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, 275 insertions, 0 deletions

diff --git a/io_uring/bpf-ops.c b/io_uring/bpf-ops.c
new file mode 100644
index 000000000..cf2bd068e
--- /dev/null
+++ b/io_uring/bpf-ops.c
@@ -0,0 +1,275 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/mutex.h>
+#include <linux/bpf.h>
+#include <linux/bpf_verifier.h>
+
+#include "io_uring.h"
+#include "register.h"
+#include "loop.h"
+#include "memmap.h"
+#include "bpf-ops.h"
+
+static DEFINE_MUTEX(io_bpf_ctrl_mutex);
+static const struct btf_type *loop_params_type;
+
+__bpf_kfunc_start_defs();
+
+__bpf_kfunc int bpf_io_uring_submit_sqes(struct iou_ctx *loop_ctx, u32 nr)
+{
+	struct io_ring_ctx *ctx = io_loop_demangle_ctx(loop_ctx);
+
+	return io_submit_sqes(ctx, nr);
+}
+
+__bpf_kfunc
+__u8 *bpf_io_uring_get_region(struct iou_ctx *loop_ctx, __u32 region_id,
+			      const size_t rdwr_buf_size)
+{
+	struct io_ring_ctx *ctx = io_loop_demangle_ctx(loop_ctx);
+	struct io_mapped_region *r;
+
+	lockdep_assert_held(&ctx->uring_lock);
+
+	switch (region_id) {
+	case IOU_REGION_MEM:
+		r = &ctx->param_region;
+		break;
+	case IOU_REGION_CQ:
+		r = &ctx->ring_region;
+		break;
+	case IOU_REGION_SQ:
+		r = &ctx->sq_region;
+		break;
+	default:
+		return NULL;
+	}
+
+	if (unlikely(rdwr_buf_size > io_region_size(r)))
+		return NULL;
+	return io_region_get_ptr(r);
+}
+
+__bpf_kfunc_end_defs();
+
+BTF_KFUNCS_START(io_uring_kfunc_set)
+BTF_ID_FLAGS(func, bpf_io_uring_submit_sqes, KF_SLEEPABLE);
+BTF_ID_FLAGS(func, bpf_io_uring_get_region, KF_RET_NULL);
+BTF_KFUNCS_END(io_uring_kfunc_set)
+
+static const struct btf_kfunc_id_set bpf_io_uring_kfunc_set = {
+	.owner = THIS_MODULE,
+	.set = &io_uring_kfunc_set,
+};
+
+static int io_bpf_ops__loop_step(struct iou_ctx *ctx,
+				 struct iou_loop_params *lp)
+{
+	return IOU_LOOP_STOP;
+}
+
+static struct io_uring_bpf_ops io_bpf_ops_stubs = {
+	.loop_step = io_bpf_ops__loop_step,
+};
+
+static bool bpf_io_is_valid_access(int off, int size,
+				    enum bpf_access_type type,
+				    const struct bpf_prog *prog,
+				    struct bpf_insn_access_aux *info)
+{
+	if (type != BPF_READ)
+		return false;
+	if (off < 0 || off >= sizeof(__u64) * MAX_BPF_FUNC_ARGS)
+		return false;
+	if (off % size != 0)
+		return false;
+
+	return btf_ctx_access(off, size, type, prog, info);
+}
+
+static int bpf_io_btf_struct_access(struct bpf_verifier_log *log,
+				    const struct bpf_reg_state *reg, int off,
+				    int size)
+{
+	const struct btf_type *t = btf_type_by_id(reg->btf, reg->btf_id);
+
+	if (t == loop_params_type) {
+		if (off + size <= offsetofend(struct iou_loop_params, cq_wait_idx))
+			return SCALAR_VALUE;
+	}
+
+	return -EACCES;
+}
+
+static const struct bpf_verifier_ops bpf_io_verifier_ops = {
+	.get_func_proto = bpf_base_func_proto,
+	.is_valid_access = bpf_io_is_valid_access,
+	.btf_struct_access = bpf_io_btf_struct_access,
+};
+
+static const struct btf_type *
+io_lookup_struct_type(struct btf *btf, const char *name)
+{
+	s32 type_id;
+
+	type_id = btf_find_by_name_kind(btf, name, BTF_KIND_STRUCT);
+	if (type_id < 0)
+		return NULL;
+	return btf_type_by_id(btf, type_id);
+}
+
+static int bpf_io_init(struct btf *btf)
+{
+	int ret;
+
+	loop_params_type = io_lookup_struct_type(btf, "iou_loop_params");
+	if (!loop_params_type) {
+		pr_err("io_uring: Failed to locate iou_loop_params\n");
