linux_dsm_epyc7002/arch/x86/kvm
Wanpeng Li 1d518c6820 KVM: LAPIC: Fix reentrancy issues with preempt notifiers
Preempt can occur in the preemption timer expiration handler:

          CPU0                    CPU1

  preemption timer vmexit
  handle_preemption_timer(vCPU0)
    kvm_lapic_expired_hv_timer
      hv_timer_is_use == true
  sched_out
                           sched_in
                           kvm_arch_vcpu_load
                             kvm_lapic_restart_hv_timer
                               restart_apic_timer
                                 start_hv_timer
                                   already-expired timer or sw timer triggerd in the window
                                 start_sw_timer
                                   cancel_hv_timer
                           /* back in kvm_lapic_expired_hv_timer */
                           cancel_hv_timer
                             WARN_ON(!apic->lapic_timer.hv_timer_in_use);  ==> Oops

This can be reproduced if CONFIG_PREEMPT is enabled.

------------[ cut here ]------------
 WARNING: CPU: 4 PID: 2972 at /home/kernel/linux/arch/x86/kvm//lapic.c:1563 kvm_lapic_expired_hv_timer+0x9e/0xb0 [kvm]
 CPU: 4 PID: 2972 Comm: qemu-system-x86 Tainted: G           OE   4.13.0-rc2+ #16
 RIP: 0010:kvm_lapic_expired_hv_timer+0x9e/0xb0 [kvm]
Call Trace:
  handle_preemption_timer+0xe/0x20 [kvm_intel]
  vmx_handle_exit+0xb8/0xd70 [kvm_intel]
  kvm_arch_vcpu_ioctl_run+0xdd1/0x1be0 [kvm]
  ? kvm_arch_vcpu_load+0x47/0x230 [kvm]
  ? kvm_arch_vcpu_load+0x62/0x230 [kvm]
  kvm_vcpu_ioctl+0x340/0x700 [kvm]
  ? kvm_vcpu_ioctl+0x340/0x700 [kvm]
  ? __fget+0xfc/0x210
  do_vfs_ioctl+0xa4/0x6a0
  ? __fget+0x11d/0x210
  SyS_ioctl+0x79/0x90
  do_syscall_64+0x81/0x220
  entry_SYSCALL64_slow_path+0x25/0x25
 ------------[ cut here ]------------
 WARNING: CPU: 4 PID: 2972 at /home/kernel/linux/arch/x86/kvm//lapic.c:1498 cancel_hv_timer.isra.40+0x4f/0x60 [kvm]
 CPU: 4 PID: 2972 Comm: qemu-system-x86 Tainted: G        W  OE   4.13.0-rc2+ #16
 RIP: 0010:cancel_hv_timer.isra.40+0x4f/0x60 [kvm]
Call Trace:
  kvm_lapic_expired_hv_timer+0x3e/0xb0 [kvm]
  handle_preemption_timer+0xe/0x20 [kvm_intel]
  vmx_handle_exit+0xb8/0xd70 [kvm_intel]
  kvm_arch_vcpu_ioctl_run+0xdd1/0x1be0 [kvm]
  ? kvm_arch_vcpu_load+0x47/0x230 [kvm]
  ? kvm_arch_vcpu_load+0x62/0x230 [kvm]
  kvm_vcpu_ioctl+0x340/0x700 [kvm]
  ? kvm_vcpu_ioctl+0x340/0x700 [kvm]
  ? __fget+0xfc/0x210
  do_vfs_ioctl+0xa4/0x6a0
  ? __fget+0x11d/0x210
  SyS_ioctl+0x79/0x90
  do_syscall_64+0x81/0x220
  entry_SYSCALL64_slow_path+0x25/0x25

This patch fixes it by making the caller of cancel_hv_timer, start_hv_timer
and start_sw_timer be in preemption-disabled regions, which trivially
avoid any reentrancy issue with preempt notifier.

Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Wanpeng Li <wanpeng.li@hotmail.com>
[Add more WARNs. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2017-07-26 19:04:53 +02:00
..
cpuid.c KVM: cpuid: Fix read/write out-of-bounds vulnerability in cpuid emulation 2017-06-08 15:38:21 +02:00
cpuid.h kvm: x86: Guest BNDCFGS requires guest MPX support 2017-06-07 16:28:15 +02:00
debugfs.c kvm: x86: export TSC information to user-space 2016-09-16 16:57:48 +02:00
emulate.c PPC: 2017-07-06 18:38:31 -07:00
hyperv.c kvm: x86: hyperv: avoid livelock in oneshot SynIC timers 2017-07-20 17:00:00 +02:00
hyperv.h kvm: x86: hyperv: make VP_INDEX managed by userspace 2017-07-14 16:28:18 +02:00
i8254.c KVM: x86: take slots_lock in kvm_free_pit 2017-07-12 22:38:26 +02:00
i8254.h KVM: x86: Handle the kthread worker using the new API 2016-12-08 15:31:11 +01:00
i8259.c KVM: x86: simplify pic_ioport_read() 2017-04-12 20:17:15 +02:00
ioapic.c KVM: x86: rename kvm_vcpu_request_scan_ioapic() 2017-04-12 20:17:14 +02:00
ioapic.h KVM: x86: convert kvm_(set|get)_ioapic() into void 2017-04-12 20:17:14 +02:00
irq_comm.c KVM: x86: don't hold kvm->lock in KVM_SET_GSI_ROUTING 2017-05-02 14:45:45 +02:00
irq.c KVM: x86: get rid of pic_irqchip() 2017-04-12 20:17:13 +02:00
irq.h KVM: x86: don't hold kvm->lock in KVM_SET_GSI_ROUTING 2017-05-02 14:45:45 +02:00
Kconfig x86: add MULTIUSER dependency for KVM 2017-07-19 16:19:14 +02:00
kvm_cache_regs.h KVM, pkeys: add pkeys support for permission_fault 2016-03-22 16:23:37 +01:00
lapic.c KVM: LAPIC: Fix reentrancy issues with preempt notifiers 2017-07-26 19:04:53 +02:00
lapic.h KVM: lapic: reorganize restart_apic_timer 2017-06-29 18:18:52 +02:00
Makefile KVM: x86: drop legacy device assignment 2017-04-07 16:49:00 +02:00
mmu_audit.c kvm: rename pfn_t to kvm_pfn_t 2016-01-15 17:56:32 -08:00
mmu.c KVM: async_pf: Let guest support delivery of async_pf from guest mode 2017-07-14 14:26:16 +02:00
mmu.h KVM: async_pf: Add L1 guest async_pf #PF vmexit handler 2017-07-14 14:25:24 +02:00
mmutrace.h kvm: x86: mmu: allow A/D bits to be disabled in an mmu 2017-07-03 11:19:54 +02:00
mtrr.c KVM: MTRR: fix kvm_mtrr_check_gfn_range_consistency page fault 2016-07-05 16:14:43 +02:00
page_track.c mm: introduce kv[mz]alloc helpers 2017-05-08 17:15:12 -07:00
paging_tmpl.h KVM: nVMX: fix EPT permissions as reported in exit qualification 2017-05-15 18:22:40 +02:00
pmu_amd.c perf/x86/amd: Make HW_CACHE_REFERENCES and HW_CACHE_MISSES measure L2 2016-09-16 16:19:49 +02:00
pmu_intel.c KVM: x86/vPMU: fix undefined shift in intel_pmu_refresh() 2017-05-19 19:59:27 +02:00
pmu.c KVM: x86: never specify a sample period for virtualized in_tx_cp counters 2017-03-01 14:19:46 +01:00
pmu.h KVM: x86/vPMU: Define kvm_pmu_ops to support vPMU function dispatch 2015-06-23 14:12:14 +02:00
svm.c KVM: async_pf: Force a nested vmexit if the injected #PF is async_pf 2017-07-14 14:26:16 +02:00
trace.h KVM: x86: support using the vmx preemption timer for tsc deadline timer 2016-06-16 10:07:48 +02:00
tss.h
vmx.c KVM: nVMX: Fix loss of L2's NMI blocking state 2017-07-26 18:57:46 +02:00
x86.c KVM: x86: do mask out upper bits of PAE CR3 2017-07-26 18:57:45 +02:00
x86.h kvm: better MWAIT emulation for guests 2017-04-21 12:50:28 +02:00