When booting a vcpu using PSCI, make sure we start it with the
endianness of the caller. Otherwise, secondaries can be pretty
unhappy to execute a BE kernel in LE mode...

This conforms to PSCI spec Rev B, 5.13.3.

Acked-by: Christoffer Dall <christoffer.dall@linaro.org>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>

Do the necessary byteswap when host and guest have different
views of the universe. Actually, the only case we need to take
care of is when the guest is BE. All the other cases are naturally
handled.

Also be careful about endianness when the data is being memcopy-ed
from/to the run buffer.

Acked-by: Christoffer Dall <christoffer.dall@linaro.org>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>

The KVM PSCI code blindly assumes that vcpu_id and MPIDR are
the same thing. This is true when vcpus are organized as a flat
topology, but is wrong when trying to emulate any other topology
(such as A15 clusters).

Change the KVM PSCI CPU_ON code to look at the MPIDR instead
of the vcpu_id to pick a target CPU.

Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>

Now that the KVM/arm code knows about affinity, remove the hard
limit of 4 vcpus per VM.

Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>

The L2CTLR register contains the number of CPUs in this cluster.

Make sure the register content is actually relevant to the vcpu
that is being configured by computing the number of cores that are
part of its cluster.

Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>

In order to be able to support more than 4 A7 or A15 CPUs,
we need to fix the MPIDR computing to reflect the fact that
both A15 and A7 can only exist in clusters of at most 4 CPUs.

Fix the MPIDR computing to allow virtual clusters to be exposed
to the guest.

Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>

Support transparent huge pages in KVM/ARM and KVM/ARM64.  The
transparent_hugepage_adjust is not very pretty, but this is also how
it's solved on x86 and seems to be simply an artifact on how THPs
behave.  This should eventually be shared across architectures if
possible, but that can always be changed down the road.

Acked-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>

Support huge pages in KVM/ARM and KVM/ARM64.  The pud_huge checking on
the unmap path may feel a bit silly as the pud_huge check is always
defined to false, but the compiler should be smart about this.

Note: This deals only with VMAs marked as huge which are allocated by
users through hugetlbfs only.  Transparent huge pages can only be
detected by looking at the underlying pages (or the page tables
themselves) and this patch so far simply maps these on a page-by-page
level in the Stage-2 page tables.

Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Russell King <rmk+kernel@arm.linux.org.uk>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>

Update comments to reflect what is really going on and add the TWE bit
to the comments in kvm_arm.h.

Also renames the function to kvm_handle_wfx like is done on arm64 for
consistency and uber-correctness.

Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>

On an (even slightly) oversubscribed system, spinlocks are quickly
becoming a bottleneck, as some vcpus are spinning, waiting for a
lock to be released, while the vcpu holding the lock may not be
running at all.

This creates contention, and the observed slowdown is 40x for
hackbench. No, this isn't a typo.

The solution is to trap blocking WFEs and tell KVM that we're
now spinning. This ensures that other vpus will get a scheduling
boost, allowing the lock to be released more quickly. Also, using
CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT slightly improves the performance
when the VM is severely overcommited.

Quick test to estimate the performance: hackbench 1 process 1000

2xA15 host (baseline):	1.843s

2xA15 guest w/o patch:	2.083s
4xA15 guest w/o patch:	80.212s
8xA15 guest w/o patch:	Could not be bothered to find out

2xA15 guest w/ patch:	2.102s
4xA15 guest w/ patch:	3.205s
8xA15 guest w/ patch:	6.887s

So we go from a 40x degradation to 1.5x in the 2x overcommit case,
which is vaguely more acceptable.

Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>

We will use that in the later patch to find the kvm ops handler

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Alexander Graf <agraf@suse.de>

Update comments to reflect what is really going on and add the TWE bit
to the comments in kvm_arm.h.

Also renames the function to kvm_handle_wfx like is done on arm64 for
consistency and uber-correctness.

Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>

On an (even slightly) oversubscribed system, spinlocks are quickly
becoming a bottleneck, as some vcpus are spinning, waiting for a
lock to be released, while the vcpu holding the lock may not be
running at all.

This creates contention, and the observed slowdown is 40x for
hackbench. No, this isn't a typo.

The solution is to trap blocking WFEs and tell KVM that we're
now spinning. This ensures that other vpus will get a scheduling
boost, allowing the lock to be released more quickly. Also, using
CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT slightly improves the performance
when the VM is severely overcommited.

Quick test to estimate the performance: hackbench 1 process 1000

2xA15 host (baseline):	1.843s

2xA15 guest w/o patch:	2.083s
4xA15 guest w/o patch:	80.212s
8xA15 guest w/o patch:	Could not be bothered to find out

2xA15 guest w/ patch:	2.102s
4xA15 guest w/ patch:	3.205s
8xA15 guest w/ patch:	6.887s

So we go from a 40x degradation to 1.5x in the 2x overcommit case,
which is vaguely more acceptable.

Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>

This patch adds support for running Cortex-A7 guests on Cortex-A7 hosts.

As Cortex-A7 is architecturally compatible with A15, this patch is largely just
generalising existing code. Areas where 'implementation defined' behaviour
is identical for A7 and A15 is moved to allow it to be used by both cores.

The check to ensure that coprocessor register tables are sorted correctly is
also moved in to 'common' code to avoid each new cpu doing its own check
(and possibly forgetting to do so!)

Signed-off-by: Jonathan Austin <jonathan.austin@arm.com>
Acked-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>

KVM does not have a notion of multiple clusters for CPUs, just a linear
array of CPUs. When using a system with cores in more than one cluster, the
current method for calculating the virtual MPIDR will leak the (physical)
cluster information into the virtual MPIDR. One effect of this is that
Linux under KVM fails to boot multiple CPUs that aren't in the 0th cluster.

This patch does away with exposing the real MPIDR fields in favour of simply
using the virtual CPU number (but preserving the U bit, as before).

Signed-off-by: Jonathan Austin <jonathan.austin@arm.com>
Acked-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>

For implementing CPU=host, we need a mechanism for querying
preferred VCPU target type on underlying Host.

This patch implements KVM_ARM_PREFERRED_TARGET vm ioctl which
returns struct kvm_vcpu_init instance containing information
about preferred VCPU target type and target specific features
available for it.

Signed-off-by: Anup Patel <anup.patel@linaro.org>
Signed-off-by: Pranavkumar Sawargaonkar <pranavkumar@linaro.org>
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>

This patch implements kvm_vcpu_preferred_target() function for
KVM ARM which will help us implement KVM_ARM_PREFERRED_TARGET ioctl
for user space.

Signed-off-by: Anup Patel <anup.patel@linaro.org>
Signed-off-by: Pranavkumar Sawargaonkar <pranavkumar@linaro.org>
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>

Very minor typo in comments of inject_abt() when we update fault status
register for injecting prefetch abort.

Signed-off-by: Anup Patel <anup.patel@linaro.org>
Signed-off-by: Pranavkumar Sawargaonkar <pranavkumar@linaro.org>
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>

cpu_reset is already #defined in <asm/proc-fns.h> as processor.reset,
so it expands here and causes problems.

Cc: <stable@vger.kernel.org>
Signed-off-by: Olof Johansson <olof@lixom.net>
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>

The panic strings are hard to read and on narrow terminals some
characters are simply truncated off the panic message.

Make is slightly prettier with a newline in the Hyp panic strings.

Acked-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>

Compilers before 4.6 do not behave well with unnamed fields in structure
initializers and therefore produces build errors:
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=10676



By refering to the unnamed union using braces, both older and newer
compilers produce the same result.

Acked-by: Marc Zyngier <marc.zyngier@arm.com>
Reported-by: Russell King <linux@arm.linux.org.uk>
Tested-by: Russell King <linux@arm.linux.org.uk>
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>

The tracepoint for kvm_guest_fault was extremely long, make it a
slightly bit shorter.

