Refactor PMU overflow handling in order to remove the request-less
vcpu kick. Now, since kvm_vgic_inject_irq() uses vcpu requests,
there should be no chance that a kick sent at just the wrong time
(between the VCPU's call to kvm_pmu_flush_hwstate() and before it
enters guest mode) results in a failure for the guest to see updated
GIC state until its next exit some time later for some other reason.
Signed-off-by: Andrew Jones <drjones@redhat.com>
Reviewed-by: Christoffer Dall <cdall@linaro.org>
Signed-off-by: Christoffer Dall <cdall@linaro.org>
Don't use request-less VCPU kicks when injecting IRQs, as a VCPU
kick meant to trigger the interrupt injection could be sent while
the VCPU is outside guest mode, which means no IPI is sent, and
after it has called kvm_vgic_flush_hwstate(), meaning it won't see
the updated GIC state until its next exit some time later for some
other reason. The receiving VCPU only needs to check this request
in VCPU RUN to handle it. By checking it, if it's pending, a
memory barrier will be issued that ensures all state is visible.
See "Ensuring Requests Are Seen" of
Documentation/virtual/kvm/vcpu-requests.rst
Signed-off-by: Andrew Jones <drjones@redhat.com>
Reviewed-by: Christoffer Dall <cdall@linaro.org>
Signed-off-by: Christoffer Dall <cdall@linaro.org>
A request called EXIT is too generic. All requests are meant to cause
exits, but different requests have different flags. Let's not make
it difficult to decide if the EXIT request is correct for some case
by just always providing unique requests for each case. This patch
changes EXIT to SLEEP, because that's what the request is asking the
VCPU to do.
Signed-off-by: Andrew Jones <drjones@redhat.com>
Acked-by: Christoffer Dall <cdall@linaro.org>
Signed-off-by: Christoffer Dall <cdall@linaro.org>
We can make a small optimization by not checking the state of
the power_off field on each run. This is done by treating
power_off like pause, only checking it when we get the EXIT
VCPU request. When a VCPU powers off another VCPU the EXIT
request is already made, so we just need to make sure the
request is also made on self power off. kvm_vcpu_kick() isn't
necessary for these cases, as the VCPU would just be kicking
itself, but we add it anyway as a self kick doesn't cost much,
and it makes the code more future-proof.
Signed-off-by: Andrew Jones <drjones@redhat.com>
Reviewed-by: Christoffer Dall <cdall@linaro.org>
Signed-off-by: Christoffer Dall <cdall@linaro.org>
System shutdown is currently using request-less VCPU kicks. This
leaves open a tiny race window, as it doesn't ensure the state
change to power_off is seen by a VCPU just about to enter guest
mode. VCPU requests, OTOH, are guaranteed to be seen (see "Ensuring
Requests Are Seen" of Documentation/virtual/kvm/vcpu-requests.rst)
This patch applies the EXIT request used by pause to power_off,
fixing the race.
Signed-off-by: Andrew Jones <drjones@redhat.com>
Reviewed-by: Christoffer Dall <cdall@linaro.org>
Signed-off-by: Christoffer Dall <cdall@linaro.org>
The current use of KVM_REQ_VCPU_EXIT for pause is fine. Even the
requester clearing the request is OK, as this is the special case
where the sole requesting thread and receiving VCPU are executing
synchronously (see "Clearing Requests" in
Documentation/virtual/kvm/vcpu-requests.rst) However, that's about
to change, so let's ensure only the receiving VCPU clears the
request. Additionally, by guaranteeing KVM_REQ_VCPU_EXIT is always
set when pause is, we can avoid checking pause directly in VCPU RUN.
Signed-off-by: Andrew Jones <drjones@redhat.com>
Reviewed-by: Christoffer Dall <cdall@linaro.org>
Signed-off-by: Christoffer Dall <cdall@linaro.org>
arm/arm64 already has one VCPU request used when setting pause,
but it doesn't properly check requests in VCPU RUN. Check it
and also make sure we set vcpu->mode at the appropriate time
(before the check) and with the appropriate barriers. See
Documentation/virtual/kvm/vcpu-requests.rst. Also make sure we
don't leave any vcpu requests we don't intend to handle later
set in the request bitmap. If we don't clear them, then
kvm_request_pending() may return true when it shouldn't.
Using VCPU requests properly fixes a small race where pause
could get set just as a VCPU was entering guest mode.
Signed-off-by: Andrew Jones <drjones@redhat.com>
Reviewed-by: Christoffer Dall <cdall@linaro.org>
Signed-off-by: Christoffer Dall <cdall@linaro.org>
We recently rewrote the sactive and cactive handlers to take the kvm
lock for guest accesses to these registers. However, when accessed from
userspace this lock is already held. Unfortunately we forgot to change
the private accessors for GICv3, because these are redistributor
registers and not distributor registers.
Signed-off-by: Christoffer Dall <cdall@linaro.org>
We have been a little loose with our intermediate VMCR representation
where we had a 'ctlr' field, but we failed to differentiate between the
GICv2 GICC_CTLR and ICC_CTLR_EL1 layouts, and therefore ended up mapping
the wrong bits into the individual fields of the ICH_VMCR_EL2 when
emulating a GICv2 on a GICv3 system.
Fix this by using explicit fields for the VMCR bits instead.
Cc: Eric Auger <eric.auger@redhat.com>
Reported-by: wanghaibin <wanghaibin.wang@huawei.com>
Signed-off-by: Christoffer Dall <cdall@linaro.org>
Reviewed-by: Marc Zyngier <marc.zyngier@arm.com>
Tested-by: Marc Zyngier <marc.zyngier@arm.com>
We don't need to stop a specific VCPU when changing the active state,
because private IRQs can only be modified by a running VCPU for the
VCPU itself and it is therefore already stopped.
However, it is also possible for two VCPUs to be modifying the active
state of SPIs at the same time, which can cause the thread being stuck
in the loop that checks other VCPU threads for a potentially very long
time, or to modify the active state of a running VCPU. Fix this by
serializing all accesses to setting and clearing the active state of
interrupts using the KVM mutex.
Reported-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: Christoffer Dall <cdall@linaro.org>
Reviewed-by: Marc Zyngier <marc.zyngier@arm.com>
Factor out the core register modifier functionality from the entry
points from the register description table, and only call the
prepare/finish functions from the guest path, not the uaccess path.
Signed-off-by: Christoffer Dall <cdall@linaro.org>
Reviewed-by: Marc Zyngier <marc.zyngier@arm.com>
We are about to differentiate between writes from a VCPU and from
userspace to the GIC's GICD_ISACTIVER and GICD_ICACTIVER registers due
to different synchronization requirements.
Expand the macro to define a register description for the GIC to take
uaccess functions as well.
Signed-off-by: Christoffer Dall <cdall@linaro.org>
Acked-by: Marc Zyngier <marc.zyngier@arm.com>
We were not holding the kvm->slots_lock as required when calling
kvm_io_bus_unregister_dev() as required.
This only affects the error path, but still, let's do our due
diligence.
Reported by: Eric Auger <eric.auger@redhat.com>
Signed-off-by: Christoffer Dall <cdall@linaro.org>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
If userspace creates the VCPUs after initializing the VGIC, then we end
up in a situation where we trigger a bug in kvm_vcpu_get_idx(), because
it is called prior to adding the VCPU into the vcpus array on the VM.
There is no tight coupling between the VCPU index and the area of the
redistributor region used for the VCPU, so we can simply ensure that all
creations of redistributors are serialized per VM, and increment an
offset when we successfully add a redistributor.
The vgic_register_redist_iodev() function can be called from two paths:
vgic_redister_all_redist_iodev() which is called via the kvm_vgic_addr()
device attribute handler. This patch already holds the kvm->lock mutex.
The other path is via kvm_vgic_vcpu_init, which is called through a
longer chain from kvm_vm_ioctl_create_vcpu(), which releases the
kvm->lock mutex just before calling kvm_arch_vcpu_create(), so we can
simply take this mutex again later for our purposes.
