Commit graph

1,089,026 commits

Author SHA1 Message Date
Maarten Lankhorst
f0b6b01b3e drm/i915: Add ww context to intel_dpt_pin, v2.
Ensure i915_vma_pin_iomap and vma_unpin are done with dpt->obj lock held.

I don't think there's much of a point in merging intel_dpt_pin() with
intel_pin_fb_obj_dpt(), they touch different objects.

Changes since v1:
- Fix using the wrong pointer to retrieve error code (Julia)

Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Julia Lawall <julia.lawall@lip6.fr>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210929085950.3063191-1-maarten.lankhorst@linux.intel.com
2021-09-30 12:45:00 +02:00
Pali Rohár
894682f0a9 PCI: xgene: Use PCI_VENDOR_ID_AMCC macro
Header file linux/pci_ids.h defines AMCC vendor id (0x10e8) macro named
PCI_VENDOR_ID_AMCC. So use this macro instead of driver custom macro.

Link: https://lore.kernel.org/r/20210927134356.11799-1-pali@kernel.org
Signed-off-by: Pali Rohár <pali@kernel.org>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Krzysztof Wilczyński <kw@linux.com>
2021-09-30 10:44:37 +01:00
Luca Ceresoli
5af9405397 PCI: dra7xx: Get an optional clock
If the clock is provided externally we need to make sure it is enabled
before starting PCI scan.

Link: https://lore.kernel.org/r/20210531085934.2662457-5-luca@lucaceresoli.net
Signed-off-by: Luca Ceresoli <luca@lucaceresoli.net>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Acked-by: Kishon Vijay Abraham I <kishon@ti.com>
2021-09-30 09:52:16 +01:00
Luca Ceresoli
b9a6943dc8 PCI: dra7xx: Remove unused include
Unused since commit e259c2926c ("PCI: pci-dra7xx: Prepare for deferred
probe with module_platform_driver").

Link: https://lore.kernel.org/r/20210531085934.2662457-4-luca@lucaceresoli.net
Signed-off-by: Luca Ceresoli <luca@lucaceresoli.net>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Acked-by: Kishon Vijay Abraham I <kishon@ti.com>
2021-09-30 09:52:16 +01:00
Luca Ceresoli
3b868d150e PCI: dra7xx: Make it a kernel module
Enable building the driver as a loadable kernel module.

Link: https://lore.kernel.org/r/20210531085934.2662457-3-luca@lucaceresoli.net
Signed-off-by: Luca Ceresoli <luca@lucaceresoli.net>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Acked-by: Kishon Vijay Abraham I <kishon@ti.com>
2021-09-30 09:52:16 +01:00
Luca Ceresoli
3a7fb86758 PCI: dwc: Export more symbols to allow modular drivers
These symbols are used by the pci-dra7xx driver. Export them to allow
building pci-dra7xx as a module.

Link: https://lore.kernel.org/r/20210531085934.2662457-2-luca@lucaceresoli.net
Signed-off-by: Luca Ceresoli <luca@lucaceresoli.net>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Acked-by: Kishon Vijay Abraham I <kishon@ti.com>
2021-09-30 09:52:16 +01:00
Ville Syrjälä
ef46972ac8 drm/i915: Configure TRANSCONF just the once with bigjoiner
Let's not configure the single transcoder's TRANSCONF multiple
times with bigjoiner. No real harm I suppose but since we already
have the bigjoiner if statement directly above might as well suck
this in there and skip the redundant programming.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210913144440.23008-11-ville.syrjala@linux.intel.com
Reviewed-by: Manasi Navare <manasi.d.navare@intel.com>
2021-09-30 11:50:47 +03:00
Ville Syrjälä
a471a526bc drm/i915: Pimp HSW+ transcoder state readout
Adjust the HSW+ transcoder state readout to just read through
all the possible transcoders for the pipe, and stuff the results
in a bitmask.

We can conveniently cross check the bitmask for invalid
combinations of enabled transcoders, and later we can easily
extend the bitmask readout to handle the bigjoiner case.

One slight change in behaviour is that we no longer read out
the AONOFF->force_pfit.pfit bit for all the enabled "panel
transcoders". But having more than one enabled would anyway
be illegal so no big loss. Also the AONOFF selection should
only ever be used on HSW, which only has the EDP transcoder
an no DSI transcoders.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210913144440.23008-10-ville.syrjala@linux.intel.com
Reviewed-by: Manasi Navare <manasi.d.navare@intel.com>
2021-09-30 11:49:09 +03:00
Abel Vesa
66173dbe9f clk: imx: Rework all clk_hw_register_gate2 wrappers
Instead of having multiple inline functions that were calling
clk_hw_register_gate2, implement a generic low-level __imx_clk_hw_gate2
and implement the rest as macros that pass on as arguments whatever
is needed in each case.

