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, 219 insertions, 0 deletions

diff --git a/lib/decompress_inflate.c b/lib/decompress_inflate.c
new file mode 100644
index 000000000..e19199f4a
--- /dev/null
+++ b/lib/decompress_inflate.c
@@ -0,0 +1,219 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifdef STATIC
+#define PREBOOT
+/* Pre-boot environment: included */
+
+/* prevent inclusion of _LINUX_KERNEL_H in pre-boot environment: lots
+ * errors about console_printk etc... on ARM */
+#define _LINUX_KERNEL_H
+
+#include "zlib_inflate/inftrees.c"
+#include "zlib_inflate/inffast.c"
+#include "zlib_inflate/inflate.c"
+#ifdef CONFIG_ZLIB_DFLTCC
+#include "zlib_dfltcc/dfltcc.c"
+#include "zlib_dfltcc/dfltcc_inflate.c"
+#endif
+
+#else /* STATIC */
+/* initramfs et al: linked */
+
+#include <linux/zutil.h>
+
+#include "zlib_inflate/inftrees.h"
+#include "zlib_inflate/inffast.h"
+#include "zlib_inflate/inflate.h"
+
+#include "zlib_inflate/infutil.h"
+#include <linux/decompress/inflate.h>
+
+#endif /* STATIC */
+
+#include <linux/decompress/mm.h>
+
+#define GZIP_IOBUF_SIZE (16*1024)
+
+static long INIT nofill(void *buffer, unsigned long len)
+{
+	return -1;
+}
+
+/* Included from initramfs et al code */
+static int INIT __gunzip(unsigned char *buf, long len,
+		       long (*fill)(void*, unsigned long),
+		       long (*flush)(void*, unsigned long),
+		       unsigned char *out_buf, long out_len,
+		       long *pos,
+		       void(*error)(char *x)) {
+	u8 *zbuf;
+	struct z_stream_s *strm;
+	int rc;
+
+	rc = -1;
+	if (flush) {
+		out_len = 0x8000; /* 32 K */
+		out_buf = malloc(out_len);
+	} else {
+		if (!out_len)
+			out_len = ((size_t)~0) - (size_t)out_buf; /* no limit */
+	}
+	if (!out_buf) {
+		error("Out of memory while allocating output buffer");
+		goto gunzip_nomem1;
+	}
+
+	if (buf)
+		zbuf = buf;
+	else {
+		zbuf = malloc(GZIP_IOBUF_SIZE);
+		len = 0;
+	}
+	if (!zbuf) {
+		error("Out of memory while allocating input buffer");
+		goto gunzip_nomem2;
+	}
+
+	strm = malloc(sizeof(*strm));
+	if (strm == NULL) {
+		error("Out of memory while allocating z_stream");
+		goto gunzip_nomem3;
+	}
+
+	strm->workspace = malloc(flush ? zlib_inflate_workspacesize() :
+#ifdef CONFIG_ZLIB_DFLTCC
+	/* Always allocate the full workspace for DFLTCC */
+				 zlib_inflate_workspacesize());
+#else
+				 sizeof(struct inflate_state));
+#endif
+	if (strm->workspace == NULL) {
+		error("Out of memory while allocating workspace");
+		goto gunzip_nomem4;
+	}
+
+	if (!fill)
+		fill = nofill;
+
+	if (len == 0)
+		len = fill(zbuf, GZIP_IOBUF_SIZE);
+
+	/* verify the gzip header */
+	if (len < 10 ||
+	   zbuf[0] != 0x1f || zbuf[1] != 0x8b || zbuf[2] != 0x08) {
+		if (pos)
+			*pos = 0;
+		error("Not a gzip file");
+		goto gunzip_5;
+	}
+
+	/* skip over gzip header (1f,8b,08... 10 bytes total +
+	 * possible asciz filename)
+	 */
+	strm->next_in = zbuf + 10;
+	strm->avail_in = len - 10;
+	/* skip over asciz filename */
+	if (zbuf[3] & 0x8) {
+		do {
+			/*
+			 * If the filename doesn't fit into the buffer,
+			 * the file is very probably corrupt. Don't try
+			 * to read more data.
+			 */
+			if (strm->avail_in == 0) {
+				error("header error");
+				goto gunzip_5;
+			}
+			--strm->avail_in;
+		} while (*strm->next_in++);
+	}
+
+	strm->next_out = out_buf;
+	strm->avail_out = out_len;
+
+	rc = zlib_inflateInit2(strm, -MAX_WBITS);
+
+#ifdef CONFIG_ZLIB_DFLTCC
+	/* Always keep the window for DFLTCC */
+#else
+	if (!flush) {
+		WS(strm)->inflate_state.wsize = 0;
+		WS(strm)->inflate_state.window = NULL;
+	}
+#endif
+
+	while (rc == Z_OK) {
+		if (strm->avail_in == 0) {
+			/* TODO: handle case where both pos and fill are set */
+			len = fill(zbuf, GZIP_IOBUF_SIZE);
+			if (len < 0) {
+				rc = -1;
+				error("read error");
+				break;
+			}
+			strm->next_in = zbuf;
+			strm->avail_in = len;
+		}
+		rc = zlib_inflate(strm, 0);
+
+		/* Write any data generated */
+		if (flush && strm->next_out > out_buf) {
+			long l = strm->next_out - out_buf;
+			if (l != flush(out_buf, l)) {
+				rc = -1;
+				error("write error");
+				break;
+			}
+			strm->next_out = out_buf;
+			strm->avail_out = out_len;
+		}
+
+		/* after Z_FINISH, only Z_STREAM_END is "we unpacked it all" */
+		if (rc == Z_STREAM_END) {
+			rc = 0;
+			break;
+		} else if (rc != Z_OK) {
+			error("uncompression error");
+			rc = -1;
+		}
+	}
+
+	zlib_inflateEnd(strm);
+	if (pos)
+		/* add + 8 to skip over trailer */
+		*pos = strm->next_in - zbuf+8;
+
+gunzip_5:
+	free(strm->workspace);
+gunzip_nomem4:
+	free(strm);
+gunzip_nomem3:
+	if (!buf)
+		free(zbuf);
+gunzip_nomem2:
+	if (flush)
+		free(out_buf);
+gunzip_nomem1:
+	return rc; /* returns Z_OK (0) if successful */
+}
+
+#ifndef PREBOOT
+STATIC int INIT gunzip(unsigned char *buf, long len,
+		       long (*fill)(void*, unsigned long),
+		       long (*flush)(void*, unsigned long),
+		       unsigned char *out_buf,
+		       long *pos,
+		       void (*error)(char *x))
+{
+	return __gunzip(buf, len, fill, flush, out_buf, 0, pos, error);
+}
+#else
+STATIC int INIT __decompress(unsigned char *buf, long len,
+			   long (*fill)(void*, unsigned long),
+			   long (*flush)(void*, unsigned long),
+			   unsigned char *out_buf, long out_len,
+			   long *pos,
+			   void (*error)(char *x))
+{
+	return __gunzip(buf, len, fill, flush, out_buf, out_len, pos, error);
+}
+#endif