Fixes: ab6f468c10 ("KVM: arm/arm64: Register iodevs when setting redist base and creating VCPUs")
Signed-off-by: Christoffer Dall <cdall@linaro.org>
Tested-by: Jean-Philippe Brucker <jean-philippe.brucker@arm.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
We yield the kvm->mmu_lock occassionaly while performing an operation
(e.g, unmap or permission changes) on a large area of stage2 mappings.
However this could possibly cause another thread to clear and free up
the stage2 page tables while we were waiting for regaining the lock and
thus the original thread could end up in accessing memory that was
freed. This patch fixes the problem by making sure that the stage2
pagetable is still valid after we regain the lock. The fact that
mmu_notifer->release() could be called twice (via __mmu_notifier_release
and mmu_notifier_unregsister) enhances the possibility of hitting
this race where there are two threads trying to unmap the entire guest
shadow pages.
While at it, cleanup the redudant checks around cond_resched_lock in
stage2_wp_range(), as cond_resched_lock already does the same checks.
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Cc: andreyknvl@google.com
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: stable@vger.kernel.org
Acked-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Reviewed-by: Christoffer Dall <cdall@linaro.org>
Signed-off-by: Christoffer Dall <cdall@linaro.org>
Make sure we don't use a cached value of the KVM stage2 PGD while
resetting the PGD.
Cc: Marc Zyngier <marc.zyngier@arm.com>
Cc: stable@vger.kernel.org
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Reviewed-by: Christoffer Dall <cdall@linaro.org>
Signed-off-by: Christoffer Dall <cdall@linaro.org>
In kvm_free_stage2_pgd() we check the stage2 PGD before holding
the lock and proceed to take the lock if it is valid. And we unmap
the page tables, followed by releasing the lock. We reset the PGD
only after dropping this lock, which could cause a race condition
where another thread waiting on or even holding the lock, could
potentially see that the PGD is still valid and proceed to perform
a stage2 operation and later encounter a NULL PGD.
[223090.242280] Unable to handle kernel NULL pointer dereference at
virtual address 00000040
[223090.262330] PC is at unmap_stage2_range+0x8c/0x428
[223090.262332] LR is at kvm_unmap_hva_handler+0x2c/0x3c
[223090.262531] Call trace:
[223090.262533] [<ffff0000080adb78>] unmap_stage2_range+0x8c/0x428
[223090.262535] [<ffff0000080adf40>] kvm_unmap_hva_handler+0x2c/0x3c
[223090.262537] [<ffff0000080ace2c>] handle_hva_to_gpa+0xb0/0x104
[223090.262539] [<ffff0000080af988>] kvm_unmap_hva+0x5c/0xbc
[223090.262543] [<ffff0000080a2478>]
kvm_mmu_notifier_invalidate_page+0x50/0x8c
[223090.262547] [<ffff0000082274f8>]
__mmu_notifier_invalidate_page+0x5c/0x84
[223090.262551] [<ffff00000820b700>] try_to_unmap_one+0x1d0/0x4a0
[223090.262553] [<ffff00000820c5c8>] rmap_walk+0x1cc/0x2e0
[223090.262555] [<ffff00000820c90c>] try_to_unmap+0x74/0xa4
[223090.262557] [<ffff000008230ce4>] migrate_pages+0x31c/0x5ac
[223090.262561] [<ffff0000081f869c>] compact_zone+0x3fc/0x7ac
[223090.262563] [<ffff0000081f8ae0>] compact_zone_order+0x94/0xb0
[223090.262564] [<ffff0000081f91c0>] try_to_compact_pages+0x108/0x290
[223090.262569] [<ffff0000081d5108>] __alloc_pages_direct_compact+0x70/0x1ac
[223090.262571] [<ffff0000081d64a0>] __alloc_pages_nodemask+0x434/0x9f4
[223090.262572] [<ffff0000082256f0>] alloc_pages_vma+0x230/0x254
[223090.262574] [<ffff000008235e5c>] do_huge_pmd_anonymous_page+0x114/0x538
[223090.262576] [<ffff000008201bec>] handle_mm_fault+0xd40/0x17a4
[223090.262577] [<ffff0000081fb324>] __get_user_pages+0x12c/0x36c
[223090.262578] [<ffff0000081fb804>] get_user_pages_unlocked+0xa4/0x1b8
[223090.262579] [<ffff0000080a3ce8>] __gfn_to_pfn_memslot+0x280/0x31c
[223090.262580] [<ffff0000080a3dd0>] gfn_to_pfn_prot+0x4c/0x5c
[223090.262582] [<ffff0000080af3f8>] kvm_handle_guest_abort+0x240/0x774
[223090.262584] [<ffff0000080b2bac>] handle_exit+0x11c/0x1ac
[223090.262586] [<ffff0000080ab99c>] kvm_arch_vcpu_ioctl_run+0x31c/0x648
[223090.262587] [<ffff0000080a1d78>] kvm_vcpu_ioctl+0x378/0x768
[223090.262590] [<ffff00000825df5c>] do_vfs_ioctl+0x324/0x5a4
[223090.262591] [<ffff00000825e26c>] SyS_ioctl+0x90/0xa4
[223090.262595] [<ffff000008085d84>] el0_svc_naked+0x38/0x3c
This patch moves the stage2 PGD manipulation under the lock.
Reported-by: Alexander Graf <agraf@suse.de>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Marc Zyngier <marc.zyngier@arm.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Reviewed-by: Christoffer Dall <cdall@linaro.org>
Reviewed-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Signed-off-by: Christoffer Dall <cdall@linaro.org>
The GICv3 documentation is extremely confusing, as it talks about
the number of priorities represented by the ICH_APxRn_EL2 registers,
while it should really talk about the number of preemption levels.
This leads to a bug where we may access undefined ICH_APxRn_EL2
registers, since PREbits is allowed to be smaller than PRIbits.
Thankfully, nobody seem to have taken this path so far...
The fix is to use ICH_VTR_EL2.PREbits instead.
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Reviewed-by: Christoffer Dall <cdall@linaro.org>
Signed-off-by: Christoffer Dall <cdall@linaro.org>
When an interrupt is injected with the HW bit set (indicating that
deactivation should be propagated to the physical distributor),
special care must be taken so that we never mark the corresponding
LR with the Active+Pending state (as the pending state is kept in
the physycal distributor).
Cc: stable@vger.kernel.org
Fixes: 59529f69f5 ("KVM: arm/arm64: vgic-new: Add GICv3 world switch backend")
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Reviewed-by: Christoffer Dall <cdall@linaro.org>
Signed-off-by: Christoffer Dall <cdall@linaro.org>
When an interrupt is injected with the HW bit set (indicating that
deactivation should be propagated to the physical distributor),
special care must be taken so that we never mark the corresponding
LR with the Active+Pending state (as the pending state is kept in
the physycal distributor).
Cc: stable@vger.kernel.org
Fixes: 140b086dd1 ("KVM: arm/arm64: vgic-new: Add GICv2 world switch backend")
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Reviewed-by: Christoffer Dall <cdall@linaro.org>
Signed-off-by: Christoffer Dall <cdall@linaro.org>
Changes include:
- A fix related to the 32-bit idmap stub
- A fix to the bitmask used to deode the operands of an AArch32 CP
instruction
- We have moved the files shared between arch/arm/kvm and
arch/arm64/kvm to virt/kvm/arm
- We add support for saving/restoring the virtual ITS state to
userspace
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1
iQEcBAABAgAGBQJZEZihAAoJEEtpOizt6ddyGDYH/jmGjDMnryORn2P2o10dUQKJ
RnHTQYnpOYqnprlkFtZFpmK+mjl/a8R1Btb7GK2EwmovTR95pMYPRqtrCTOL0aQA
4OToh7+vFGatwxsGCS6utazdhmx0UT/LhO/GEF4G1zOb7eVa4ZtS1NKLP2WjPD1E
RU3Qn8wa0pESv3tJScv8qo2+PWVX4krbFllhY2Hk0AkVQcI66ExkdVq4ikm1eUXn
rxzIayLG2bv3KEPNCzozdwoY9tDL+b40q6vN/RHGJmM05SZbbSx2/Bkw2RbslSpD
2hvhHWX7xeuEBcd5mZO7sP4WS3hM/BI8eX7q+uMeNJ9B+nM82yjGfOTtglVi2cc=
=JfvQ
-----END PGP SIGNATURE-----
Merge tag 'kvm-arm-for-v4.12-round2' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD
Second round of KVM/ARM Changes for v4.12.
