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, 356 insertions, 0 deletions

diff --git a/io_uring/futex.c b/io_uring/futex.c
new file mode 100644
index 000000000..eaee14242
--- /dev/null
+++ b/io_uring/futex.c
@@ -0,0 +1,356 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/io_uring.h>
+
+#include <uapi/linux/io_uring.h>
+
+#include "../kernel/futex/futex.h"
+#include "io_uring.h"
+#include "alloc_cache.h"
+#include "futex.h"
+
+struct io_futex {
+	struct file	*file;
+	void __user	*uaddr;
+	unsigned long	futex_val;
+	unsigned long	futex_mask;
+	u32		futex_flags;
+	unsigned int	futex_nr;
+	bool		futexv_unqueued;
+};
+
+struct io_futex_data {
+	struct futex_q	q;
+	struct io_kiocb	*req;
+};
+
+struct io_futexv_data {
+	unsigned long		owned;
+	struct futex_vector	futexv[];
+};
+
+#define IO_FUTEX_ALLOC_CACHE_MAX	32
+
+bool io_futex_cache_init(struct io_ring_ctx *ctx)
+{
+	return io_alloc_cache_init(&ctx->futex_cache, IO_FUTEX_ALLOC_CACHE_MAX,
+				sizeof(struct io_futex_data), 0);
+}
+
+void io_futex_cache_free(struct io_ring_ctx *ctx)
+{
+	io_alloc_cache_free(&ctx->futex_cache, kfree);
+}
+
+static void __io_futex_complete(struct io_tw_req tw_req, io_tw_token_t tw)
+{
+	hlist_del_init(&tw_req.req->hash_node);
+	io_req_task_complete(tw_req, tw);
+}
+
+static void io_futex_complete(struct io_tw_req tw_req, io_tw_token_t tw)
+{
+	struct io_kiocb *req = tw_req.req;
+	struct io_ring_ctx *ctx = req->ctx;
+
+	io_tw_lock(ctx, tw);
+	io_cache_free(&ctx->futex_cache, req->async_data);
+	io_req_async_data_clear(req, 0);
+	__io_futex_complete(tw_req, tw);
+}
+
+static void io_futexv_complete(struct io_tw_req tw_req, io_tw_token_t tw)
+{
+	struct io_kiocb *req = tw_req.req;
+	struct io_futex *iof = io_kiocb_to_cmd(req, struct io_futex);
+	struct io_futexv_data *ifd = req->async_data;
+
+	io_tw_lock(req->ctx, tw);
+
+	if (!iof->futexv_unqueued) {
+		int res;
+
+		res = futex_unqueue_multiple(ifd->futexv, iof->futex_nr);
+		if (res != -1)
+			io_req_set_res(req, res, 0);
+	}
+
+	io_req_async_data_free(req);
+	__io_futex_complete(tw_req, tw);
+}
+
+static bool io_futexv_claim(struct io_futexv_data *ifd)
+{
+	if (test_bit(0, &ifd->owned) || test_and_set_bit_lock(0, &ifd->owned))
+		return false;
+	return true;
+}
+
+static bool __io_futex_cancel(struct io_kiocb *req)
+{
+	/* futex wake already done or in progress */
+	if (req->opcode == IORING_OP_FUTEX_WAIT) {
+		struct io_futex_data *ifd = req->async_data;
+
+		if (!futex_unqueue(&ifd->q))
+			return false;
+		req->io_task_work.func = io_futex_complete;
+	} else {
+		struct io_futexv_data *ifd = req->async_data;
+
+		if (!io_futexv_claim(ifd))
+			return false;
+		req->io_task_work.func = io_futexv_complete;
+	}
+
+	hlist_del_init(&req->hash_node);
+	io_req_set_res(req, -ECANCELED, 0);
+	io_req_task_work_add(req);
+	return true;
+}
+
+int io_futex_cancel(struct io_ring_ctx *ctx, struct io_cancel_data *cd,
+		    unsigned int issue_flags)
+{
+	return io_cancel_remove(ctx, cd, issue_flags, &ctx->futex_list, __io_futex_cancel);
+}
+
+bool io_futex_remove_all(struct io_ring_ctx *ctx, struct io_uring_task *tctx,
+			 bool cancel_all)
+{
+	return io_cancel_remove_all(ctx, tctx, &ctx->futex_list, cancel_all, __io_futex_cancel);
+}
+
+int io_futex_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+	struct io_futex *iof = io_kiocb_to_cmd(req, struct io_futex);
