x86/kprobes: Fix crash when probing CS CALL instructionsgrafted

When using eBPF to probe CS CALL instructions within a function,
a crash can be triggered.

The eBPF tool probes offset 257 of the __hrtimer_run_queues()
function:

<__hrtimer_run_queues+249>:  nopl   0x0(%rax,%rax,1)
<__hrtimer_run_queues+254>:  mov    %r14,%rdi
<__hrtimer_run_queues+257>:  cs call <__x86_indirect_thunk_r12>
<__hrtimer_run_queues+263>:  mov    %eax,%r12d
<__hrtimer_run_queues+266>:  xchg   %ax,%ax
<__hrtimer_run_queues+268>:  mov    %r13,%rdi

Which triggers this crash:

  BUG: unable to handle page fault for address: 00000000000f41c9
  #PF: supervisor write access in kernel mode
  #PF: error_code(0x0002) - not-present page
  PGD 0 P4D 0
  Oops: 0002 [#1] SMP NOPTI
  CPU: 1 PID: 0 Comm: swapper/1 Kdump: loaded Tainted: P
  RIP: 0010:__hrtimer_run_queues+0x106/0x230

Note that __hrtimer_run_queues+0x106 is __hrtimer_run_queues+262, which is
at the 6th byte of the above CS CALL instruction. Since the CS CALL
instruction occupies 6 bytes, the exception occurred in the middle of that
call instruction.

The root cause is that when using eBPF tools to probe in the middle of a
function, a kprobe with INT3 is used as the underlying implementation.

During single-step emulation of the original CALL instruction,
int3_emulate_call() assumes that the probed CALL instruction is 5 bytes
long. However, the actual CS-prefixed CALL instruction occupies 6 bytes,
so it constructs an incorrect exception return address. When the CPU
returns from the kprobe handler, the next instruction to be executed is at
the address of the last byte of that CS CALL instruction. Coincidentally,
starting from that address, the CPU fetches and decodes a completely
different instruction, which ultimately triggers a kernel crash.

Fix the issue by using the actual instruction length obtained from
the instruction decoder when constructing the exception return
address, rather than relying on the hardcoded CALL_INSN_SIZE macro.

[ mingo: Refined the changelog ]

Fixes: 6256e668b7af ("x86/kprobes: Use int3 instead of debug trap for single-step")
Suggested-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Jinke Han <jinkehan@didiglobal.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Acked-by: Yafang Shao <laoar.shao@gmail.com>
Acked-by: Borislav Petkov <bp@alien8.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://patch.msgid.link/20260908073742.GA10517@didi-ThinkCentre-M920t-N000