Changes include:
- A fix related to the 32-bit idmap stub
- A fix to the bitmask used to deode the operands of an AArch32 CP
instruction
- We have moved the files shared between arch/arm/kvm and
arch/arm64/kvm to virt/kvm/arm
- We add support for saving/restoring the virtual ITS state to
userspace
When failing to restore the ITT for a DTE, we should remove the failed
device entry from the list and free the object.
We slightly refactor vgic_its_destroy to be able to reuse the now
separate vgic_its_free_dte() function.
Signed-off-by: Christoffer Dall <cdall@linaro.org>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
The only reason we called kvm_vgic_map_resources() when restoring the
ITS tables was because we wanted to have the KVM iodevs registered in
the KVM IO bus framework at the time when the ITS was restored such that
a restored and active device can inject MSIs prior to otherwise calling
kvm_vgic_map_resources() from the first run of a VCPU.
Since we now register the KVM iodevs for the redestributors and ITS as
soon as possible (when setting the base addresses), we no longer need
this call and kvm_vgic_map_resources() is again called only when first
running a VCPU.
Signed-off-by: Christoffer Dall <cdall@linaro.org>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
We have to register the ITS iodevice before running the VM, because in
migration scenarios, we may be restoring a live device that wishes to
inject MSIs before the VCPUs have started.
All we need to register the ITS io device is the base address of the
ITS, so we can simply register that when the base address of the ITS is
set.
[ Code to fix concurrency issues when setting the ITS base address and
to fix the undef base address check written by Marc Zyngier ]
Signed-off-by: Christoffer Dall <cdall@linaro.org>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
The its->initialized doesn't bring much to the table, and creates
unnecessary ordering between setting the address and initializing it
(which amounts to exactly nothing).
Let's kill it altogether, making KVM_DEV_ARM_VGIC_CTRL_INIT the no-op
it deserves to be.
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Christoffer Dall <cdall@linaro.org>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Instead of waiting with registering KVM iodevs until the first VCPU is
run, we can actually create the iodevs when the redist base address is
set. The only downside is that we must now also check if we need to do
this for VCPUs which are created after creating the VGIC, because there
is no enforced ordering between creating the VGIC (and setting its base
addresses) and creating the VCPUs.
Signed-off-by: Christoffer Dall <cdall@linaro.org>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
As we are about to handle setting the address for the redistributor base
region separately from some of the other base addresses, let's rework
this function to leave a little more room for being flexible in what
each type of base address does.
Signed-off-by: Christoffer Dall <cdall@linaro.org>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
As we are about to fiddle with the IO device registration mechanism,
let's be a little more careful when setting base addresses as early as
possible. When setting a base address, we can check that there's
address space enough for its scope and when the last of the two
base addresses (dist and redist) get set, we can also check if the
regions overlap at that time.
This allows us to provide error messages to the user at time when trying
to set the base address, as opposed to later when trying to run the VM.
To do this, we make vgic_v3_check_base available in the core vgic-v3
code as well as in the other parts of the GICv3 code, namely the MMIO
config code.
We also return true for undefined base addresses so that the function
can be used before all base addresses are set; all callers already check
for uninitialized addresses before calling this function.
Signed-off-by: Christoffer Dall <cdall@linaro.org>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Split out the function to register all the redistributor iodevs into a
function that handles a single redistributor at a time in preparation
for being able to call this per VCPU as these get created.
Signed-off-by: Christoffer Dall <cdall@linaro.org>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
The main thing here is a new implementation of the in-kernel
XICS interrupt controller emulation for POWER9 machines, from Ben
Herrenschmidt.
POWER9 has a new interrupt controller called XIVE (eXternal Interrupt
Virtualization Engine) which is able to deliver interrupts directly
to guest virtual CPUs in hardware without hypervisor intervention.
With this new code, the guest still sees the old XICS interface but
performance is better because the XICS emulation in the host uses the
XIVE directly rather than going through a XICS emulation in firmware.
Conflicts:
arch/powerpc/kernel/cpu_setup_power.S [cherry-picked fix]
arch/powerpc/kvm/book3s_xive.c [include asm/debugfs.h]
In vm_stat_get_per_vm_fops and vcpu_stat_get_per_vm_fops, since we
use nonseekable_open() to open, we should use no_llseek() to seek,
not generic_file_llseek().
Signed-off-by: Geliang Tang <geliangtang@gmail.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
This function really doesn't init anything, it enables the CPU
interface, so name it as such, which gives us the name to use for actual
init work later on.
Signed-off-by: Christoffer Dall <cdall@linaro.org>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Merge more updates from Andrew Morton:
- the rest of MM
- various misc things
- procfs updates
- lib/ updates
- checkpatch updates
- kdump/kexec updates
- add kvmalloc helpers, use them
- time helper updates for Y2038 issues. We're almost ready to remove
current_fs_time() but that awaits a btrfs merge.
- add tracepoints to DAX
* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (114 commits)
drivers/staging/ccree/ssi_hash.c: fix build with gcc-4.4.4
selftests/vm: add a test for virtual address range mapping
dax: add tracepoint to dax_insert_mapping()
dax: add tracepoint to dax_writeback_one()
dax: add tracepoints to dax_writeback_mapping_range()
dax: add tracepoints to dax_load_hole()
dax: add tracepoints to dax_pfn_mkwrite()
dax: add tracepoints to dax_iomap_pte_fault()
mtd: nand: nandsim: convert to memalloc_noreclaim_*()
treewide: convert PF_MEMALLOC manipulations to new helpers
mm: introduce memalloc_noreclaim_{save,restore}
mm: prevent potential recursive reclaim due to clearing PF_MEMALLOC
mm/huge_memory.c: deposit a pgtable for DAX PMD faults when required
mm/huge_memory.c: use zap_deposited_table() more
time: delete CURRENT_TIME_SEC and CURRENT_TIME
gfs2: replace CURRENT_TIME with current_time
apparmorfs: replace CURRENT_TIME with current_time()
lustre: replace CURRENT_TIME macro
fs: ubifs: replace CURRENT_TIME_SEC with current_time
fs: ufs: use ktime_get_real_ts64() for birthtime
...
Patch series "kvmalloc", v5.
There are many open coded kmalloc with vmalloc fallback instances in the
tree. Most of them are not careful enough or simply do not care about
the underlying semantic of the kmalloc/page allocator which means that
a) some vmalloc fallbacks are basically unreachable because the kmalloc
part will keep retrying until it succeeds b) the page allocator can
invoke a really disruptive steps like the OOM killer to move forward
which doesn't sound appropriate when we consider that the vmalloc
fallback is available.
As it can be seen implementing kvmalloc requires quite an intimate
knowledge if the page allocator and the memory reclaim internals which
strongly suggests that a helper should be implemented in the memory
subsystem proper.
Most callers, I could find, have been converted to use the helper
instead. This is patch 6. There are some more relying on __GFP_REPEAT
in the networking stack which I have converted as well and Eric Dumazet
was not opposed [2] to convert them as well.
