linux.git/arch/powerpc/kernel/exceptions-64s.S, branch v3.8

powerpc: Add relocation on exception vector handlers

2012-11-15T04:08:05+00:00

POWER8/v2.07 allows exceptions to be taken with the MMU still on.

A new set of exception vectors is added at 0xc000_0000_0000_4xxx.  When the HW
takes us here, MSR IR/DR will be set already and we no longer need a costly
RFID to turn the MMU back on again.

The original 0x0 based exception vectors remain for when the HW can't leave the
MMU on.  Examples of this are when we can't trust the current MMU mappings,
like when we are changing from guest to hypervisor (HV 0 -> 1) or when the MMU
was off already.  In these cases the HW will take us to the original 0x0 based
exception vectors with the MMU off as before.

This uses the new macros added previously too implement these new execption
vectors at 0xc000_0000_0000_4xxx.  We exit these exception vectors using
mflr/blr (rather than mtspr SSR0/RFID), since we don't need the costly MMU
switch anymore.

This moves the __end_interrupts marker down past these new 0x4000 vectors since
they will need to be copied down to 0x0 when the kernel is not at 0x0.

Signed-off-by: Matt Evans 
Signed-off-by: Michael Neuling 
Signed-off-by: Benjamin Herrenschmidt

powerpc: Add new macros needed for relocation on exceptions

2012-11-15T04:08:04+00:00

POWER8/v2.07 allows exceptions to be taken with the MMU still on.

A new set of exception vectors is added at 0xc000_0000_0000_4xxx.  When the HW
takes us here, MSR IR/DR will be set already and we no longer need a costly
RFID to turn the MMU back on again.

The original 0x0 based exception vectors remain for when the HW can't leave the
MMU on.  Examples of this are when we can't trust the current the MMU mappings,
like when we are changing from guest to hypervisor (HV 0 -> 1) or when the MMU
was off already.  In these cases the HW will take us to the original 0x0 based
exception vectors with the MMU off as before.

The below macros are copies of the macros used at the 0x0 offset but modified
to handle the MMU being on.  In these macros we use the link register to jump
to the secondary handlers rather than using RFID (RFID was also use to turn on
the MMU).

Signed-off-by: Matt Evans 
Signed-off-by: Michael Neuling 
Signed-off-by: Benjamin Herrenschmidt

powerpc: Turn syscall handler into macros

2012-11-15T04:08:04+00:00

This turns the syscall handler into macros as we are going to want to reuse
them again later.

Signed-off-by: Matt Evans 
Signed-off-by: Michael Neuling 
Signed-off-by: Benjamin Herrenschmidt

powerpc: Make load_hander handle upto 64k offset

2012-11-15T04:08:03+00:00

If we change load_hander() to use an ori instead of addi, we can load handlers
upto 64k away provided we are still 64k aligned.

Signed-off-by: Benjamin Herrenschmidt

powerpc: Remove unessessary 0x3000 location enforcement

2012-11-15T04:08:03+00:00

This removes the large gap between 0x1800 and 0x3000.

Signed-off-by: Michael Neuling 
Signed-off-by: Benjamin Herrenschmidt

powerpc: Whitespace changes in exception64s.S

2012-11-15T04:08:02+00:00

Remove redundancy spaces and make tab usage consistent.

Signed-off-by: Michael Neuling 
Signed-off-by: Benjamin Herrenschmidt

powerpc: Fix denorm symbol name

2012-11-15T02:00:48+00:00

Fix global symbol name to match actual denorm_exception_hv label.

Signed-off-by: Michael Neuling 
Signed-off-by: Benjamin Herrenschmidt

powerpc/mm: Add 64TB support

2012-09-17T06:31:51+00:00

Increase max addressable range to 64TB. This is not tested on
real hardware yet.

Reviewed-by: Paul Mackerras 
Signed-off-by: Aneesh Kumar K.V 
Signed-off-by: Benjamin Herrenschmidt

powerpc: Add denormalisation exception handling for POWER6/7

2012-09-17T06:31:47+00:00

On POWER6 and POWER7 if the input operand to an instruction is a
denormalised single precision binary floating point value we can take
a denormalisation exception where it's expected that the hypervisor
(HV=1) will fix up the inputs before the instruction is run.

This adds code to handle this denormalisation exception for POWER6 and
POWER7.

It also add a CONFIG_PPC_DENORMALISATION option and sets it in
pseries/ppc64_defconfig.

This is useful on bare metal systems only.  Based on patch from Milton
Miller.

Signed-off-by: Michael Neuling 
Signed-off-by: Benjamin Herrenschmidt

powerpc: Give hypervisor decrementer interrupts their own handler

2012-09-05T06:05:19+00:00

At the moment the handler for hypervisor decrementer interrupts is
the same as for decrementer interrupts, i.e. timer_interrupt().
This is bogus; if we ever do get a hypervisor decrementer interrupt
it won't have anything to do with the next timer event.  In fact
the only time we get hypervisor decrementer interrupts is when one
is left pending on exit from a KVM guest.

When we get a hypervisor decrementer interrupt we don't need to do
anything special to clear it, since they are edge-triggered on the
transition of HDEC from 0 to -1.  Thus this adds an empty handler
function for them.  We don't need to have them masked when interrupts
are soft-disabled, so we use STD_EXCEPTION_HV instead of
MASKABLE_EXCEPTION_HV.

Signed-off-by: Paul Mackerras 
Signed-off-by: Benjamin Herrenschmidt