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, 141 insertions, 0 deletions

diff --git a/lib/earlycpio.c b/lib/earlycpio.c
new file mode 100644
index 000000000..d2c37d64f
--- /dev/null
+++ b/lib/earlycpio.c
@@ -0,0 +1,141 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* ----------------------------------------------------------------------- *
+ *
+ *   Copyright 2012 Intel Corporation; author H. Peter Anvin
+ *
+ * ----------------------------------------------------------------------- */
+
+/*
+ * earlycpio.c
+ *
+ * Find a specific cpio member; must precede any compressed content.
+ * This is used to locate data items in the initramfs used by the
+ * kernel itself during early boot (before the main initramfs is
+ * decompressed.)  It is the responsibility of the initramfs creator
+ * to ensure that these items are uncompressed at the head of the
+ * blob.  Depending on the boot loader or package tool that may be a
+ * separate file or part of the same file.
+ */
+
+#include <linux/earlycpio.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+
+enum cpio_fields {
+	C_MAGIC,
+	C_INO,
+	C_MODE,
+	C_UID,
+	C_GID,
+	C_NLINK,
+	C_MTIME,
+	C_FILESIZE,
+	C_MAJ,
+	C_MIN,
+	C_RMAJ,
+	C_RMIN,
+	C_NAMESIZE,
+	C_CHKSUM,
+	C_NFIELDS
+};
+
+/**
+ * find_cpio_data - Search for files in an uncompressed cpio
+ * @path:       The directory to search for, including a slash at the end
+ * @data:       Pointer to the cpio archive or a header inside
+ * @len:        Remaining length of the cpio based on data pointer
+ * @nextoff:    When a matching file is found, this is the offset from the
+ *              beginning of the cpio to the beginning of the next file, not the
+ *              matching file itself. It can be used to iterate through the cpio
+ *              to find all files inside of a directory path.
+ *
+ * Return:      &struct cpio_data containing the address, length and
+ *              filename (with the directory path cut off) of the found file.
+ *              If you search for a filename and not for files in a directory,
+ *              pass the absolute path of the filename in the cpio and make sure
+ *              the match returned an empty filename string.
+ */
+
+struct cpio_data find_cpio_data(const char *path, void *data,
+				size_t len,  long *nextoff)
+{
+	const size_t cpio_header_len = 8*C_NFIELDS - 2;
+	struct cpio_data cd = { NULL, 0, "" };
+	const char *p, *dptr, *nptr;
+	unsigned int ch[C_NFIELDS], *chp, v;
+	unsigned char c, x;
+	size_t mypathsize = strlen(path);
+	int i, j;
+
+	p = data;
+
+	while (len > cpio_header_len) {
+		if (!*p) {
+			/* All cpio headers need to be 4-byte aligned */
+			p += 4;
+			len -= 4;
+			continue;
+		}
+
+		j = 6;		/* The magic field is only 6 characters */
+		chp = ch;
+		for (i = C_NFIELDS; i; i--) {
+			v = 0;
+			while (j--) {
+				v <<= 4;
+				c = *p++;
+
+				x = c - '0';
+				if (x < 10) {
+					v += x;
+					continue;
+				}
+
+				x = (c | 0x20) - 'a';
+				if (x < 6) {
+					v += x + 10;
+					continue;
+				}
+
+				goto quit; /* Invalid hexadecimal */
+			}
+			*chp++ = v;
+			j = 8;	/* All other fields are 8 characters */
+		}
+
+		if ((ch[C_MAGIC] - 0x070701) > 1)
+			goto quit; /* Invalid magic */
+
+		len -= cpio_header_len;
+
+		dptr = PTR_ALIGN(p + ch[C_NAMESIZE], 4);
+		nptr = PTR_ALIGN(dptr + ch[C_FILESIZE], 4);
+
+		if (nptr > p + len || dptr < p || nptr < dptr)
+			goto quit; /* Buffer overrun */
+
+		if ((ch[C_MODE] & 0170000) == 0100000 &&
+		    ch[C_NAMESIZE] >= mypathsize &&
+		    !memcmp(p, path, mypathsize)) {
+
+			if (nextoff)
+				*nextoff = (long)nptr - (long)data;
+
+			if (ch[C_NAMESIZE] - mypathsize >= MAX_CPIO_FILE_NAME) {
+				pr_warn(
+				"File %s exceeding MAX_CPIO_FILE_NAME [%d]\n",
+				p, MAX_CPIO_FILE_NAME);
+			}
+			strscpy(cd.name, p + mypathsize, MAX_CPIO_FILE_NAME);
+
+			cd.data = (void *)dptr;
+			cd.size = ch[C_FILESIZE];
+			return cd; /* Found it! */
+		}
+		len -= (nptr - p);
+		p = nptr;
+	}
+
+quit:
+	return cd;
+}