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, 90 insertions, 0 deletions

diff --git a/drivers/firmware/imx/rm.c b/drivers/firmware/imx/rm.c
new file mode 100644
index 000000000..d492b99e1
--- /dev/null
+++ b/drivers/firmware/imx/rm.c
@@ -0,0 +1,90 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright 2020 NXP
+ *
+ * File containing client-side RPC functions for the RM service. These
+ * function are ported to clients that communicate to the SC.
+ */
+
+#include <linux/firmware/imx/svc/rm.h>
+
+struct imx_sc_msg_rm_rsrc_owned {
+	struct imx_sc_rpc_msg hdr;
+	u16 resource;
+} __packed __aligned(4);
+
+/*
+ * This function check @resource is owned by current partition or not
+ *
+ * @param[in]     ipc         IPC handle
+ * @param[in]     resource    resource the control is associated with
+ *
+ * @return Returns 0 for not owned and 1 for owned.
+ */
+bool imx_sc_rm_is_resource_owned(struct imx_sc_ipc *ipc, u16 resource)
+{
+	struct imx_sc_msg_rm_rsrc_owned msg;
+	struct imx_sc_rpc_msg *hdr = &msg.hdr;
+
+	hdr->ver = IMX_SC_RPC_VERSION;
+	hdr->svc = IMX_SC_RPC_SVC_RM;
+	hdr->func = IMX_SC_RM_FUNC_IS_RESOURCE_OWNED;
+	hdr->size = 2;
+
+	msg.resource = resource;
+
+	/*
+	 * SCU firmware only returns value 0 or 1
+	 * for resource owned check which means not owned or owned.
+	 * So it is always successful.
+	 */
+	imx_scu_call_rpc(ipc, &msg, true);
+
+	return hdr->func;
+}
+EXPORT_SYMBOL(imx_sc_rm_is_resource_owned);
+
+struct imx_sc_msg_rm_get_resource_owner {
+	struct imx_sc_rpc_msg hdr;
+	union {
+		struct {
+			u16 resource;
+		} req;
+		struct {
+			u8 val;
+		} resp;
+	} data;
+} __packed __aligned(4);
+
+/*
+ * This function get @resource partition number
+ *
+ * @param[in]     ipc         IPC handle
+ * @param[in]     resource    resource the control is associated with
+ * @param[out]    pt          pointer to return the partition number
+ *
+ * @return Returns 0 for success and < 0 for errors.
+ */
+int imx_sc_rm_get_resource_owner(struct imx_sc_ipc *ipc, u16 resource, u8 *pt)
+{
+	struct imx_sc_msg_rm_get_resource_owner msg;
+	struct imx_sc_rpc_msg *hdr = &msg.hdr;
+	int ret;
+
+	hdr->ver = IMX_SC_RPC_VERSION;
+	hdr->svc = IMX_SC_RPC_SVC_RM;
+	hdr->func = IMX_SC_RM_FUNC_GET_RESOURCE_OWNER;
+	hdr->size = 2;
+
+	msg.data.req.resource = resource;
+
+	ret = imx_scu_call_rpc(ipc, &msg, true);
+	if (ret)
+		return ret;
+
+	if (pt)
+		*pt = msg.data.resp.val;
+
+	return 0;
+}
+EXPORT_SYMBOL(imx_sc_rm_get_resource_owner);