1 files changed, 257 insertions, 0 deletions

diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
new file mode 100644
index 000000000..b6bc2fc86
--- /dev/null
+++ b/arch/powerpc/kvm/Kconfig
@@ -0,0 +1,257 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# KVM configuration
+#
+
+source "virt/kvm/Kconfig"
+
+menuconfig VIRTUALIZATION
+	bool "Virtualization"
+	help
+	  Say Y here to get to see options for using your Linux host to run
+	  other operating systems inside virtual machines (guests).
+	  This option alone does not add any kernel code.
+
+	  If you say N, all options in this submenu will be skipped and
+	  disabled.
+
+if VIRTUALIZATION
+
+config KVM
+	bool
+	select KVM_COMMON
+	select KVM_VFIO
+	select HAVE_KVM_IRQ_BYPASS
+	select VIRT_XFER_TO_GUEST_WORK
+
+config KVM_BOOK3S_HANDLER
+	bool
+
+config KVM_BOOK3S_32_HANDLER
+	bool
+	select KVM_BOOK3S_HANDLER
+	select KVM_MMIO
+
+config KVM_BOOK3S_64_HANDLER
+	bool
+	select KVM_BOOK3S_HANDLER
+
+config KVM_BOOK3S_PR_POSSIBLE
+	bool
+	select KVM_MMIO
+
+config KVM_BOOK3S_HV_POSSIBLE
+	bool
+
+config KVM_BOOK3S_32
+	tristate "KVM support for PowerPC book3s_32 processors"
+	depends on PPC_BOOK3S_32 && !SMP && !PTE_64BIT
+	depends on !CONTEXT_TRACKING_USER
+	select KVM
+	select KVM_BOOK3S_32_HANDLER
+	select KVM_BOOK3S_PR_POSSIBLE
+	select PPC_FPU
+	help
+	  Support running unmodified book3s_32 guest kernels
+	  in virtual machines on book3s_32 host processors.
+
+	  This module provides access to the hardware capabilities through
+	  a character device node named /dev/kvm.
+
+	  If unsure, say N.
+
+config KVM_BOOK3S_64
+	tristate "KVM support for PowerPC book3s_64 processors"
+	depends on PPC_BOOK3S_64
+	select KVM_BOOK3S_64_HANDLER
+	select KVM
+	select KVM_BOOK3S_PR_POSSIBLE if !KVM_BOOK3S_HV_POSSIBLE
+	select PPC_64S_HASH_MMU
+	select SPAPR_TCE_IOMMU if IOMMU_SUPPORT && (PPC_PSERIES || PPC_POWERNV)
+	help
+	  Support running unmodified book3s_64 and book3s_32 guest kernels
+	  in virtual machines on book3s_64 host processors.
+
+	  This module provides access to the hardware capabilities through
+	  a character device node named /dev/kvm.
+
+	  If unsure, say N.
+
+config KVM_BOOK3S_64_HV
+	tristate "KVM for POWER7 and later using hypervisor mode in host"
+	depends on KVM_BOOK3S_64 && PPC_POWERNV
+	select KVM_BOOK3S_HV_POSSIBLE
+	select KVM_BOOK3S_HV_PMU
+	select CMA
+	help
+	  Support running unmodified book3s_64 guest kernels in
+	  virtual machines on POWER7 and newer processors that have
+	  hypervisor mode available to the host.
+
+	  If you say Y here, KVM will use the hardware virtualization
+	  facilities of POWER7 (and later) processors, meaning that
+	  guest operating systems will run at full hardware speed
+	  using supervisor and user modes.  However, this also means
+	  that KVM is not usable under PowerVM (pHyp), is only usable
+	  on POWER7 or later processors, and cannot emulate a
+	  different processor from the host processor.
+
+	  If unsure, say N.
+
+config KVM_BOOK3S_64_PR
+	tristate "KVM support without using hypervisor mode in host"
+	depends on KVM_BOOK3S_64
+	depends on !CONTEXT_TRACKING_USER
+	select KVM_BOOK3S_PR_POSSIBLE
+	help
+	  Support running guest kernels in virtual machines on processors
+	  without using hypervisor mode in the host, by running the
+	  guest in user mode (problem state) and emulating all
+	  privileged instructions and registers.
+
+	  This is only available for hash MMU mode and only supports
+	  guests that use hash MMU mode.
+
+	  This is not as fast as using hypervisor mode, but works on
+	  machines where hypervisor mode is not available or not usable,
+	  and can emulate processors that are different from the host
+	  processor, including emulating 32-bit processors on a 64-bit
+	  host.
+
+	  Selecting this option will cause the SCV facility to be
+	  disabled when the kernel is booted on the pseries platform in
+	  hash MMU mode (regardless of PR VMs running). When any PR VMs
+	  are running, "AIL" mode is disabled which may slow interrupts
+	  and system calls on the host.
+
+config KVM_BOOK3S_HV_EXIT_TIMING
+	bool
+
+config KVM_BOOK3S_HV_P9_TIMING
+	bool "Detailed timing for the P9 entry point"
+	select KVM_BOOK3S_HV_EXIT_TIMING
+	depends on KVM_BOOK3S_HV_POSSIBLE && DEBUG_FS