Signed-off-by: Abel Vesa <abel.vesa@nxp.com>
Link: https://lore.kernel.org/r/1631521490-17171-5-git-send-email-abel.vesa@nxp.com
Reviewed-by: Stephen Boyd <sboyd@kernel.org>
2021-09-30 11:48:24 +03:00
Ville Syrjälä
2709abc8d1 drm/i915/fbc: Allow FBC with Yf tiling
FBC+Yf tiling seems to work just fine, and unlike with linear
the hardware does appear to correctly calculate the CFB stride
with using the override stride on both cfl and glk. So no need
for any additional tweaks.

Cc: Uma Shankar <uma.shankar@intel.com> #v2
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210924141330.1515-1-ville.syrjala@linux.intel.com
Reviewed-by: Uma Shankar <uma.shankar@intel.com>
2021-09-30 11:44:11 +03:00
Yee Lee
528a4ab453 scs: Release kasan vmalloc poison in scs_free process
Since scs allocation is moved to vmalloc region, the
shadow stack is protected by kasan_posion_vmalloc.
However, the vfree_atomic operation needs to access
its context for scs_free process and causes kasan error
as the dump info below.

This patch Adds kasan_unpoison_vmalloc() before vfree_atomic,
which aligns to the prior flow as using kmem_cache.
The vmalloc region will go back posioned in the following
vumap() operations.

 ==================================================================
 BUG: KASAN: vmalloc-out-of-bounds in llist_add_batch+0x60/0xd4
 Write of size 8 at addr ffff8000100b9000 by task kthreadd/2

 CPU: 0 PID: 2 Comm: kthreadd Not tainted 5.15.0-rc2-11681-g92477dd1faa6-dirty #1
 Hardware name: linux,dummy-virt (DT)
 Call trace:
  dump_backtrace+0x0/0x43c
  show_stack+0x1c/0x2c
  dump_stack_lvl+0x68/0x84
  print_address_description+0x80/0x394
  kasan_report+0x180/0x1dc
  __asan_report_store8_noabort+0x48/0x58
  llist_add_batch+0x60/0xd4
  vfree_atomic+0x60/0xe0
  scs_free+0x1dc/0x1fc
  scs_release+0xa4/0xd4
  free_task+0x30/0xe4
  __put_task_struct+0x1ec/0x2e0
  delayed_put_task_struct+0x5c/0xa0
  rcu_do_batch+0x62c/0x8a0
  rcu_core+0x60c/0xc14
  rcu_core_si+0x14/0x24
  __do_softirq+0x19c/0x68c
  irq_exit+0x118/0x2dc
  handle_domain_irq+0xcc/0x134
  gic_handle_irq+0x7c/0x1bc
  call_on_irq_stack+0x40/0x70
  do_interrupt_handler+0x78/0x9c
  el1_interrupt+0x34/0x60
  el1h_64_irq_handler+0x1c/0x2c
  el1h_64_irq+0x78/0x7c
  _raw_spin_unlock_irqrestore+0x40/0xcc
  sched_fork+0x4f0/0xb00
  copy_process+0xacc/0x3648
  kernel_clone+0x168/0x534
  kernel_thread+0x13c/0x1b0
  kthreadd+0x2bc/0x400
  ret_from_fork+0x10/0x20

 Memory state around the buggy address:
  ffff8000100b8f00: f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8
  ffff8000100b8f80: f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8
 >ffff8000100b9000: f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8
                    ^
  ffff8000100b9080: f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8
  ffff8000100b9100: f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8
 ==================================================================

Suggested-by: Kuan-Ying Lee <kuan-ying.lee@mediatek.com>
Acked-by: Will Deacon <will@kernel.org>
Tested-by: Will Deacon <will@kernel.org>
Reviewed-by: Sami Tolvanen <samitolvanen@google.com>
Signed-off-by: Yee Lee <yee.lee@mediatek.com>
Fixes: a2abe7cbd8 ("scs: switch to vmapped shadow stacks")
Link: https://lore.kernel.org/r/20210930081619.30091-1-yee.lee@mediatek.com
Signed-off-by: Will Deacon <will@kernel.org>
2021-09-30 09:37:27 +01:00
Tony Lindgren
b232537074 soc: ti: omap-prm: Fix external abort for am335x pruss
Starting with v5.15-rc1, we may now see some am335x beaglebone black
device produce the following error on pruss probe:

Unhandled fault: external abort on non-linefetch (0x1008) at 0xe0326000

This has started with the enabling of pruss for am335x in the dts files.

Turns out the is caused by the PRM reset handling not waiting for the
reset bit to clear. To fix the issue, let's always wait for the reset
bit to clear, even if there is a separate reset status register.

We attempted to fix a similar issue for dra7 iva with a udelay() in
commit effe89e400 ("soc: ti: omap-prm: Fix occasional abort on reset
deassert for dra7 iva"). There is no longer a need for the udelay()
for dra7 iva reset either with the check added for reset bit clearing.

