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, 96 insertions, 0 deletions

diff --git a/drivers/md/dm-vdo/status-codes.c b/drivers/md/dm-vdo/status-codes.c
new file mode 100644
index 000000000..9df5e4d7f
--- /dev/null
+++ b/drivers/md/dm-vdo/status-codes.c
@@ -0,0 +1,96 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright 2023 Red Hat
+ */
+
+#include "status-codes.h"
+
+#include "errors.h"
+#include "logger.h"
+#include "permassert.h"
+#include "thread-utils.h"
+
+const struct error_info vdo_status_list[] = {
+	{ "VDO_NOT_IMPLEMENTED", "Not implemented" },
+	{ "VDO_OUT_OF_RANGE", "Out of range" },
+	{ "VDO_REF_COUNT_INVALID", "Reference count would become invalid" },
+	{ "VDO_NO_SPACE", "Out of space" },
+	{ "VDO_BAD_CONFIGURATION", "Bad configuration option" },
+	{ "VDO_COMPONENT_BUSY", "Prior operation still in progress" },
+	{ "VDO_BAD_PAGE", "Corrupt or incorrect page" },
+	{ "VDO_UNSUPPORTED_VERSION", "Unsupported component version" },
+	{ "VDO_INCORRECT_COMPONENT", "Component id mismatch in decoder" },
+	{ "VDO_PARAMETER_MISMATCH", "Parameters have conflicting values" },
+	{ "VDO_UNKNOWN_PARTITION", "No partition exists with a given id" },
+	{ "VDO_PARTITION_EXISTS", "A partition already exists with a given id" },
+	{ "VDO_INCREMENT_TOO_SMALL", "Physical block growth of too few blocks" },
+	{ "VDO_CHECKSUM_MISMATCH", "Incorrect checksum" },
+	{ "VDO_LOCK_ERROR", "A lock is held incorrectly" },
+	{ "VDO_READ_ONLY", "The device is in read-only mode" },
+	{ "VDO_SHUTTING_DOWN", "The device is shutting down" },
+	{ "VDO_CORRUPT_JOURNAL", "Recovery journal corrupted" },
+	{ "VDO_TOO_MANY_SLABS", "Exceeds maximum number of slabs supported" },
+	{ "VDO_INVALID_FRAGMENT", "Compressed block fragment is invalid" },
+	{ "VDO_RETRY_AFTER_REBUILD", "Retry operation after rebuilding finishes" },
+	{ "VDO_BAD_MAPPING", "Invalid page mapping" },
+	{ "VDO_BIO_CREATION_FAILED", "Bio creation failed" },
+	{ "VDO_BAD_MAGIC", "Bad magic number" },
+	{ "VDO_BAD_NONCE", "Bad nonce" },
+	{ "VDO_JOURNAL_OVERFLOW", "Journal sequence number overflow" },
+	{ "VDO_INVALID_ADMIN_STATE", "Invalid operation for current state" },
+};
+
+/**
+ * vdo_register_status_codes() - Register the VDO status codes.
+ * Return: A success or error code.
+ */
+int vdo_register_status_codes(void)
+{
+	int result;
+
+	BUILD_BUG_ON((VDO_STATUS_CODE_LAST - VDO_STATUS_CODE_BASE) !=
+		     ARRAY_SIZE(vdo_status_list));
+
+	result = uds_register_error_block("VDO Status", VDO_STATUS_CODE_BASE,
+					  VDO_STATUS_CODE_BLOCK_END, vdo_status_list,
+					  sizeof(vdo_status_list));
+	return (result == UDS_SUCCESS) ? VDO_SUCCESS : result;
+}
+
+/**
+ * vdo_status_to_errno() - Given an error code, return a value we can return to the OS.
+ * @error: The error code to convert.
+ *
+ * The input error code may be a system-generated value (such as -EIO), an errno macro used in our
+ * code (such as EIO), or a UDS or VDO status code; the result must be something the rest of the OS
+ * can consume (negative errno values such as -EIO, in the case of the kernel).
+ *
+ * Return: A system error code value.
+ */
+int vdo_status_to_errno(int error)
+{
+	char error_name[VDO_MAX_ERROR_NAME_SIZE];
+	char error_message[VDO_MAX_ERROR_MESSAGE_SIZE];
+
+	/* 0 is success, negative a system error code */
+	if (likely(error <= 0))
+		return error;
+	if (error < 1024)
+		return -error;
+
+	/* VDO or UDS error */
+	switch (error) {
+	case VDO_BAD_CONFIGURATION:
+		return -EINVAL;
+	case VDO_NO_SPACE:
+		return -ENOSPC;
+	case VDO_READ_ONLY:
+		return -EIO;
+	default:
+		vdo_log_info("%s: mapping internal status code %d (%s: %s) to EIO",
+			     __func__, error,
+			     uds_string_error_name(error, error_name, sizeof(error_name)),
+			     uds_string_error(error, error_message, sizeof(error_message)));
+		return -EIO;
+	}
+}