ifdef.
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

Currently the MSR TM bit is always set if the hardware is TM capable.
This adds extra overhead as it means the TM SPRS (TFHAR, TEXASR and
TFAIR) must be swapped for each process regardless of if they use TM.

For processes that don't use TM the TM MSR bit can be turned off
allowing the kernel to avoid the expensive swap of the TM registers.

A TM unavailable exception will occur if a thread does use TM and the
kernel will enable MSR_TM and leave it so for some time afterwards.
Signed-off-by: NCyril Bur <cyrilbur@gmail.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

If the kernel disables transactional memory (TM) and userspace still
tries TM related actions (TM instructions or TM SPR accesses) TM aware
hardware will cause the kernel to take a facility unavailable
exception.

Add checks for the exception being caused by illegal TM access in
userspace.
Signed-off-by: NCyril Bur <cyrilbur@gmail.com>
[mpe: Rewrite comment entirely, bugs in it are mine]
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

Previous rework of TM code leaves these functions unused
Signed-off-by: NCyril Bur <cyrilbur@gmail.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

Make the structures being used for checkpointed state named
consistently with the pt_regs/ckpt_regs.
Signed-off-by: NCyril Bur <cyrilbur@gmail.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

There is currently an inconsistency as to how the entire CPU register
state is saved and restored when a thread uses transactional memory
(TM).

Using transactional memory results in the CPU having duplicated
(almost) all of its register state. This duplication results in a set
of registers which can be considered 'live', those being currently
modified by the instructions being executed and another set that is
frozen at a point in time.

On context switch, both sets of state have to be saved and (later)
restored. These two states are often called a variety of different
things. Common terms for the state which only exists after the CPU has
entered a transaction (performed a TBEGIN instruction) in hardware are
'transactional' or 'speculative'.

Between a TBEGIN and a TEND or TABORT (or an event that causes the
hardware to abort), regardless of the use of TSUSPEND the
transactional state can be referred to as the live state.

The second state is often to referred to as the 'checkpointed' state
and is a duplication of the live state when the TBEGIN instruction is
executed. This state is kept in the hardware and will be rolled back
to on transaction failure.

Currently all the registers stored in pt_regs are ALWAYS the live
registers, that is, when a thread has transactional registers their
values are stored in pt_regs and the checkpointed state is in
ckpt_regs. A strange opposite is true for fp_state/vr_state. When a
thread is non transactional fp_state/vr_state holds the live
registers. When a thread has initiated a transaction fp_state/vr_state
holds the checkpointed state and transact_fp/transact_vr become the
structure which holds the live state (at this point it is a
transactional state).

This method creates confusion as to where the live state is, in some
circumstances it requires extra work to determine where to put the
live state and prevents the use of common functions designed (probably
before TM) to save the live state.

With this patch pt_regs, fp_state and vr_state all represent the
same thing and the other structures [pending rename] are for
checkpointed state.
Acked-by: NSimon Guo <wei.guo.simon@gmail.com>
Signed-off-by: NCyril Bur <cyrilbur@gmail.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

Much of the signal code takes a pt_regs on which it operates. Over
time the signal code has needed to know more about the thread than
what pt_regs can supply, this information is obtained as needed by
using 'current'.

This approach is not strictly incorrect however it does mean that
there is now a hard requirement that the pt_regs being passed around
does belong to current, this is never checked. A safer approach is for
the majority of the signal functions to take a task_struct from which
they can obtain pt_regs and any other information they need. The
caveat that the task_struct they are passed must be current doesn't go
away but can more easily be checked for.

Functions called from outside powerpc signal code are passed a pt_regs
and they can confirm that the pt_regs is that of current and pass
current to other functions, furthurmore, powerpc signal functions can
check that the task_struct they are passed is the same as current
avoiding possible corruption of current (or the task they are passed)
if this assertion ever fails.

CC: paulus@samba.org
Signed-off-by: NCyril Bur <cyrilbur@gmail.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

After a thread is reclaimed from its active or suspended transactional
state the checkpointed state exists on CPU, this state (along with the
live/transactional state) has been saved in its entirety by the
reclaiming process.

There exists a sequence of events that would cause the kernel to call
one of enable_kernel_fp(), enable_kernel_altivec() or
enable_kernel_vsx() after a thread has been reclaimed. These functions
save away any user state on the CPU so that the kernel can use the
registers. Not only is this saving away unnecessary at this point, it
is actually incorrect. It causes a save of the checkpointed state to
the live structures within the thread struct thus destroying the true
live state for that thread.
Signed-off-by: NCyril Bur <cyrilbur@gmail.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

msr_check_and_set() always performs a mfmsr() to determine if it needs
to perform an mtmsr(), as mfmsr() can be a costly operation
msr_check_and_set() could return the MSR now on the CPU to avoid
callers of msr_check_and_set having to make their own mfmsr() call.
Signed-off-by: NCyril Bur <cyrilbur@gmail.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

giveup_all() causes FPU/VMX/VSX facilities to be disabled in a threads
MSR. If the thread performing the giveup was transactional, the kernel
must record which facilities were in use before the giveup as the
thread must have these facilities re-enabled on return to userspace.

