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, 133 insertions, 0 deletions

diff --git a/fs/btrfs/bio.h b/fs/btrfs/bio.h
new file mode 100644
index 000000000..303ed6c71
--- /dev/null
+++ b/fs/btrfs/bio.h
@@ -0,0 +1,133 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2007 Oracle.  All rights reserved.
+ * Copyright (C) 2022 Christoph Hellwig.
+ */
+
+#ifndef BTRFS_BIO_H
+#define BTRFS_BIO_H
+
+#include <linux/types.h>
+#include <linux/bio.h>
+#include <linux/workqueue.h>
+#include "tree-checker.h"
+
+struct btrfs_bio;
+struct btrfs_fs_info;
+struct btrfs_inode;
+
+#define BTRFS_BIO_INLINE_CSUM_SIZE	64
+
+typedef void (*btrfs_bio_end_io_t)(struct btrfs_bio *bbio);
+
+/*
+ * Highlevel btrfs I/O structure.  It is allocated by btrfs_bio_alloc and
+ * passed to btrfs_submit_bbio() for mapping to the physical devices.
+ */
+struct btrfs_bio {
+	/*
+	 * Inode and offset into it that this I/O operates on.
+	 *
+	 * If the inode is a data one, csum verification and read-repair
+	 * will be done automatically.
+	 * If the inode is a metadata one, everything is handled by the caller.
+	 */
+	struct btrfs_inode *inode;
+	u64 file_offset;
+
+	union {
+		/*
+		 * For data reads: checksumming and original I/O information.
+		 * (for internal use in the btrfs_submit_bbio() machinery only)
+		 */
+		struct {
+			u8 *csum;
+			u8 csum_inline[BTRFS_BIO_INLINE_CSUM_SIZE];
+			struct bvec_iter saved_iter;
+		};
+
+		/*
+		 * For data writes:
+		 * - ordered extent covering the bio
+		 * - pointer to the checksums for this bio
+		 * - original physical address from the allocator
+		 *   (for zone append only)
+		 * - original logical address, used for checksumming fscrypt bios
+		 */
+		struct {
+			struct btrfs_ordered_extent *ordered;
+			struct btrfs_ordered_sum *sums;
+			struct work_struct csum_work;
+			struct completion csum_done;
+			struct bvec_iter csum_saved_iter;
+			u64 orig_physical;
+			u64 orig_logical;
+		};
+
+		/* For metadata reads: parentness verification. */
+		struct btrfs_tree_parent_check parent_check;
+	};
+
+	/* For internal use in read end I/O handling */
+	struct work_struct end_io_work;
+
+	/* End I/O information supplied to btrfs_bio_alloc */
+	btrfs_bio_end_io_t end_io;
+	void *private;
+
+	atomic_t pending_ios;
+	u16 mirror_num;
+
+	/* Save the first error status of split bio. */
+	blk_status_t status;
+
+	/* Use the commit root to look up csums (data read bio only). */
+	bool csum_search_commit_root:1;
+
+	/*
+	 * Since scrub will reuse btree inode, we need this flag to distinguish
+	 * scrub bios.
+	 */
+	bool is_scrub:1;
+
+	/* Whether the bio is coming from copy_remapped_data_io(). */
+	bool is_remap:1;
+
+	/* Whether the csum generation for data write is async. */
+	bool async_csum:1;
+
+	/* Whether the bio is written using zone append. */
+	bool can_use_append:1;
+
+	/*
+	 * This member must come last, bio_alloc_bioset will allocate enough
+	 * bytes for entire btrfs_bio but relies on bio being last.
+	 */
+	struct bio bio;
+};
+
+static inline struct btrfs_bio *btrfs_bio(struct bio *bio)
+{
+	return container_of(bio, struct btrfs_bio, bio);
+}
+
+int __init btrfs_bioset_init(void);
+void __cold btrfs_bioset_exit(void);
+
+void btrfs_bio_init(struct btrfs_bio *bbio, struct btrfs_inode *inode, u64 file_offset,
+		    btrfs_bio_end_io_t end_io, void *private);
+struct btrfs_bio *btrfs_bio_alloc(unsigned int nr_vecs, blk_opf_t opf,
+				  struct btrfs_inode *inode, u64 file_offset,
+				  btrfs_bio_end_io_t end_io, void *private);
+void btrfs_bio_end_io(struct btrfs_bio *bbio, blk_status_t status);
+
+/* Submit using blkcg_punt_bio_submit. */
+#define REQ_BTRFS_CGROUP_PUNT			REQ_FS_PRIVATE
+
+void btrfs_submit_bbio(struct btrfs_bio *bbio, int mirror_num);
+void btrfs_submit_repair_write(struct btrfs_bio *bbio, int mirror_num, bool dev_replace);
+int btrfs_repair_io_failure(struct btrfs_fs_info *fs_info, u64 ino, u64 fileoff,
+			    u32 length, u64 logical, const phys_addr_t paddrs[],
+			    unsigned int step, int mirror_num);
+
+#endif