[1] http://lkml.kernel.org/r/20170130094940.13546-1-mhocko@kernel.org
[2] http://lkml.kernel.org/r/1485273626.16328.301.camel@edumazet-glaptop3.roam.corp.google.com
This patch (of 9):
Using kmalloc with the vmalloc fallback for larger allocations is a
common pattern in the kernel code. Yet we do not have any common helper
for that and so users have invented their own helpers. Some of them are
really creative when doing so. Let's just add kv[mz]alloc and make sure
it is implemented properly. This implementation makes sure to not make
a large memory pressure for > PAGE_SZE requests (__GFP_NORETRY) and also
to not warn about allocation failures. This also rules out the OOM
killer as the vmalloc is a more approapriate fallback than a disruptive
user visible action.
This patch also changes some existing users and removes helpers which
are specific for them. In some cases this is not possible (e.g.
ext4_kvmalloc, libcfs_kvzalloc) because those seems to be broken and
require GFP_NO{FS,IO} context which is not vmalloc compatible in general
(note that the page table allocation is GFP_KERNEL). Those need to be
fixed separately.
While we are at it, document that __vmalloc{_node} about unsupported gfp
mask because there seems to be a lot of confusion out there.
kvmalloc_node will warn about GFP_KERNEL incompatible (which are not
superset) flags to catch new abusers. Existing ones would have to die
slowly.
[sfr@canb.auug.org.au: f2fs fixup]
Link: http://lkml.kernel.org/r/20170320163735.332e64b7@canb.auug.org.au
Link: http://lkml.kernel.org/r/20170306103032.2540-2-mhocko@kernel.org
Signed-off-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Reviewed-by: Andreas Dilger <adilger@dilger.ca> [ext4 part]
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: David Miller <davem@davemloft.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
support; virtual interrupt controller performance improvements; support
for userspace virtual interrupt controller (slower, but necessary for
KVM on the weird Broadcom SoCs used by the Raspberry Pi 3)
* MIPS: basic support for hardware virtualization (ImgTec
P5600/P6600/I6400 and Cavium Octeon III)
* PPC: in-kernel acceleration for VFIO
* s390: support for guests without storage keys; adapter interruption
suppression
* x86: usual range of nVMX improvements, notably nested EPT support for
accessed and dirty bits; emulation of CPL3 CPUID faulting
* generic: first part of VCPU thread request API; kvm_stat improvements
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2.0.22 (GNU/Linux)
iQEcBAABAgAGBQJZEHUkAAoJEL/70l94x66DBeYH/09wrpJ2FjU4Rqv7FxmqgWfH
9WGi4wvn/Z+XzQSyfMJiu2SfZVzU69/Y67OMHudy7vBT6knB+ziM7Ntoiu/hUfbG
0g5KsDX79FW15HuvuuGh9kSjUsj7qsQdyPZwP4FW/6ZoDArV9mibSvdjSmiUSMV/
2wxaoLzjoShdOuCe9EABaPhKK0XCrOYkygT6Paz1pItDxaSn8iW3ulaCuWMprUfG
Niq+dFemK464E4yn6HVD88xg5j2eUM6bfuXB3qR3eTR76mHLgtwejBzZdDjLG9fk
32PNYKhJNomBxHVqtksJ9/7cSR6iNPs7neQ1XHemKWTuYqwYQMlPj1NDy0aslQU=
=IsiZ
-----END PGP SIGNATURE-----
Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm
Pull KVM updates from Paolo Bonzini:
"ARM:
- HYP mode stub supports kexec/kdump on 32-bit
- improved PMU support
- virtual interrupt controller performance improvements
- support for userspace virtual interrupt controller (slower, but
necessary for KVM on the weird Broadcom SoCs used by the Raspberry
Pi 3)
MIPS:
- basic support for hardware virtualization (ImgTec P5600/P6600/I6400
and Cavium Octeon III)
PPC:
- in-kernel acceleration for VFIO
s390:
- support for guests without storage keys
- adapter interruption suppression
x86:
- usual range of nVMX improvements, notably nested EPT support for
accessed and dirty bits
- emulation of CPL3 CPUID faulting
generic:
- first part of VCPU thread request API
- kvm_stat improvements"
* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (227 commits)
kvm: nVMX: Don't validate disabled secondary controls
KVM: put back #ifndef CONFIG_S390 around kvm_vcpu_kick
Revert "KVM: Support vCPU-based gfn->hva cache"
tools/kvm: fix top level makefile
KVM: x86: don't hold kvm->lock in KVM_SET_GSI_ROUTING
KVM: Documentation: remove VM mmap documentation
kvm: nVMX: Remove superfluous VMX instruction fault checks
KVM: x86: fix emulation of RSM and IRET instructions
KVM: mark requests that need synchronization
KVM: return if kvm_vcpu_wake_up() did wake up the VCPU
KVM: add explicit barrier to kvm_vcpu_kick
KVM: perform a wake_up in kvm_make_all_cpus_request
KVM: mark requests that do not need a wakeup
KVM: remove #ifndef CONFIG_S390 around kvm_vcpu_wake_up
KVM: x86: always use kvm_make_request instead of set_bit
KVM: add kvm_{test,clear}_request to replace {test,clear}_bit
s390: kvm: Cpu model support for msa6, msa7 and msa8
KVM: x86: remove irq disablement around KVM_SET_CLOCK/KVM_GET_CLOCK
kvm: better MWAIT emulation for guests
KVM: x86: virtualize cpuid faulting
...
This patch adds a new attribute to GICV3 KVM device
KVM_DEV_ARM_VGIC_GRP_CTRL group. This allows userspace to
flush all GICR pending tables into guest RAM.
Signed-off-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Christoffer Dall <cdall@linaro.org>
Acked-by: Marc Zyngier <marc.zyngier@arm.com>
In its_sync_lpi_pending_table() we currently ignore the
target_vcpu of the LPIs. We sync the pending bit found in
the vcpu pending table even if the LPI is not targeting it.
Also in vgic_its_cmd_handle_invall() we are supposed to
read the config table data for the LPIs associated to the
collection ID. At the moment we refresh all LPI config
information.
This patch passes a vpcu to vgic_copy_lpi_list() so that
this latter returns a snapshot of the LPIs targeting this
CPU and only those.
Signed-off-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Christoffer Dall <cdall@linaro.org>
Acked-by: Marc Zyngier <marc.zyngier@arm.com>
Implement routines to save and restore device ITT and their
interrupt table entries (ITE).
Signed-off-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Christoffer Dall <cdall@linaro.org>
This patch saves the device table entries into guest RAM.
Both flat table and 2 stage tables are supported. DeviceId
indexing is used.
For each device listed in the device table, we also save
the translation table using the vgic_its_save/restore_itt
routines. Those functions will be implemented in a subsequent
patch.
On restore, devices are re-allocated and their itt are
re-built.
Signed-off-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Christoffer Dall <cdall@linaro.org>
As vgic_its_check_id() computes the device/collection entry's
GPA, let's return it so that new callers can retrieve it easily.
Signed-off-by: Eric Auger <eric.auger@redhat.com>
Acked-by: Christoffer Dall <cdall@linaro.org>
Acked-by: Marc Zyngier <marc.zyngier@arm.com>
The save path copies the collection entries into guest RAM
at the GPA specified in the BASER register. This obviously
requires the BASER to be set. The last written element is a
dummy collection table entry.
We do not index by collection ID as the collection entry
can fit into 8 bytes while containing the collection ID.
On restore path we re-allocate the collection objects.
Signed-off-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Christoffer Dall <cdall@linaro.org>
Reviewed-by: Marc Zyngier <marc.zyngier@arm.com>
Add a generic scan_its_table() helper whose role consists in
scanning a contiguous table located in guest RAM and applying
a callback on each entry. Entries can be handled as linked lists
since the callback may return an id offset to the next entry and
also indicate whether the entry is the last one.
Helper functions also are added to compute the device/event ID
offset to the next DTE/ITE.
compute_next_devid_offset, compute_next_eventid_offset and
scan_table will become static in subsequent patches
Signed-off-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Christoffer Dall <cdall@linaro.org>
Reviewed-by: Marc Zyngier <marc.zyngier@arm.com>
Add two new helpers to allocate an its ite and an its device.
