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, 86 insertions, 0 deletions

diff --git a/drivers/md/dm-vdo/status-codes.h b/drivers/md/dm-vdo/status-codes.h
new file mode 100644
index 000000000..426dc8e2c
--- /dev/null
+++ b/drivers/md/dm-vdo/status-codes.h
@@ -0,0 +1,86 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright 2023 Red Hat
+ */
+
+#ifndef VDO_STATUS_CODES_H
+#define VDO_STATUS_CODES_H
+
+#include "errors.h"
+
+enum {
+	UDS_ERRORS_BLOCK_SIZE = UDS_ERROR_CODE_BLOCK_END - UDS_ERROR_CODE_BASE,
+	VDO_ERRORS_BLOCK_START = UDS_ERROR_CODE_BLOCK_END,
+	VDO_ERRORS_BLOCK_END = VDO_ERRORS_BLOCK_START + UDS_ERRORS_BLOCK_SIZE,
+};
+
+/* VDO-specific status codes. */
+enum vdo_status_codes {
+	/* base of all VDO errors */
+	VDO_STATUS_CODE_BASE = VDO_ERRORS_BLOCK_START,
+	/* we haven't written this yet */
+	VDO_NOT_IMPLEMENTED = VDO_STATUS_CODE_BASE,
+	/* input out of range */
+	VDO_OUT_OF_RANGE,
+	/* an invalid reference count would result */
+	VDO_REF_COUNT_INVALID,
+	/* a free block could not be allocated */
+	VDO_NO_SPACE,
+	/* improper or missing configuration option */
+	VDO_BAD_CONFIGURATION,
+	/* prior operation still in progress */
+	VDO_COMPONENT_BUSY,
+	/* page contents incorrect or corrupt data */
+	VDO_BAD_PAGE,
+	/* unsupported version of some component */
+	VDO_UNSUPPORTED_VERSION,
+	/* component id mismatch in decoder */
+	VDO_INCORRECT_COMPONENT,
+	/* parameters have conflicting values */
+	VDO_PARAMETER_MISMATCH,
+	/* no partition exists with a given id */
+	VDO_UNKNOWN_PARTITION,
+	/* a partition already exists with a given id */
+	VDO_PARTITION_EXISTS,
+	/* physical block growth of too few blocks */
+	VDO_INCREMENT_TOO_SMALL,
+	/* incorrect checksum */
+	VDO_CHECKSUM_MISMATCH,
+	/* a lock is held incorrectly */
+	VDO_LOCK_ERROR,
+	/* the VDO is in read-only mode */
+	VDO_READ_ONLY,
+	/* the VDO is shutting down */
+	VDO_SHUTTING_DOWN,
+	/* the recovery journal has corrupt entries or corrupt metadata */
+	VDO_CORRUPT_JOURNAL,
+	/* exceeds maximum number of slabs supported */
+	VDO_TOO_MANY_SLABS,
+	/* a compressed block fragment is invalid */
+	VDO_INVALID_FRAGMENT,
+	/* action is unsupported while rebuilding */
+	VDO_RETRY_AFTER_REBUILD,
+	/* a block map entry is invalid */
+	VDO_BAD_MAPPING,
+	/* bio_add_page failed */
+	VDO_BIO_CREATION_FAILED,
+	/* bad magic number */
+	VDO_BAD_MAGIC,
+	/* bad nonce */
+	VDO_BAD_NONCE,
+	/* sequence number overflow */
+	VDO_JOURNAL_OVERFLOW,
+	/* the VDO is not in a state to perform an admin operation */
+	VDO_INVALID_ADMIN_STATE,
+	/* one more than last error code */
+	VDO_STATUS_CODE_LAST,
+	VDO_STATUS_CODE_BLOCK_END = VDO_ERRORS_BLOCK_END
+};
+
+extern const struct error_info vdo_status_list[];
+
+int vdo_register_status_codes(void);
+
+int vdo_status_to_errno(int error);
+
+#endif /* VDO_STATUS_CODES_H */