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, 172 insertions, 0 deletions

diff --git a/arch/alpha/boot/misc.c b/arch/alpha/boot/misc.c
new file mode 100644
index 000000000..1ab91852d
--- /dev/null
+++ b/arch/alpha/boot/misc.c
@@ -0,0 +1,172 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * misc.c
+ * 
+ * This is a collection of several routines from gzip-1.0.3 
+ * adapted for Linux.
+ *
+ * malloc by Hannu Savolainen 1993 and Matthias Urlichs 1994
+ *
+ * Modified for ARM Linux by Russell King
+ *
+ * Nicolas Pitre <nico@visuaide.com>  1999/04/14 :
+ *  For this code to run directly from Flash, all constant variables must
+ *  be marked with 'const' and all other variables initialized at run-time 
+ *  only.  This way all non constant variables will end up in the bss segment,
+ *  which should point to addresses in RAM and cleared to 0 on start.
+ *  This allows for a much quicker boot time.
+ *
+ * Modified for Alpha, from the ARM version, by Jay Estabrook 2003.
+ */
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+
+#include <linux/uaccess.h>
+
+#define memzero(s,n)	memset ((s),0,(n))
+#define puts		srm_printk
+extern long srm_printk(const char *, ...)
+     __attribute__ ((format (printf, 1, 2)));
+
+/*
+ * gzip declarations
+ */
+#define OF(args)  args
+#define STATIC static
+
+typedef unsigned char  uch;
+typedef unsigned short ush;
+typedef unsigned long  ulg;
+
+#define WSIZE 0x8000		/* Window size must be at least 32k, */
+				/* and a power of two */
+
+static uch *inbuf;		/* input buffer */
+static uch *window;		/* Sliding window buffer */
+
+static unsigned insize;		/* valid bytes in inbuf */
+static unsigned inptr;		/* index of next byte to be processed in inbuf */
+static unsigned outcnt;		/* bytes in output buffer */
+
+/* gzip flag byte */
+#define ASCII_FLAG   0x01 /* bit 0 set: file probably ascii text */
+#define CONTINUATION 0x02 /* bit 1 set: continuation of multi-part gzip file */
+#define EXTRA_FIELD  0x04 /* bit 2 set: extra field present */
+#define ORIG_NAME    0x08 /* bit 3 set: original file name present */
+#define COMMENT      0x10 /* bit 4 set: file comment present */
+#define ENCRYPTED    0x20 /* bit 5 set: file is encrypted */
+#define RESERVED     0xC0 /* bit 6,7:   reserved */
+
+#define get_byte()  (inptr < insize ? inbuf[inptr++] : fill_inbuf())
+
+/* Diagnostic functions */
+#ifdef DEBUG
+#  define Assert(cond,msg) {if(!(cond)) error(msg);}
+#  define Trace(x) fprintf x
+#  define Tracev(x) {if (verbose) fprintf x ;}
+#  define Tracevv(x) {if (verbose>1) fprintf x ;}
+#  define Tracec(c,x) {if (verbose && (c)) fprintf x ;}
+#  define Tracecv(c,x) {if (verbose>1 && (c)) fprintf x ;}
+#else
+#  define Assert(cond,msg)
+#  define Trace(x)
+#  define Tracev(x)
+#  define Tracevv(x)
+#  define Tracec(c,x)
+#  define Tracecv(c,x)
+#endif
+
+static int  fill_inbuf(void);
+static void flush_window(void);
+static void error(char *m);
+
+static char *input_data;
+static int  input_data_size;
+
+static uch *output_data;
+static ulg output_ptr;
+static ulg bytes_out;
+
+static void error(char *m);
+
+extern int end;
+static ulg free_mem_ptr;
+static ulg free_mem_end_ptr;
+
+#define HEAP_SIZE 0x3000
+
+#include "../../../lib/inflate.c"
+
+/* ===========================================================================
+ * Fill the input buffer. This is called only when the buffer is empty
+ * and at least one byte is really needed.
+ */
+int fill_inbuf(void)
+{
+	if (insize != 0)
+		error("ran out of input data");
+
+	inbuf = input_data;
+	insize = input_data_size;
+
+	inptr = 1;
+	return inbuf[0];
+}
+
+/* ===========================================================================
+ * Write the output window window[0..outcnt-1] and update crc and bytes_out.
+ * (Used for the decompressed data only.)
+ */
+void flush_window(void)
+{
+	ulg c = crc;
+	unsigned n;
+	uch *in, *out, ch;
+
+	in = window;
+	out = &output_data[output_ptr];
+	for (n = 0; n < outcnt; n++) {
+		ch = *out++ = *in++;
+		c = crc_32_tab[((int)c ^ ch) & 0xff] ^ (c >> 8);
+	}
+	crc = c;
+	bytes_out += (ulg)outcnt;
+	output_ptr += (ulg)outcnt;
+	outcnt = 0;
+/*	puts("."); */
+}
+
+static void error(char *x)
+{
+	puts("\n\n");
+	puts(x);
+	puts("\n\n -- System halted");
+
+	while(1);	/* Halt */
+}
+
+unsigned int
+decompress_kernel(void *output_start,
+		  void *input_start,
+		  size_t ksize,
+		  size_t kzsize)
+{
+	output_data		= (uch *)output_start;
+	input_data		= (uch *)input_start;
+	input_data_size		= kzsize; /* use compressed size */
+
+	/* FIXME FIXME FIXME */
+	free_mem_ptr		= (ulg)output_start + ksize;
+	free_mem_end_ptr	= (ulg)output_start + ksize + 0x200000;
+	/* FIXME FIXME FIXME */
+
+	/* put in temp area to reduce initial footprint */
+	window = malloc(WSIZE);
+
+	makecrc();
+/*	puts("Uncompressing Linux..."); */
+	gunzip();
+/*	puts(" done, booting the kernel.\n"); */
+	return output_ptr;
+}