Cc: Drew Fustini <pdp7pdp7@gmail.com>
Cc: Grygorii Strashko <grygorii.strashko@ti.com>
Cc: "H. Nikolaus Schaller" <hns@goldelico.com>
Cc: Robert Nelson <robertcnelson@gmail.com>
Cc: Yongqin Liu <yongqin.liu@linaro.org>
Fixes: effe89e400 ("soc: ti: omap-prm: Fix occasional abort on reset deassert for dra7 iva")
Reported-by: Matti Vaittinen <mazziesaccount@gmail.com>
Tested-by: Matti Vaittinen <matti.vaittinen@fi.rohmeurope.com>
Signed-off-by: Tony Lindgren <tony@atomide.com>
2021-09-30 11:30:03 +03:00
Ville Syrjälä
1e39da5a20 drm/i915: Enable TPS3/4 on all platforms that support them
Stop using HBR2/3 support as a proxy for TPS3/4 support.
The two are no longer 1:1 in the hardware, arguably they
never were due to HSW ULX which does support TPS3 while
being limited to HBR1.

In more recent times GLK gained support for TPS4 while
being limited to HBR2. And on CNL+ some ports support
HBR3 while others are limited to HBR2, but all ports
support TPS4.

v2: s/INTEL_GEN/DISPLAY_VER/

Reviewed-by: Manasi Navare <manasi.d.navare@intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210929162404.6717-1-ville.syrjala@linux.intel.com
Acked-by: Jani Nikula <jani.nikula@intel.com>
2021-09-30 11:27:55 +03:00
Maxim Levitsky
4c84926e22 KVM: x86: SVM: add module param to control LBR virtualization
This is useful for debug and also makes it consistent with
the rest of the SVM optional features.

Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Message-Id: <20210914154825.104886-9-mlevitsk@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2021-09-30 04:27:11 -04:00
Maxim Levitsky
0226a45c46 KVM: x86: nSVM: don't copy pause related settings
According to the SDM, the CPU never modifies these settings.
It loads them on VM entry and updates an internal copy instead.

Also don't load them from the vmcb12 as we don't expose these
features to the nested guest yet.

Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Message-Id: <20210914154825.104886-5-mlevitsk@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2021-09-30 04:27:11 -04:00
Longpeng(Mike)
515a0c79e7 kvm: irqfd: avoid update unmodified entries of the routing
All of the irqfds would to be updated when update the irq
routing, it's too expensive if there're too many irqfds.

However we can reduce the cost by avoid some unnecessary
updates. For irqs of MSI type on X86, the update can be
saved if the msi values are not change.

The vfio migration could receives benefit from this optimi-
zaiton. The test VM has 128 vcpus and 8 VF (with 65 vectors
enabled), so the VM has more than 520 irqfds. We mesure the
cost of the vfio_msix_enable (in QEMU, it would set routing
for each irqfd) for each VF, and we can see the total cost
can be significantly reduced.

                Origin         Apply this Patch
1st             8              4
2nd             15             5
3rd             22             6
4th             24             6
5th             36             7
6th             44             7
7th             51             8
8th             58             8
Total           258ms          51ms

We're also tring to optimize the QEMU part [1], but it's still
worth to optimize the KVM to gain more benefits.

[1] https://lists.gnu.org/archive/html/qemu-devel/2021-08/msg04215.html

Signed-off-by: Longpeng(Mike) <longpeng2@huawei.com>
Message-Id: <20210827080003.2689-1-longpeng2@huawei.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2021-09-30 04:27:10 -04:00
Lai Jiangshan
8b8f9d753b KVM: X86: Don't check unsync if the original spte is writible
If the original spte is writable, the target gfn should not be the
gfn of synchronized shadowpage and can continue to be writable.

When !can_unsync, speculative must be false.  So when the check of
"!can_unsync" is removed, we need to move the label of "out" up.

Signed-off-by: Lai Jiangshan <laijs@linux.alibaba.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20210918005636.3675-11-jiangshanlai@gmail.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2021-09-30 04:27:10 -04:00
Lai Jiangshan
f1c4a88c41 KVM: X86: Don't unsync pagetables when speculative
We'd better only unsync the pagetable when there just was a really
write fault on a level-1 pagetable.

Signed-off-by: Lai Jiangshan <laijs@linux.alibaba.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20210918005636.3675-10-jiangshanlai@gmail.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2021-09-30 04:27:10 -04:00
Lai Jiangshan
cc2a8e66bb KVM: X86: Remove FNAME(update_pte)
Its solo caller is changed to use FNAME(prefetch_gpte) directly.

