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, 268 insertions, 0 deletions

diff --git a/fs/netfs/objects.c b/fs/netfs/objects.c
new file mode 100644
index 000000000..7f6a3e912
--- /dev/null
+++ b/fs/netfs/objects.c
@@ -0,0 +1,268 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Object lifetime handling and tracing.
+ *
+ * Copyright (C) 2022 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include <linux/slab.h>
+#include <linux/mempool.h>
+#include "internal.h"
+
+static void netfs_free_request(struct work_struct *work);
+
+/*
+ * Allocate an I/O request and initialise it.
+ */
+struct netfs_io_request *netfs_alloc_request(struct address_space *mapping,
+					     struct file *file,
+					     loff_t start, size_t len,
+					     enum netfs_io_origin origin)
+{
+	static atomic_t debug_ids;
+	struct inode *inode = file ? file_inode(file) : mapping->host;
+	struct netfs_inode *ctx = netfs_inode(inode);
+	struct netfs_io_request *rreq;
+	mempool_t *mempool = ctx->ops->request_pool ?: &netfs_request_pool;
+	struct kmem_cache *cache = mempool->pool_data;
+	gfp_t gfp = GFP_KERNEL;
+	int ret;
+
+	/* Writeback is part of memory reclaim and must not fail due to ENOMEM. */
+	if (origin == NETFS_WRITEBACK || origin == NETFS_WRITEBACK_SINGLE) {
+		gfp = GFP_NOFS; /* Allows use of mempools. */
+
+		rreq = mempool_alloc(mempool, gfp);
+	} else {
+		rreq = mempool->alloc(gfp, mempool->pool_data);
+		if (!rreq)
+			return ERR_PTR(-ENOMEM);
+	}
+
+	memset(rreq, 0, kmem_cache_size(cache));
+	INIT_WORK(&rreq->cleanup_work, netfs_free_request);
+	rreq->gfp		= gfp;
+	rreq->start		= start;
+	rreq->collected_to	= start;
+	rreq->cleaned_to	= start;
+	rreq->len		= len;
+	rreq->progress_at	= 0;
+	rreq->origin		= origin;
+	rreq->netfs_ops		= ctx->ops;
+	rreq->mapping		= mapping;
+	rreq->inode		= inode;
+	rreq->i_size		= i_size_read(inode);
+	rreq->debug_id		= atomic_inc_return(&debug_ids);
+	rreq->wsize		= INT_MAX;
+	rreq->io_streams[0].sreq_max_len = ULONG_MAX;
+	rreq->io_streams[0].sreq_max_segs = 0;
+	spin_lock_init(&rreq->lock);
+	init_waitqueue_head(&rreq->waitq);
+	refcount_set(&rreq->ref, 2);
+
+	for (int s = 0; s < NR_IO_STREAMS; s++) {
+		struct netfs_io_stream *stream = &rreq->io_streams[s];
+
+		INIT_LIST_HEAD(&stream->subrequests);
+		stream->collected_to = rreq->start;
+	}
+
+	if (origin == NETFS_READAHEAD ||
+	    origin == NETFS_READPAGE ||
+	    origin == NETFS_READ_GAPS ||
+	    origin == NETFS_READ_SINGLE ||
+	    origin == NETFS_READ_FOR_WRITE ||
+	    origin == NETFS_UNBUFFERED_READ ||
+	    origin == NETFS_DIO_READ) {
+		INIT_WORK(&rreq->work, netfs_read_collection_worker);
+		rreq->io_streams[0].avail = true;
+	} else {
+		INIT_WORK(&rreq->work, netfs_write_collection_worker);
+	}
+
+	__set_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags);
+	if (rreq->netfs_ops->init_request) {
+		ret = rreq->netfs_ops->init_request(rreq, file);
+		if (ret < 0) {
+			mempool_free(rreq, rreq->netfs_ops->request_pool ?: &netfs_request_pool);
+			return ERR_PTR(ret);
+		}
+	}
+
+	atomic_inc(&ctx->io_count);
+	trace_netfs_rreq_ref(rreq->debug_id, refcount_read(&rreq->ref), netfs_rreq_trace_new);
+	netfs_proc_add_rreq(rreq);
+	netfs_stat(&netfs_n_rh_rreq);
+	return rreq;
+}
+
+void netfs_get_request(struct netfs_io_request *rreq, enum netfs_rreq_ref_trace what)
+{
+	int r;
+
+	__refcount_inc(&rreq->ref, &r);
+	trace_netfs_rreq_ref(rreq->debug_id, r + 1, what);
+}
+
+void netfs_clear_subrequests(struct netfs_io_request *rreq)
+{
+	struct netfs_io_subrequest *subreq;
+	struct netfs_io_stream *stream;
+	int s;
+
+	for (s = 0; s < ARRAY_SIZE(rreq->io_streams); s++) {
+		stream = &rreq->io_streams[s];
+		while (!list_empty(&stream->subrequests)) {
+			subreq = list_first_entry(&stream->subrequests,
+						  struct netfs_io_subrequest, rreq_link);
+			list_del(&subreq->rreq_link);
+			netfs_put_subrequest(subreq, netfs_sreq_trace_put_clear);
+		}
+	}
+}
+
+static void netfs_free_request_rcu(struct rcu_head *rcu)
+{
+	struct netfs_io_request *rreq = container_of(rcu, struct netfs_io_request, rcu);
+
+	mempool_free(rreq, rreq->netfs_ops->request_pool ?: &netfs_request_pool);
+	netfs_stat_d(&netfs_n_rh_rreq);
+}
+
+static void netfs_deinit_request(struct netfs_io_request *rreq)
+{
+	struct netfs_inode *ictx = netfs_inode(rreq->inode);
+	unsigned int i;
+
+	trace_netfs_rreq(rreq, netfs_rreq_trace_free);
+
+	/* Cancel/flush the result collection worker.  That does not carry a
+	 * ref of its own, so we must wait for it somewhere.
