commit 6794ad54 ("KVM: arm/arm64: Fix unintended stage 2 PMD mappings")
made the checks to skip huge mappings, stricter. However it introduced
a bug where we still use huge mappings, ignoring the flag to
use PTE mappings, by not reseting the vma_pagesize to PAGE_SIZE.

Also, the checks do not cover the PUD huge pages, that was
under review during the same period. This patch fixes both
the issues.

Fixes : 6794ad54 ("KVM: arm/arm64: Fix unintended stage 2 PMD mappings")
Reported-by: NZenghui Yu <yuzenghui@huawei.com>
Cc: Zenghui Yu <yuzenghui@huawei.com>
Cc: Christoffer Dall <christoffer.dall@arm.com>
Signed-off-by: NSuzuki K Poulose <suzuki.poulose@arm.com>
Signed-off-by: NMarc Zyngier <marc.zyngier@arm.com>

Calling kvm_is_visible_gfn() implies that we're parsing the memslots,
and doing this without the srcu lock is frown upon:

[12704.164532] =============================
[12704.164544] WARNING: suspicious RCU usage
[12704.164560] 5.1.0-rc1-00008-g600025238f51-dirty #16 Tainted: G        W
[12704.164573] -----------------------------
[12704.164589] ./include/linux/kvm_host.h:605 suspicious rcu_dereference_check() usage!
[12704.164602] other info that might help us debug this:
[12704.164616] rcu_scheduler_active = 2, debug_locks = 1
[12704.164631] 6 locks held by qemu-system-aar/13968:
[12704.164644]  #0: 000000007ebdae4f (&kvm->lock){+.+.}, at: vgic_its_set_attr+0x244/0x3a0
[12704.164691]  #1: 000000007d751022 (&its->its_lock){+.+.}, at: vgic_its_set_attr+0x250/0x3a0
[12704.164726]  #2: 00000000219d2706 (&vcpu->mutex){+.+.}, at: lock_all_vcpus+0x64/0xd0
[12704.164761]  #3: 00000000a760aecd (&vcpu->mutex){+.+.}, at: lock_all_vcpus+0x64/0xd0
[12704.164794]  #4: 000000000ef8e31d (&vcpu->mutex){+.+.}, at: lock_all_vcpus+0x64/0xd0
[12704.164827]  #5: 000000007a872093 (&vcpu->mutex){+.+.}, at: lock_all_vcpus+0x64/0xd0
[12704.164861] stack backtrace:
[12704.164878] CPU: 2 PID: 13968 Comm: qemu-system-aar Tainted: G        W         5.1.0-rc1-00008-g600025238f51-dirty #16
[12704.164887] Hardware name: rockchip evb_rk3399/evb_rk3399, BIOS 2019.04-rc3-00124-g2feec69fb1 03/15/2019
[12704.164896] Call trace:
[12704.164910]  dump_backtrace+0x0/0x138
[12704.164920]  show_stack+0x24/0x30
[12704.164934]  dump_stack+0xbc/0x104
[12704.164946]  lockdep_rcu_suspicious+0xcc/0x110
[12704.164958]  gfn_to_memslot+0x174/0x190
[12704.164969]  kvm_is_visible_gfn+0x28/0x70
[12704.164980]  vgic_its_check_id.isra.0+0xec/0x1e8
[12704.164991]  vgic_its_save_tables_v0+0x1ac/0x330
[12704.165001]  vgic_its_set_attr+0x298/0x3a0
[12704.165012]  kvm_device_ioctl_attr+0x9c/0xd8
[12704.165022]  kvm_device_ioctl+0x8c/0xf8
[12704.165035]  do_vfs_ioctl+0xc8/0x960
[12704.165045]  ksys_ioctl+0x8c/0xa0
[12704.165055]  __arm64_sys_ioctl+0x28/0x38
[12704.165067]  el0_svc_common+0xd8/0x138
[12704.165078]  el0_svc_handler+0x38/0x78
[12704.165089]  el0_svc+0x8/0xc

Make sure the lock is taken when doing this.