>From process.c:
 /*
  * This is called if we are on the way out to userspace and the
  * TIF_RESTORE_TM flag is set.  It checks if we need to reload
  * FP and/or vector state and does so if necessary.
  * If userspace is inside a transaction (whether active or
  * suspended) and FP/VMX/VSX instructions have ever been enabled
  * inside that transaction, then we have to keep them enabled
  * and keep the FP/VMX/VSX state loaded while ever the transaction
  * continues.  The reason is that if we didn't, and subsequently
  * got a FP/VMX/VSX unavailable interrupt inside a transaction,
  * we don't know whether it's the same transaction, and thus we
  * don't know which of the checkpointed state and the transactional
  * state to use.
  */

Calling check_if_tm_restore_required() will set TIF_RESTORE_TM and
save the MSR if needed.

Fixes: c2085059 ("powerpc: create giveup_all()")
Signed-off-by: NCyril Bur <cyrilbur@gmail.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

Comment from arch/powerpc/kernel/process.c:967:
 If userspace is inside a transaction (whether active or
 suspended) and FP/VMX/VSX instructions have ever been enabled
 inside that transaction, then we have to keep them enabled
 and keep the FP/VMX/VSX state loaded while ever the transaction
 continues.  The reason is that if we didn't, and subsequently
 got a FP/VMX/VSX unavailable interrupt inside a transaction,
 we don't know whether it's the same transaction, and thus we
 don't know which of the checkpointed state and the ransactional
 state to use.

restore_math() restore_fp() and restore_altivec() currently may not
restore the registers. It doesn't appear that this is more serious
than a performance penalty. If the math registers aren't restored the
userspace thread will still be run with the facility disabled.
Userspace will not be able to read invalid values. On the first access
it will take an facility unavailable exception and the kernel will
detected an active transaction, at which point it will abort the
transaction. There is the possibility for a pathological case
preventing any progress by transactions, however, transactions
are never guaranteed to make progress.

Fixes: 70fe3d98 ("powerpc: Restore FPU/VEC/VSX if previously used")
Signed-off-by: NCyril Bur <cyrilbur@gmail.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

This fixes warning reported from sparse:

  pci-ioda.c:451:49: warning: incorrect type in argument 2 (different base types)

Fixes: 262af557 ("powerpc/powernv: Enable M64 aperatus for PHB3")
Signed-off-by: NGavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

This fixes the warnings reported from sparse:

  pci.c:312:33: warning: restricted __be64 degrades to integer
  pci.c:313:33: warning: restricted __be64 degrades to integer

Fixes: cee72d5b ("powerpc/powernv: Display diag data on p7ioc EEH errors")
Cc: stable@vger.kernel.org # v3.3+
Signed-off-by: NGavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

This fixes the warning reported from sparse:

  eeh-powernv.c:875:23: warning: constant 0x8000000000000000 is so big it is unsigned long

Fixes: ebe22531 ("powerpc/powernv: Support PCI slot ID")
Suggested-by: NMichael Ellerman <mpe@ellerman.id.au>
Signed-off-by: NGavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

The hub diag-data type is filled with big-endian data by OPAL call
opal_pci_get_hub_diag_data(). We need convert it to CPU-endian value
before using it. The issue is reported by sparse as pointed by Michael
Ellerman:

  eeh-powernv.c:1309:21: warning: restricted __be16 degrades to integer

This converts hub diag-data type to CPU-endian before using it in
pnv_eeh_get_and_dump_hub_diag().

Fixes: 2a485ad7 ("powerpc/powernv: Drop PHB operation next_error()")
Cc: stable@vger.kernel.org # v4.1+
Suggested-by: NMichael Ellerman <mpe@ellerman.id.au>
Signed-off-by: NGavin Shan <gwshan@linux.vnet.ibm.com>
Reviewed-by: NRussell Currey <ruscur@russell.cc>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

The PE number (@frozen_pe_no), filled by opal_pci_next_error() is in
big-endian format. It should be converted to CPU-endian before it is
passed to opal_pci_eeh_freeze_clear() when clearing the frozen state if
the PE is invalid one. As Michael Ellerman pointed out, the issue is
also detected by sparse:

  eeh-powernv.c:1541:41: warning: incorrect type in argument 2 (different base types)

This passes CPU-endian PE number to opal_pci_eeh_freeze_clear() and it
should be part of commit <0f36db77> ("powerpc/eeh: Fix wrong printed
PE number"), which was merged to 4.3 kernel.

Fixes: 71b540ad ("powerpc/powernv: Don't escalate non-existing frozen PE")
Cc: stable@vger.kernel.org # v4.3+
Suggested-by: NPaul Mackerras <paulus@samba.org>
Signed-off-by: NGavin Shan <gwshan@linux.vnet.ibm.com>
Reviewed-by: NRussell Currey <ruscur@russell.cc>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

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: NAnton Blanchard <anton@samba.org>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

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: NAnton Blanchard <anton@samba.org>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

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: NAnton Blanchard <anton@samba.org>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

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: NAnton Blanchard <anton@samba.org>
Acked-by: NBalbir Singh <bsingharora@gmail.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

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

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

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: NAnton Blanchard <anton@samba.org>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

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: NAnton Blanchard <anton@samba.org>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>