This will avoid duplication on restore path.
Signed-off-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Christoffer Dall <cdall@linaro.org>
Reviewed-by: Marc Zyngier <marc.zyngier@arm.com>
Introduce new attributes in KVM_DEV_ARM_VGIC_GRP_CTRL group:
- KVM_DEV_ARM_ITS_SAVE_TABLES: saves the ITS tables into guest RAM
- KVM_DEV_ARM_ITS_RESTORE_TABLES: restores them into VGIC internal
structures.
We hold the vcpus lock during the save and restore to make
sure no vcpu is running.
At this stage the functionality is not yet implemented. Only
the skeleton is put in place.
Signed-off-by: Eric Auger <eric.auger@redhat.com>
[Given we will move the iodev register until setting the base addr]
Reviewed-by: Christoffer Dall <cdall@linaro.org>
When creating the lpi we now ask the redistributor what is the state
of the LPI (priority, enabled, pending).
Signed-off-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Marc Zyngier <marc.zyngier@arm.com>
Reviewed-by: Christoffer Dall <cdall@linaro.org>
this new helper synchronizes the irq pending_latch
with the LPI pending bit status found in rdist pending table.
As the status is consumed, we reset the bit in pending table.
As we need the PENDBASER_ADDRESS() in vgic-v3, let's move its
definition in the irqchip header. We restore the full length
of the field, ie [51:16]. Same for PROPBASER_ADDRESS with full
field length of [51:12].
Signed-off-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Marc Zyngier <marc.zyngier@arm.com>
Reviewed-by: Christoffer Dall <cdall@linaro.org>
On MAPD we currently check the device id can be stored in the device table.
Let's first check it can be encoded within the range defined by TYPER
DEVBITS.
Also check the collection ID belongs to the 16 bit range as GITS_TYPER
CIL field equals to 0.
Signed-off-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Christoffer Dall <cdall@linaro.org>
Reviewed-by: Marc Zyngier <marc.zyngier@arm.com>
Up to now the MAPD ITT_addr had been ignored. We will need it
for save/restore. Let's record it in the its_device struct.
Signed-off-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Christoffer Dall <cdall@linaro.org>
Reviewed-by: Marc Zyngier <marc.zyngier@arm.com>
Up to now the MAPD's ITT size field has been ignored. It encodes
the number of eventid bit minus 1. It should be used to check
the eventid when a MAPTI command is issued on a device. Let's
store the number of eventid bits in the its_device and do the
check on MAPTI. Also make sure the ITT size field does
not exceed the GITS_TYPER IDBITS field.
Signed-off-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Christoffer Dall <cdall@linaro.org>
Reviewed-by: Marc Zyngier <marc.zyngier@arm.com>
The GITS_IIDR revision field is used to encode the migration ABI
revision. So we need to restore it to check the table layout is
readable by the destination.
By writing the IIDR, userspace thus forces the ABI revision to be
used and this must be less than or equal to the max revision KVM
supports.
Signed-off-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Christoffer Dall <cdall@linaro.org>
We plan to support different migration ABIs, ie. characterizing
the ITS table layout format in guest RAM. For example, a new ABI
will be needed if vLPIs get supported for nested use case.
So let's introduce an array of supported ABIs (at the moment a single
ABI is supported though). The following characteristics are foreseen
to vary with the ABI: size of table entries, save/restore operation,
the way abi settings are applied.
By default the MAX_ABI_REV is applied on its creation. In subsequent
patches we will introduce a way for the userspace to change the ABI
in use.
The entry sizes now are set according to the ABI version and not
hardcoded anymore.
Signed-off-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Christoffer Dall <cdall@linaro.org>
GITS_CREADR needs to be restored so let's implement the associated
uaccess_write_its callback. The write only is allowed if the its
is disabled.
Signed-off-by: Eric Auger <eric.auger@redhat.com>
Acked-by: Marc Zyngier <marc.zyngier@arm.com>
Reviewed-by: Christoffer Dall <cdall@linaro.org>
This patch implements vgic_its_has_attr_regs and vgic_its_attr_regs_access
upon the MMIO framework. VGIC ITS KVM device KVM_DEV_ARM_VGIC_GRP_ITS_REGS
group becomes functional.
At least GITS_CREADR and GITS_IIDR require to differentiate a guest write
action from a user access. As such let's introduce a new uaccess_its_write
vgic_register_region callback.
Signed-off-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Christoffer Dall <cdall@linaro.org>
Reviewed-by: Marc Zyngier <marc.zyngier@arm.com>
We need to use those helpers in vgic-its.c so let's
expose them in the private vgic header.
Signed-off-by: Eric Auger <eric.auger@redhat.com>
Acked-by: Marc Zyngier <marc.zyngier@arm.com>
Acked-by: Christoffer Dall <cdall@linaro.org>
The ITS KVM device exposes a new KVM_DEV_ARM_VGIC_GRP_ITS_REGS
group which allows the userspace to save/restore ITS registers.
At this stage the get/set/has operations are not yet implemented.
Signed-off-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Andre Przywara <andre.przywara@arm.com>
Reviewed-by: Christoffer Dall <cdall@linaro.org>
Acked-by: Marc Zyngier <marc.zyngier@arm.com>
We plan to use vgic_find_mmio_region in vgic-its.c so let's
turn it into a public function.
Also let's take the opportunity to rename the region parameter
into regions to emphasize this latter is an array of regions.
Signed-off-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Andre Przywara <andre.przywara@arm.com>
Acked-by: Marc Zyngier <marc.zyngier@arm.com>
Acked-by: Christoffer Dall <cdall@linaro.org>
The actual abbreviation for the interrupt translation table entry
is ITE. Let's rename all itte instances by ite.