Fixes: bf308242 ("KVM: arm/arm64: VGIC/ITS: protect kvm_read_guest() calls with SRCU lock")
Reviewed-by: NEric Auger <eric.auger@redhat.com>
Signed-off-by: NMarc Zyngier <marc.zyngier@arm.com>

When halting a guest, QEMU flushes the virtual ITS caches, which
amounts to writing to the various tables that the guest has allocated.

When doing this, we fail to take the srcu lock, and the kernel
shouts loudly if running a lockdep kernel:

[   69.680416] =============================
[   69.680819] WARNING: suspicious RCU usage
[   69.681526] 5.1.0-rc1-00008-g600025238f51-dirty #18 Not tainted
[   69.682096] -----------------------------
[   69.682501] ./include/linux/kvm_host.h:605 suspicious rcu_dereference_check() usage!
[   69.683225]
[   69.683225] other info that might help us debug this:
[   69.683225]
[   69.683975]
[   69.683975] rcu_scheduler_active = 2, debug_locks = 1
[   69.684598] 6 locks held by qemu-system-aar/4097:
[   69.685059]  #0: 0000000034196013 (&kvm->lock){+.+.}, at: vgic_its_set_attr+0x244/0x3a0
[   69.686087]  #1: 00000000f2ed935e (&its->its_lock){+.+.}, at: vgic_its_set_attr+0x250/0x3a0
[   69.686919]  #2: 000000005e71ea54 (&vcpu->mutex){+.+.}, at: lock_all_vcpus+0x64/0xd0
[   69.687698]  #3: 00000000c17e548d (&vcpu->mutex){+.+.}, at: lock_all_vcpus+0x64/0xd0
[   69.688475]  #4: 00000000ba386017 (&vcpu->mutex){+.+.}, at: lock_all_vcpus+0x64/0xd0
[   69.689978]  #5: 00000000c2c3c335 (&vcpu->mutex){+.+.}, at: lock_all_vcpus+0x64/0xd0
[   69.690729]
[   69.690729] stack backtrace:
[   69.691151] CPU: 2 PID: 4097 Comm: qemu-system-aar Not tainted 5.1.0-rc1-00008-g600025238f51-dirty #18
[   69.691984] Hardware name: rockchip evb_rk3399/evb_rk3399, BIOS 2019.04-rc3-00124-g2feec69fb1 03/15/2019
[   69.692831] Call trace:
[   69.694072]  lockdep_rcu_suspicious+0xcc/0x110
[   69.694490]  gfn_to_memslot+0x174/0x190
[   69.694853]  kvm_write_guest+0x50/0xb0
[   69.695209]  vgic_its_save_tables_v0+0x248/0x330
[   69.695639]  vgic_its_set_attr+0x298/0x3a0
[   69.696024]  kvm_device_ioctl_attr+0x9c/0xd8
[   69.696424]  kvm_device_ioctl+0x8c/0xf8
[   69.696788]  do_vfs_ioctl+0xc8/0x960
[   69.697128]  ksys_ioctl+0x8c/0xa0
[   69.697445]  __arm64_sys_ioctl+0x28/0x38
[   69.697817]  el0_svc_common+0xd8/0x138
[   69.698173]  el0_svc_handler+0x38/0x78
[   69.698528]  el0_svc+0x8/0xc

The fix is to obviously take the srcu lock, just like we do on the
read side of things since bf308242. One wonders why this wasn't
fixed at the same time, but hey...

Fixes: bf308242 ("KVM: arm/arm64: VGIC/ITS: protect kvm_read_guest() calls with SRCU lock")
Signed-off-by: NMarc Zyngier <marc.zyngier@arm.com>

The normal interrupt flow is not to enable the vgic when no virtual
interrupt is to be injected (i.e. the LRs are empty). But when a guest
is likely to use GICv4 for LPIs, we absolutely need to switch it on
at all times. Otherwise, VLPIs only get delivered when there is something
in the LRs, which doesn't happen very often.
Reported-by: NNianyao Tang <tangnianyao@huawei.com>
Tested-by: NShameerali Kolothum Thodi <shameerali.kolothum.thodi@huawei.com>
Signed-off-by: NMarc Zyngier <marc.zyngier@arm.com>

debugfs can now report an error code if something went wrong instead of
just NULL.  So if the return value is to be used as a "real" dentry, it
needs to be checked if it is an error before dereferencing it.