Cc: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Acked-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>

THe L_PTE_USER actually has nothing to do with stage 2 mappings and the
L_PTE_S2_RDWR value sets the readable bit, which was what L_PTE_USER
was used for before proper handling of stage 2 memory defines.

Changelog:
  [v3]: Drop call to kvm_set_s2pte_writable in mmu.c
  [v2]: Change default mappings to be r/w instead of r/o, as per Marc
     Zyngier's suggestion.

Cc: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>

When flushing the TLB at PL2 in response to remapping at stage-2 or VMID
rollover, we have a dsb instruction to ensure completion of the command
before continuing.

Since we only care about other processors for TLB invalidation, use the
inner-shareable variant of the dsb instruction instead.

Acked-by: Marc Zyngier <marc.zyngier@arm.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>

The 'len' variable was declared an unsigned and then checked for less
than 0, which results in warnings on some compilers.  Since len is
assigned an int, make it an int.

Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>

When using 64kB pages, we only have two levels of page tables,
meaning that PGD, PUD and PMD are fused. In this case, trying
to refcount PUDs and PMDs independently is a a complete disaster,
as they are the same.

We manage to get it right for the allocation (stage2_set_pte uses
{pmd,pud}_none), but the unmapping path clears both pud and pmd
refcounts, which fails spectacularly with 2-level page tables.

The fix is to avoid calling clear_pud_entry when both the pmd and
pud pages are empty. For this, and instead of introducing another
pud_empty function, consolidate both pte_empty and pmd_empty into
page_empty (the code is actually identical) and use that to also
test the validity of the pud.

Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>

The unmap_range function did not properly cover the case when the start
address was not aligned to PMD_SIZE or PUD_SIZE and an entire pte table
or pmd table was cleared, causing us to leak memory when incrementing
the addr.

The fix is to always move onto the next page table entry boundary
instead of adding the full size of the VA range covered by the
corresponding table level entry.

Acked-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>

The PAR was exported as CRn == 7 and CRm == 0, but in fact the primary
coprocessor register number was determined by CRm for 64-bit coprocessor
registers as the user space API was modeled after the coprocessor
access instructions (see the ARM ARM rev. C - B3-1445).

However, just changing the CRn to CRm breaks the sorting check when
booting the kernel, because the internal kernel logic always treats CRn
as the primary register number, and it makes the table sorting
impossible to understand for humans.

Alternatively we could change the logic to always have CRn == CRm, but
that becomes unclear in the number of ways we do look up of a coprocessor
register.  We could also have a separate 64-bit table but that feels
somewhat over-engineered.  Instead, keep CRn the primary representation
of the primary coproc. register number in-kernel and always export the
primary number as CRm as per the existing user space ABI.

Note: The TTBR registers just magically worked because they happened to
follow the CRn(0) regs and were considered CRn(0) in the in-kernel
representation.

Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>

This is called right after the memslots is updated, i.e. when the result
of update_memslots() gets installed in install_new_memslots().  Since
the memslots needs to be updated twice when we delete or move a memslot,
kvm_arch_commit_memory_region() does not correspond to this exactly.

In the following patch, x86 will use this new API to check if the mmio
generation has reached its maximum value, in which case mmio sptes need
to be flushed out.

Signed-off-by: Takuya Yoshikawa <yoshikawa_takuya_b1@lab.ntt.co.jp>
Acked-by: Alexander Graf <agraf@suse.de>
Reviewed-by: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

The virtio configuration has recently moved and is now visible everywhere.
Including the file again from KVM as we used to need earlier now causes
dependency problems:

warning: (CAIF_VIRTIO && VIRTIO_PCI && VIRTIO_MMIO && REMOTEPROC && RPMSG)
selects VIRTIO which has unmet direct dependencies (VIRTUALIZATION)

Cc: Christoffer Dall <cdall@cs.columbia.edu>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>

Commit d21a1c83 (ARM: KVM: define KVM_ARM_MAX_VCPUS
unconditionally) changed the Kconfig logic for KVM_ARM_MAX_VCPUS to work around a
build error arising from the use of KVM_ARM_MAX_VCPUS when CONFIG_KVM=n.  The
resulting Kconfig logic is a bit awkward and leaves a KVM_ARM_MAX_VCPUS always
defined in the kernel config file.