Signed-off-by: Eric Auger <eric.auger@redhat.com>
Acked-by: Marc Zyngier <marc.zyngier@arm.com>
Acked-by: Christoffer Dall <cdall@linaro.org>
- kdump support, including two necessary memblock additions:
memblock_clear_nomap() and memblock_cap_memory_range()
- ARMv8.3 HWCAP bits for JavaScript conversion instructions, complex
numbers and weaker release consistency
- arm64 ACPI platform MSI support
- arm perf updates: ACPI PMU support, L3 cache PMU in some Qualcomm
SoCs, Cortex-A53 L2 cache events and DTLB refills, MAINTAINERS update
for DT perf bindings
- architected timer errata framework (the arch/arm64 changes only)
- support for DMA_ATTR_FORCE_CONTIGUOUS in the arm64 iommu DMA API
- arm64 KVM refactoring to use common system register definitions
- remove support for ASID-tagged VIVT I-cache (no ARMv8 implementation
using it and deprecated in the architecture) together with some
I-cache handling clean-up
- PE/COFF EFI header clean-up/hardening
- define BUG() instruction without CONFIG_BUG
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1
iQIcBAABAgAGBQJZDKMoAAoJEGvWsS0AyF7xR+YP/0EMEz5MDfCv0PVYj7/AIa0G
Zphl7OhysIkeDAz7urXw9Jdl0NfORNIqmD1vZNVSc321IyNp56Od+kWd82lBrOWB
ad3nNT67pEmu0pAW7CO48ju3rTesEnEl3ra45E1tULeLihmv93jc4ZlfXgumlKq3
/GE84XJ5ZFmluuhq1zgNefeUtyl1tbxTxHJ74+INF7dTd/5sJcphpqS4Dzpb+msT
20WYliccQCBF9zBFUYHc2KjcXXKRQGxLulGS3MuoN2DLkD+U9YyR/OmA7SoXh2J2
WXC5b0x856xTQJFCJ39pb7rw5xHjt3l5zfU3VLSvqEVL/+asBqCcgGNtNUgOW1Es
dEHC6bc66Ley6mn7bbpFE3MK8D+K5q8HwMF6G5KDtIVB6DB/iQ6kzi5aXKoupxtb
1EuU4OW6cDhmOFQYjgIDofLgqbmVvJofdF6+NfxasfZmWrMgHzv0rYvaCDnAV/Tr
t7bhH7hf9/KcP/wpk86O2AMKKpgoNTqe1Qy8cWVFFLnut567Pb6zs/L3ZXfleoLv
t613yM8Zj2fE05ja8ylMDjaasidNpXGttb08/4kAn06Daaoueqla0jmduAhy4aaV
dQ3OFP9lJ5MFaFnMMTPfU3vtvNLMHuo9MZsYCrv5zCaNNs3lpAPUiPNh588ZscKa
sWx4PEiaCi+wcOsLsJvh
=SDkm
-----END PGP SIGNATURE-----
Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux
Pull arm64 updates from Catalin Marinas:
- kdump support, including two necessary memblock additions:
memblock_clear_nomap() and memblock_cap_memory_range()
- ARMv8.3 HWCAP bits for JavaScript conversion instructions, complex
numbers and weaker release consistency
- arm64 ACPI platform MSI support
- arm perf updates: ACPI PMU support, L3 cache PMU in some Qualcomm
SoCs, Cortex-A53 L2 cache events and DTLB refills, MAINTAINERS update
for DT perf bindings
- architected timer errata framework (the arch/arm64 changes only)
- support for DMA_ATTR_FORCE_CONTIGUOUS in the arm64 iommu DMA API
- arm64 KVM refactoring to use common system register definitions
- remove support for ASID-tagged VIVT I-cache (no ARMv8 implementation
using it and deprecated in the architecture) together with some
I-cache handling clean-up
- PE/COFF EFI header clean-up/hardening
- define BUG() instruction without CONFIG_BUG
* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (92 commits)
arm64: Fix the DMA mmap and get_sgtable API with DMA_ATTR_FORCE_CONTIGUOUS
arm64: Print DT machine model in setup_machine_fdt()
arm64: pmu: Wire-up Cortex A53 L2 cache events and DTLB refills
arm64: module: split core and init PLT sections
arm64: pmuv3: handle pmuv3+
arm64: Add CNTFRQ_EL0 trap handler
arm64: Silence spurious kbuild warning on menuconfig
arm64: pmuv3: use arm_pmu ACPI framework
arm64: pmuv3: handle !PMUv3 when probing
drivers/perf: arm_pmu: add ACPI framework
arm64: add function to get a cpu's MADT GICC table
drivers/perf: arm_pmu: split out platform device probe logic
drivers/perf: arm_pmu: move irq request/free into probe
drivers/perf: arm_pmu: split cpu-local irq request/free
drivers/perf: arm_pmu: rename irq request/free functions
drivers/perf: arm_pmu: handle no platform_device
drivers/perf: arm_pmu: simplify cpu_pmu_request_irqs()
drivers/perf: arm_pmu: factor out pmu registration
drivers/perf: arm_pmu: fold init into alloc
drivers/perf: arm_pmu: define armpmu_init_fn
...
The #ifndef was removed in 75aaafb79f,
but it was also protecting smp_send_reschedule() in kvm_vcpu_kick().
Acked-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
For some time now we have been having a lot of shared functionality
between the arm and arm64 KVM support in arch/arm, which not only
required a horrible inter-arch reference from the Makefile in
arch/arm64/kvm, but also created confusion for newcomers to the code
base, as was recently seen on the mailing list.
Further, it causes confusion for things like cscope, which needs special
attention to index specific shared files for arm64 from the arm tree.
Move the shared files into virt/kvm/arm and move the trace points along
with it. When moving the tracepoints we have to modify the way the vgic
creates definitions of the trace points, so we take the chance to
include the VGIC tracepoints in its very own special vgic trace.h file.
Signed-off-by: Christoffer Dall <cdall@linaro.org>
This reverts commit bbd6411513.
I've been sitting on this revert for too long and it unfortunately
missed 4.11. It's also the reason why I haven't merged ring-based
dirty tracking for 4.12.
Using kvm_vcpu_memslots in kvm_gfn_to_hva_cache_init and
kvm_vcpu_write_guest_offset_cached means that the MSR value can
now be used to access SMRAM, simply by making it point to an SMRAM
physical address. This is problematic because it lets the guest
OS overwrite memory that it shouldn't be able to touch.
Cc: stable@vger.kernel.org
Fixes: bbd6411513
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
We needed the lock to avoid racing with creation of the irqchip on x86. As
kvm_set_irq_routing() calls srcu_synchronize_expedited(), this lock
might be held for a longer time.
Let's introduce an arch specific callback to check if we can actually
add irq routes. For x86, all we have to do is check if we have an
irqchip in the kernel. We don't need kvm->lock at that point as the
irqchip is marked as inititalized only when actually fully created.
Reported-by: Steve Rutherford <srutherford@google.com>
Reviewed-by: Radim Krčmář <rkrcmar@redhat.com>
Fixes: 1df6ddede1 ("KVM: x86: race between KVM_SET_GSI_ROUTING and KVM_CREATE_IRQCHIP")
Signed-off-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
This merges in the powerpc topic/xive branch to bring in the code for
the in-kernel XICS interrupt controller emulation to use the new XIVE
(eXternal Interrupt Virtualization Engine) hardware in the POWER9 chip
directly, rather than via a XICS emulation in firmware.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
Changes include:
- Using the common sysreg definitions between KVM and arm64
- Improved hyp-stub implementation with support for kexec and kdump on the 32-bit side
- Proper PMU exception handling
- Performance improvements of our GIC handling
- Support for irqchip in userspace with in-kernel arch-timers and PMU support
- A fix for a race condition in our PSCI code
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1
iQEcBAABAgAGBQJY/IasAAoJEEtpOizt6ddyd7gH/2N3BIMxi/Uqigx0e0byA43s
f+8gNq8A71VBTERGW2l9QP1/AZAXpQYNWdWmN2jn+91x2yoVL7AT00gEsliSLEZv
tqZaTGFXKi1vNihYrxEWm1mfVNzhRrnbW6vjLrO4J5Advq7T3OWhNuVt2BLTxz3Y
h0iqOWNVrUD9h3QSBFH8tz7yXhguDTSppAcXbE0tACdRu4vN50wqEWokHJG5TsMG
Tl3KYWrcc3YCKlAJGuJi7t5rMrXk+g1q6HnxlIN6OSk0POC2Vmw9/Gigtltj1Qwh
ZEAwsnka/U8ak8WaWeZa3EsGTSFSoAk/+pKv2FB8mFN+uOmWDqVlEiol4dW49AY=
=mEOk
-----END PGP SIGNATURE-----
Merge tag 'kvm-arm-for-v4.12' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD
KVM/ARM Changes for v4.12.
Changes include:
- Using the common sysreg definitions between KVM and arm64
- Improved hyp-stub implementation with support for kexec and kdump on the 32-bit side
- Proper PMU exception handling
- Performance improvements of our GIC handling
- Support for irqchip in userspace with in-kernel arch-timers and PMU support
- A fix for a race condition in our PSCI code
Conflicts:
Documentation/virtual/kvm/api.txt
include/uapi/linux/kvm.h
kvm_make_all_requests() provides a synchronization that waits until all
kicked VCPUs have acknowledged the kick. This is important for
KVM_REQ_MMU_RELOAD as it prevents freeing while lockless paging is
underway.
This patch adds the synchronization property into all requests that are
currently being used with kvm_make_all_requests() in order to preserve
the current behavior and only introduce a new framework. Removing it
from requests where it is not necessary is left for future patches.
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
No need to kick a VCPU that we have just woken up.