Signed-off-by: Lai Jiangshan <laijs@linux.alibaba.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20210918005636.3675-9-jiangshanlai@gmail.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2021-09-30 04:27:10 -04:00
Lai Jiangshan
5591c0694d KVM: X86: Zap the invalid list after remote tlb flushing
In mmu_sync_children(), it can zap the invalid list after remote tlb flushing.
Emptifying the invalid list ASAP might help reduce a remote tlb flushing
in some cases.

Signed-off-by: Lai Jiangshan <laijs@linux.alibaba.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20210918005636.3675-8-jiangshanlai@gmail.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2021-09-30 04:27:09 -04:00
Lai Jiangshan
c3e5e415bc KVM: X86: Change kvm_sync_page() to return true when remote flush is needed
Currently kvm_sync_page() returns true when there is any present spte.
But the return value is ignored in the callers.

Changing kvm_sync_page() to return true when remote flush is needed and
changing mmu->sync_page() not to directly flush can combine and reduce
remote flush requests.

Signed-off-by: Lai Jiangshan <laijs@linux.alibaba.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20210918005636.3675-7-jiangshanlai@gmail.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2021-09-30 04:27:09 -04:00
Lai Jiangshan
06152b2dec KVM: X86: Remove kvm_mmu_flush_or_zap()
Because local_flush is useless, kvm_mmu_flush_or_zap() can be removed
and kvm_mmu_remote_flush_or_zap is used instead.

Signed-off-by: Lai Jiangshan <laijs@linux.alibaba.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20210918005636.3675-6-jiangshanlai@gmail.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2021-09-30 04:27:09 -04:00
Lai Jiangshan
bd047e5440 KVM: X86: Don't flush current tlb on shadow page modification
After any shadow page modification, flushing tlb only on current VCPU
is weird due to other VCPU's tlb might still be stale.

In other words, if there is any mandatory tlb-flushing after shadow page
modification, SET_SPTE_NEED_REMOTE_TLB_FLUSH or remote_flush should be
set and the tlbs of all VCPUs should be flushed.  There is not point to
only flush current tlb except when the request is from vCPU's or pCPU's
activities.

If there was any bug that mandatory tlb-flushing is required and
SET_SPTE_NEED_REMOTE_TLB_FLUSH/remote_flush is failed to set, this patch
would expose the bug in a more destructive way.  The related code paths
are checked and no missing SET_SPTE_NEED_REMOTE_TLB_FLUSH is found yet.

Currently, there is no optional tlb-flushing after sync page related code
is changed to flush tlb timely.  So we can just remove these local flushing
code.

Signed-off-by: Lai Jiangshan <laijs@linux.alibaba.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20210918005636.3675-5-jiangshanlai@gmail.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2021-09-30 04:27:09 -04:00
Sean Christopherson
c6cecc4b93 KVM: x86/mmu: Complete prefetch for trailing SPTEs for direct, legacy MMU
Make a final call to direct_pte_prefetch_many() if there are "trailing"
SPTEs to prefetch, i.e. SPTEs for GFNs following the faulting GFN.  The
call to direct_pte_prefetch_many() in the loop only handles the case
where there are !PRESENT SPTEs preceding a PRESENT SPTE.

E.g. if the faulting GFN is a multiple of 8 (the prefetch size) and all
SPTEs for the following GFNs are !PRESENT, the loop will terminate with
"start = sptep+1" and not prefetch any SPTEs.

Prefetching trailing SPTEs as intended can drastically reduce the number
of guest page faults, e.g. accessing the first byte of every 4kb page in
a 6gb chunk of virtual memory, in a VM with 8gb of preallocated memory,
the number of pf_fixed events observed in L0 drops from ~1.75M to <0.27M.

Note, this only affects memory that is backed by 4kb pages as KVM doesn't
prefetch when installing hugepages.  Shadow paging prefetching is not
affected as it does not batch the prefetches due to the need to process
the corresponding guest PTE.  The TDP MMU is not affected because it
doesn't have prefetching, yet...

Fixes: 957ed9effd ("KVM: MMU: prefetch ptes when intercepted guest #PF")
Cc: Sergey Senozhatsky <senozhatsky@google.com>
Cc: Ben Gardon <bgardon@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210818235615.2047588-1-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2021-09-30 04:27:08 -04:00
Thomas Huth
22d7108ce4 KVM: selftests: Fix kvm_vm_free() in cr4_cpuid_sync and vmx_tsc_adjust tests
The kvm_vm_free() statement here is currently dead code, since the loop
in front of it can only be left with the "goto done" that jumps right
after the kvm_vm_free(). Fix it by swapping the locations of the "done"
label and the kvm_vm_free().

Signed-off-by: Thomas Huth <thuth@redhat.com>
Message-Id: <20210826074928.240942-1-thuth@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2021-09-30 04:27:08 -04:00
Colin Ian King
d22869aff4 kvm: selftests: Fix spelling mistake "missmatch" -> "mismatch"
There is a spelling mistake in an error message. Fix it.