+	u32 flags;
+
+	if (unlikely(sqe->len || sqe->futex_flags || sqe->buf_index ||
+		     sqe->file_index))
+		return -EINVAL;
+
+	iof->uaddr = u64_to_user_ptr(READ_ONCE(sqe->addr));
+	iof->futex_val = READ_ONCE(sqe->addr2);
+	iof->futex_mask = READ_ONCE(sqe->addr3);
+	flags = READ_ONCE(sqe->fd);
+
+	if (flags & ~FUTEX2_VALID_MASK)
+		return -EINVAL;
+
+	iof->futex_flags = futex2_to_flags(flags);
+	if (!futex_flags_valid(iof->futex_flags))
+		return -EINVAL;
+
+	if (!futex_validate_input(iof->futex_flags, iof->futex_val) ||
+	    !futex_validate_input(iof->futex_flags, iof->futex_mask))
+		return -EINVAL;
+
+	return 0;
+}
+
+int io_futex_wait_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+	struct io_futex *iof = io_kiocb_to_cmd(req, struct io_futex);
+	int ret;
+
+	ret = io_futex_prep(req, sqe);
+	if (unlikely(ret))
+		return ret;
+
+	/* inflight tracking only needed for mm private hash */
+	if (!(iof->futex_flags & FLAGS_SHARED))
+		io_req_track_inflight(req);
+	return 0;
+}
+
+static void io_futex_wakev_fn(struct wake_q_head *wake_q, struct futex_q *q)
+{
+	struct io_kiocb *req = q->wake_data;
+	struct io_futexv_data *ifd = req->async_data;
+
+	if (!io_futexv_claim(ifd)) {
+		__futex_wake_mark(q);
+		return;
+	}
+	if (unlikely(!__futex_wake_mark(q)))
+		return;
+
+	io_req_set_res(req, 0, 0);
+	req->io_task_work.func = io_futexv_complete;
+	__io_req_task_work_add(req, IOU_F_TWQ_IN_WAKE);
+}
+
+int io_futexv_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+	struct io_futex *iof = io_kiocb_to_cmd(req, struct io_futex);
+	struct io_futexv_data *ifd;
+	unsigned int i;
+	int ret;
+
+	/* No flags or mask supported for waitv */
+	if (unlikely(sqe->fd || sqe->buf_index || sqe->file_index ||
+		     sqe->addr2 || sqe->futex_flags || sqe->addr3))
+		return -EINVAL;
+
+	iof->uaddr = u64_to_user_ptr(READ_ONCE(sqe->addr));
+	iof->futex_nr = READ_ONCE(sqe->len);
+	if (!iof->futex_nr || iof->futex_nr > FUTEX_WAITV_MAX)
+		return -EINVAL;
+
+	ifd = kzalloc_flex(struct io_futexv_data, futexv, iof->futex_nr,
+			   GFP_KERNEL_ACCOUNT);
+	if (!ifd)
+		return -ENOMEM;
+
+	ret = futex_parse_waitv(ifd->futexv, iof->uaddr, iof->futex_nr,
+				io_futex_wakev_fn, req);
+	if (ret) {
+		kfree(ifd);
+		return ret;
+	}
+
+	/* inflight tracking only needed for mm private hash */
+	for (i = 0; i < iof->futex_nr; i++) {
+		if (!(ifd->futexv[i].w.flags & FLAGS_SHARED)) {
+			io_req_track_inflight(req);
+			break;
+		}
+	}
+
+	iof->futexv_unqueued = 0;
+	req->flags |= REQ_F_ASYNC_DATA;
+	req->async_data = ifd;
+	return 0;
+}
+
+static void io_futex_wake_fn(struct wake_q_head *wake_q, struct futex_q *q)
+{
+	struct io_futex_data *ifd = container_of(q, struct io_futex_data, q);
+	struct io_kiocb *req = ifd->req;
+
+	if (unlikely(!__futex_wake_mark(q)))
+		return;
+
+	io_req_set_res(req, 0, 0);
+	req->io_task_work.func = io_futex_complete;
+	__io_req_task_work_add(req, IOU_F_TWQ_IN_WAKE);
+}
+
+int io_futexv_wait(struct io_kiocb *req, unsigned int issue_flags)
+{
+	struct io_futex *iof = io_kiocb_to_cmd(req, struct io_futex);
+	struct io_futexv_data *ifd = req->async_data;
+	struct io_ring_ctx *ctx = req->ctx;
+	int ret, woken = -1;
+
+	io_ring_submit_lock(ctx, issue_flags);
+
+	ret = futex_wait_multiple_setup(ifd->futexv, iof->futex_nr, &woken);
+
+	/*
+	 * Error case, ret is < 0. Mark the request as failed.
