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, 141 insertions, 0 deletions

diff --git a/fs/fuse/poll.c b/fs/fuse/poll.c
new file mode 100644
index 000000000..bce3ee2e8
--- /dev/null
+++ b/fs/fuse/poll.c
@@ -0,0 +1,141 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include "dev.h"
+#include "fuse_i.h"
+
+void fuse_end_polls(struct fuse_conn *fc)
+{
+	struct rb_node *p;
+
+	spin_lock(&fc->lock);
+	p = rb_first(&fc->polled_files);
+
+	while (p) {
+		struct fuse_file *ff;
+		ff = rb_entry(p, struct fuse_file, polled_node);
+		wake_up_interruptible_all(&ff->poll_wait);
+
+		p = rb_next(p);
+	}
+	spin_unlock(&fc->lock);
+}
+
+/*
+ * All files which have been polled are linked to RB tree
+ * fuse_conn->polled_files which is indexed by kh.  Walk the tree and
+ * find the matching one.
+ */
+static struct rb_node **fuse_find_polled_node(struct fuse_conn *fc, u64 kh,
+					      struct rb_node **parent_out)
+{
+	struct rb_node **link = &fc->polled_files.rb_node;
+	struct rb_node *last = NULL;
+
+	while (*link) {
+		struct fuse_file *ff;
+
+		last = *link;
+		ff = rb_entry(last, struct fuse_file, polled_node);
+
+		if (kh < ff->kh)
+			link = &last->rb_left;
+		else if (kh > ff->kh)
+			link = &last->rb_right;
+		else
+			return link;
+	}
+
+	if (parent_out)
+		*parent_out = last;
+	return link;
+}
+
+/*
+ * The file is about to be polled.  Make sure it's on the polled_files
+ * RB tree.  Note that files once added to the polled_files tree are
+ * not removed before the file is released.  This is because a file
+ * polled once is likely to be polled again.
+ */
+static void fuse_register_polled_file(struct fuse_conn *fc,
+				      struct fuse_file *ff)
+{
+	spin_lock(&fc->lock);
+	if (RB_EMPTY_NODE(&ff->polled_node)) {
+		struct rb_node **link, *parent;
+
+		link = fuse_find_polled_node(fc, ff->kh, &parent);
+		BUG_ON(*link);
+		rb_link_node(&ff->polled_node, parent, link);
+		rb_insert_color(&ff->polled_node, &fc->polled_files);
+	}
+	spin_unlock(&fc->lock);
+}
+
+__poll_t fuse_file_poll(struct file *file, poll_table *wait)
+{
+	struct fuse_file *ff = file->private_data;
+	struct fuse_mount *fm = ff->fm;
+	struct fuse_poll_in inarg = { .fh = ff->fh, .kh = ff->kh };
+	struct fuse_poll_out outarg;
+	FUSE_ARGS(args);
+	int err;
+
+	if (fm->fc->no_poll)
+		return DEFAULT_POLLMASK;
+
+	poll_wait(file, &ff->poll_wait, wait);
+	inarg.events = mangle_poll(poll_requested_events(wait));
+
+	/*
+	 * Ask for notification iff there's someone waiting for it.
+	 * The client may ignore the flag and always notify.
+	 */
+	if (waitqueue_active(&ff->poll_wait)) {
+		inarg.flags |= FUSE_POLL_SCHEDULE_NOTIFY;
+		fuse_register_polled_file(fm->fc, ff);
+	}
+
+	args.opcode = FUSE_POLL;
+	args.nodeid = ff->nodeid;
+	args.in_numargs = 1;
+	args.in_args[0].size = sizeof(inarg);
+	args.in_args[0].value = &inarg;
+	args.out_numargs = 1;
+	args.out_args[0].size = sizeof(outarg);
+	args.out_args[0].value = &outarg;
+	err = fuse_simple_request(fm, &args);
+
+	if (!err)
+		return demangle_poll(outarg.revents);
+	if (err == -ENOSYS) {
+		fm->fc->no_poll = 1;
+		return DEFAULT_POLLMASK;
+	}
+	return EPOLLERR;
+}
+EXPORT_SYMBOL_GPL(fuse_file_poll);
+
+/*
+ * This is called from fuse_handle_notify() on FUSE_NOTIFY_POLL and
+ * wakes up the poll waiters.
+ */
+int fuse_notify_poll_wakeup(struct fuse_conn *fc,
+			    struct fuse_notify_poll_wakeup_out *outarg)
+{
+	u64 kh = outarg->kh;
+	struct rb_node **link;
+
+	spin_lock(&fc->lock);
+
+	link = fuse_find_polled_node(fc, kh, NULL);
+	if (*link) {
+		struct fuse_file *ff;
+
+		ff = rb_entry(*link, struct fuse_file, polled_node);
+		wake_up_interruptible_sync(&ff->poll_wait);
+	}
+
+	spin_unlock(&fc->lock);
+	return 0;
+}
+