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, 181 insertions, 0 deletions

diff --git a/tools/lib/bitmap.c b/tools/lib/bitmap.c
new file mode 100644
index 000000000..fedc9070f
--- /dev/null
+++ b/tools/lib/bitmap.c
@@ -0,0 +1,181 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * From lib/bitmap.c
+ * Helper functions for bitmap.h.
+ */
+#include <linux/bitmap.h>
+
+unsigned int __bitmap_weight(const unsigned long *bitmap, int bits)
+{
+	unsigned int k, w = 0, lim = bits/BITS_PER_LONG;
+
+	for (k = 0; k < lim; k++)
+		w += hweight_long(bitmap[k]);
+
+	if (bits % BITS_PER_LONG)
+		w += hweight_long(bitmap[k] & BITMAP_LAST_WORD_MASK(bits));
+
+	return w;
+}
+
+void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1,
+		 const unsigned long *bitmap2, int bits)
+{
+	int k;
+	int nr = BITS_TO_LONGS(bits);
+
+	for (k = 0; k < nr; k++)
+		dst[k] = bitmap1[k] | bitmap2[k];
+}
+
+size_t bitmap_scnprintf(unsigned long *bitmap, unsigned int nbits,
+			char *buf, size_t size)
+{
+	/* current bit is 'cur', most recently seen range is [rbot, rtop] */
+	unsigned int cur, rbot, rtop;
+	bool first = true;
+	size_t ret = 0;
+
+	rbot = cur = find_first_bit(bitmap, nbits);
+	while (cur < nbits) {
+		rtop = cur;
+		cur = find_next_bit(bitmap, nbits, cur + 1);
+		if (cur < nbits && cur <= rtop + 1)
+			continue;
+
+		if (!first)
+			ret += scnprintf(buf + ret, size - ret, ",");
+
+		first = false;
+
+		ret += scnprintf(buf + ret, size - ret, "%d", rbot);
+		if (rbot < rtop)
+			ret += scnprintf(buf + ret, size - ret, "-%d", rtop);
+
+		rbot = cur;
+	}
+	return ret;
+}
+
+bool __bitmap_and(unsigned long *dst, const unsigned long *bitmap1,
+		 const unsigned long *bitmap2, unsigned int bits)
+{
+	unsigned int k;
+	unsigned int lim = bits/BITS_PER_LONG;
+	unsigned long result = 0;
+
+	for (k = 0; k < lim; k++)
+		result |= (dst[k] = bitmap1[k] & bitmap2[k]);
+	if (bits % BITS_PER_LONG)
+		result |= (dst[k] = bitmap1[k] & bitmap2[k] &
+			   BITMAP_LAST_WORD_MASK(bits));
+	return result != 0;
+}
+
+bool __bitmap_equal(const unsigned long *bitmap1,
+		    const unsigned long *bitmap2, unsigned int bits)
+{
+	unsigned int k, lim = bits/BITS_PER_LONG;
+	for (k = 0; k < lim; ++k)
+		if (bitmap1[k] != bitmap2[k])
+			return false;
+
+	if (bits % BITS_PER_LONG)
+		if ((bitmap1[k] ^ bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits))
+			return false;
+
+	return true;
+}
+
+bool __bitmap_intersects(const unsigned long *bitmap1,
+			 const unsigned long *bitmap2, unsigned int bits)
+{
+	unsigned int k, lim = bits/BITS_PER_LONG;
+	for (k = 0; k < lim; ++k)
+		if (bitmap1[k] & bitmap2[k])
+			return true;
+
+	if (bits % BITS_PER_LONG)
+		if ((bitmap1[k] & bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits))
+			return true;
+	return false;
+}
+
+void __bitmap_set(unsigned long *map, unsigned int start, int len)
+{
+	unsigned long *p = map + BIT_WORD(start);
+	const unsigned int size = start + len;
+	int bits_to_set = BITS_PER_LONG - (start % BITS_PER_LONG);
+	unsigned long mask_to_set = BITMAP_FIRST_WORD_MASK(start);
+
+	while (len - bits_to_set >= 0) {
+		*p |= mask_to_set;
+		len -= bits_to_set;
+		bits_to_set = BITS_PER_LONG;
+		mask_to_set = ~0UL;
+		p++;
+	}
+	if (len) {
+		mask_to_set &= BITMAP_LAST_WORD_MASK(size);
+		*p |= mask_to_set;
+	}
+}
+
+void __bitmap_clear(unsigned long *map, unsigned int start, int len)
+{
+	unsigned long *p = map + BIT_WORD(start);
+	const unsigned int size = start + len;
+	int bits_to_clear = BITS_PER_LONG - (start % BITS_PER_LONG);
+	unsigned long mask_to_clear = BITMAP_FIRST_WORD_MASK(start);
+
+	while (len - bits_to_clear >= 0) {
+		*p &= ~mask_to_clear;
+		len -= bits_to_clear;
+		bits_to_clear = BITS_PER_LONG;
+		mask_to_clear = ~0UL;
+		p++;
+	}
+	if (len) {
+		mask_to_clear &= BITMAP_LAST_WORD_MASK(size);
+		*p &= ~mask_to_clear;
+	}
+}
+
+bool __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1,
+				const unsigned long *bitmap2, unsigned int bits)
+{
+	unsigned int k;
+	unsigned int lim = bits/BITS_PER_LONG;
+	unsigned long result = 0;
+
+	for (k = 0; k < lim; k++)
+		result |= (dst[k] = bitmap1[k] & ~bitmap2[k]);
+	if (bits % BITS_PER_LONG)
+		result |= (dst[k] = bitmap1[k] & ~bitmap2[k] &
+			   BITMAP_LAST_WORD_MASK(bits));
+	return result != 0;
+}
+
+bool __bitmap_subset(const unsigned long *bitmap1,
+		     const unsigned long *bitmap2, unsigned int bits)
+{
+	unsigned int k, lim = bits/BITS_PER_LONG;
+	for (k = 0; k < lim; ++k)
+		if (bitmap1[k] & ~bitmap2[k])
+			return false;
+
+	if (bits % BITS_PER_LONG)
+		if ((bitmap1[k] & ~bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits))
+			return false;
+	return true;
+}
+
+void __bitmap_xor(unsigned long *dst, const unsigned long *bitmap1,
+				const unsigned long *bitmap2, unsigned int bits)
+{
+	unsigned int k;
+	unsigned int nr = BITS_TO_LONGS(bits);
+
+	for (k = 0; k < nr; k++)
+		dst[k] = bitmap1[k] ^ bitmap2[k];
+}