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Reviewed-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
kvm_vcpu_kick() must issue a general memory barrier prior to reading
vcpu->mode in order to ensure correctness of the mutual-exclusion
memory barrier pattern used with vcpu->requests. While the cmpxchg
called from kvm_vcpu_kick():
kvm_vcpu_kick
kvm_arch_vcpu_should_kick
kvm_vcpu_exiting_guest_mode
cmpxchg
implies general memory barriers before and after the operation, that
implication is only valid when cmpxchg succeeds. We need an explicit
barrier for when it fails, otherwise a VCPU thread on its entry path
that reads zero for vcpu->requests does not exclude the possibility
the requesting thread sees !IN_GUEST_MODE when it reads vcpu->mode.
kvm_make_all_cpus_request already had a barrier, so we remove it, as
now it would be redundant.
Signed-off-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
We want to have kvm_make_all_cpus_request() to be an optmized version of
kvm_for_each_vcpu(i, vcpu, kvm) {
kvm_make_request(vcpu, request);
kvm_vcpu_kick(vcpu);
}
and kvm_vcpu_kick() wakes up the target vcpu. We know which requests do
not need the wake up and use it to optimize the loop.
Thanks to that, this patch doesn't change the behavior of current users
(the all don't need the wake up) and only prepares for future where the
wake up is going to be needed.
I think that most requests do not need the wake up, so we would flip the
bit then.
Later on, kvm_make_request() will take care of kicking too, using this
bit to make the decision whether to kick or not.
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Reviewed-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
The #ifndef was protecting a missing halt_wakeup stat, but that is no
longer necessary.
Acked-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Reviewed-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
This patch makes KVM capable of using the XIVE interrupt controller
to provide the standard PAPR "XICS" style hypercalls. It is necessary
for proper operations when the host uses XIVE natively.
This has been lightly tested on an actual system, including PCI
pass-through with a TG3 device.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
[mpe: Cleanup pr_xxx(), unsplit pr_xxx() strings, etc., fix build
failures by adding KVM_XIVE which depends on KVM_XICS and XIVE, and
adding empty stubs for the kvm_xive_xxx() routines, fixup subject,
integrate fixes from Paul for building PR=y HV=n]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
This allows the host kernel to handle H_PUT_TCE, H_PUT_TCE_INDIRECT
and H_STUFF_TCE requests targeted an IOMMU TCE table used for VFIO
without passing them to user space which saves time on switching
to user space and back.
This adds H_PUT_TCE/H_PUT_TCE_INDIRECT/H_STUFF_TCE handlers to KVM.
KVM tries to handle a TCE request in the real mode, if failed
it passes the request to the virtual mode to complete the operation.
If it a virtual mode handler fails, the request is passed to
the user space; this is not expected to happen though.
To avoid dealing with page use counters (which is tricky in real mode),
this only accelerates SPAPR TCE IOMMU v2 clients which are required
to pre-register the userspace memory. The very first TCE request will
be handled in the VFIO SPAPR TCE driver anyway as the userspace view
of the TCE table (iommu_table::it_userspace) is not allocated till
the very first mapping happens and we cannot call vmalloc in real mode.
If we fail to update a hardware IOMMU table unexpected reason, we just
clear it and move on as there is nothing really we can do about it -
for example, if we hot plug a VFIO device to a guest, existing TCE tables
will be mirrored automatically to the hardware and there is no interface
to report to the guest about possible failures.
This adds new attribute - KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE - to
the VFIO KVM device. It takes a VFIO group fd and SPAPR TCE table fd
and associates a physical IOMMU table with the SPAPR TCE table (which
is a guest view of the hardware IOMMU table). The iommu_table object
is cached and referenced so we do not have to look up for it in real mode.
This does not implement the UNSET counterpart as there is no use for it -
once the acceleration is enabled, the existing userspace won't
disable it unless a VFIO container is destroyed; this adds necessary
cleanup to the KVM_DEV_VFIO_GROUP_DEL handler.
This advertises the new KVM_CAP_SPAPR_TCE_VFIO capability to the user
space.
This adds real mode version of WARN_ON_ONCE() as the generic version
causes problems with rcu_sched. Since we testing what vmalloc_to_phys()
returns in the code, this also adds a check for already existing
vmalloc_to_phys() call in kvmppc_rm_h_put_tce_indirect().
This finally makes use of vfio_external_user_iommu_id() which was
introduced quite some time ago and was considered for removal.
Tests show that this patch increases transmission speed from 220MB/s
to 750..1020MB/s on 10Gb network (Chelsea CXGB3 10Gb ethernet card).
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Acked-by: Alex Williamson <alex.williamson@redhat.com>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
When iterating over the used LRs, be careful not to try to access
an unused LR, or even an unimplemented one if you're unlucky...
Reviewed-by: Christoffer Dall <cdall@linaro.org>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Christoffer Dall <cdall@linaro.org>
When emulating a GICv2-on-GICv3, special care must be taken to only
save/restore VMCR_EL2 when ICC_SRE_EL1.SRE is cleared. Otherwise,
all Group-0 interrupts end-up being delivered as FIQ, which is
probably not what the guest expects, as demonstrated here with
an unhappy EFI:
FIQ Exception at 0x000000013BD21CC4
This means that we cannot perform the load/put trick when dealing
with VMCR_EL2 (because the host has SRE set), and we have to deal
with it in the world-switch.
Fortunately, this is not the most common case (modern guests should
be able to deal with GICv3 directly), and the performance is not worse
than what it was before the VMCR optimization.
Reviewed-by: Christoffer Dall <cdall@linaro.org>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Christoffer Dall <cdall@linaro.org>
Let's drop the goto and return the error value directly.
Suggested-by: Peter Xu <peterx@redhat.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Let's rename it into a proper arch specific callback.
Signed-off-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Avoid races between KVM_SET_GSI_ROUTING and KVM_CREATE_IRQCHIP by taking
the kvm->lock when setting up routes.
If KVM_CREATE_IRQCHIP fails, KVM_SET_GSI_ROUTING could have already set
up routes pointing at pic/ioapic, being silently removed already.
Also, as a side effect, this patch makes sure that KVM_SET_GSI_ROUTING
and KVM_CAP_SPLIT_IRQCHIP cannot run in parallel.
Signed-off-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
When not using an in-kernel VGIC, but instead emulating an interrupt
controller in userspace, we should report the PMU overflow status to
that userspace interrupt controller using the KVM_CAP_ARM_USER_IRQ
feature.
Reviewed-by: Alexander Graf <agraf@suse.de>
Reviewed-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
If you're running with a userspace gic or other interrupt controller
(that is no vgic in the kernel), then you have so far not been able to
use the architected timers, because the output of the architected
timers, which are driven inside the kernel, was a kernel-only construct
between the arch timer code and the vgic.
This patch implements the new KVM_CAP_ARM_USER_IRQ feature, where we use a
side channel on the kvm_run structure, run->s.regs.device_irq_level, to
always notify userspace of the timer output levels when using a userspace
irqchip.
This works by ensuring that before we enter the guest, if the timer
output level has changed compared to what we last told userspace, we
don't enter the guest, but instead return to userspace to notify it of
the new level. If we are exiting, because of an MMIO for example, and
the level changed at the same time, the value is also updated and
userspace can sample the line as it needs. This is nicely achieved
simply always updating the timer_irq_level field after the main run
loop.
Note that the kvm_timer_update_irq trace event is changed to show the
host IRQ number for the timer instead of the guest IRQ number, because
the kernel no longer know which IRQ userspace wires up the timer signal
to.
Also note that this patch implements all required functionality but does
not yet advertise the capability.
Reviewed-by: Alexander Graf <agraf@suse.de>
Reviewed-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
Currently we check if we have an in-kernel irqchip and if the vgic was
properly implemented several places in the arch timer code. But, we
already predicate our enablement of the arm timers on having a valid
and initialized gic, so we can simply check if the timers are enabled or
not.
This also gets rid of the ugly "error that's not an error but used to
signal that the timer shouldn't poke the gic" construct we have.
Reviewed-by: Alexander Graf <agraf@suse.de>
Reviewed-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
There is no need to call any functions to fold LRs when we don't use any
LRs and we don't need to mess with overflow flags, take spinlocks, or
prune the AP list if the AP list is empty.