+	 */
+	if (unlikely(ret < 0)) {
+		io_ring_submit_unlock(ctx, issue_flags);
+		req_set_fail(req);
+		io_req_set_res(req, ret, 0);
+		io_req_async_data_free(req);
+		return IOU_COMPLETE;
+	}
+
+	/*
+	 * 0 return means that we successfully setup the waiters, and that
+	 * nobody triggered a wakeup while we were doing so. If the wakeup
+	 * happened post setup, the task_work will be run post this issue and
+	 * under the submission lock. 1 means We got woken while setting up,
+	 * let that side do the completion. Note that
+	 * futex_wait_multiple_setup() will have unqueued all the futexes in
+	 * this case. Mark us as having done that already, since this is
+	 * different from normal wakeup.
+	 */
+	if (!ret) {
+		/*
+		 * If futex_wait_multiple_setup() returns 0 for a
+		 * successful setup, then the task state will not be
+		 * runnable. This is fine for the sync syscall, as
+		 * it'll be blocking unless we already got one of the
+		 * futexes woken, but it obviously won't work for an
+		 * async invocation. Mark us runnable again.
+		 */
+		__set_current_state(TASK_RUNNING);
+		hlist_add_head(&req->hash_node, &ctx->futex_list);
+	} else {
+		iof->futexv_unqueued = 1;
+		if (woken != -1)
+			io_req_set_res(req, woken, 0);
+	}
+
+	io_ring_submit_unlock(ctx, issue_flags);
+	return IOU_ISSUE_SKIP_COMPLETE;
+}
+
+int io_futex_wait(struct io_kiocb *req, unsigned int issue_flags)
+{
+	struct io_futex *iof = io_kiocb_to_cmd(req, struct io_futex);
+	struct io_ring_ctx *ctx = req->ctx;
+	struct io_futex_data *ifd = NULL;
+	int ret;
+
+	if (!iof->futex_mask) {
+		ret = -EINVAL;
+		goto done;
+	}
+
+	io_ring_submit_lock(ctx, issue_flags);
+	ifd = io_cache_alloc(&ctx->futex_cache, GFP_NOWAIT);
+	if (!ifd) {
+		ret = -ENOMEM;
+		goto done_unlock;
+	}
+
+	req->flags |= REQ_F_ASYNC_DATA;
+	req->async_data = ifd;
+	ifd->q = futex_q_init;
+	ifd->q.bitset = iof->futex_mask;
+	ifd->q.wake = io_futex_wake_fn;
+	ifd->req = req;
+
+	ret = futex_wait_setup(iof->uaddr, iof->futex_val, iof->futex_flags,
+			       &ifd->q, NULL, NULL);
+	if (!ret) {
+		hlist_add_head(&req->hash_node, &ctx->futex_list);
+		io_ring_submit_unlock(ctx, issue_flags);
+
+		return IOU_ISSUE_SKIP_COMPLETE;
+	}
+
+done_unlock:
+	io_ring_submit_unlock(ctx, issue_flags);
+done:
+	if (ret < 0)
+		req_set_fail(req);
+	io_req_set_res(req, ret, 0);
+	io_req_async_data_free(req);
+	return IOU_COMPLETE;
+}
+
+int io_futex_wake(struct io_kiocb *req, unsigned int issue_flags)
+{
+	struct io_futex *iof = io_kiocb_to_cmd(req, struct io_futex);
+	int ret;
+
+	/*
+	 * Strict flags - ensure that waking 0 futexes yields a 0 result.
+	 * See commit 43adf8449510 ("futex: FLAGS_STRICT") for details.
+	 */
+	ret = futex_wake(iof->uaddr, FLAGS_STRICT | iof->futex_flags, NULL,
+			 iof->futex_val, iof->futex_mask);
+	if (ret < 0)
+		req_set_fail(req);
+	io_req_set_res(req, ret, 0);
+	return IOU_COMPLETE;
+}