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, 272 insertions, 0 deletions

diff --git a/io_uring/fdinfo.c b/io_uring/fdinfo.c
new file mode 100644
index 000000000..3ae480476
--- /dev/null
+++ b/io_uring/fdinfo.c
@@ -0,0 +1,272 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <linux/nospec.h>
+#include <linux/io_uring.h>
+
+#include <uapi/linux/io_uring.h>
+
+#include "filetable.h"
+#include "sqpoll.h"
+#include "fdinfo.h"
+#include "cancel.h"
+#include "rsrc.h"
+#include "opdef.h"
+
+#ifdef CONFIG_NET_RX_BUSY_POLL
+static __cold void common_tracking_show_fdinfo(struct io_ring_ctx *ctx,
+					       struct seq_file *m,
+					       const char *tracking_strategy)
+{
+	seq_puts(m, "NAPI:\tenabled\n");
+	seq_printf(m, "napi tracking:\t%s\n", tracking_strategy);
+	seq_printf(m, "napi_busy_poll_dt:\t%llu\n", ctx->napi_busy_poll_dt);
+	if (ctx->napi_prefer_busy_poll)
+		seq_puts(m, "napi_prefer_busy_poll:\ttrue\n");
+	else
+		seq_puts(m, "napi_prefer_busy_poll:\tfalse\n");
+}
+
+static __cold void napi_show_fdinfo(struct io_ring_ctx *ctx,
+				    struct seq_file *m)
+{
+	unsigned int mode = READ_ONCE(ctx->napi_track_mode);
+
+	switch (mode) {
+	case IO_URING_NAPI_TRACKING_INACTIVE:
+		seq_puts(m, "NAPI:\tdisabled\n");
+		break;
+	case IO_URING_NAPI_TRACKING_DYNAMIC:
+		common_tracking_show_fdinfo(ctx, m, "dynamic");
+		break;
+	case IO_URING_NAPI_TRACKING_STATIC:
+		common_tracking_show_fdinfo(ctx, m, "static");
+		break;
+	default:
+		seq_printf(m, "NAPI:\tunknown mode (%u)\n", mode);
+	}
+}
+#else
+static inline void napi_show_fdinfo(struct io_ring_ctx *ctx,
+				    struct seq_file *m)
+{
+}
+#endif
+
+static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m)
+{
+	struct io_overflow_cqe *ocqe;
+	struct io_rings *r = ctx->rings;
+	unsigned int sq_mask = ctx->sq_entries - 1, cq_mask = ctx->cq_entries - 1;
+	unsigned int sq_head = READ_ONCE(r->sq.head);
+	unsigned int sq_tail = READ_ONCE(r->sq.tail);
+	unsigned int cq_head = READ_ONCE(r->cq.head);
+	unsigned int cq_tail = READ_ONCE(r->cq.tail);
+	unsigned int sq_shift = 0;
+	unsigned int cq_entries, sq_entries;
+	int sq_pid = -1, sq_cpu = -1;
+	u64 sq_total_time = 0, sq_work_time = 0;
+	unsigned int i;
+
+	if (ctx->flags & IORING_SETUP_SQE128)
+		sq_shift = 1;
+
+	/*
+	 * we may get imprecise sqe and cqe info if uring is actively running
+	 * since we get cached_sq_head and cached_cq_tail without uring_lock
+	 * and sq_tail and cq_head are changed by userspace. But it's ok since
+	 * we usually use these info when it is stuck.