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Message-Id: <20210826120752.12633-1-colin.king@canonical.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2021-09-30 04:27:08 -04:00
Sean Christopherson
25b9784586 KVM: x86: Manually retrieve CPUID.0x1 when getting FMS for RESET/INIT
Manually look for a CPUID.0x1 entry instead of bouncing through
kvm_cpuid() when retrieving the Family-Model-Stepping information for
vCPU RESET/INIT.  This fixes a potential undefined behavior bug due to
kvm_cpuid() using the uninitialized "dummy" param as the ECX _input_,
a.k.a. the index.

A more minimal fix would be to simply zero "dummy", but the extra work in
kvm_cpuid() is wasteful, and KVM should be treating the FMS retrieval as
an out-of-band access, e.g. same as how KVM computes guest.MAXPHYADDR.
Both Intel's SDM and AMD's APM describe the RDX value at RESET/INIT as
holding the CPU's FMS information, not as holding CPUID.0x1.EAX.  KVM's
usage of CPUID entries to get FMS is simply a pragmatic approach to avoid
having yet another way for userspace to provide inconsistent data.

No functional change intended.

Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Jim Mattson <jmattson@google.com>
Message-Id: <20210929222426.1855730-3-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2021-09-30 04:27:08 -04:00
Sean Christopherson
62dd57dd67 KVM: x86: WARN on non-zero CRs at RESET to detect improper initalization
WARN if CR0, CR3, or CR4 are non-zero at RESET, which given the current
KVM implementation, really means WARN if they're not zeroed at vCPU
creation.  VMX in particular has several ->set_*() flows that read other
registers to handle side effects, and because those flows are common to
RESET and INIT, KVM subtly relies on emulated/virtualized registers to be
zeroed at vCPU creation in order to do the right thing at RESET.

Use CRs as a sentinel because they are most likely to be written as side
effects, and because KVM specifically needs CR0.PG and CR0.PE to be '0'
to correctly reflect the state of the vCPU's MMU.  CRs are also loaded
and stored from/to the VMCS, and so adds some level of coverage to verify
that KVM doesn't conflate zero-allocating the VMCS with properly
initializing the VMCS with VMWRITEs.

Note, '0' is somewhat arbitrary, vCPU creation can technically stuff any
value for a register so long as it's coherent with respect to the current
vCPU state.  In practice, '0' works for all registers and is convenient.

Suggested-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20210921000303.400537-11-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2021-09-30 04:27:07 -04:00
Sean Christopherson
9ebe530b9f KVM: SVM: Move RESET emulation to svm_vcpu_reset()
Move RESET emulation for SVM vCPUs to svm_vcpu_reset(), and drop an extra
init_vmcb() from svm_create_vcpu() in the process.  Hopefully KVM will
someday expose a dedicated RESET ioctl(), and in the meantime separating
"create" from "RESET" is a nice cleanup.

Keep the call to svm_switch_vmcb() so that misuse of svm->vmcb at worst
breaks the guest, e.g. premature accesses doesn't cause a NULL pointer
dereference.

Cc: Reiji Watanabe <reijiw@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20210921000303.400537-10-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2021-09-30 04:27:07 -04:00
Sean Christopherson
06692e4b80 KVM: VMX: Move RESET emulation to vmx_vcpu_reset()
Move vCPU RESET emulation, including initializating of select VMCS state,
to vmx_vcpu_reset().  Drop the open coded "vCPU load" sequence, as
->vcpu_reset() is invoked while the vCPU is properly loaded (which is
kind of the point of ->vcpu_reset()...).  Hopefully KVM will someday
expose a dedicated RESET ioctl(), and in the meantime separating "create"
from "RESET" is a nice cleanup.

Deferring VMCS initialization is effectively a nop as it's impossible to
safely access the VMCS between the current call site and its new home, as
both the vCPU and the pCPU are put immediately after init_vmcs(), i.e.
the VMCS isn't guaranteed to be loaded.

Note, task preemption is not a problem as vmx_sched_in() _can't_ touch
the VMCS as ->sched_in() is invoked before the vCPU, and thus VMCS, is
reloaded.  I.e. the preemption path also can't consume VMCS state.

Cc: Reiji Watanabe <reijiw@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20210921000303.400537-9-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2021-09-30 04:27:07 -04:00
Sean Christopherson
d06567353e KVM: VMX: Drop explicit zeroing of MSR guest values at vCPU creation
Don't zero out user return and nested MSRs during vCPU creation, and
instead rely on vcpu_vmx being zero-allocated.  Explicitly zeroing MSRs
is not wrong, and is in fact necessary if KVM ever emulates vCPU RESET
outside of vCPU creation, but zeroing only a subset of MSRs is confusing.