This is now happening because of ff9fb72b ("debugfs: return error
values, not NULL").  syzbot has found a way to trigger multiple debugfs
files attempting to be created, which fails, and then the error code
gets passed to dentry_path_raw() which obviously does not like it.
Reported-by: NEric Biggers <ebiggers@kernel.org>
Reported-and-tested-by: syzbot+7857962b4d45e602b8ad@syzkaller.appspotmail.com
Cc: "Radim Krčmář" <rkrcmar@redhat.com>
Cc: kvm@vger.kernel.org
Acked-by: NPaolo Bonzini <pbonzini@redhat.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

This patch contains two minor cleanups: firstly it puts exported symbol
for kvm_io_bus_write() by following the function definition; secondly it
removes a redundant blank line.
Signed-off-by: NLeo Yan <leo.yan@linaro.org>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

The 'timer' local variable became unused after commit bee038a6
("KVM: arm/arm64: Rework the timer code to use a timer_map").
Remove it to avoid [-Wunused-but-set-variable] warning.

Cc: Christoffer Dall <christoffer.dall@arm.com>
Cc: James Morse <james.morse@arm.com>
Cc: Suzuki K Pouloze <suzuki.poulose@arm.com>
Reviewed-by: NJulien Thierry <julien.thierry@arm.com>
Signed-off-by: NShaokun Zhang <zhangshaokun@hisilicon.com>
Signed-off-by: NMarc Zyngier <marc.zyngier@arm.com>

The value of "dirty_bitmap[i]" is already check before setting its value
to mask. The following check of "mask" is redundant. The check of "mask" was
introduced by commit 58d2930f ("KVM: Eliminate extra function calls in
kvm_get_dirty_log_protect()"), revert it.
Signed-off-by: NLan Tianyu <Tianyu.Lan@microsoft.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

grow_halt_poll_ns() have a strange behaviour in case
(vcpu->halt_poll_ns != 0) &&
(vcpu->halt_poll_ns < halt_poll_ns_grow_start).

In this case, vcpu->halt_poll_ns will be multiplied by grow factor
(halt_poll_ns_grow) which will require several grow iteration in order
to reach a value bigger than halt_poll_ns_grow_start.
This means that growing vcpu->halt_poll_ns from value of 0 is slower
than growing it from a positive value less than halt_poll_ns_grow_start.
Which is misleading and inaccurate.

Fix issue by changing grow_halt_poll_ns() to set vcpu->halt_poll_ns
to halt_poll_ns_grow_start in any case that
(vcpu->halt_poll_ns < halt_poll_ns_grow_start).
Regardless if vcpu->halt_poll_ns is 0.

use READ_ONCE to get a consistent number for all cases.
Reviewed-by: NBoris Ostrovsky <boris.ostrovsky@oracle.com>
Reviewed-by: NLiran Alon <liran.alon@oracle.com>
Signed-off-by: NNir Weiner <nir.weiner@oracle.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

The hard-coded value 10000 in grow_halt_poll_ns() stands for the initial
start value when raising up vcpu->halt_poll_ns.
It actually sets the first timeout to the first polling session.
This value has significant effect on how tolerant we are to outliers.
On the standard case, higher value is better - we will spend more time
in the polling busyloop, handle events/interrupts faster and result
in better performance.
But on outliers it puts us in a busy loop that does nothing.
Even if the shrink factor is zero, we will still waste time on the first
iteration.
The optimal value changes between different workloads. It depends on
outliers rate and polling sessions length.
As this value has significant effect on the dynamic halt-polling
algorithm, it should be configurable and exposed.
Reviewed-by: NBoris Ostrovsky <boris.ostrovsky@oracle.com>
Reviewed-by: NLiran Alon <liran.alon@oracle.com>
Signed-off-by: NNir Weiner <nir.weiner@oracle.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

grow_halt_poll_ns() have a strange behavior in case
(halt_poll_ns_grow == 0) && (vcpu->halt_poll_ns != 0).

In this case, vcpu->halt_pol_ns will be set to zero.
That results in shrinking instead of growing.