This change reverts the Kconfig logic back and adds a simple preprocessor
conditional in kvm_host.h to handle when CONFIG_KVM_ARM_MAX_VCPUS is undefined.

Signed-off-by: Geoff Levand <geoff@infradead.org>
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>

Make sure we clear the exclusive monitor on all exception returns,
which otherwise could lead to lock corruptions.

Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>

When performing a Stage-2 TLB invalidation, it is necessary to
make sure the write to the page tables is observable by all CPUs.

For this purpose, add a dsb instruction to __kvm_tlb_flush_vmid_ipa
before doing the TLB invalidation itself.

Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>

Not saving PAR is an unfortunate oversight. If the guest performs
an AT* operation and gets scheduled out before reading the result
of the translation from PAR, it could become corrupted by another
guest or the host.

Saving this register is made slightly more complicated as KVM also
uses it on the permission fault handling path, leading to an ugly
"stash and restore" sequence. Fortunately, this is already a slow
path so we don't really care. Also, Linux doesn't do any AT*
operation, so Linux guests are not impacted by this bug.

  [ Slightly tweaked to use an even register as first operand to ldrd
    and strd operations in interrupts_head.S - Christoffer ]

Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>

S2_PGD_SIZE defines the number of pages used by a stage-2 PGD
and is unused, except for a VM_BUG_ON check that missuses the
define.

As the check is very unlikely to ever triggered except in
circumstances where KVM is the least of our worries, just kill
both the define and the VM_BUG_ON check.

Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Christoffer Dall <cdall@cs.columbia.edu>

Admitedly, reading a MMIO register to load PC is very weird.
Writing PC to a MMIO register is probably even worse. But
the architecture doesn't forbid any of these, and injecting
a Prefetch Abort is the wrong thing to do anyway.

Remove this check altogether, and let the adventurous guest
wander into LaLaLand if they feel compelled to do so.

Reported-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Christoffer Dall <cdall@cs.columbia.edu>

HYP PGDs are passed around as phys_addr_t, except just before calling
into the hypervisor init code, where they are cast to a rather weird
unsigned long long.

Just keep them around as phys_addr_t, which is what makes the most
sense.

Reported-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Christoffer Dall <cdall@cs.columbia.edu>

Currently, kvmtool unconditionally declares that HVC should be used
to call PSCI, so the function numbers in the DT tell the guest
nothing about the function ID namespace or calling convention for
SMC.

We already assume that the guest will examine and honour the DT,
since there is no way it could possibly guess the KVM-specific PSCI
function IDs otherwise.  So let's not encourage guests to violate
what's specified in the DT by using SMC to make the call.

[ Modified to apply to top of kvm/arm tree - Christoffer ]

Signed-off-by: Dave P Martin <Dave.Martin@arm.com>
Acked-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Christoffer Dall <cdall@cs.columbia.edu>

The arch_timer irq numbers (or PPI numbers) are implementation dependent,
so the host virtual timer irq number can be different from guest virtual
timer irq number.

This patch ensures that host virtual timer irq number is read from DTB and
guest virtual timer irq is determined based on vcpu target type.

Signed-off-by: Anup Patel <anup.patel@linaro.org>
Signed-off-by: Pranavkumar Sawargaonkar <pranavkumar@linaro.org>
Signed-off-by: Christoffer Dall <cdall@cs.columbia.edu>

ARMv8 cores have the exact same timer as ARMv7 cores. Make sure the
KVM timer code can match it in the device tree.

Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>