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, 109 insertions, 0 deletions

diff --git a/fs/netfs/fscache_main.c b/fs/netfs/fscache_main.c
new file mode 100644
index 000000000..49849005e
--- /dev/null
+++ b/fs/netfs/fscache_main.c
@@ -0,0 +1,109 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* General filesystem local caching manager
+ *
+ * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#define FSCACHE_DEBUG_LEVEL CACHE
+#include <linux/module.h>
+#include <linux/init.h>
+#include "internal.h"
+#define CREATE_TRACE_POINTS
+#include <trace/events/fscache.h>
+
+EXPORT_TRACEPOINT_SYMBOL(fscache_access_cache);
+EXPORT_TRACEPOINT_SYMBOL(fscache_access_volume);
+EXPORT_TRACEPOINT_SYMBOL(fscache_access);
+
+struct workqueue_struct *fscache_wq;
+EXPORT_SYMBOL(fscache_wq);
+
+/*
+ * Mixing scores (in bits) for (7,20):
+ * Input delta: 1-bit      2-bit
+ * 1 round:     330.3     9201.6
+ * 2 rounds:   1246.4    25475.4
+ * 3 rounds:   1907.1    31295.1
+ * 4 rounds:   2042.3    31718.6
+ * Perfect:    2048      31744
+ *            (32*64)   (32*31/2 * 64)
+ */
+#define HASH_MIX(x, y, a)	\
+	(	x ^= (a),	\
+	y ^= x,	x = rol32(x, 7),\
+	x += y,	y = rol32(y,20),\
+	y *= 9			)
+
+static inline unsigned int fold_hash(unsigned long x, unsigned long y)
+{
+	/* Use arch-optimized multiply if one exists */
+	return __hash_32(y ^ __hash_32(x));
+}
+
+/*
+ * Generate a hash.  This is derived from full_name_hash(), but we want to be
+ * sure it is arch independent and that it doesn't change as bits of the
+ * computed hash value might appear on disk.  The caller must guarantee that
+ * the source data is a multiple of four bytes in size.
+ */
+unsigned int fscache_hash(unsigned int salt, const void *data, size_t len)
+{
+	const __le32 *p = data;
+	unsigned int a, x = 0, y = salt, n = len / sizeof(__le32);
+
+	for (; n; n--) {
+		a = le32_to_cpu(*p++);
+		HASH_MIX(x, y, a);
+	}
+	return fold_hash(x, y);
+}
+
+/*
+ * initialise the fs caching module
+ */
+int __init fscache_init(void)
+{
+	int ret = -ENOMEM;
+
+	fscache_wq = alloc_workqueue("fscache", WQ_UNBOUND | WQ_FREEZABLE, 0);
+	if (!fscache_wq)
+		goto error_wq;
+
+	ret = fscache_proc_init();
+	if (ret < 0)
+		goto error_proc;
+
+	fscache_cookie_jar = kmem_cache_create("fscache_cookie_jar",
+					       sizeof(struct fscache_cookie),
+					       0, 0, NULL);
+	if (!fscache_cookie_jar) {
+		pr_notice("Failed to allocate a cookie jar\n");
+		ret = -ENOMEM;
+		goto error_cookie_jar;
+	}
+
+	pr_notice("FS-Cache loaded\n");
+	return 0;
+
+error_cookie_jar:
+	fscache_proc_cleanup();
+error_proc:
+	destroy_workqueue(fscache_wq);
+error_wq:
+	return ret;
+}
+
+/*
+ * clean up on module removal
+ */
+void __exit fscache_exit(void)
+{
+	_enter("");
+
+	kmem_cache_destroy(fscache_cookie_jar);
+	fscache_proc_cleanup();
+	timer_shutdown_sync(&fscache_cookie_lru_timer);
+	destroy_workqueue(fscache_wq);
+	pr_notice("FS-Cache unloaded\n");
+}