Fix issue by changing grow_halt_poll_ns() to not modify
vcpu->halt_poll_ns in case halt_poll_ns_grow is zero
Reviewed-by: NBoris Ostrovsky <boris.ostrovsky@oracle.com>
Reviewed-by: NLiran Alon <liran.alon@oracle.com>
Signed-off-by: NNir Weiner <nir.weiner@oracle.com>
Suggested-by: NLiran Alon <liran.alon@oracle.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

...now that KVM won't explode by moving it out of bit 0.  Using bit 63
eliminates the need to jump over bit 0, e.g. when calculating a new
memslots generation or when propagating the memslots generation to an
MMIO spte.
Signed-off-by: NSean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

x86 captures a subset of the memslot generation (19 bits) in its MMIO
sptes so that it can expedite emulated MMIO handling by checking only
the releveant spte, i.e. doesn't need to do a full page fault walk.

Because the MMIO sptes capture only 19 bits (due to limited space in
the sptes), there is a non-zero probability that the MMIO generation
could wrap, e.g. after 500k memslot updates.  Since normal usage is
extremely unlikely to result in 500k memslot updates, a hack was added
by commit 69c9ea93 ("KVM: MMU: init kvm generation close to mmio
wrap-around value") to offset the MMIO generation in order to trigger
a wraparound, e.g. after 150 memslot updates.

When separate memslot generation sequences were assigned to each
address space, commit 00f034a1 ("KVM: do not bias the generation
number in kvm_current_mmio_generation") moved the offset logic into the
initialization of the memslot generation itself so that the per-address
space bit(s) were not dropped/corrupted by the MMIO shenanigans.

Remove the offset hack for three reasons:

  - While it does exercise x86's kvm_mmu_invalidate_mmio_sptes(), simply
    wrapping the generation doesn't actually test the interesting case
    of having stale MMIO sptes with the new generation number, e.g. old
    sptes with a generation number of 0.

  - Triggering kvm_mmu_invalidate_mmio_sptes() prematurely makes its
    performance rather important since the probability of invalidating
    MMIO sptes jumps from "effectively never" to "fairly likely".  This
    limits what can be done in future patches, e.g. to simplify the
    invalidation code, as doing so without proper caution could lead to
    a noticeable performance regression.

  - Forcing the memslots generation, which is a 64-bit number, to wrap
    prevents KVM from assuming the memslots generation will never wrap.
    This in turn prevents KVM from using an arbitrary bit for the
    "update in-progress" flag, e.g. using bit 63 would immediately
    collide with using a large value as the starting generation number.
    The "update in-progress" flag is effectively forced into bit 0 so
    that it's (subtly) taken into account when incrementing the
    generation.
Signed-off-by: NSean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

KVM uses bit 0 of the memslots generation as an "update in-progress"
flag, which is used by x86 to prevent caching MMIO access while the
memslots are changing.  Although the intended behavior is flag-like,
e.g. MMIO sptes intentionally drop the in-progress bit so as to avoid
caching data from in-flux memslots, the implementation oftentimes treats
the bit as part of the generation number itself, e.g. incrementing the
generation increments twice, once to set the flag and once to clear it.

Prior to commit 4bd518f1 ("KVM: use separate generations for
each address space"), incorporating the "update in-progress" bit into
the generation number largely made sense, e.g. "real" generations are
even, "bogus" generations are odd, most code doesn't need to be aware of
the bit, etc...

Now that unique memslots generation numbers are assigned to each address
space, stealthing the in-progress status into the generation number
results in a wide variety of subtle code, e.g. kvm_create_vm() jumps
over bit 0 when initializing the memslots generation without any hint as
to why.

Explicitly define the flag and convert as much code as possible (which
isn't much) to actually treat it like a flag.  This paves the way for
eventually using a different bit for "update in-progress" so that it can
be a flag in truth instead of a awkward extension to the generation
number.
Signed-off-by: NSean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

kvm_arch_memslots_updated() is at this point in time an x86-specific
hook for handling MMIO generation wraparound.  x86 stashes 19 bits of
the memslots generation number in its MMIO sptes in order to avoid
full page fault walks for repeat faults on emulated MMIO addresses.
Because only 19 bits are used, wrapping the MMIO generation number is
possible, if unlikely.  kvm_arch_memslots_updated() alerts x86 that
the generation has changed so that it can invalidate all MMIO sptes in
case the effective MMIO generation has wrapped so as to avoid using a
stale spte, e.g. a (very) old spte that was created with generation==0.

