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, 115 insertions, 0 deletions

diff --git a/arch/powerpc/perf/callchain.c b/arch/powerpc/perf/callchain.c
new file mode 100644
index 000000000..992cc5c98
--- /dev/null
+++ b/arch/powerpc/perf/callchain.c
@@ -0,0 +1,115 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Performance counter callchain support - powerpc architecture code
+ *
+ * Copyright © 2009 Paul Mackerras, IBM Corporation.
+ */
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/perf_event.h>
+#include <linux/percpu.h>
+#include <linux/uaccess.h>
+#include <linux/mm.h>
+#include <asm/ptrace.h>
+#include <asm/sigcontext.h>
+#include <asm/ucontext.h>
+#include <asm/vdso.h>
+#include <asm/pte-walk.h>
+
+#include "callchain.h"
+
+/*
+ * Is sp valid as the address of the next kernel stack frame after prev_sp?
+ * The next frame may be in a different stack area but should not go
+ * back down in the same stack area.
+ */
+static int valid_next_sp(unsigned long sp, unsigned long prev_sp)
+{
+	if (sp & 0xf)
+		return 0;		/* must be 16-byte aligned */
+	if (!validate_sp(sp, current))
+		return 0;
+	if (sp >= prev_sp + STACK_FRAME_MIN_SIZE)
+		return 1;
+	/*
+	 * sp could decrease when we jump off an interrupt stack
+	 * back to the regular process stack.
+	 */
+	if ((sp & ~(THREAD_SIZE - 1)) != (prev_sp & ~(THREAD_SIZE - 1)))
+		return 1;
+	return 0;
+}
+
+void __no_sanitize_address
+perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
+{
+	unsigned long sp, next_sp;
+	unsigned long next_ip;
+	unsigned long lr;
+	long level = 0;
+	unsigned long *fp;
+
+	lr = regs->link;
+	sp = regs->gpr[1];
+	perf_callchain_store(entry, perf_arch_instruction_pointer(regs));
+
+	if (!validate_sp(sp, current))
+		return;
+
+	for (;;) {
+		fp = (unsigned long *) sp;
+		next_sp = fp[0];
+
+		if (next_sp == sp + STACK_INT_FRAME_SIZE &&
+		    validate_sp_size(sp, current, STACK_INT_FRAME_SIZE) &&
+		    fp[STACK_INT_FRAME_MARKER_LONGS] == STACK_FRAME_REGS_MARKER) {
+			/*
+			 * This looks like an interrupt frame for an
+			 * interrupt that occurred in the kernel
+			 */
+			regs = (struct pt_regs *)(sp + STACK_INT_FRAME_REGS);
+			next_ip = regs->nip;
+			lr = regs->link;
+			level = 0;
+			perf_callchain_store_context(entry, PERF_CONTEXT_KERNEL);
+
+		} else {
+			if (level == 0)
+				next_ip = lr;
+			else
+				next_ip = fp[STACK_FRAME_LR_SAVE];
+
+			/*
+			 * We can't tell which of the first two addresses
+			 * we get are valid, but we can filter out the
+			 * obviously bogus ones here.  We replace them
+			 * with 0 rather than removing them entirely so
+			 * that userspace can tell which is which.
+			 */
+			if ((level == 1 && next_ip == lr) ||
+			    (level <= 1 && !kernel_text_address(next_ip)))
+				next_ip = 0;
+
+			++level;
+		}
+
+		perf_callchain_store(entry, next_ip);
+		if (!valid_next_sp(next_sp, sp))
+			return;
+		sp = next_sp;
+	}
+}
+
+void
+perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
+{
+	perf_callchain_store(entry, perf_arch_instruction_pointer(regs));
+
+	if (!current->mm)
+		return;
+
+	if (!is_32bit_task())
+		perf_callchain_user_64(entry, regs);
+	else
+		perf_callchain_user_32(entry, regs);
+}