Note: list_empty is a single atomic read (uses READ_ONCE) and can
therefore check if a list is empty or not without the need to take the
spinlock protecting the list.
Reviewed-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Christoffer Dall <cdall@linaro.org>
Now when we do an early init of the static parts of the VGIC data
structures, we can do things like checking if the AP lists are empty
directly without having to explicitly check if the vgic is initialized
and reduce a bit of work in our critical path.
Acked-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Christoffer Dall <cdall@linaro.org>
Implement early initialization for both the distributor and the CPU
interfaces. The basic idea is that even though the VGIC is not
functional or not requested from user space, the critical path of the
run loop can still call VGIC functions that just won't do anything,
without them having to check additional initialization flags to ensure
they don't look at uninitialized data structures.
Acked-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Christoffer Dall <cdall@linaro.org>
We don't use these fields anymore so let's nuke them completely.
Acked-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
Now when we don't look at the MISR and EISR values anymore, we can get
rid of the logic to save them in the GIC save/restore code.
Acked-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
Since we always read back the LRs that we wrote to the guest and the
MISR and EISR registers simply provide a summary of the configuration of
the bits in the LRs, there is really no need to read back those status
registers and process them. We might as well just signal the
notifyfd when folding the LR state and save some cycles in the process.
We now clear the underflow bit in the fold_lr_state functions as we only
need to clear this bit if we had used all the LRs, so this is as good a
place as any to do that work.
Reviewed-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
We currently assume that all the interrupts in our AP list will be
queued to LRs, but that's not necessarily the case, because some of them
could have been migrated away to different VCPUs and only the VCPU
thread itself can remove interrupts from its AP list.
Therefore, slightly change the logic to only setting the underflow
interrupt when we actually run out of LRs.
As it turns out, this allows us to further simplify the handling in
vgic_sync_hwstate in later patches.
Acked-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Christoffer Dall <cdall@linaro.org>
There is no need to calculate and maintain live_lrs when we always
populate the lowest numbered LRs first on every entry and clear all LRs
on every exit.
Acked-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
We do not need to flush vgic states in each world switch unless
there is pending IRQ queued to the vgic's ap list. We can thus reduce
the overhead by not grabbing the spinlock and not making the extra
function call to vgic_flush_lr_state.
Note: list_empty is a single atomic read (uses READ_ONCE) and can
therefore check if a list is empty or not without the need to take the
spinlock protecting the list.
Reviewed-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Shih-Wei Li <shihwei@cs.columbia.edu>
Signed-off-by: Christoffer Dall <cdall@linaro.org>
We don't have to save/restore the VMCR on every entry to/from the guest,
since on GICv2 we can access the control interface from EL1 and on VHE
systems with GICv3 we can access the control interface from KVM running
in EL2.
GICv3 systems without VHE becomes the rare case, which has to
save/restore the register on each round trip.
Note that userspace accesses may see out-of-date values if the VCPU is
running while accessing the VGIC state via the KVM device API, but this
is already the case and it is up to userspace to quiesce the CPUs before
reading the CPU registers from the GIC for an up-to-date view.
Reviewed-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Christoffer Dall <cdall@cs.columbia.edu>
Signed-off-by: Christoffer Dall <cdall@linaro.org>
Its value has never changed; we might as well make it part of the ABI instead
of using the return value of KVM_CHECK_EXTENSION(KVM_CAP_COALESCED_MMIO).
Because PPC does not always make MMIO available, the code has to be made
dependent on CONFIG_KVM_MMIO rather than KVM_COALESCED_MMIO_PAGE_OFFSET.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Remove code from architecture files that can be moved to virt/kvm, since there
is already common code for coalesced MMIO.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
[Removed a pointless 'break' after 'return'.]
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Legacy device assignment has been deprecated since 4.2 (released
1.5 years ago). VFIO is better and everyone should have switched to it.
If they haven't, this should convince them. :)
Reviewed-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Fixes include:
- Fix a problem with GICv3 userspace save/restore
- Clarify GICv2 userspace save/restore ABI
- Be more careful in clearing GIC LRs
- Add missing synchronization primitive to our MMU handling code
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1
iQEcBAABAgAGBQJY5MItAAoJEEtpOizt6ddy4mUH/1Z2rt2mUAYFQpWD/vy9WMxf
zJKMtcLlZZGjeU78zFfWuOxEo1bbDO+tOTV1docNnY8xjyszCZ5XKOqMeo2a7Vfh
1QYHxJTOmgxcRmMsOnJpqUXhhYm9hDxrbU88U/wvoNllLjWBea01ZXiJbWFPBssT
jrdtcCVstDGp3x3D91RgYNNzj9jNw80RBekACZZwYokDRpBZyUb8DYKfUgABFEKT
UPiHrxb8UOVqvbCuXMBNzhUZcuMoAh3oY02R9sV7u1QOXAJYfRV4fOV12fIcYbHf
tnyU8cCxEkSI1pHrpVG6SStcMt8yznQ+UPo0okQNBJXim2yI8+QKHtQlvx7Tjo8=
=tPDd
-----END PGP SIGNATURE-----
Merge tag 'kvm-arm-for-v4.11-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm
From: Christoffer Dall <cdall@linaro.org>
KVM/ARM Fixes for v4.11-rc6
Fixes include:
- Fix a problem with GICv3 userspace save/restore
- Clarify GICv2 userspace save/restore ABI
- Be more careful in clearing GIC LRs
- Add missing synchronization primitive to our MMU handling code
As an oversight, for GICv2, we accidentally export the GICC_PMR register
in the format of the GICH_VMCR.VMPriMask field in the lower 5 bits of a
word, meaning that userspace must always use the lower 5 bits to
communicate with the KVM device and must shift the value left by 3
places to obtain the actual priority mask level.
Since GICv3 supports the full 8 bits of priority masking in the ICH_VMCR,
we have to fix the value we export when emulating a GICv2 on top of a
hardware GICv3 and exporting the emulated GICv2 state to userspace.
Take the chance to clarify this aspect of the ABI.
Reviewed-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Christoffer Dall <cdall@linaro.org>
We currently have some code to clear the list registers on GICv3, but we
never call this code, because the caller got nuked when removing the old
vgic. We also used to have a similar GICv2 part, but that got lost in
the process too.
Let's reintroduce the logic for GICv2 and call the logic when we
initialize the use of hypervisors on the CPU, for example when first
loading KVM or when exiting a low power state.
Reviewed-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
or VM memory are not put thus leaked in kvm_iommu_unmap_memslots() when
destroy VM.
This is consistent with current vfio implementation.
Signed-off-by: herongguang <herongguang.he@huawei.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
No caller currently checks the return value of
kvm_io_bus_unregister_dev(). This is evil, as all callers silently go on
freeing their device. A stale reference will remain in the io_bus,
getting at least used again, when the iobus gets teared down on
kvm_destroy_vm() - leading to use after free errors.
There is nothing the callers could do, except retrying over and over
again.
So let's simply remove the bus altogether, print an error and make
sure no one can access this broken bus again (returning -ENOMEM on any
attempt to access it).
Fixes: e93f8a0f82 ("KVM: convert io_bus to SRCU")
Cc: stable@vger.kernel.org # 3.4+
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Reviewed-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
The kvm_vgic_global_state struct contains a static key which is
written to by jump_label_init() at boot time. So in preparation of
making .text regions truly (well, almost truly) read-only, mark
kvm_vgic_global_state __ro_after_init so it moves to the .rodata
section instead.
Acked-by: Marc Zyngier <marc.zyngier@arm.com>
Reviewed-by: Laura Abbott <labbott@redhat.com>
Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Tested-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
When releasing the bus, let's clear the bus pointers to mark it out. If
any further device unregister happens on this bus, we know that we're
done if we found the bus being released already.
Signed-off-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Andrew Jones