If the guest fpu is loaded, there is nothing interesing about cr0.ts; let
the guest play with it as it will.  This makes context switches between fpu
intensive guest processes faster, as we won't trap the clts and cr0 write
instructions.

[marcelo: fix cr0 read shadow update on fpu deactivation; kills F8 install]
Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

Defer fpu deactivation as much as possible - if the guest fpu is loaded, keep
it loaded until the next heavyweight exit (where we are forced to unload it).
This reduces unnecessary exits.

We also defer fpu activation on clts; while clts signals the intent to use the
fpu, we can't be sure the guest will actually use it.
Signed-off-by: Avi Kivity <avi@redhat.com>

We will use this later to give the guest ownership of cr0.ts.
Signed-off-by: Avi Kivity <avi@redhat.com>

Since we'd like to allow the guest to own a few bits of cr0 at times, we need
to know when we access those bits.
Signed-off-by: Avi Kivity <avi@redhat.com>

clts writes cr0.ts; lmsw writes cr0[0:15] - record that in ftrace.
Signed-off-by: Avi Kivity <avi@redhat.com>

An SLB entry contains two pieces of information related to size:

  1) PTE size
  2) SLB size

The L bit defines the PTE be "large" (usually means 16MB),
SLB_VSID_B_1T defines that the SLB should span 1 GB instead of the
default 256MB.

Apparently I messed things up and just put those two in one box,
shaked it heavily and came up with the current code which handles
large pages incorrectly, because it also treats large page SLB entries
as "1TB" segment entries.

This patch splits those two features apart, making Linux guests boot
even when they have > 256MB.
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>

When we get a program interrupt in guest kernel mode, we try to emulate the
instruction.

If that doesn't fail, we report to the user and try again - at the exact same
instruction pointer. So if the guest kernel really does trigger an invalid
instruction, we loop forever.

So let's better go and forward program exceptions to the guest when we don't
know the instruction we're supposed to emulate.
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>

When we need to reinject a program interrupt into the guest, we also need to
reinject the corresponding flags into the guest.
Signed-off-by: Alexander Graf <agraf@suse.de>
Reported-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Avi Kivity <avi@redhat.com>

The code to unset HID5.dcbz32 is broken.
This patch makes it do the right rotate magic.
Signed-off-by: Alexander Graf <agraf@suse.de>
Reported-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Avi Kivity <avi@redhat.com>

Book3S needs some flags in SRR1 to get to know details about an interrupt.

One such example is the trap instruction. It tells the guest kernel that
a program interrupt is due to a trap using a bit in SRR1.

This patch implements above behavior, making WARN_ON behave like WARN_ON.
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>

Currently we're racy when doing the transition from IR=1 to IR=0, from
the module memory entry code to the real mode SLB switching code.

To work around that I took a look at the RTAS entry code which is faced
with a similar problem and did the same thing:

  A small helper in linear mapped memory that does mtmsr with IR=0 and
  then RFIs info the actual handler.

Thanks to that trick we can safely take page faults in the entry code
and only need to be really wary of what to do as of the SLB switching
part.
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>

Using an RFI in IR=1 is dangerous. We need to set two SRRs and then do an RFI
without getting interrupted at all, because every interrupt could potentially
overwrite the SRR values.

Fortunately, we don't need to RFI in at least this particular case of the code,
so we can just replace it with an mtmsr and b.
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>

To fetch the last instruction we were interrupted on, we enable DR in early
exit code, where we are still in a very transitional phase between guest
and host state.

Most of the time this seemed to work, but another CPU can easily flush our
TLB and HTAB which makes us go in the Linux page fault handler which totally
breaks because we still use the guest's SLB entries.

To work around that, let's introduce a second KVM guest mode that defines
that whenever we get a trap, we don't call the Linux handler or go into
the KVM exit code, but just jump over the faulting instruction.

That way a potentially bad lwz doesn't trigger any faults and we can later
on interpret the invalid instruction we fetched as "fetch didn't work".
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>

We're being horribly racy right now. All the entry and exit code hijacks
random fields from the PACA that could easily be used by different code in
case we get interrupted, for example by a #MC or even page fault.

After discussing this with Ben, we figured it's best to reserve some more
space in the PACA and just shove off some vcpu state to there.

That way we can drastically improve the readability of the code, make it
less racy and less complex.
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>

We now have helpers for the GPRs, so let's also add some for CR and XER.

