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, 116 insertions, 0 deletions

diff --git a/fs/ntfs3/upcase.c b/fs/ntfs3/upcase.c
new file mode 100644
index 000000000..7681eefac
--- /dev/null
+++ b/fs/ntfs3/upcase.c
@@ -0,0 +1,116 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *
+ * Copyright (C) 2019-2021 Paragon Software GmbH, All rights reserved.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+
+#include "ntfs_fs.h"
+
+static inline u16 upcase_unicode_char(const u16 *upcase, u16 chr)
+{
+	if (chr < 'a')
+		return chr;
+
+	if (chr <= 'z')
+		return chr - ('a' - 'A');
+
+	return upcase[chr];
+}
+
+/*
+ * ntfs_cmp_names
+ *
+ * Thanks Kari Argillander <kari.argillander@gmail.com> for idea and implementation 'bothcase'
+ *
+ * Straight way to compare names:
+ * - Case insensitive
+ * - If name equals and 'bothcases' then
+ * - Case sensitive
+ * 'Straight way' code scans input names twice in worst case.
+ * Optimized code scans input names only once.
+ */
+int ntfs_cmp_names(const __le16 *s1, size_t l1, const __le16 *s2, size_t l2,
+		   const u16 *upcase, bool bothcase)
+{
+	int diff1 = 0;
+	int diff2;
+	size_t len = min(l1, l2);
+
+	if (!bothcase && upcase)
+		goto case_insentive;
+
+	for (; len; s1++, s2++, len--) {
+		diff1 = le16_to_cpu(*s1) - le16_to_cpu(*s2);
+		if (diff1) {
+			if (bothcase && upcase)
+				goto case_insentive;
+
+			return diff1;
+		}
+	}
+	return l1 - l2;
+
+case_insentive:
+	for (; len; s1++, s2++, len--) {
+		diff2 = upcase_unicode_char(upcase, le16_to_cpu(*s1)) -
+			upcase_unicode_char(upcase, le16_to_cpu(*s2));
+		if (diff2)
+			return diff2;
+	}
+
+	diff2 = l1 - l2;
+	return diff2 ? diff2 : diff1;
+}
+
+int ntfs_cmp_names_cpu(const struct cpu_str *uni1, const struct le_str *uni2,
+		       const u16 *upcase, bool bothcase)
+{
+	const u16 *s1 = uni1->name;
+	const __le16 *s2 = uni2->name;
+	size_t l1 = uni1->len;
+	size_t l2 = uni2->len;
+	size_t len = min(l1, l2);
+	int diff1 = 0;
+	int diff2;
+
+	if (!bothcase && upcase)
+		goto case_insentive;
+
+	for (; len; s1++, s2++, len--) {
+		diff1 = *s1 - le16_to_cpu(*s2);
+		if (diff1) {
+			if (bothcase && upcase)
+				goto case_insentive;
+
+			return diff1;
+		}
+	}
+	return l1 - l2;
+
+case_insentive:
+	for (; len; s1++, s2++, len--) {
+		diff2 = upcase_unicode_char(upcase, *s1) -
+			upcase_unicode_char(upcase, le16_to_cpu(*s2));
+		if (diff2)
+			return diff2;
+	}
+
+	diff2 = l1 - l2;
+	return diff2 ? diff2 : diff1;
+}
+
+/* Helper function for ntfs_d_hash. */
+unsigned long ntfs_names_hash(const u16 *name, size_t len, const u16 *upcase,
+			      unsigned long hash)
+{
+	while (len--) {
+		unsigned int c = upcase_unicode_char(upcase, *name++);
+		hash = partial_name_hash(c, hash);
+	}
+
+	return hash;
+}