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, 150 insertions, 0 deletions

diff --git a/drivers/tee/qcomtee/shm.c b/drivers/tee/qcomtee/shm.c
new file mode 100644
index 000000000..b67909ef3
--- /dev/null
+++ b/drivers/tee/qcomtee/shm.c
@@ -0,0 +1,150 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/firmware/qcom/qcom_tzmem.h>
+#include <linux/mm.h>
+
+#include "qcomtee.h"
+
+/**
+ * define MAX_OUTBOUND_BUFFER_SIZE - Maximum size of outbound buffers.
+ *
+ * The size of outbound buffer depends on QTEE callback requests.
+ */
+#define MAX_OUTBOUND_BUFFER_SIZE SZ_4K
+
+/**
+ * define MAX_INBOUND_BUFFER_SIZE - Maximum size of the inbound buffer.
+ *
+ * The size of the inbound buffer depends on the user's requests,
+ * specifically the number of IB and OB arguments. If an invocation
+ * requires a size larger than %MAX_INBOUND_BUFFER_SIZE, the user should
+ * consider using another form of shared memory with QTEE.
+ */
+#define MAX_INBOUND_BUFFER_SIZE SZ_4M
+
+/**
+ * qcomtee_msg_buffers_alloc() - Allocate inbound and outbound buffers.
+ * @oic: context to use for the current invocation.
+ * @u: array of arguments for the current invocation.
+ *
+ * It calculates the size of inbound and outbound buffers based on the
+ * arguments in @u. It allocates the buffers from the teedev pool.
+ *
+ * Return: On success, returns 0. On error, returns < 0.
+ */
+int qcomtee_msg_buffers_alloc(struct qcomtee_object_invoke_ctx *oic,
+			      struct qcomtee_arg *u)
+{
+	struct tee_context *ctx = oic->ctx;
+	struct tee_shm *shm;
+	size_t size;
+	int i;
+
+	/* Start offset in a message for buffer arguments. */
+	size = qcomtee_msg_buffer_args(struct qcomtee_msg_object_invoke,
+				       qcomtee_args_len(u));
+	if (size > MAX_INBOUND_BUFFER_SIZE)
+		return -EINVAL;
+
+	/* Add size of IB arguments. */
+	qcomtee_arg_for_each_input_buffer(i, u) {
+		size = size_add(size, qcomtee_msg_offset_align(u[i].b.size));
+		if (size > MAX_INBOUND_BUFFER_SIZE)
+			return -EINVAL;
+	}
+
+	/* Add size of OB arguments. */
+	qcomtee_arg_for_each_output_buffer(i, u) {
+		size = size_add(size, qcomtee_msg_offset_align(u[i].b.size));
+		if (size > MAX_INBOUND_BUFFER_SIZE)
+			return -EINVAL;
+	}
+
+	shm = tee_shm_alloc_priv_buf(ctx, size);
+	if (IS_ERR(shm))
+		return PTR_ERR(shm);
+
+	/* Allocate inbound buffer. */
+	oic->in_shm = shm;
+	shm = tee_shm_alloc_priv_buf(ctx, MAX_OUTBOUND_BUFFER_SIZE);
+	if (IS_ERR(shm)) {
+		tee_shm_free(oic->in_shm);
+
+		return PTR_ERR(shm);
+	}
+	/* Allocate outbound buffer. */
+	oic->out_shm = shm;
+
+	oic->in_msg.addr = tee_shm_get_va(oic->in_shm, 0);
+	oic->in_msg.size = tee_shm_get_size(oic->in_shm);
+	oic->out_msg.addr = tee_shm_get_va(oic->out_shm, 0);
+	oic->out_msg.size = tee_shm_get_size(oic->out_shm);
+	/* QTEE assume unused buffers are zeroed. */
+	memzero_explicit(oic->in_msg.addr, oic->in_msg.size);
+	memzero_explicit(oic->out_msg.addr, oic->out_msg.size);
+
+	return 0;
+}
+
+void qcomtee_msg_buffers_free(struct qcomtee_object_invoke_ctx *oic)
+{
+	tee_shm_free(oic->in_shm);
+	tee_shm_free(oic->out_shm);
+}
+
+/* Dynamic shared memory pool based on tee_dyn_shm_alloc_helper(). */
+
+static int qcomtee_shm_register(struct tee_context *ctx, struct tee_shm *shm,
+				struct page **pages, size_t num_pages,
+				unsigned long start)
+{
+	return qcom_tzmem_shm_bridge_create(shm->paddr, shm->size,
+					    &shm->sec_world_id);
+}
+
+static int qcomtee_shm_unregister(struct tee_context *ctx, struct tee_shm *shm)
+{
+	qcom_tzmem_shm_bridge_delete(shm->sec_world_id);
+
+	return 0;
+}
+
+static int pool_op_alloc(struct tee_shm_pool *pool, struct tee_shm *shm,
+			 size_t size, size_t align)
+{
+	return tee_dyn_shm_alloc_helper(shm, size, align, qcomtee_shm_register);
+}
+
+static void pool_op_free(struct tee_shm_pool *pool, struct tee_shm *shm)
+{
+	tee_dyn_shm_free_helper(shm, qcomtee_shm_unregister);
+}
+
+static void pool_op_destroy_pool(struct tee_shm_pool *pool)
+{
+	kfree(pool);
+}
+
+static const struct tee_shm_pool_ops pool_ops = {
+	.alloc = pool_op_alloc,
+	.free = pool_op_free,
+	.destroy_pool = pool_op_destroy_pool,
+};
+
+struct tee_shm_pool *qcomtee_shm_pool_alloc(void)
+{
+	struct tee_shm_pool *pool;
+
+	pool = kzalloc_obj(*pool);
+	if (!pool)
+		return ERR_PTR(-ENOMEM);
+
+	pool->ops = &pool_ops;
+
+	return pool;
+}