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, 142 insertions, 0 deletions

diff --git a/fs/fuse/req_timeout.c b/fs/fuse/req_timeout.c
new file mode 100644
index 000000000..95a1acd7b
--- /dev/null
+++ b/fs/fuse/req_timeout.c
@@ -0,0 +1,142 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include "dev.h"
+#include "sysctl.h"
+#include "fuse_dev_i.h"
+#include "dev_uring_i.h"
+
+/* Frequency (in seconds) of request timeout checks, if opted into */
+#define FUSE_TIMEOUT_TIMER_FREQ 15
+
+/* Frequency (in jiffies) of request timeout checks, if opted into */
+static const unsigned long fuse_timeout_timer_freq =
+	secs_to_jiffies(FUSE_TIMEOUT_TIMER_FREQ);
+
+/*
+ * Default timeout (in seconds) for the server to reply to a request
+ * before the connection is aborted, if no timeout was specified on mount.
+ *
+ * Exported via sysctl
+ */
+unsigned int fuse_default_req_timeout;
+
+/*
+ * Max timeout (in seconds) for the server to reply to a request before
+ * the connection is aborted.
+ *
+ * Exported via sysctl
+ */
+unsigned int fuse_max_req_timeout;
+
+bool fuse_request_expired(struct fuse_chan *fch, struct list_head *list)
+{
+	struct fuse_req *req;
+
+	req = list_first_entry_or_null(list, struct fuse_req, list);
+	if (!req)
+		return false;
+	return time_is_before_jiffies(req->create_time + fch->timeout.req_timeout);
+}
+
+static bool fuse_fpq_processing_expired(struct fuse_chan *fch, struct list_head *processing)
+{
+	int i;
+
+	for (i = 0; i < FUSE_PQ_HASH_SIZE; i++)
+		if (fuse_request_expired(fch, &processing[i]))
+			return true;
+
+	return false;
+}
+
+/*
+ * Check if any requests aren't being completed by the time the request timeout
+ * elapses. To do so, we:
+ * - check the fiq pending list
+ * - check the bg queue
+ * - check the fpq io and processing lists
+ *
+ * To make this fast, we only check against the head request on each list since
+ * these are generally queued in order of creation time (eg newer requests get
+ * queued to the tail). We might miss a few edge cases (eg requests transitioning
+ * between lists, re-sent requests at the head of the pending list having a
+ * later creation time than other requests on that list, etc.) but that is fine
+ * since if the request never gets fulfilled, it will eventually be caught.
+ */
+static void fuse_check_timeout(struct work_struct *work)
+{
+	struct delayed_work *dwork = to_delayed_work(work);
+	struct fuse_chan *fch = container_of(dwork, struct fuse_chan, timeout.work);
+	struct fuse_iqueue *fiq = &fch->iq;
+	struct fuse_dev *fud;
+	struct fuse_pqueue *fpq;
+	bool expired = false;
+
+	if (!atomic_read(&fch->num_waiting))
+		goto out;
+
+	spin_lock(&fiq->lock);
+	expired = fuse_request_expired(fch, &fiq->pending);
+	spin_unlock(&fiq->lock);
+	if (expired)
+		goto chan_abort;
+
+	spin_lock(&fch->bg_lock);
+	expired = fuse_request_expired(fch, &fch->bg_queue);
+	spin_unlock(&fch->bg_lock);
+	if (expired)
+		goto chan_abort;
+
+	spin_lock(&fch->lock);
+	if (!fch->connected) {
+		spin_unlock(&fch->lock);
+		return;
+	}
+	list_for_each_entry(fud, &fch->devices, entry) {
+		fpq = &fud->pq;
+		spin_lock(&fpq->lock);
+		if (fuse_request_expired(fch, &fpq->io) ||
+		    fuse_fpq_processing_expired(fch, fpq->processing)) {
+			spin_unlock(&fpq->lock);
+			spin_unlock(&fch->lock);
+			goto chan_abort;
+		}
+
+		spin_unlock(&fpq->lock);
+	}
+	spin_unlock(&fch->lock);
+
+	if (fuse_uring_request_expired(fch))
+		goto chan_abort;
+
+out:
+	queue_delayed_work(system_percpu_wq, &fch->timeout.work,
+			   fuse_timeout_timer_freq);
+	return;
+
+chan_abort:
+	fuse_chan_abort(fch, false);
+}
+
+static void set_request_timeout(struct fuse_chan *fch, unsigned int timeout)
+{
+	fch->timeout.req_timeout = secs_to_jiffies(timeout);
+	INIT_DELAYED_WORK(&fch->timeout.work, fuse_check_timeout);
+	queue_delayed_work(system_percpu_wq, &fch->timeout.work,
+			   fuse_timeout_timer_freq);
+}
+
+void fuse_init_server_timeout(struct fuse_chan *fch, unsigned int timeout)
+{
+	if (!timeout)
+		timeout = fuse_default_req_timeout;
+
+	timeout = min_not_zero(timeout, fuse_max_req_timeout);
+	if (!timeout)
+		return;
+
+	timeout = max(FUSE_TIMEOUT_TIMER_FREQ, timeout);
+
+	set_request_timeout(fch, timeout);
+}
+