+		return -EINVAL;
+	}
+
+	ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS,
+					&bpf_io_uring_kfunc_set);
+	if (ret) {
+		pr_err("io_uring: Failed to register kfuncs (%d)\n", ret);
+		return ret;
+	}
+	return 0;
+}
+
+static int bpf_io_check_member(const struct btf_type *t,
+				const struct btf_member *member,
+				const struct bpf_prog *prog)
+{
+	return 0;
+}
+
+static int bpf_io_init_member(const struct btf_type *t,
+			       const struct btf_member *member,
+			       void *kdata, const void *udata)
+{
+	u32 moff = __btf_member_bit_offset(t, member) / 8;
+	const struct io_uring_bpf_ops *uops = udata;
+	struct io_uring_bpf_ops *ops = kdata;
+
+	switch (moff) {
+	case offsetof(struct io_uring_bpf_ops, ring_fd):
+		ops->ring_fd = uops->ring_fd;
+		return 1;
+	}
+	return 0;
+}
+
+static int io_install_bpf(struct io_ring_ctx *ctx, struct io_uring_bpf_ops *ops)
+{
+	if (ctx->flags & (IORING_SETUP_SQPOLL | IORING_SETUP_IOPOLL))
+		return -EOPNOTSUPP;
+	if (!(ctx->flags & IORING_SETUP_DEFER_TASKRUN))
+		return -EOPNOTSUPP;
+
+	if (ctx->bpf_ops)
+		return -EBUSY;
+	if (ops->priv)
+		return -EBUSY;
+	if (WARN_ON_ONCE(!ops->loop_step))
+		return -EINVAL;
+
+	ops->priv = ctx;
+	ctx->bpf_ops = ops;
+	ctx->loop_step = ops->loop_step;
+	return 0;
+}
+
+static int bpf_io_reg(void *kdata, struct bpf_link *link)
+{
+	struct io_uring_bpf_ops *ops = kdata;
+	struct io_ring_ctx *ctx;
+	struct file *file;
+	int ret = -EBUSY;
+
+	file = io_uring_ctx_get_file(ops->ring_fd, false);
+	if (IS_ERR(file))
+		return PTR_ERR(file);
+	ctx = file->private_data;
+
+	scoped_guard(mutex, &io_bpf_ctrl_mutex) {
+		guard(mutex)(&ctx->uring_lock);
+		ret = io_install_bpf(ctx, ops);
+	}
+
+	fput(file);
+	return ret;
+}
+
+static void io_eject_bpf(struct io_ring_ctx *ctx)
+{
+	struct io_uring_bpf_ops *ops = ctx->bpf_ops;
+
+	if (WARN_ON_ONCE(!ops))
+		return;
+	if (WARN_ON_ONCE(ops->priv != ctx))
+		return;
+
+	ops->priv = NULL;
+	ctx->bpf_ops = NULL;
+	ctx->loop_step = NULL;
+}
+
+static void bpf_io_unreg(void *kdata, struct bpf_link *link)
+{
+	struct io_uring_bpf_ops *ops = kdata;
+	struct io_ring_ctx *ctx;
+
+	guard(mutex)(&io_bpf_ctrl_mutex);
+	ctx = ops->priv;
+	if (ctx) {
+		guard(mutex)(&ctx->uring_lock);
+		if (WARN_ON_ONCE(ctx->bpf_ops != ops))
+			return;
+
+		io_eject_bpf(ctx);
+	}
+}
+
+void io_unregister_bpf_ops(struct io_ring_ctx *ctx)
+{
+	/*
+	 * ->bpf_ops is write protected by io_bpf_ctrl_mutex and uring_lock,
+	 * and read protected by either. Try to avoid taking the global lock
+	 * for rings that never had any bpf installed.
+	 */
+	scoped_guard(mutex, &ctx->uring_lock) {
+		if (!ctx->bpf_ops)
+			return;
+	}
+
+	guard(mutex)(&io_bpf_ctrl_mutex);
+	guard(mutex)(&ctx->uring_lock);
+	if (ctx->bpf_ops)
+		io_eject_bpf(ctx);
+}
+
+static struct bpf_struct_ops bpf_ring_ops = {
+	.verifier_ops = &bpf_io_verifier_ops,
+	.reg = bpf_io_reg,
+	.unreg = bpf_io_unreg,
+	.check_member = bpf_io_check_member,
+	.init_member = bpf_io_init_member,
+	.init = bpf_io_init,
+	.cfi_stubs = &io_bpf_ops_stubs,
+	.name = "io_uring_bpf_ops",
+	.owner = THIS_MODULE,
+};
+
+static int __init io_uring_bpf_init(void)
+{
+	int ret;
+
+	ret = register_bpf_struct_ops(&bpf_ring_ops, io_uring_bpf_ops);
+	if (ret) {
+		pr_err("io_uring: Failed to register struct_ops (%d)\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+__initcall(io_uring_bpf_init);