+	 */
+	seq_printf(m, "SqMask:\t0x%x\n", sq_mask);
+	seq_printf(m, "SqHead:\t%u\n", sq_head);
+	seq_printf(m, "SqTail:\t%u\n", sq_tail);
+	seq_printf(m, "CachedSqHead:\t%u\n", data_race(ctx->cached_sq_head));
+	seq_printf(m, "CqMask:\t0x%x\n", cq_mask);
+	seq_printf(m, "CqHead:\t%u\n", cq_head);
+	seq_printf(m, "CqTail:\t%u\n", cq_tail);
+	seq_printf(m, "CachedCqTail:\t%u\n", data_race(ctx->cached_cq_tail));
+	seq_printf(m, "SQEs:\t%u\n", sq_tail - sq_head);
+	sq_entries = min(sq_tail - sq_head, ctx->sq_entries);
+	for (i = 0; i < sq_entries; i++) {
+		unsigned int entry = i + sq_head;
+		struct io_uring_sqe *sqe;
+		unsigned int sq_idx;
+		bool sqe128 = false;
+		u8 opcode;
+
+		if (ctx->flags & IORING_SETUP_NO_SQARRAY)
+			sq_idx = entry & sq_mask;
+		else
+			sq_idx = READ_ONCE(ctx->sq_array[entry & sq_mask]);
+		if (sq_idx > sq_mask)
+			continue;
+
+		sqe = &ctx->sq_sqes[sq_idx << sq_shift];
+		opcode = READ_ONCE(sqe->opcode);
+		if (opcode >= IORING_OP_LAST)
+			continue;
+		opcode = array_index_nospec(opcode, IORING_OP_LAST);
+		if (sq_shift) {
+			sqe128 = true;
+		} else if (io_issue_defs[opcode].is_128) {
+			if (!(ctx->flags & IORING_SETUP_SQE_MIXED)) {
+				seq_printf(m,
+					"%5u: invalid sqe, 128B entry on non-mixed sq\n",
+					sq_idx);
+				break;
+			}
+			if (sq_idx == sq_mask) {
+				seq_printf(m,
+					"%5u: corrupted sqe, wrapping 128B entry\n",
+					sq_idx);
+				break;
+			}
+			sq_head++;
+			i++;
+			sqe128 = true;
+		}
+		seq_printf(m, "%5u: opcode:%s, fd:%d, flags:%x, off:%llu, "
+			      "addr:0x%llx, rw_flags:0x%x, buf_index:%d "
+			      "user_data:%llu",
+			   sq_idx, io_uring_get_opcode(opcode), sqe->fd,
+			   sqe->flags, (unsigned long long) sqe->off,
+			   (unsigned long long) sqe->addr, sqe->rw_flags,
+			   sqe->buf_index, sqe->user_data);
+		if (sqe128) {
+			u64 *sqeb = (void *) (sqe + 1);
+			int size = sizeof(struct io_uring_sqe) / sizeof(u64);
+			int j;
+
+			for (j = 0; j < size; j++) {
+				seq_printf(m, ", e%d:0x%llx", j,
+						(unsigned long long) *sqeb);
+				sqeb++;
+			}
+		}
+		seq_printf(m, "\n");
+		cond_resched();
+	}
+	seq_printf(m, "CQEs:\t%u\n", cq_tail - cq_head);
+	cq_entries = min(cq_tail - cq_head, ctx->cq_entries);
+	for (i = 0; i < cq_entries; i++) {
+		struct io_uring_cqe *cqe;
+		bool cqe32 = false;
+
+		cqe = &r->cqes[(cq_head & cq_mask)];
+		if (cqe->flags & IORING_CQE_F_32 || ctx->flags & IORING_SETUP_CQE32)
+			cqe32 = true;
+		seq_printf(m, "%5u: user_data:%llu, res:%d, flags:%x",
+			   cq_head & cq_mask, cqe->user_data, cqe->res,
+			   cqe->flags);
+		if (cqe32)
+			seq_printf(m, ", extra1:%llu, extra2:%llu",
+					cqe->big_cqe[0], cqe->big_cqe[1]);
+		seq_printf(m, "\n");
+		cq_head++;
+		if (cqe32) {
+			cq_head++;
+			i++;
+		}
+		cond_resched();
+	}
+
+	if (ctx->flags & IORING_SETUP_SQPOLL) {
+		struct io_sq_data *sq = ctx->sq_data;
+		struct task_struct *tsk;
+
+		rcu_read_lock();
+		tsk = rcu_dereference(sq->thread);
+		/*
+		 * sq->thread might be NULL if we raced with the sqpoll
+		 * thread termination.