Poking directly into KVM's backing is also undesirable in that it doesn't
scale and is error prone.  Ideally KVM would have a common RESET path for
all MSRs, e.g. by expanding kvm_set_msr(), which would obviate the need
for this out-of-bad code (to support standalone RESET).

No functional change intended.

Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20210921000303.400537-8-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2021-09-30 04:27:07 -04:00
Sean Christopherson
583d369b36 KVM: x86: Fold fx_init() into kvm_arch_vcpu_create()
Move the few bits of relevant fx_init() code into kvm_arch_vcpu_create(),
dropping the superfluous check on vcpu->arch.guest_fpu that was blindly
and wrongly added by commit ed02b21309 ("KVM: SVM: Guest FPU state
save/restore not needed for SEV-ES guest").

Note, KVM currently allocates and then frees FPU state for SEV-ES guests,
rather than avoid the allocation in the first place.  While that approach
is inarguably inefficient and unnecessary, it's a cleanup for the future.

No functional change intended.

Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20210921000303.400537-7-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2021-09-30 04:27:06 -04:00
Sean Christopherson
e8f65b9bb4 KVM: x86: Remove defunct setting of XCR0 for guest during vCPU create
Drop code to initialize XCR0 during fx_init(), a.k.a. vCPU creation, as
XCR0 has been initialized during kvm_vcpu_reset() (for RESET) since
commit a554d207dc ("KVM: X86: Processor States following Reset or INIT").

Back when XCR0 support was added by commit 2acf923e38 ("KVM: VMX:
Enable XSAVE/XRSTOR for guest"), KVM didn't differentiate between RESET
and INIT.  Ignoring the fact that calling fx_init() for INIT is obviously
wrong, e.g. FPU state after INIT is not the same as after RESET, setting
XCR0 in fx_init() was correct.

Eventually fx_init() got moved to kvm_arch_vcpu_init(), a.k.a. vCPU
creation (ignore the terrible name) by commit 0ee6a51725 ("x86/fpu,
kvm: Simplify fx_init()").  Finally, commit 95a0d01eef ("KVM: x86: Move
all vcpu init code into kvm_arch_vcpu_create()") killed off
kvm_arch_vcpu_init(), leaving behind the oddity of redundant setting of
guest state during vCPU creation.

No functional change intended.

Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20210921000303.400537-6-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2021-09-30 04:27:06 -04:00
Sean Christopherson
5ebbc470d7 KVM: x86: Remove defunct setting of CR0.ET for guests during vCPU create
Drop code to set CR0.ET for the guest during initialization of the guest
FPU.  The code was added as a misguided bug fix by commit 380102c8e4
("KVM Set the ET flag in CR0 after initializing FX") to resolve an issue
where vcpu->cr0 (now vcpu->arch.cr0) was not correctly initialized on SVM
systems.  While init_vmcb() did set CR0.ET, it only did so in the VMCB,
and subtly did not update vcpu->cr0.  Stuffing CR0.ET worked around the
immediate problem, but did not fix the real bug of vcpu->cr0 and the VMCB
being out of sync.  That underlying bug was eventually remedied by commit
18fa000ae4 ("KVM: SVM: Reset cr0 properly on vcpu reset").

No functional change intended.

Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20210921000303.400537-5-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2021-09-30 04:27:06 -04:00
Sean Christopherson
ff8828c84f KVM: x86: Do not mark all registers as avail/dirty during RESET/INIT
Do not blindly mark all registers as available+dirty at RESET/INIT, and
instead rely on writes to registers to go through the proper mutators or
to explicitly mark registers as dirty.  INIT in particular does not blindly
overwrite all registers, e.g. select bits in CR0 are preserved across INIT,
thus marking registers available+dirty without first reading the register
from hardware is incorrect.

In practice this is a benign bug as KVM doesn't let the guest control CR0
bits that are preserved across INIT, and all other true registers are
explicitly written during the RESET/INIT flows.  The PDPTRs and EX_INFO
"registers" are not explicitly written, but accessing those values during
RESET/INIT is nonsensical and would be a KVM bug regardless of register
caching.

Fixes: 66f7b72e11 ("KVM: x86: Make register state after reset conform to specification")
[sean: !!! NOT FOR STABLE !!!]
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20210921000303.400537-4-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2021-09-30 04:27:05 -04:00
Sean Christopherson
94c641ba7a KVM: x86: Simplify retrieving the page offset when loading PDTPRs
Replace impressively complex "logic" for computing the page offset from
CR3 when loading PDPTRs.  Unlike other paging modes, the address held in
CR3 for PAE paging is 32-byte aligned, i.e. occupies bits 31:5, thus bits
11:5 need to be used as the offset from the gfn when reading PDPTRs.

The existing calculation originated in commit 1342d3536d ("[PATCH] KVM:
MMU: Load the pae pdptrs on cr3 change like the processor does"), which
read the PDPTRs from guest memory as individual 8-byte loads.  At the
time, the so called "offset" was the base index of PDPTR0 as a _u64_, not
a byte offset.  Naming aside, the computation was useful and arguably
simplified the overall flow.

