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, 139 insertions, 0 deletions

diff --git a/arch/powerpc/boot/ps3.c b/arch/powerpc/boot/ps3.c
new file mode 100644
index 000000000..89ff46b8b
--- /dev/null
+++ b/arch/powerpc/boot/ps3.c
@@ -0,0 +1,139 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *  PS3 bootwrapper support.
+ *
+ *  Copyright (C) 2007 Sony Computer Entertainment Inc.
+ *  Copyright 2007 Sony Corp.
+ */
+
+#include <stdarg.h>
+#include <stddef.h>
+#include "types.h"
+#include "elf.h"
+#include "string.h"
+#include "stdio.h"
+#include "page.h"
+#include "ops.h"
+
+extern int lv1_panic(u64 in_1);
+extern int lv1_get_logical_partition_id(u64 *out_1);
+extern int lv1_get_logical_ppe_id(u64 *out_1);
+extern int lv1_get_repository_node_value(u64 in_1, u64 in_2, u64 in_3,
+	u64 in_4, u64 in_5, u64 *out_1, u64 *out_2);
+
+BSS_STACK(4096);
+
+/* A buffer that may be edited by tools operating on a zImage binary so as to
+ * edit the command line passed to vmlinux (by setting /chosen/bootargs).
+ * The buffer is put in its own section so that tools may locate it easier.
+ */
+
+static char cmdline[BOOT_COMMAND_LINE_SIZE]
+	__attribute__((__section__("__builtin_cmdline")));
+
+static void prep_cmdline(void *chosen)
+{
+	if (cmdline[0] == '\0')
+		getprop(chosen, "bootargs", cmdline, BOOT_COMMAND_LINE_SIZE-1);
+	else
+		setprop_str(chosen, "bootargs", cmdline);
+
+	printf("cmdline: '%s'\n", cmdline);
+}
+
+static void ps3_console_write(const char *buf, int len)
+{
+}
+
+static void ps3_exit(void)
+{
+	printf("ps3_exit\n");
+
+	/* lv1_panic will shutdown the lpar. */
+
+	lv1_panic(0); /* zero = do not reboot */
+	while (1);
+}
+
+static int ps3_repository_read_rm_size(u64 *rm_size)
+{
+	int result;
+	u64 lpar_id;
+	u64 ppe_id;
+	u64 v2;
+
+	result = lv1_get_logical_partition_id(&lpar_id);
+
+	if (result)
+		return -1;
+
+	result = lv1_get_logical_ppe_id(&ppe_id);
+
+	if (result)
+		return -1;
+
+	/*
+	 * n1: 0000000062690000 : ....bi..
+	 * n2: 7075000000000000 : pu......
+	 * n3: 0000000000000001 : ........
+	 * n4: 726d5f73697a6500 : rm_size.
+	*/
+
+	result = lv1_get_repository_node_value(lpar_id, 0x0000000062690000ULL,
+		0x7075000000000000ULL, ppe_id, 0x726d5f73697a6500ULL, rm_size,
+		&v2);
+
+	printf("%s:%d: ppe_id  %lu \n", __func__, __LINE__,
+		(unsigned long)ppe_id);
+	printf("%s:%d: lpar_id %lu \n", __func__, __LINE__,
+		(unsigned long)lpar_id);
+	printf("%s:%d: rm_size %llxh \n", __func__, __LINE__, *rm_size);
+
+	return result ? -1 : 0;
+}
+
+void ps3_copy_vectors(void)
+{
+	extern char __system_reset_kernel[];
+
+	memcpy((void *)0x100, __system_reset_kernel, 512);
+	flush_cache((void *)0x100, 512);
+}
+
+void platform_init(void)
+{
+	const u32 heapsize = 0x1000000 - (u32)_end; /* 16MiB */
+	void *chosen;
+	unsigned long ft_addr;
+	u64 rm_size;
+
+	console_ops.write = ps3_console_write;
+	platform_ops.exit = ps3_exit;
+
+	printf("\n-- PS3 bootwrapper --\n");
+
+	simple_alloc_init(_end, heapsize, 32, 64);
+	fdt_init(_dtb_start);
+
+	chosen = finddevice("/chosen");
+
+	ps3_repository_read_rm_size(&rm_size);
+	dt_fixup_memory(0, rm_size);
+
+	if (&_initrd_end > &_initrd_start) {
+		setprop_val(chosen, "linux,initrd-start", (u32)(_initrd_start));
+		setprop_val(chosen, "linux,initrd-end", (u32)(_initrd_end));
+	}
+
+	prep_cmdline(chosen);
+
+	ft_addr = dt_ops.finalize();
+
+	ps3_copy_vectors();
+
+	printf(" flat tree at 0x%lx\n\r", ft_addr);
+
+	((kernel_entry_t)0)(ft_addr, 0, NULL);
+
+	ps3_exit();
+}