Given that the purpose of kvm_arch_memslots_updated() is to prevent
consuming stale entries, it needs to be called before the new generation
is propagated to memslots.  Invalidating the MMIO sptes after updating
memslots means that there is a window where a vCPU could dereference
the new memslots generation, e.g. 0, and incorrectly reuse an old MMIO
spte that was created with (pre-wrap) generation==0.

Fixes: e59dbe09 ("KVM: Introduce kvm_arch_memslots_updated()")
Cc: <stable@vger.kernel.org>
Signed-off-by: NSean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

There are many KVM kernel memory allocations which are tied to the life of
the VM process and should be charged to the VM process's cgroup. If the
allocations aren't tied to the process, the OOM killer will not know
that killing the process will free the associated kernel memory.
Add __GFP_ACCOUNT flags to many of the allocations which are not yet being
charged to the VM process's cgroup.

Tested:
	Ran all kvm-unit-tests on a 64 bit Haswell machine, the patch
	introduced no new failures.
	Ran a kernel memory accounting test which creates a VM to touch
	memory and then checks that the kernel memory allocated for the
	process is within certain bounds.
	With this patch we account for much more of the vmalloc and slab memory
	allocated for the VM.

There remain a few allocations which should be charged to the VM's
cgroup but are not. In they include:
        vcpu->run
        kvm->coalesced_mmio_ring
There allocations are unaccounted in this patch because they are mapped
to userspace, and accounting them to a cgroup causes problems. This
should be addressed in a future patch.
Signed-off-by: NBen Gardon <bgardon@google.com>
Reviewed-by: NShakeel Butt <shakeelb@google.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

One of the more common cases of allocation size calculations is finding
the size of a structure that has a zero-sized array at the end, along
with memory for some number of elements for that array. For example:

struct foo {
    int stuff;
    void *entry[];
};

instance = kmalloc(sizeof(struct foo) + sizeof(void *) * count, GFP_KERNEL);

Instead of leaving these open-coded and prone to type mistakes, we can
now use the new struct_size() helper:

instance = kmalloc(struct_size(instance, entry, count), GFP_KERNEL);

This code was detected with the help of Coccinelle.
Signed-off-by: NGustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

The 'gpa_end' local variable is never used and let's remove it.

Cc: Christoffer Dall <christoffer.dall@arm.com>
Signed-off-by: NShaokun Zhang <zhangshaokun@hisilicon.com>
Signed-off-by: NMarc Zyngier <marc.zyngier@arm.com>

There is a spelling mistake in a kvm_err error message. Fix it.
Signed-off-by: NColin Ian King <colin.king@canonical.com>
Signed-off-by: NMarc Zyngier <marc.zyngier@arm.com>

As the comment block in include/trace/define_trace.h says,
TRACE_INCLUDE_PATH should be a relative path to the define_trace.h

../../virt/kvm/arm is the correct relative path.

../../../virt/kvm/arm is working by coincidence because the top
Makefile adds -I$(srctree)/arch/$(SRCARCH)/include as a header
search path, but we should not rely on it.
Acked-by: NChristoffer Dall <christoffer.dall@arm.com>
Signed-off-by: NMasahiro Yamada <yamada.masahiro@socionext.com>
Signed-off-by: NMarc Zyngier <marc.zyngier@arm.com>

When a guest gets scheduled, KVM performs a "load" operation,
which for the timer includes evaluating the virtual "active" state
of the interrupt, and replicating it on the physical side. This
ensures that the deactivation in the guest will also take place
in the physical GIC distributor.

If the interrupt is not yet active, we flag it as inactive on the
physical side.  This means that on restoring the timer registers,
if the timer has expired, we'll immediately take an interrupt.
That's absolutely fine, as the interrupt will then be flagged as
active on the physical side. What this assumes though is that we'll
enter the guest right after having taken the interrupt, and that
the guest will quickly ACK the interrupt, making it active at on
the virtual side.

