[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

[PATCH 00/15] perf: KVM: Fix, optimize, and clean up callbacks

This started out as a small series[1] to fix a KVM bug related to Intel PT
interrupt handling and snowballed horribly.

The main problem being addressed is that the perf_guest_cbs are shared by
all CPUs, can be nullified by KVM during module unload, and are not
protected against concurrent access from NMI context.

The bug has escaped notice because all dereferences of perf_guest_cbs
follow the same "perf_guest_cbs && perf_guest_cbs->is_in_guest()" pattern,
and AFAICT the compiler never reloads perf_guest_cbs in this sequence.
The compiler does reload perf_guest_cbs for any future dereferences, but
the ->is_in_guest() guard all but guarantees the PMI handler will win the
race, e.g. to nullify perf_guest_cbs, KVM has to completely exit the guest
and teardown down all VMs before it can be unloaded.

But with help, e.g. READ_ONCE(perf_guest_cbs), unloading kvm_intel can
trigger a NULL pointer derference (see below).  Manual intervention aside,
the bug is a bit of a time bomb, e.g. my patch 3 from the original PT
handling series would have omitted the ->is_in_guest() guard.

This series fixes the problem by making the callbacks per-CPU, and
registering/unregistering the callbacks only with preemption disabled
(except for the Xen case, which doesn't unregister).

This approach also allows for several nice cleanups in this series.
KVM x86 and arm64 can share callbacks, KVM x86 drops its somewhat
redundant current_vcpu, and the retpoline that is currently hit when KVM
is loaded (due to always checking ->is_in_guest()) goes away (it's still
there when running as Xen Dom0).

Changing to per-CPU callbacks also provides a good excuse to excise
copy+paste code from architectures that can't possibly have guest

This series conflicts horribly with a proposed patch[2] to use static
calls for perf_guest_cbs.  But that patch is broken as it completely
fails to handle unregister, and it's not clear to me whether or not
it can correctly handle unregister without fixing the underlying race
(I don't know enough about the code patching for static calls).

This tweak

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 1eb45139fcc6..202e5ad97f82 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -2954,7 +2954,7 @@ unsigned long perf_misc_flags(struct pt_regs *regs)
        int misc = 0;

-       if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
+       if (READ_ONCE(perf_guest_cbs) && 
READ_ONCE(perf_guest_cbs)->is_in_guest()) {
                if (perf_guest_cbs->is_user_mode())
                        misc |= PERF_RECORD_MISC_GUEST_USER;

while spamming module load/unload leads to:

  BUG: kernel NULL pointer dereference, address: 0000000000000000
  #PF: supervisor read access in kernel mode
  #PF: error_code(0x0000) - not-present page
  PGD 0 P4D 0
  Oops: 0000 [#1] PREEMPT SMP
  CPU: 6 PID: 1825 Comm: stress Not tainted 5.14.0-rc2+ #459
  Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015
  RIP: 0010:perf_misc_flags+0x1c/0x70
  Call Trace:

[1] https://lkml.kernel.org/r/20210823193709.55886-1-seanjc@xxxxxxxxxx
[2] https://lkml.kernel.org/r/20210806133802.3528-2-lingshan.zhu@xxxxxxxxx

Sean Christopherson (15):
  KVM: x86: Register perf callbacks after calling vendor's
  KVM: x86: Register Processor Trace interrupt hook iff PT enabled in
  perf: Stop pretending that perf can handle multiple guest callbacks
  perf: Force architectures to opt-in to guest callbacks
  perf: Track guest callbacks on a per-CPU basis
  KVM: x86: Register perf callbacks only when actively handling
  KVM: Use dedicated flag to track if KVM is handling an NMI from guest
  KVM: x86: Drop current_vcpu in favor of kvm_running_vcpu
  KVM: arm64: Register/unregister perf callbacks at vcpu load/put
  KVM: Move x86's perf guest info callbacks to generic KVM
  KVM: x86: Move Intel Processor Trace interrupt handler to vmx.c
  KVM: arm64: Convert to the generic perf callbacks
  KVM: arm64: Drop perf.c and fold its tiny bit of code into pmu.c
  perf: Disallow bulk unregistering of guest callbacks and do cleanup
  perf: KVM: Indicate "in guest" via NULL ->is_in_guest callback

 arch/arm/kernel/perf_callchain.c   | 28 ++------------
 arch/arm64/Kconfig                 |  1 +
 arch/arm64/include/asm/kvm_host.h  |  8 +++-
 arch/arm64/kernel/perf_callchain.c | 18 ++++++---
 arch/arm64/kvm/Makefile            |  2 +-
 arch/arm64/kvm/arm.c               | 13 ++++++-
 arch/arm64/kvm/perf.c              | 62 ------------------------------
 arch/arm64/kvm/pmu.c               |  8 ++++
 arch/csky/kernel/perf_callchain.c  | 10 -----
 arch/nds32/kernel/perf_event_cpu.c | 29 ++------------
 arch/riscv/kernel/perf_callchain.c | 10 -----
 arch/x86/Kconfig                   |  1 +
 arch/x86/events/core.c             | 17 +++++---
 arch/x86/events/intel/core.c       |  7 ++--
 arch/x86/include/asm/kvm_host.h    |  4 +-
 arch/x86/kvm/pmu.c                 |  2 +-
 arch/x86/kvm/pmu.h                 |  1 +
 arch/x86/kvm/svm/svm.c             |  2 +-
 arch/x86/kvm/vmx/vmx.c             | 25 ++++++++++--
 arch/x86/kvm/x86.c                 | 54 +++-----------------------
 arch/x86/kvm/x86.h                 | 12 +++---
 arch/x86/xen/pmu.c                 |  2 +-
 include/kvm/arm_pmu.h              |  1 +
 include/linux/kvm_host.h           | 12 ++++++
 include/linux/perf_event.h         | 33 ++++++++++++----
 init/Kconfig                       |  3 ++
 kernel/events/core.c               | 28 ++++++++------
 virt/kvm/kvm_main.c                | 42 ++++++++++++++++++++
 28 files changed, 204 insertions(+), 231 deletions(-)
 delete mode 100644 arch/arm64/kvm/perf.c




Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.