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, 208 insertions, 0 deletions

diff --git a/drivers/md/md-bitmap.h b/drivers/md/md-bitmap.h
new file mode 100644
index 000000000..b69c78174
--- /dev/null
+++ b/drivers/md/md-bitmap.h
@@ -0,0 +1,208 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * bitmap.h: Copyright (C) Peter T. Breuer (ptb@ot.uc3m.es) 2003
+ *
+ * additions: Copyright (C) 2003-2004, Paul Clements, SteelEye Technology, Inc.
+ */
+#ifndef BITMAP_H
+#define BITMAP_H 1
+
+#define BITMAP_MAGIC 0x6d746962
+
+/*
+ * version 3 is host-endian order, this is deprecated and not used for new
+ * array
+ */
+#define BITMAP_MAJOR_LO		3
+#define BITMAP_MAJOR_HOSTENDIAN	3
+/* version 4 is little-endian order, the default value */
+#define BITMAP_MAJOR_HI		4
+/* version 5 is only used for cluster */
+#define BITMAP_MAJOR_CLUSTERED	5
+/* version 6 is only used for lockless bitmap */
+#define BITMAP_MAJOR_LOCKLESS	6
+
+/* use these for bitmap->flags and bitmap->sb->state bit-fields */
+enum bitmap_state {
+	BITMAP_STALE	   = 1, /* the bitmap file is out of date or had -EIO */
+	BITMAP_WRITE_ERROR = 2, /* A write error has occurred */
+	BITMAP_FIRST_USE   = 3, /* llbitmap is just created */
+	BITMAP_CLEAN       = 4, /* llbitmap is created with assume_clean */
+	BITMAP_DAEMON_BUSY = 5, /* llbitmap daemon is not finished after daemon_sleep */
+	BITMAP_SHUTDOWN    = 6, /* llbitmap is being destroyed */
+	BITMAP_HOSTENDIAN  =15,
+};
+
+/* the superblock at the front of the bitmap file -- little endian */
+typedef struct bitmap_super_s {
+	__le32 magic;        /*  0  BITMAP_MAGIC */
+	__le32 version;      /*  4  the bitmap major for now, could change... */
+	__u8  uuid[16];      /*  8  128 bit uuid - must match md device uuid */
+	__le64 events;       /* 24  event counter for the bitmap (1)*/
+	__le64 events_cleared;/*32  event counter when last bit cleared (2) */
+	__le64 sync_size;    /* 40  the size of the md device's sync range(3) */
+	__le32 state;        /* 48  bitmap state information */
+	__le32 chunksize;    /* 52  the bitmap chunk size in bytes */
+	__le32 daemon_sleep; /* 56  seconds between disk flushes */
+	__le32 write_behind; /* 60  number of outstanding write-behind writes */
+	__le32 sectors_reserved; /* 64 number of 512-byte sectors that are
+				  * reserved for the bitmap. */
+	__le32 nodes;        /* 68 the maximum number of nodes in cluster. */
+	__u8 cluster_name[64]; /* 72 cluster name to which this md belongs */
+	__u8  pad[256 - 136]; /* set to zero */
+} bitmap_super_t;
+
+/* notes:
+ * (1) This event counter is updated before the eventcounter in the md superblock
+ *    When a bitmap is loaded, it is only accepted if this event counter is equal
+ *    to, or one greater than, the event counter in the superblock.
+ * (2) This event counter is updated when the other one is *if*and*only*if* the
+ *    array is not degraded.  As bits are not cleared when the array is degraded,
+ *    this represents the last time that any bits were cleared.
+ *    If a device is being added that has an event count with this value or
+ *    higher, it is accepted as conforming to the bitmap.
+ * (3)This is the number of sectors represented by the bitmap, and is the range that
+ *    resync happens across.  For raid1 and raid5/6 it is the size of individual
+ *    devices.  For raid10 it is the size of the array.
