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, 118 insertions, 0 deletions

diff --git a/drivers/md/dm-ima.h b/drivers/md/dm-ima.h
new file mode 100644
index 000000000..0ec013d15
--- /dev/null
+++ b/drivers/md/dm-ima.h
@@ -0,0 +1,118 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2021 Microsoft Corporation
+ *
+ * Author: Tushar Sugandhi <tusharsu@linux.microsoft.com>
+ *
+ * Header file for device mapper IMA measurements.
+ */
+
+#ifndef DM_IMA_H
+#define DM_IMA_H
+
+#define DM_IMA_MEASUREMENT_BUF_LEN	4096
+#define DM_IMA_DEVICE_BUF_LEN		1024
+#define DM_IMA_TARGET_METADATA_BUF_LEN	128
+#define DM_IMA_TARGET_DATA_BUF_LEN	2048
+#define DM_IMA_DEVICE_CAPACITY_BUF_LEN	128
+
+#define __dm_ima_stringify(s) #s
+#define __dm_ima_str(s) __dm_ima_stringify(s)
+
+#define DM_IMA_VERSION_STR "dm_version="	\
+	__dm_ima_str(DM_VERSION_MAJOR) "."	\
+	__dm_ima_str(DM_VERSION_MINOR) "."	\
+	__dm_ima_str(DM_VERSION_PATCHLEVEL) ";"
+
+enum dm_ima_table_op {
+	DM_IMA_TABLE_SAVE,
+	DM_IMA_TABLE_RESTORE,
+};
+
+#ifdef CONFIG_IMA
+
+struct dm_ima_device_table_metadata {
+	/*
+	 * Contains data specific to the device which is common across
+	 * all the targets in the table (e.g. name, uuid, major, minor, etc).
+	 * The values are stored in comma separated list of key1=val1,key2=val2;
+	 * pairs delimited by a semicolon at the end of the list.
+	 */
+	char *device_metadata;
+	unsigned int device_metadata_len;
+	unsigned int num_targets;
+	sector_t capacity;
+
+	/*
+	 * Contains the sha256 hashes of the IMA measurements of the target
+	 * attributes' key-value pairs from the active/inactive tables.
+	 */
+	char *hash;
+	unsigned int hash_len;
+};
+
+struct dm_ima_context {
+	struct dm_ima_device_table_metadata table;
+	unsigned int update_idx;
+	char dev_name[DM_NAME_LEN*2];
+	char dev_uuid[DM_UUID_LEN*2];
+};
+
+/*
+ * This structure contains device metadata, and table hash for
+ * active and inactive tables for ima measurements.
+ */
+struct dm_ima_measurements {
+	unsigned int update_idx;
+	unsigned int measure_idx;
+	struct wait_queue_head ima_wq;
+	spinlock_t ima_lock;
+	struct dm_ima_device_table_metadata active_table;
+	struct dm_ima_device_table_metadata inactive_table;
+};
+
+void dm_ima_init(struct mapped_device *md);
+void dm_ima_alloc_context(struct dm_ima_context **context, bool noio);
+void dm_ima_free_context(struct dm_ima_context *context);
+void dm_ima_context_table_op(struct mapped_device *md,
+			     struct dm_ima_context *context,
+			     enum dm_ima_table_op op);
+void dm_ima_measure_on_table_load(struct dm_table *table,
+				  struct dm_ima_context *context);
+void dm_ima_measure_on_device_resume(struct mapped_device *md, bool swap,
+				     struct dm_ima_context *context);
+void dm_ima_measure_on_device_remove(struct mapped_device *md, bool remove_all,
+				     struct dm_ima_context *context,
+				     unsigned int idx);
+void dm_ima_measure_on_table_clear(struct mapped_device *md,
+				   struct dm_ima_context *context);
+void dm_ima_measure_on_device_rename(struct mapped_device *md,
+				     struct dm_ima_context *context);
+
+#else
+
+struct dm_ima_context;
+
+static inline void dm_ima_init(struct mapped_device *md) {}
+static inline void dm_ima_alloc_context(struct dm_ima_context **context, bool noio) {}
+static inline void dm_ima_free_context(struct dm_ima_context *context) {}
+static inline void dm_ima_context_table_op(struct mapped_device *md,
+					   struct dm_ima_context *context,
+					   enum dm_ima_table_op op) {}
+static inline void dm_ima_measure_on_table_load(struct dm_table *table,
+						struct dm_ima_context *context) {}
+static inline void dm_ima_measure_on_device_resume(struct mapped_device *md,
+						   bool swap,
+						   struct dm_ima_context *context) {}
+static inline void dm_ima_measure_on_device_remove(struct mapped_device *md,
+						   bool remove_all,
+						   struct dm_ima_context *context,
+						   unsigned int idx) {}
+static inline void dm_ima_measure_on_table_clear(struct mapped_device *md,
+						 struct dm_ima_context *context) {}
+static inline void dm_ima_measure_on_device_rename(struct mapped_device *md,
+						   struct dm_ima_context *context) {}
+
+#endif /* CONFIG_IMA */
+
+#endif /* DM_IMA_H */