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, 95 insertions, 0 deletions

diff --git a/arch/powerpc/kvm/timing.h b/arch/powerpc/kvm/timing.h
new file mode 100644
index 000000000..14b0e23f6
--- /dev/null
+++ b/arch/powerpc/kvm/timing.h
@@ -0,0 +1,95 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ *
+ * Copyright IBM Corp. 2008
+ *
+ * Authors: Christian Ehrhardt <ehrhardt@linux.vnet.ibm.com>
+ */
+
+#ifndef __POWERPC_KVM_EXITTIMING_H__
+#define __POWERPC_KVM_EXITTIMING_H__
+
+#include <linux/kvm_host.h>
+
+#ifdef CONFIG_KVM_EXIT_TIMING
+void kvmppc_init_timing_stats(struct kvm_vcpu *vcpu);
+void kvmppc_update_timing_stats(struct kvm_vcpu *vcpu);
+int kvmppc_create_vcpu_debugfs_e500(struct kvm_vcpu *vcpu,
+				    struct dentry *debugfs_dentry);
+
+static inline void kvmppc_set_exit_type(struct kvm_vcpu *vcpu, int type)
+{
+	vcpu->arch.last_exit_type = type;
+}
+
+#else
+/* if exit timing is not configured there is no need to build the c file */
+static inline void kvmppc_init_timing_stats(struct kvm_vcpu *vcpu) {}
+static inline void kvmppc_update_timing_stats(struct kvm_vcpu *vcpu) {}
+static inline int kvmppc_create_vcpu_debugfs_e500(struct kvm_vcpu *vcpu,
+						  struct dentry *debugfs_dentry)
+{
+	return 0;
+}
+static inline void kvmppc_set_exit_type(struct kvm_vcpu *vcpu, int type) {}
+#endif /* CONFIG_KVM_EXIT_TIMING */
+
+/* account the exit in kvm_stats */
+static inline void kvmppc_account_exit_stat(struct kvm_vcpu *vcpu, int type)
+{
+	/* type has to be known at build time for optimization */
+	BUILD_BUG_ON(!__builtin_constant_p(type));
+	switch (type) {
+	case EXT_INTR_EXITS:
+		vcpu->stat.ext_intr_exits++;
+		break;
+	case DEC_EXITS:
+		vcpu->stat.dec_exits++;
+		break;
+	case EMULATED_INST_EXITS:
+		vcpu->stat.emulated_inst_exits++;
+		break;
+	case DSI_EXITS:
+		vcpu->stat.dsi_exits++;
+		break;
+	case ISI_EXITS:
+		vcpu->stat.isi_exits++;
+		break;
+	case SYSCALL_EXITS:
+		vcpu->stat.syscall_exits++;
+		break;
+	case DTLB_REAL_MISS_EXITS:
+		vcpu->stat.dtlb_real_miss_exits++;
+		break;
+	case DTLB_VIRT_MISS_EXITS:
+		vcpu->stat.dtlb_virt_miss_exits++;
+		break;
+	case MMIO_EXITS:
+		vcpu->stat.mmio_exits++;
+		break;
+	case ITLB_REAL_MISS_EXITS:
+		vcpu->stat.itlb_real_miss_exits++;
+		break;
+	case ITLB_VIRT_MISS_EXITS:
+		vcpu->stat.itlb_virt_miss_exits++;
+		break;
+	case SIGNAL_EXITS:
+		vcpu->stat.signal_exits++;
+		break;
+	case DBELL_EXITS:
+		vcpu->stat.dbell_exits++;
+		break;
+	case GDBELL_EXITS:
+		vcpu->stat.gdbell_exits++;
+		break;
+	}
+}
+
+/* wrapper to set exit time and account for it in kvm_stats */
+static inline void kvmppc_account_exit(struct kvm_vcpu *vcpu, int type)
+{
+	kvmppc_set_exit_type(vcpu, type);
+	kvmppc_account_exit_stat(vcpu, type);
+}
+
+#endif /* __POWERPC_KVM_EXITTIMING_H__ */