Unfortunately, when commit 195aefde9c ("KVM: Add general accessors to
read and write guest memory") added accessors with offsets at byte
granularity, the cleverness of the original code was lost and KVM was
left with convoluted code for a simple operation.

No functional change intended.

Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20210831164224.1119728-4-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2021-09-30 04:27:05 -04:00
Sean Christopherson
15cabbc259 KVM: x86: Subsume nested GPA read helper into load_pdptrs()
Open code the call to mmu->translate_gpa() when loading nested PDPTRs and
kill off the existing helper, kvm_read_guest_page_mmu(), to discourage
incorrect use.  Reading guest memory straight from an L2 GPA is extremely
rare (as evidenced by the lack of users), as very few constructs in x86
specify physical addresses, even fewer are virtualized by KVM, and even
fewer yet require emulation of L2 by L0 KVM.

No functional change intended.

Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20210831164224.1119728-3-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2021-09-30 04:27:05 -04:00
Juergen Gross
a1c42ddedf kvm: rename KVM_MAX_VCPU_ID to KVM_MAX_VCPU_IDS
KVM_MAX_VCPU_ID is not specifying the highest allowed vcpu-id, but the
number of allowed vcpu-ids. This has already led to confusion, so
rename KVM_MAX_VCPU_ID to KVM_MAX_VCPU_IDS to make its semantics more
clear

Suggested-by: Eduardo Habkost <ehabkost@redhat.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20210913135745.13944-3-jgross@suse.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2021-09-30 04:27:05 -04:00
Juergen Gross
1e254d0d86 Revert "x86/kvm: fix vcpu-id indexed array sizes"
This reverts commit 76b4f357d0.

The commit has the wrong reasoning, as KVM_MAX_VCPU_ID is not defining the
maximum allowed vcpu-id as its name suggests, but the number of vcpu-ids.
So revert this patch again.

Suggested-by: Eduardo Habkost <ehabkost@redhat.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20210913135745.13944-2-jgross@suse.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2021-09-30 04:27:04 -04:00
Vitaly Kuznetsov
620b2438ab KVM: Make kvm_make_vcpus_request_mask() use pre-allocated cpu_kick_mask
kvm_make_vcpus_request_mask() already disables preemption so just like
kvm_make_all_cpus_request_except() it can be switched to using
pre-allocated per-cpu cpumasks. This allows for improvements for both
users of the function: in Hyper-V emulation code 'tlb_flush' can now be
dropped from 'struct kvm_vcpu_hv' and kvm_make_scan_ioapic_request_mask()
gets rid of dynamic allocation.

cpumask_available() checks in kvm_make_vcpu_request() and
kvm_kick_many_cpus() can now be dropped as they checks for an impossible
condition: kvm_init() makes sure per-cpu masks are allocated.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Reviewed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20210903075141.403071-9-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2021-09-30 04:27:04 -04:00
Vitaly Kuznetsov
baff59ccdc KVM: Pre-allocate cpumasks for kvm_make_all_cpus_request_except()
Allocating cpumask dynamically in zalloc_cpumask_var() is not ideal.
Allocation is somewhat slow and can (in theory and when CPUMASK_OFFSTACK)
fail. kvm_make_all_cpus_request_except() already disables preemption so
we can use pre-allocated per-cpu cpumasks instead.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Reviewed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20210903075141.403071-8-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2021-09-30 04:27:04 -04:00
Vitaly Kuznetsov
381cecc5d7 KVM: Drop 'except' parameter from kvm_make_vcpus_request_mask()
Both remaining callers of kvm_make_vcpus_request_mask() pass 'NULL' for
'except' parameter so it can just be dropped.

No functional change intended ©.

Suggested-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20210903075141.403071-6-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2021-09-30 04:27:04 -04:00
Vitaly Kuznetsov
ae0946cd36 KVM: Optimize kvm_make_vcpus_request_mask() a bit
Iterating over set bits in 'vcpu_bitmap' should be faster than going
through all vCPUs, especially when just a few bits are set.

Drop kvm_make_vcpus_request_mask() call from kvm_make_all_cpus_request_except()
to avoid handling the special case when 'vcpu_bitmap' is NULL, move the
code to kvm_make_all_cpus_request_except() itself.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Reviewed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20210903075141.403071-5-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2021-09-30 04:27:03 -04:00
Vitaly Kuznetsov
6470accc7b KVM: x86: hyper-v: Avoid calling kvm_make_vcpus_request_mask() with vcpu_mask==NULL
In preparation to making kvm_make_vcpus_request_mask() use for_each_set_bit()
switch kvm_hv_flush_tlb() to calling kvm_make_all_cpus_request() for 'all cpus'
case.