It turns out that quite often, this assumption doesn't really hold.
The guest may be preempted on the back on this interrupt, either
from kernel space or whilst running at EL1 when a host interrupt
fires. When this happens, we repeat the whole sequence on the
next load (interrupt marked as inactive, timer registers restored,
interrupt fires). And if it takes a really long time for a guest
to activate the interrupt (as it does with nested virt), we end-up
with many such events in quick succession, leading to the guest only
making very slow progress.

This can also be seen with the number of virtual timer interrupt on the
host being far greater than the same number in the guest.

An easy way to fix this is to evaluate the timer state when performing
the "load" operation, just like we do when the interrupt actually fires.
If the timer has a pending virtual interrupt at this stage, then we
can safely flag the physical interrupt as being active, which prevents
spurious exits.
Signed-off-by: NMarc Zyngier <marc.zyngier@arm.com>

Move this little function to the header files for arm/arm64 so other
code can make use of it directly.
Signed-off-by: NChristoffer Dall <christoffer.dall@arm.com>
Signed-off-by: NMarc Zyngier <marc.zyngier@arm.com>

We are currently emulating two timers in two different ways.  When we
add support for nested virtualization in the future, we are going to be
emulating either two timers in two diffferent ways, or four timers in a
single way.

We need a unified data structure to keep track of how we map virtual
state to physical state and we need to cleanup some of the timer code to
operate more independently on a struct arch_timer_context instead of
trying to consider the global state of the VCPU and recomputing all
state.

Co-written with Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: NMarc Zyngier <marc.zyngier@arm.com>
Signed-off-by: NChristoffer Dall <christoffer.dall@arm.com>

VHE systems don't have to emulate the physical timer, we can simply
assign the EL1 physical timer directly to the VM as the host always
uses the EL2 timers.

In order to minimize the amount of cruft, AArch32 gets definitions for
the physical timer too, but is should be generally unused on this
architecture.

Co-written with Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: NMarc Zyngier <marc.zyngier@arm.com>
Signed-off-by: NChristoffer Dall <christoffer.dall@arm.com>

Prepare for having 4 timer data structures (2 for now).

Move loaded to the cpu data structure and not the individual timer
structure, in preparation for assigning the EL1 phys timer as well.
Signed-off-by: NChristoffer Dall <christoffer.dall@arm.com>
Signed-off-by: NMarc Zyngier <marc.zyngier@arm.com>

At the moment we have separate system register emulation handlers for
each timer register. Actually they are quite similar, and we rely on
kvm_arm_timer_[gs]et_reg() for the actual emulation anyways, so let's
just merge all of those handlers into one function, which just marshalls
the arguments and then hands off to a set of common accessors.
This makes extending the emulation to include EL2 timers much easier.
Signed-off-by: NAndre Przywara <andre.przywara@arm.com>
[Fixed 32-bit VM breakage and reduced to reworking existing code]
Signed-off-by: NChristoffer Dall <christoffer.dall@arm.com>
[Fixed 32bit host, general cleanup]
Signed-off-by: NMarc Zyngier <marc.zyngier@arm.com>

We previously incorrectly named the define for this system register.
Signed-off-by: NMarc Zyngier <marc.zyngier@arm.com>
Signed-off-by: NChristoffer Dall <christoffer.dall@arm.com>

Instead of calling into kvm_timer_[un]schedule from the main kvm
blocking path, test if the VCPU is on the wait queue from the load/put
path and perform the background timer setup/cancel in this path.

This has the distinct advantage that we no longer race between load/put
and schedule/unschedule and programming and canceling of the bg_timer
always happens when the timer state is not loaded.

Note that we must now remove the checks in kvm_timer_blocking that do
not schedule a background timer if one of the timers can fire, because
we no longer have a guarantee that kvm_vcpu_check_block() will be called
before kvm_timer_blocking.
Reported-by: NAndre Przywara <andre.przywara@arm.com>
Signed-off-by: NChristoffer Dall <christoffer.dall@arm.com>
Signed-off-by: NMarc Zyngier <marc.zyngier@arm.com>

In preparation for nested virtualization where we are going to have more
than a single VMID per VM, let's factor out the VMID data into a
separate VMID data structure and change the VMID allocator to operate on
this new structure instead of using a struct kvm.

