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, 155 insertions, 0 deletions

diff --git a/drivers/acpi/riscv/cppc.c b/drivers/acpi/riscv/cppc.c
new file mode 100644
index 000000000..42c1a9052
--- /dev/null
+++ b/drivers/acpi/riscv/cppc.c
@@ -0,0 +1,155 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Implement CPPC FFH helper routines for RISC-V.
+ *
+ * Copyright (C) 2024 Ventana Micro Systems Inc.
+ */
+
+#include <acpi/cppc_acpi.h>
+#include <asm/csr.h>
+#include <asm/sbi.h>
+
+#define SBI_EXT_CPPC 0x43505043
+
+/* CPPC interfaces defined in SBI spec */
+#define SBI_CPPC_PROBE			0x0
+#define SBI_CPPC_READ			0x1
+#define SBI_CPPC_READ_HI		0x2
+#define SBI_CPPC_WRITE			0x3
+
+/* RISC-V FFH definitions from RISC-V FFH spec */
+#define FFH_CPPC_TYPE(r)		(((r) & GENMASK_ULL(63, 60)) >> 60)
+#define FFH_CPPC_SBI_REG(r)		((r) & GENMASK(31, 0))
+#define FFH_CPPC_CSR_NUM(r)		((r) & GENMASK(11, 0))
+
+#define FFH_CPPC_SBI			0x1
+#define FFH_CPPC_CSR			0x2
+
+struct sbi_cppc_data {
+	u64 val;
+	u32 reg;
+	struct sbiret ret;
+};
+
+static bool cppc_ext_present;
+
+static int __init sbi_cppc_init(void)
+{
+	if (sbi_spec_version >= sbi_mk_version(2, 0) &&
+	    sbi_probe_extension(SBI_EXT_CPPC) > 0) {
+		cppc_ext_present = true;
+	} else {
+		cppc_ext_present = false;
+	}
+
+	return 0;
+}
+device_initcall(sbi_cppc_init);
+
+static void sbi_cppc_read(void *read_data)
+{
+	struct sbi_cppc_data *data = (struct sbi_cppc_data *)read_data;
+
+	data->ret = sbi_ecall(SBI_EXT_CPPC, SBI_CPPC_READ,
+			      data->reg, 0, 0, 0, 0, 0);
+}
+
+static void sbi_cppc_write(void *write_data)
+{
+	struct sbi_cppc_data *data = (struct sbi_cppc_data *)write_data;
+
+	data->ret = sbi_ecall(SBI_EXT_CPPC, SBI_CPPC_WRITE,
+			      data->reg, data->val, 0, 0, 0, 0);
+}
+
+static void cppc_ffh_csr_read(void *read_data)
+{
+	struct sbi_cppc_data *data = (struct sbi_cppc_data *)read_data;
+
+	switch (data->reg) {
+	/* Support only TIME CSR for now */
+	case CSR_TIME:
+		data->ret.value = csr_read(CSR_TIME);
+		data->ret.error = 0;
+		break;
+	default:
+		data->ret.error = -EINVAL;
+		break;
+	}
+}
+
+static void cppc_ffh_csr_write(void *write_data)
+{
+	struct sbi_cppc_data *data = (struct sbi_cppc_data *)write_data;
+
+	data->ret.error = -EINVAL;
+}
+
+/*
+ * Refer to drivers/acpi/cppc_acpi.c for the description of the functions
+ * below.
+ */
+bool cpc_ffh_supported(void)
+{
+	return true;
+}
+
+int cpc_read_ffh(int cpu, struct cpc_reg *reg, u64 *val)
+{
+	struct sbi_cppc_data data;
+
+	if (WARN_ON_ONCE(irqs_disabled()))
+		return -EPERM;
+
+	if (FFH_CPPC_TYPE(reg->address) == FFH_CPPC_SBI) {
+		if (!cppc_ext_present)
+			return -EINVAL;
+
+		data.reg = FFH_CPPC_SBI_REG(reg->address);
+
+		smp_call_function_single(cpu, sbi_cppc_read, &data, 1);
+
+		*val = data.ret.value;
+
+		return (data.ret.error) ? sbi_err_map_linux_errno(data.ret.error) : 0;
+	} else if (FFH_CPPC_TYPE(reg->address) == FFH_CPPC_CSR) {
+		data.reg = FFH_CPPC_CSR_NUM(reg->address);
+
+		smp_call_function_single(cpu, cppc_ffh_csr_read, &data, 1);
+
+		*val = data.ret.value;
+
+		return data.ret.error;
+	}
+
+	return -EINVAL;
+}
+
+int cpc_write_ffh(int cpu, struct cpc_reg *reg, u64 val)
+{
+	struct sbi_cppc_data data;
+
+	if (WARN_ON_ONCE(irqs_disabled()))
+		return -EPERM;
+
+	if (FFH_CPPC_TYPE(reg->address) == FFH_CPPC_SBI) {
+		if (!cppc_ext_present)
+			return -EINVAL;
+
+		data.reg = FFH_CPPC_SBI_REG(reg->address);
+		data.val = val;
+
+		smp_call_function_single(cpu, sbi_cppc_write, &data, 1);
+
+		return (data.ret.error) ? sbi_err_map_linux_errno(data.ret.error) : 0;
+	} else if (FFH_CPPC_TYPE(reg->address) == FFH_CPPC_CSR) {
+		data.reg = FFH_CPPC_CSR_NUM(reg->address);
+		data.val = val;
+
+		smp_call_function_single(cpu, cppc_ffh_csr_write, &data, 1);
+
+		return data.ret.error;
+	}
+
+	return -EINVAL;
+}