Note: kvm_make_all_cpus_request() (unlike kvm_make_vcpus_request_mask())
currently dynamically allocates cpumask on each call and this is suboptimal.
Both kvm_make_all_cpus_request() and kvm_make_vcpus_request_mask() are
going to be switched to using pre-allocated per-cpu masks.

Reviewed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20210903075141.403071-4-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2021-09-30 04:27:03 -04:00
Yang Li
11476d277e KVM: use vma_pages() helper
Use vma_pages function on vma object instead of explicit computation.

Fix the following coccicheck warning:
./virt/kvm/kvm_main.c:3526:29-35: WARNING: Consider using vma_pages
helper on vma

Reported-by: Abaci Robot <abaci@linux.alibaba.com>
Signed-off-by: Yang Li <yang.lee@linux.alibaba.com>
Message-Id: <1632900526-119643-1-git-send-email-yang.lee@linux.alibaba.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2021-09-30 04:27:03 -04:00
Vitaly Kuznetsov
feb3162f9d KVM: nVMX: Reset vmxon_ptr upon VMXOFF emulation.
Currently, 'vmx->nested.vmxon_ptr' is not reset upon VMXOFF
emulation. This is not a problem per se as we never access
it when !vmx->nested.vmxon. But this should be done to avoid
any issue in the future.

Also, initialize the vmxon_ptr when vcpu is created.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Yu Zhang <yu.c.zhang@linux.intel.com>
Message-Id: <20210929175154.11396-3-yu.c.zhang@linux.intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2021-09-30 04:27:02 -04:00
Yu Zhang
64c785082c KVM: nVMX: Use INVALID_GPA for pointers used in nVMX.
Clean up nested.c and vmx.c by using INVALID_GPA instead of "-1ull",
to denote an invalid address in nested VMX. Affected addresses are
the ones of VMXON region, current VMCS, VMCS link pointer, virtual-
APIC page, ENCLS-exiting bitmap, and IO bitmap etc.

Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Yu Zhang <yu.c.zhang@linux.intel.com>
Message-Id: <20210929175154.11396-2-yu.c.zhang@linux.intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2021-09-30 04:27:02 -04:00
Sean Christopherson
7b0035eaa7 KVM: selftests: Ensure all migrations are performed when test is affined
Rework the CPU selection in the migration worker to ensure the specified
number of migrations are performed when the test iteslf is affined to a
subset of CPUs.  The existing logic skips iterations if the target CPU is
not in the original set of possible CPUs, which causes the test to fail
if too many iterations are skipped.

  ==== Test Assertion Failure ====
  rseq_test.c:228: i > (NR_TASK_MIGRATIONS / 2)
  pid=10127 tid=10127 errno=4 - Interrupted system call
     1  0x00000000004018e5: main at rseq_test.c:227
     2  0x00007fcc8fc66bf6: ?? ??:0
     3  0x0000000000401959: _start at ??:?
  Only performed 4 KVM_RUNs, task stalled too much?

Calculate the min/max possible CPUs as a cheap "best effort" to avoid
high runtimes when the test is affined to a small percentage of CPUs.
Alternatively, a list or xarray of the possible CPUs could be used, but
even in a horrendously inefficient setup, such optimizations are not
needed because the runtime is completely dominated by the cost of
migrating the task, and the absolute runtime is well under a minute in
even truly absurd setups, e.g. running on a subset of vCPUs in a VM that
is heavily overcommited (16 vCPUs per pCPU).

Fixes: 61e52f1630 ("KVM: selftests: Add a test for KVM_RUN+rseq to detect task migration bugs")
Reported-by: Dongli Zhang <dongli.zhang@oracle.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210929234112.1862848-1-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2021-09-30 04:25:57 -04:00
Ville Syrjälä
7eadfbfe0f drm/i915: Drop pointless fixed_mode checks from dsi code
We don't support dsi displays without a fixed mode, so drop
all the pointless checks.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210923200109.4459-7-ville.syrjala@linux.intel.com
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
2021-09-30 11:21:35 +03:00
Ville Syrjälä
f5b8c31609 drm/i915: Reject user modes that don't match fixed mode's refresh rate
When using a panel with a fixed mode we don't change the refresh
rate of the display. Reject any user requested mode which doesn't
match that fixed refresh rate.

Unfortunately when Xorg sees the scaling_mode property on the
connecor it likes to automagically cook up modes whose refresh
rate is a fair bit off from the fixed refresh rate we use. So
we have to give it some extra latitude so that we don't start to
reject all of it.

v2: sDVO now uses intel_panel_compute_config() too
v3: Add a debug message to inform the user what happened

References: https://gitlab.freedesktop.org/drm/intel/-/issues/2939
References: https://gitlab.freedesktop.org/drm/intel/-/issues/3969
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210929184536.8332-1-ville.syrjala@linux.intel.com
2021-09-30 11:20:40 +03:00