+ */
+
+struct md_bitmap_stats {
+	u64		events_cleared;
+	int		behind_writes;
+	bool		behind_wait;
+
+	unsigned long	missing_pages;
+	unsigned long	file_pages;
+	unsigned long	sync_size;
+	unsigned long	pages;
+	struct file	*file;
+};
+
+typedef void (md_bitmap_fn)(struct mddev *mddev, sector_t offset,
+			    unsigned long sectors);
+
+struct bitmap_operations {
+	struct md_submodule_head head;
+
+	bool (*enabled)(void *data, bool flush);
+	int (*create)(struct mddev *mddev);
+	int (*resize)(struct mddev *mddev, sector_t blocks, int chunksize);
+
+	int (*load)(struct mddev *mddev);
+	void (*destroy)(struct mddev *mddev);
+	void (*flush)(struct mddev *mddev);
+	void (*write_all)(struct mddev *mddev);
+	void (*dirty_bits)(struct mddev *mddev, unsigned long s,
+			   unsigned long e);
+	/* Prepare a range for this bitmap implementation. */
+	void (*prepare_range)(struct mddev *mddev,
+			      sector_t *offset,
+			      unsigned long *sectors,
+			      bool discard);
+	void (*reshape_finish)(struct mddev *mddev);
+	int (*reshape_can_start)(struct mddev *mddev);
+	void (*reshape_mark)(struct mddev *mddev, sector_t old_pos,
+			     sector_t new_pos);
+	void (*unplug)(struct mddev *mddev, bool sync);
+	void (*daemon_work)(struct mddev *mddev);
+
+	void (*start_behind_write)(struct mddev *mddev);
+	void (*end_behind_write)(struct mddev *mddev);
+	void (*wait_behind_writes)(struct mddev *mddev);
+
+	md_bitmap_fn *start_write;
+	md_bitmap_fn *end_write;
+	md_bitmap_fn *start_discard;
+	md_bitmap_fn *end_discard;
+
+	sector_t (*skip_sync_blocks)(struct mddev *mddev, sector_t offset);
+	bool (*blocks_synced)(struct mddev *mddev, sector_t offset);
+	bool (*start_sync)(struct mddev *mddev, sector_t offset,
+			   sector_t *blocks, bool degraded);
+	void (*end_sync)(struct mddev *mddev, sector_t offset, sector_t *blocks);
+	void (*cond_end_sync)(struct mddev *mddev, sector_t sector, bool force);
+	void (*close_sync)(struct mddev *mddev);
+
+	void (*update_sb)(void *data);
+	int (*get_stats)(void *data, struct md_bitmap_stats *stats);
+
+	void (*sync_with_cluster)(struct mddev *mddev,
+				  sector_t old_lo, sector_t old_hi,
+				  sector_t new_lo, sector_t new_hi);
+	void *(*get_from_slot)(struct mddev *mddev, int slot);
+	int (*copy_from_slot)(struct mddev *mddev, int slot, sector_t *lo,
+			      sector_t *hi, bool clear_bits);
+	void (*set_pages)(void *data, unsigned long pages);
+	void (*free)(void *data);
+
+	const struct attribute_group **groups;
+};
+
+/* the bitmap API */
+static inline bool md_bitmap_registered(struct mddev *mddev)
+{
+	return mddev->bitmap_ops != NULL;
+}
+
+static inline bool md_bitmap_enabled(struct mddev *mddev, bool flush)
+{
+	/* bitmap_ops must be registered before creating bitmap. */
+	if (!md_bitmap_registered(mddev))
+		return false;
+
+	if (!mddev->bitmap)
+		return false;
+
+	return mddev->bitmap_ops->enabled(mddev->bitmap, flush);
+}
+
+static inline bool md_bitmap_start_sync(struct mddev *mddev, sector_t offset,
+					sector_t *blocks, bool degraded)
+{
+	/* always resync if no bitmap */
+	if (!md_bitmap_enabled(mddev, false)) {
+		*blocks = 1024;
+		return true;
+	}
+
+	return mddev->bitmap_ops->start_sync(mddev, offset, blocks, degraded);
+}
+
+static inline void md_bitmap_end_sync(struct mddev *mddev, sector_t offset,
+				      sector_t *blocks)
+{
+	if (!md_bitmap_enabled(mddev, false)) {
+		*blocks = 1024;
+		return;
+	}
+
+	mddev->bitmap_ops->end_sync(mddev, offset, blocks);
+}
+
+#ifdef CONFIG_MD_BITMAP
+int md_bitmap_init(void);
+void md_bitmap_exit(void);
+#else
+static inline int md_bitmap_init(void)
+{
+	return 0;
+}
+static inline void md_bitmap_exit(void)
+{
+}
+#endif
+
+#ifdef CONFIG_MD_LLBITMAP
+int md_llbitmap_init(void);
+void md_llbitmap_exit(void);
+#else
+static inline int md_llbitmap_init(void)
+{
+	return 0;
+}
+static inline void md_llbitmap_exit(void)
+{
+}
+#endif
+
+#endif