+	 */
+	cancel_work_sync(&rreq->work);
+
+	netfs_proc_del_rreq(rreq);
+	netfs_clear_subrequests(rreq);
+	if (rreq->netfs_ops->free_request)
+		rreq->netfs_ops->free_request(rreq);
+	if (rreq->cache_resources.ops)
+		rreq->cache_resources.ops->end_operation(&rreq->cache_resources);
+	if (rreq->direct_bv) {
+		for (i = 0; i < rreq->direct_bv_count; i++) {
+			if (rreq->direct_bv[i].bv_page) {
+				if (rreq->direct_bv_unpin)
+					unpin_user_page(rreq->direct_bv[i].bv_page);
+			}
+		}
+		kvfree(rreq->direct_bv);
+	}
+	rolling_buffer_clear(&rreq->buffer);
+
+	if (atomic_dec_and_test(&ictx->io_count))
+		wake_up_var(&ictx->io_count);
+}
+
+static void netfs_free_request(struct work_struct *work)
+{
+	struct netfs_io_request *rreq =
+		container_of(work, struct netfs_io_request, cleanup_work);
+
+	netfs_deinit_request(rreq);
+	call_rcu(&rreq->rcu, netfs_free_request_rcu);
+}
+
+void netfs_put_request(struct netfs_io_request *rreq, enum netfs_rreq_ref_trace what)
+{
+	unsigned int debug_id;
+	bool dead;
+	int r;
+
+	if (rreq) {
+		debug_id = rreq->debug_id;
+		dead = __refcount_dec_and_test(&rreq->ref, &r);
+		trace_netfs_rreq_ref(debug_id, r - 1, what);
+		if (dead)
+			WARN_ON(!queue_work(system_dfl_wq, &rreq->cleanup_work));
+	}
+}
+
+/*
+ * Free a request (synchronously) that was just allocated but has
+ * failed before it could be submitted.
+ */
+void netfs_put_failed_request(struct netfs_io_request *rreq)
+{
+	int r = refcount_read(&rreq->ref);
+
+	/* new requests have two references (see
+	 * netfs_alloc_request(), and this function is only allowed on
+	 * new request objects
+	 */
+	WARN_ON_ONCE(r != 2);
+
+	trace_netfs_rreq_ref(rreq->debug_id, r, netfs_rreq_trace_put_failed);
+	netfs_free_request(&rreq->cleanup_work);
+}
+
+/*
+ * Allocate and partially initialise an I/O request structure.
+ */
+struct netfs_io_subrequest *netfs_alloc_subrequest(struct netfs_io_request *rreq)
+{
+	struct netfs_io_subrequest *subreq;
+	mempool_t *mempool = rreq->netfs_ops->subrequest_pool ?: &netfs_subrequest_pool;
+	struct kmem_cache *cache = mempool->pool_data;
+
+	if (rreq->gfp == GFP_KERNEL)
+		subreq = mempool->alloc(rreq->gfp, mempool->pool_data);
+	else
+		subreq = mempool_alloc(mempool, rreq->gfp);
+	if (!subreq)
+		return NULL;
+
+	memset(subreq, 0, kmem_cache_size(cache));
+	INIT_WORK(&subreq->work, NULL);
+	INIT_LIST_HEAD(&subreq->rreq_link);
+	refcount_set(&subreq->ref, 2);
+	subreq->rreq = rreq;
+	subreq->debug_index = atomic_inc_return(&rreq->subreq_counter);
+	netfs_get_request(rreq, netfs_rreq_trace_get_subreq);
+	netfs_stat(&netfs_n_rh_sreq);
+	return subreq;
+}
+
+void netfs_get_subrequest(struct netfs_io_subrequest *subreq,
+			  enum netfs_sreq_ref_trace what)
+{
+	int r;
+
+	__refcount_inc(&subreq->ref, &r);
+	trace_netfs_sreq_ref(subreq->rreq->debug_id, subreq->debug_index, r + 1,
+			     what);
+}
+
+static void netfs_free_subrequest(struct netfs_io_subrequest *subreq)
+{
+	struct netfs_io_request *rreq = subreq->rreq;
+
+	trace_netfs_sreq(subreq, netfs_sreq_trace_free);
+	if (rreq->netfs_ops->free_subrequest)
+		rreq->netfs_ops->free_subrequest(subreq);
+	mempool_free(subreq, rreq->netfs_ops->subrequest_pool ?: &netfs_subrequest_pool);
+	netfs_stat_d(&netfs_n_rh_sreq);
+	netfs_put_request(rreq, netfs_rreq_trace_put_subreq);
+}
+
+void netfs_put_subrequest(struct netfs_io_subrequest *subreq,
+			  enum netfs_sreq_ref_trace what)
+{
+	unsigned int debug_index = subreq->debug_index;
+	unsigned int debug_id = subreq->rreq->debug_id;
+	bool dead;
+	int r;
+
+	dead = __refcount_dec_and_test(&subreq->ref, &r);
+	trace_netfs_sreq_ref(debug_id, debug_index, r - 1, what);
+	if (dead)
+		netfs_free_subrequest(subreq);
+}