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, 131 insertions, 0 deletions

diff --git a/net/ceph/ceph_hash.c b/net/ceph/ceph_hash.c
new file mode 100644
index 000000000..16a47c0ee
--- /dev/null
+++ b/net/ceph/ceph_hash.c
@@ -0,0 +1,131 @@
+
+#include <linux/ceph/types.h>
+#include <linux/module.h>
+
+/*
+ * Robert Jenkin's hash function.
+ * https://burtleburtle.net/bob/hash/evahash.html
+ * This is in the public domain.
+ */
+#define mix(a, b, c)						\
+	do {							\
+		a = a - b;  a = a - c;  a = a ^ (c >> 13);	\
+		b = b - c;  b = b - a;  b = b ^ (a << 8);	\
+		c = c - a;  c = c - b;  c = c ^ (b >> 13);	\
+		a = a - b;  a = a - c;  a = a ^ (c >> 12);	\
+		b = b - c;  b = b - a;  b = b ^ (a << 16);	\
+		c = c - a;  c = c - b;  c = c ^ (b >> 5);	\
+		a = a - b;  a = a - c;  a = a ^ (c >> 3);	\
+		b = b - c;  b = b - a;  b = b ^ (a << 10);	\
+		c = c - a;  c = c - b;  c = c ^ (b >> 15);	\
+	} while (0)
+
+unsigned int ceph_str_hash_rjenkins(const char *str, unsigned int length)
+{
+	const unsigned char *k = (const unsigned char *)str;
+	__u32 a, b, c;  /* the internal state */
+	__u32 len;      /* how many key bytes still need mixing */
+
+	/* Set up the internal state */
+	len = length;
+	a = 0x9e3779b9;      /* the golden ratio; an arbitrary value */
+	b = a;
+	c = 0;               /* variable initialization of internal state */
+
+	/* handle most of the key */
+	while (len >= 12) {
+		a = a + (k[0] + ((__u32)k[1] << 8) + ((__u32)k[2] << 16) +
+			 ((__u32)k[3] << 24));
+		b = b + (k[4] + ((__u32)k[5] << 8) + ((__u32)k[6] << 16) +
+			 ((__u32)k[7] << 24));
+		c = c + (k[8] + ((__u32)k[9] << 8) + ((__u32)k[10] << 16) +
+			 ((__u32)k[11] << 24));
+		mix(a, b, c);
+		k = k + 12;
+		len = len - 12;
+	}
+
+	/* handle the last 11 bytes */
+	c = c + length;
+	switch (len) {
+	case 11:
+		c = c + ((__u32)k[10] << 24);
+		fallthrough;
+	case 10:
+		c = c + ((__u32)k[9] << 16);
+		fallthrough;
+	case 9:
+		c = c + ((__u32)k[8] << 8);
+		/* the first byte of c is reserved for the length */
+		fallthrough;
+	case 8:
+		b = b + ((__u32)k[7] << 24);
+		fallthrough;
+	case 7:
+		b = b + ((__u32)k[6] << 16);
+		fallthrough;
+	case 6:
+		b = b + ((__u32)k[5] << 8);
+		fallthrough;
+	case 5:
+		b = b + k[4];
+		fallthrough;
+	case 4:
+		a = a + ((__u32)k[3] << 24);
+		fallthrough;
+	case 3:
+		a = a + ((__u32)k[2] << 16);
+		fallthrough;
+	case 2:
+		a = a + ((__u32)k[1] << 8);
+		fallthrough;
+	case 1:
+		a = a + k[0];
+		/* case 0: nothing left to add */
+	}
+	mix(a, b, c);
+
+	return c;
+}
+
+/*
+ * linux dcache hash
+ */
+unsigned int ceph_str_hash_linux(const char *str, unsigned int length)
+{
+	unsigned long hash = 0;
+	unsigned char c;
+
+	while (length--) {
+		c = *str++;
+		hash = (hash + (c << 4) + (c >> 4)) * 11;
+	}
+	return hash;
+}
+
+
+unsigned int ceph_str_hash(int type, const char *s, unsigned int len)
+{
+	switch (type) {
+	case CEPH_STR_HASH_LINUX:
+		return ceph_str_hash_linux(s, len);
+	case CEPH_STR_HASH_RJENKINS:
+		return ceph_str_hash_rjenkins(s, len);
+	default:
+		return -1;
+	}
+}
+EXPORT_SYMBOL(ceph_str_hash);
+
+const char *ceph_str_hash_name(int type)
+{
+	switch (type) {
+	case CEPH_STR_HASH_LINUX:
+		return "linux";
+	case CEPH_STR_HASH_RJENKINS:
+		return "rjenkins";
+	default:
+		return "unknown";
+	}
+}
+EXPORT_SYMBOL(ceph_str_hash_name);