+		 */
+		if (tsk) {
+			u64 usec;
+
+			get_task_struct(tsk);
+			rcu_read_unlock();
+			usec = io_sq_cpu_usec(tsk);
+			sq_pid = task_pid_nr_ns(tsk,
+						proc_pid_ns(file_inode(m->file)->i_sb));
+			put_task_struct(tsk);
+			sq_cpu = sq->sq_cpu;
+			sq_total_time = usec;
+			sq_work_time = sq->work_time;
+		} else {
+			rcu_read_unlock();
+		}
+	}
+
+	seq_printf(m, "SqThread:\t%d\n", sq_pid);
+	seq_printf(m, "SqThreadCpu:\t%d\n", sq_cpu);
+	seq_printf(m, "SqTotalTime:\t%llu\n", sq_total_time);
+	seq_printf(m, "SqWorkTime:\t%llu\n", sq_work_time);
+	seq_printf(m, "UserFiles:\t%u\n", ctx->file_table.data.nr);
+	for (i = 0; i < ctx->file_table.data.nr; i++) {
+		struct file *f = NULL;
+
+		if (ctx->file_table.data.nodes[i])
+			f = io_slot_file(ctx->file_table.data.nodes[i]);
+		if (f) {
+			seq_printf(m, "%5u: ", i);
+			seq_file_path(m, f, " \t\n\\");
+			seq_puts(m, "\n");
+		}
+	}
+	seq_printf(m, "UserBufs:\t%u\n", ctx->buf_table.nr);
+	for (i = 0; i < ctx->buf_table.nr; i++) {
+		struct io_mapped_ubuf *buf = NULL;
+
+		if (ctx->buf_table.nodes[i])
+			buf = ctx->buf_table.nodes[i]->buf;
+		if (buf)
+			seq_printf(m, "%5u: 0x%llx/%zu\n", i, buf->ubuf, buf->len);
+		else
+			seq_printf(m, "%5u: <none>\n", i);
+	}
+
+	seq_puts(m, "PollList:\n");
+	for (i = 0; i < (1U << ctx->cancel_table.hash_bits); i++) {
+		struct io_hash_bucket *hb = &ctx->cancel_table.hbs[i];
+		struct io_kiocb *req;
+
+		hlist_for_each_entry(req, &hb->list, hash_node)
+			seq_printf(m, "  op=%d, task_works=%d\n", req->opcode,
+					task_work_pending(req->tctx->task));
+	}
+
+	seq_puts(m, "CqOverflowList:\n");
+	spin_lock(&ctx->completion_lock);
+	list_for_each_entry(ocqe, &ctx->cq_overflow_list, list) {
+		struct io_uring_cqe *cqe = &ocqe->cqe;
+
+		seq_printf(m, "  user_data=%llu, res=%d, flags=%x\n",
+			   cqe->user_data, cqe->res, cqe->flags);
+
+	}
+	spin_unlock(&ctx->completion_lock);
+	napi_show_fdinfo(ctx, m);
+}
+
+/*
+ * Caller holds a reference to the file already, we don't need to do
+ * anything else to get an extra reference.
+ */
+__cold void io_uring_show_fdinfo(struct seq_file *m, struct file *file)
+{
+	struct io_ring_ctx *ctx = file->private_data;
+
+	/*
+	 * Avoid ABBA deadlock between the seq lock and the io_uring mutex,
+	 * since fdinfo case grabs it in the opposite direction of normal use
+	 * cases.
+	 */
+	if (mutex_trylock(&ctx->uring_lock)) {
+		__io_uring_show_fdinfo(ctx, m);
+		mutex_unlock(&ctx->uring_lock);
+	}
+}