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, 183 insertions, 0 deletions

diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h
new file mode 100644
index 000000000..1022dc53e
--- /dev/null
+++ b/fs/btrfs/compression.h
@@ -0,0 +1,183 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2008 Oracle.  All rights reserved.
+ */
+
+#ifndef BTRFS_COMPRESSION_H
+#define BTRFS_COMPRESSION_H
+
+#include <linux/sizes.h>
+#include <linux/mm.h>
+#include <linux/list.h>
+#include <linux/workqueue.h>
+#include <linux/wait.h>
+#include <linux/pagemap.h>
+#include "bio.h"
+#include "fs.h"
+#include "btrfs_inode.h"
+
+struct address_space;
+struct inode;
+struct btrfs_inode;
+struct btrfs_ordered_extent;
+
+/*
+ * We want to make sure that amount of RAM required to uncompress an extent is
+ * reasonable, so we limit the total size in ram of a compressed extent to
+ * 128k.  This is a crucial number because it also controls how easily we can
+ * spread reads across cpus for decompression.
+ *
+ * We also want to make sure the amount of IO required to do a random read is
+ * reasonably small, so we limit the size of a compressed extent to 128k.
+ */
+
+/* Maximum length of compressed data stored on disk */
+#define BTRFS_MAX_COMPRESSED		(SZ_128K)
+#define BTRFS_MAX_COMPRESSED_PAGES	(BTRFS_MAX_COMPRESSED / PAGE_SIZE)
+static_assert((BTRFS_MAX_COMPRESSED % PAGE_SIZE) == 0);
+
+/* The max size for a single worker to compress. */
+#define BTRFS_COMPRESSION_CHUNK_SIZE	(SZ_512K)
+
+/* Maximum size of data before compression */
+#define BTRFS_MAX_UNCOMPRESSED		(SZ_128K)
+
+#define	BTRFS_ZLIB_DEFAULT_LEVEL		3
+
+struct compressed_bio {
+	/* starting offset in the inode for our pages */
+	u64 start;
+
+	/* Number of bytes in the inode we're working on */
+	unsigned int len;
+
+	/* The compression algorithm for this bio */
+	u8 compress_type;
+
+	/* Whether this is a write for writeback. */
+	bool writeback;
+
+	/* For reads, this is the bio we are copying the data into. */
+	struct btrfs_bio *orig_bbio;
+
+	/* Must be last. */
+	struct btrfs_bio bbio;
+};
+
+static inline struct btrfs_fs_info *cb_to_fs_info(const struct compressed_bio *cb)
+{
+	return cb->bbio.inode->root->fs_info;
+}
+
+/* @range_end must be exclusive. */
+static inline u32 btrfs_calc_input_length(struct folio *folio, u64 range_end, u64 cur)
+{
+	/* @cur must be inside the folio. */
+	ASSERT(folio_pos(folio) <= cur);
+	ASSERT(cur < folio_next_pos(folio));
+	return umin(range_end, folio_next_pos(folio)) - cur;
+}
+
+int btrfs_alloc_compress_wsm(struct btrfs_fs_info *fs_info);
+void btrfs_free_compress_wsm(struct btrfs_fs_info *fs_info);
+
+int __init btrfs_init_compress(void);
+void __cold btrfs_exit_compress(void);
+
+bool btrfs_compress_level_valid(unsigned int type, int level);
+int btrfs_decompress(int type, const u8 *data_in, struct folio *dest_folio,
+		     unsigned long dest_pgoff, size_t srclen, size_t destlen);
+int btrfs_decompress_buf2page(const char *buf, u32 buf_len,
+			      struct compressed_bio *cb, u32 decompressed);
+
+struct compressed_bio *btrfs_alloc_compressed_write(struct btrfs_inode *inode,
+						    u64 start, u64 len);
+void btrfs_submit_compressed_write(struct btrfs_ordered_extent *ordered,
+				   struct compressed_bio *cb);
+void btrfs_submit_compressed_read(struct btrfs_bio *bbio);
+
+int btrfs_compress_str2level(unsigned int type, const char *str, int *level_ret);
+
+struct folio *btrfs_alloc_compr_folio(struct btrfs_fs_info *fs_info, gfp_t gfp);