This also means that udate_vttbr now becomes update_vmid, and that the
vttbr itself is generated on the fly based on the stage 2 page table
base address and the vmid.

We cache the physical address of the pgd when allocating the pgd to
avoid doing the calculation on every entry to the guest and to avoid
calling into potentially non-hyp-mapped code from hyp/EL2.

If we wanted to merge the VMID allocator with the arm64 ASID allocator
at some point in the future, it should actually become easier to do that
after this patch.

Note that to avoid mapping the kvm_vmid_bits variable into hyp, we
simply forego the masking of the vmid value in kvm_get_vttbr and rely on
update_vmid to always assign a valid vmid value (within the supported
range).
Reviewed-by: NMarc Zyngier <marc.zyngier@arm.com>
[maz: minor cleanups]
Reviewed-by: NJulien Thierry <julien.thierry@arm.com>
Signed-off-by: NChristoffer Dall <christoffer.dall@arm.com>
Signed-off-by: NMarc Zyngier <marc.zyngier@arm.com>

We currently eagerly save/restore MPIDR. It turns out to be
slightly pointless:
- On the host, this value is known as soon as we're scheduled on a
  physical CPU
- In the guest, this value cannot change, as it is set by KVM
  (and this is a read-only register)

The result of the above is that we can perfectly avoid the eager
saving of MPIDR_EL1, and only keep the restore. We just have
to setup the host contexts appropriately at boot time.
Signed-off-by: NMarc Zyngier <marc.zyngier@arm.com>
Acked-by: NChristoffer Dall <christoffer.dall@arm.com>
Signed-off-by: NChristoffer Dall <christoffer.dall@arm.com>

Until now, we haven't differentiated between HYP calls that
have a return value and those who don't. As we're about to
change this, introduce kvm_call_hyp_ret(), and change all
call sites that actually make use of a return value.
Signed-off-by: NMarc Zyngier <marc.zyngier@arm.com>
Acked-by: NChristoffer Dall <christoffer.dall@arm.com>
Signed-off-by: NChristoffer Dall <christoffer.dall@arm.com>

To split up APEIs in_nmi() path, the caller needs to always be
in_nmi(). KVM shouldn't have to know about this, pull the RAS plumbing
out into a header file.

Currently guest synchronous external aborts are claimed as RAS
notifications by handle_guest_sea(), which is hidden in the arch codes
mm/fault.c. 32bit gets a dummy declaration in system_misc.h.

There is going to be more of this in the future if/when the kernel
supports the SError-based firmware-first notification mechanism and/or
kernel-first notifications for both synchronous external abort and
SError. Each of these will come with some Kconfig symbols and a
handful of header files.

Create a header file for all this.

This patch gives handle_guest_sea() a 'kvm_' prefix, and moves the
declarations to kvm_ras.h as preparation for a future patch that moves
the ACPI-specific RAS code out of mm/fault.c.
Signed-off-by: NJames Morse <james.morse@arm.com>
Reviewed-by: NPunit Agrawal <punit.agrawal@arm.com>
Acked-by: NMarc Zyngier <marc.zyngier@arm.com>
Tested-by: NTyler Baicar <tbaicar@codeaurora.org>
Acked-by: NCatalin Marinas <catalin.marinas@arm.com>
Signed-off-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>

kvm_ioctl_create_device() does the following:

1. creates a device that holds a reference to the VM object (with a borrowed
   reference, the VM's refcount has not been bumped yet)
2. initializes the device
3. transfers the reference to the device to the caller's file descriptor table
4. calls kvm_get_kvm() to turn the borrowed reference to the VM into a real
   reference

The ownership transfer in step 3 must not happen before the reference to the VM
becomes a proper, non-borrowed reference, which only happens in step 4.
After step 3, an attacker can close the file descriptor and drop the borrowed
reference, which can cause the refcount of the kvm object to drop to zero.

This means that we need to grab a reference for the device before
anon_inode_getfd(), otherwise the VM can disappear from under us.