Having them in the PACA simplifies code a lot, as we don't need to care
about where to store CC or not to overflow any integers.
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>

All code in PPC KVM currently accesses gprs in the vcpu struct directly.

While there's nothing wrong with that wrt the current way gprs are stored
and loaded, it doesn't suffice for the PACA acceleration that will follow
in this patchset.

So let's just create little wrapper inline functions that we call whenever
a GPR needs to be read from or written to. The compiled code shouldn't really
change at all for now.
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>

The explanation of write_emulated is confused with
that of read_emulated. This patch fix it.
Signed-off-by: Takuya Yoshikawa <yoshikawa.takuya@oss.ntt.co.jp>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

Signed-off-by: Sheng Yang <sheng@linux.intel.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

Then the callback can provide the maximum supported large page level, which
is more flexible.

Also move the gb page support into x86_64 specific.
Signed-off-by: Sheng Yang <sheng@linux.intel.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

We can use them in x86.c and vmx.c now...
Signed-off-by: Sheng Yang <sheng@linux.intel.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

The PowerPC C ABI defines that registers r14-r31 need to be preserved across
function calls. Since our exit handler is written in C, we can make use of that
and don't need to reload r14-r31 on every entry/exit cycle.

This technique is also used in the BookE code and is called "lightweight exits"
there. To follow the tradition, it's called the same in Book3S.

So far this optimization was disabled though, as the code didn't do what it was
expected to do, but failed to work.

This patch fixes and enables lightweight exits again.
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

When we're loading bolted entries into the SLB again, we're checking if an
entry is in use and only slbmte it when it is.

Unfortunately, the check always goes to the skip label of the first entry,
resulting in an endless loop when it actually gets triggered.
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

When the guest acknowledges an interrupt, it sends an EOI message to the local
apic, which broadcasts it to the ioapic.  To handle the EOI, we need to take
the ioapic mutex.

On large guests, this causes a lot of contention on this mutex.  Since large
guests usually don't route interrupts via the ioapic (they use msi instead),
this is completely unnecessary.

Avoid taking the mutex by introducing a handled_vectors bitmap.  Before taking
the mutex, check if the ioapic was actually responsible for the acked vector.
If not, we can return early.
Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

Some exit reasons missed their strings; fill out the table.
Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

With slots_lock converted to rcu, the entire kvm hotpath on modern processors
(with npt or ept) now scales beautifully.  Increase the maximum vcpu count to
64 to reflect this.
Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

Using a similar two-step procedure as for memslots.
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

Use two steps for memslot deletion: mark the slot invalid (which stops
instantiation of new shadow pages for that slot, but allows destruction),
then instantiate the new empty slot.

Also simplifies kvm_handle_hva locking.
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

So its possible to iommu map a memslot before making it visible to
kvm.
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

Which takes a memslot pointer instead of using kvm->memslots.

To be used by SRCU convertion later.
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

Required for SRCU convertion later.
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

Have a pointer to an allocated region inside x86's kvm_arch.
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

Have a pointer to an allocated region inside struct kvm.

[alex: fix ppc book 3s]
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

Progress on KVM for Embedded PowerPC has stalled, but for Book3S there's quite
a lot of work to do and going on.

So in agreement with Hollis and Avi, we should switch maintainers for PowerPC.
Signed-off-by: Alexander Graf <agraf@suse.de>
Acked-by: Hollis Blanchard <hollis@penguinppc.org>
Signed-off-by: Avi Kivity <avi@redhat.com>

Because we now emulate the DEC interrupt according to real life behavior,
there's no need to keep the AGGRESSIVE_DEC hack around.

Let's just remove it.
Signed-off-by: Alexander Graf <agraf@suse.de>
Acked-by: Acked-by: Hollis Blanchard <hollis@penguinppc.org>
Signed-off-by: Avi Kivity <avi@redhat.com>

We treated the DEC interrupt like an edge based one. This is not true for
Book3s. The DEC keeps firing until mtdec is issued again and thus clears
the interrupt line.

So let's implement this logic in KVM too. This patch moves the line clearing
from the firing of the interrupt to the mtdec emulation.

This makes PPC64 guests work without AGGRESSIVE_DEC defined.
Signed-off-by: Alexander Graf <agraf@suse.de>
Acked-by: Acked-by: Hollis Blanchard <hollis@penguinppc.org>
Signed-off-by: Avi Kivity <avi@redhat.com>