+void btrfs_free_compr_folio(struct folio *folio);
+
+struct workspace_manager {
+	struct list_head idle_ws;
+	spinlock_t ws_lock;
+	/* Number of free workspaces */
+	int free_ws;
+	/* Total number of allocated workspaces */
+	atomic_t total_ws;
+	/* Waiters for a free workspace */
+	wait_queue_head_t ws_wait;
+};
+
+struct list_head *btrfs_get_workspace(struct btrfs_fs_info *fs_info, int type, int level);
+void btrfs_put_workspace(struct btrfs_fs_info *fs_info, int type, struct list_head *ws);
+
+struct btrfs_compress_levels {
+	/* Maximum level supported by the compression algorithm */
+	int min_level;
+	int max_level;
+	int default_level;
+};
+
+/* The heuristic workspaces are managed via the 0th workspace manager */
+#define BTRFS_NR_WORKSPACE_MANAGERS	BTRFS_NR_COMPRESS_TYPES
+
+extern const struct btrfs_compress_levels btrfs_heuristic_compress;
+extern const struct btrfs_compress_levels btrfs_zlib_compress;
+extern const struct btrfs_compress_levels btrfs_lzo_compress;
+extern const struct btrfs_compress_levels btrfs_zstd_compress;
+
+const char* btrfs_compress_type2str(enum btrfs_compression_type type);
+bool btrfs_compress_is_valid_type(const char *str, size_t len);
+
+int btrfs_compress_heuristic(struct btrfs_inode *inode, u64 start, u64 end);
+
+int btrfs_compress_filemap_get_folio(struct address_space *mapping, u64 start,
+				     struct folio **in_folio_ret);
+struct compressed_bio *btrfs_compress_bio(struct btrfs_inode *inode,
+					  u64 start, u32 len, unsigned int type,
+					  int level, blk_opf_t write_flags);
+
+static inline void cleanup_compressed_bio(struct compressed_bio *cb)
+{
+	struct bio *bio = &cb->bbio.bio;
+	struct folio_iter fi;
+
+	bio_for_each_folio_all(fi, bio)
+		btrfs_free_compr_folio(fi.folio);
+	bio_put(bio);
+}
+
+int zlib_compress_bio(struct list_head *ws, struct compressed_bio *cb);
+int zlib_decompress_bio(struct list_head *ws, struct compressed_bio *cb);
+int zlib_decompress(struct list_head *ws, const u8 *data_in,
+		struct folio *dest_folio, unsigned long dest_pgoff, size_t srclen,
+		size_t destlen);
+struct list_head *zlib_alloc_workspace(struct btrfs_fs_info *fs_info, unsigned int level);
+void zlib_free_workspace(struct list_head *ws);
+struct list_head *zlib_get_workspace(struct btrfs_fs_info *fs_info, unsigned int level);
+
+int lzo_compress_bio(struct list_head *ws, struct compressed_bio *cb);
+int lzo_decompress_bio(struct list_head *ws, struct compressed_bio *cb);
+int lzo_decompress(struct list_head *ws, const u8 *data_in,
+		struct folio *dest_folio, unsigned long dest_pgoff, size_t srclen,
+		size_t destlen);
+struct list_head *lzo_alloc_workspace(struct btrfs_fs_info *fs_info);
+void lzo_free_workspace(struct list_head *ws);
+
+int zstd_compress_bio(struct list_head *ws, struct compressed_bio *cb);
+int zstd_decompress_bio(struct list_head *ws, struct compressed_bio *cb);
+int zstd_decompress(struct list_head *ws, const u8 *data_in,
+		struct folio *dest_folio, unsigned long dest_pgoff, size_t srclen,
+		size_t destlen);
+int zstd_alloc_workspace_manager(struct btrfs_fs_info *fs_info);
+void zstd_free_workspace_manager(struct btrfs_fs_info *fs_info);
+struct list_head *zstd_alloc_workspace(struct btrfs_fs_info *fs_info, int level);
+void zstd_free_workspace(struct list_head *ws);
+struct list_head *zstd_get_workspace(struct btrfs_fs_info *fs_info, int level);
+void zstd_put_workspace(struct btrfs_fs_info *fs_info, struct list_head *ws);
+
+#endif