Fixes: 852b6d57 ("kvm: add device control API")
Cc: stable@kernel.org
Signed-off-by: NJann Horn <jannh@google.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

We restrict mapping the PUD huge pages in stage2 to only when the
stage2 has 4 level page table, leaving the feature unused with
the default IPA size. But we could use it even with a 3
level page table, i.e, when the PUD level is folded into PGD,
just like the stage1. Relax the condition to allow using the
PUD huge page mappings at stage2 when it is possible.

Cc: Christoffer Dall <christoffer.dall@arm.com>
Reviewed-by: NMarc Zyngier <marc.zyngier@arm.com>
Signed-off-by: NSuzuki K Poulose <suzuki.poulose@arm.com>
Signed-off-by: NMarc Zyngier <marc.zyngier@arm.com>

We currently initialize the group of private IRQs during
kvm_vgic_vcpu_init, and the value of the group depends on the GIC model
we are emulating.  However, CPUs created before creating (and
initializing) the VGIC might end up with the wrong group if the VGIC
is created as GICv3 later.

Since we have no enforced ordering of creating the VGIC and creating
VCPUs, we can end up with part the VCPUs being properly intialized and
the remaining incorrectly initialized.  That also means that we have no
single place to do the per-cpu data structure initialization which
depends on knowing the emulated GIC model (which is only the group
field).

This patch removes the incorrect comment from kvm_vgic_vcpu_init and
initializes the group of all previously created VCPUs's private
interrupts in vgic_init in addition to the existing initialization in
kvm_vgic_vcpu_init.
Signed-off-by: NChristoffer Dall <christoffer.dall@arm.com>
Signed-off-by: NMarc Zyngier <marc.zyngier@arm.com>

The current kvm_psci_vcpu_on implementation will directly try to
manipulate the state of the VCPU to reset it.  However, since this is
not done on the thread that runs the VCPU, we can end up in a strangely
corrupted state when the source and target VCPUs are running at the same
time.

Fix this by factoring out all reset logic from the PSCI implementation
and forwarding the required information along with a request to the
target VCPU.
Reviewed-by: NAndrew Jones <drjones@redhat.com>
Signed-off-by: NMarc Zyngier <marc.zyngier@arm.com>
Signed-off-by: NChristoffer Dall <christoffer.dall@arm.com>

lockdep_assert_held() is better suited to checking locking requirements,
since it only checks if the current thread holds the lock regardless of
whether someone else does. This is also a step towards possibly removing
spin_is_locked().
Signed-off-by: NPaul E. McKenney <paulmck@linux.ibm.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: "Radim Krčmář" <rkrcmar@redhat.com>
Cc: <kvm@vger.kernel.org>
Acked-by: NPaolo Bonzini <pbonzini@redhat.com>

vgic_cpu->ap_list_lock must always be taken with interrupts disabled as
it is used in interrupt context.

For configurations such as PREEMPT_RT_FULL, this means that it should
be a raw_spinlock since RT spinlocks are interruptible.
Signed-off-by: NJulien Thierry <julien.thierry@arm.com>
Acked-by: NChristoffer Dall <christoffer.dall@arm.com>
Acked-by: NMarc Zyngier <marc.zyngier@arm.com>
Signed-off-by: NChristoffer Dall <christoffer.dall@arm.com>

vgic_dist->lpi_list_lock must always be taken with interrupts disabled as
it is used in interrupt context.

For configurations such as PREEMPT_RT_FULL, this means that it should
be a raw_spinlock since RT spinlocks are interruptible.
Signed-off-by: NJulien Thierry <julien.thierry@arm.com>
Acked-by: NChristoffer Dall <christoffer.dall@arm.com>
Acked-by: NMarc Zyngier <marc.zyngier@arm.com>
Signed-off-by: NChristoffer Dall <christoffer.dall@arm.com>

vgic_irq->irq_lock must always be taken with interrupts disabled as
it is used in interrupt context.

For configurations such as PREEMPT_RT_FULL, this means that it should
be a raw_spinlock since RT spinlocks are interruptible.
Signed-off-by: NJulien Thierry <julien.thierry@arm.com>
Acked-by: NChristoffer Dall <christoffer.dall@arm.com>
Acked-by: NMarc Zyngier <marc.zyngier@arm.com>
Signed-off-by: NChristoffer Dall <christoffer.dall@arm.com>