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, 103 insertions, 0 deletions

diff --git a/arch/alpha/lib/stacktrace.c b/arch/alpha/lib/stacktrace.c
new file mode 100644
index 000000000..2b1176dd5
--- /dev/null
+++ b/arch/alpha/lib/stacktrace.c
@@ -0,0 +1,103 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/kernel.h>
+
+typedef unsigned int instr;
+
+#define MAJOR_OP	0xfc000000
+#define LDA_OP		0x20000000
+#define STQ_OP		0xb4000000
+#define BR_OP		0xc0000000
+
+#define STK_ALLOC_1	0x23de8000 /* lda $30,-X($30) */
+#define STK_ALLOC_1M	0xffff8000
+#define STK_ALLOC_2	0x43c0153e /* subq $30,X,$30 */
+#define STK_ALLOC_2M	0xffe01fff
+
+#define MEM_REG		0x03e00000
+#define MEM_BASE	0x001f0000
+#define MEM_OFF		0x0000ffff
+#define MEM_OFF_SIGN	0x00008000
+#define	BASE_SP		0x001e0000
+
+#define STK_ALLOC_MATCH(INSTR)			\
+  (((INSTR) & STK_ALLOC_1M) == STK_ALLOC_1	\
+   || ((INSTR) & STK_ALLOC_2M) == STK_ALLOC_2)
+#define STK_PUSH_MATCH(INSTR) \
+  (((INSTR) & (MAJOR_OP | MEM_BASE | MEM_OFF_SIGN)) == (STQ_OP | BASE_SP))
+#define MEM_OP_OFFSET(INSTR) \
+  (((long)((INSTR) & MEM_OFF) << 48) >> 48)
+#define MEM_OP_REG(INSTR) \
+  (((INSTR) & MEM_REG) >> 22)
+
+/* Branches, jumps, PAL calls, and illegal opcodes end a basic block. */
+#define BB_END(INSTR)						\
+  (((instr)(INSTR) >= BR_OP) | ((instr)(INSTR) < LDA_OP) |	\
+   ((((instr)(INSTR) ^ 0x60000000) < 0x20000000) &		\
+    (((instr)(INSTR) & 0x0c000000) != 0)))
+
+#define IS_KERNEL_TEXT(PC) ((unsigned long)(PC) > START_ADDR)
+
+static char reg_name[][4] = {
+	"v0 ", "t0 ", "t1 ", "t2 ", "t3 ", "t4 ", "t5 ", "t6 ", "t7 ",
+	"s0 ", "s1 ", "s2 ", "s3 ", "s4 ", "s5 ", "s6 ", "a0 ", "a1 ",
+	"a2 ", "a3 ", "a4 ", "a5 ", "t8 ", "t9 ", "t10", "t11", "ra ",
+	"pv ", "at ", "gp ", "sp ", "0"
+};
+
+
+static instr *
+display_stored_regs(instr * pro_pc, unsigned char * sp)
+{
+	instr * ret_pc = 0;
+	int reg;
+	unsigned long value;
+
+	printk("Prologue [<%p>], Frame %p:\n", pro_pc, sp);
+	while (!BB_END(*pro_pc))
+		if (STK_PUSH_MATCH(*pro_pc)) {
+			reg = (*pro_pc & MEM_REG) >> 21;
+			value = *(unsigned long *)(sp + (*pro_pc & MEM_OFF));
+			if (reg == 26)
+				ret_pc = (instr *)value;
+			printk("\t\t%s / 0x%016lx\n", reg_name[reg], value);
+		}
+	return ret_pc;
+}
+
+static instr *
+seek_prologue(instr * pc)
+{
+	while (!STK_ALLOC_MATCH(*pc))
+		--pc;
+	while (!BB_END(*(pc - 1)))
+		--pc;
+	return pc;
+}
+
+static long
+stack_increment(instr * prologue_pc)
+{
+	while (!STK_ALLOC_MATCH(*prologue_pc))
+		++prologue_pc;
+
+	/* Count the bytes allocated. */
+	if ((*prologue_pc & STK_ALLOC_1M) == STK_ALLOC_1M)
+		return -(((long)(*prologue_pc) << 48) >> 48);
+	else
+		return (*prologue_pc >> 13) & 0xff;
+}
+
+void
+stacktrace(void)
+{
+	instr * ret_pc;
+	instr * prologue = (instr *)stacktrace;
+	unsigned char *sp = (unsigned char *)current_stack_pointer;
+
+	printk("\tstack trace:\n");
+	do {
+		ret_pc = display_stored_regs(prologue, sp);
+		sp += stack_increment(prologue);
+		prologue = seek_prologue(ret_pc);
+	} while (IS_KERNEL_TEXT(ret_pc));
+}