+	help
+	  Calculate time taken for each vcpu during vcpu entry and
+	  exit, time spent inside the guest and time spent handling
+	  hypercalls and page faults. The total, minimum and maximum
+	  times in nanoseconds together with the number of executions
+	  are reported in debugfs in kvm/vm#/vcpu#/timings.
+
+	  If unsure, say N.
+
+config KVM_BOOK3S_HV_P8_TIMING
+	bool "Detailed timing for hypervisor real-mode code (for POWER8)"
+	select KVM_BOOK3S_HV_EXIT_TIMING
+	depends on KVM_BOOK3S_HV_POSSIBLE && DEBUG_FS && !KVM_BOOK3S_HV_P9_TIMING
+	help
+	  Calculate time taken for each vcpu in the real-mode guest entry,
+	  exit, and interrupt handling code, plus time spent in the guest
+	  and in nap mode due to idle (cede) while other threads are still
+	  in the guest.  The total, minimum and maximum times in nanoseconds
+	  together with the number of executions are reported in debugfs in
+	  kvm/vm#/vcpu#/timings.  The overhead is of the order of 30 - 40
+	  ns per exit on POWER8.
+
+	  If unsure, say N.
+
+config KVM_BOOK3S_HV_NESTED_PMU_WORKAROUND
+	bool "Nested L0 host workaround for L1 KVM host PMU handling bug" if EXPERT
+	depends on KVM_BOOK3S_HV_POSSIBLE
+	default !EXPERT
+	help
+	  Old nested HV capable Linux guests have a bug where they don't
+	  reflect the PMU in-use status of their L2 guest to the L0 host
+	  while the L2 PMU registers are live. This can result in loss
+	  of L2 PMU register state, causing perf to not work correctly in
+	  L2 guests.
+
+	  Selecting this option for the L0 host implements a workaround for
+	  those buggy L1s which saves the L2 state, at the cost of performance
+	  in all nested-capable guest entry/exit.
+
+config KVM_BOOK3S_HV_PMU
+	tristate "Hypervisor Perf events for KVM Book3s-HV"
+	depends on KVM_BOOK3S_64_HV
+	help
+	  Enable Book3s-HV Hypervisor Perf events PMU named 'kvm-hv'. These
+	  Perf events give an overview of hypervisor performance overall
+	  instead of a specific guests. Currently the PMU reports
+	  L0-Hypervisor stats on a kvm-hv enabled PSeries LPAR like:
+	  * Total/Used Guest-Heap
+	  * Total/Used Guest Page-table Memory
+	  * Total amount of Guest Page-table Memory reclaimed
+
+config KVM_BOOKE_HV
+	bool
+
+config KVM_EXIT_TIMING
+	bool "Detailed exit timing"
+	depends on KVM_E500V2 || KVM_E500MC
+	help
+	  Calculate elapsed time for every exit/enter cycle. A per-vcpu
+	  report is available in debugfs kvm/vm#_vcpu#_timing.
+	  The overhead is relatively small, however it is not recommended for
+	  production environments.
+
+	  If unsure, say N.
+
+config KVM_E500V2
+	bool "KVM support for PowerPC E500v2 processors"
+	depends on PPC_E500 && !PPC_E500MC
+	depends on !CONTEXT_TRACKING_USER
+	select KVM
+	select KVM_MMIO
+	help
+	  Support running unmodified E500 guest kernels in virtual machines on
+	  E500v2 host processors.
+
+	  This module provides access to the hardware capabilities through
+	  a character device node named /dev/kvm.
+
+	  If unsure, say N.
+
+config KVM_E500MC
+	bool "KVM support for PowerPC E500MC/E5500/E6500 processors"
+	depends on PPC_E500MC
+	depends on !CONTEXT_TRACKING_USER
+	select KVM
+	select KVM_MMIO
+	select KVM_BOOKE_HV
+	help
+	  Support running unmodified E500MC/E5500/E6500 guest kernels in
+	  virtual machines on E500MC/E5500/E6500 host processors.
+
+	  This module provides access to the hardware capabilities through
+	  a character device node named /dev/kvm.
+
+	  If unsure, say N.
+
+config KVM_MPIC
+	bool "KVM in-kernel MPIC emulation"
+	depends on KVM && PPC_E500
+	select HAVE_KVM_IRQCHIP
+	select HAVE_KVM_IRQ_ROUTING
+	select HAVE_KVM_MSI
+	help
+	  Enable support for emulating MPIC devices inside the
+	  host kernel, rather than relying on userspace to emulate.
+	  Currently, support is limited to certain versions of
+	  Freescale's MPIC implementation.
+
+config KVM_XICS
+	bool "KVM in-kernel XICS emulation"
+	depends on KVM_BOOK3S_64 && !KVM_MPIC
+	select HAVE_KVM_IRQCHIP
+	default y
+	help
+	  Include support for the XICS (eXternal Interrupt Controller
+	  Specification) interrupt controller architecture used on
+	  IBM POWER (pSeries) servers.
+
+config KVM_XIVE
+	bool
+	default y
+	depends on KVM_XICS && PPC_XIVE_NATIVE && KVM_BOOK3S_HV_POSSIBLE
+
+endif # VIRTUALIZATION