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, 162 insertions, 0 deletions

diff --git a/fs/nfsd/attr4.h b/fs/nfsd/attr4.h
new file mode 100644
index 000000000..f0b51f805
--- /dev/null
+++ b/fs/nfsd/attr4.h
@@ -0,0 +1,162 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * NFSv4 file attributes supported by this implementation
+ */
+
+#ifndef _LINUX_NFSD_ATTR4_H
+#define _LINUX_NFSD_ATTR4_H
+
+#include <linux/types.h>
+#include <linux/nfs4.h>
+
+/*
+ * The following attributes are not implemented by NFSD:
+ *    ARCHIVE       (deprecated anyway)
+ *    HIDDEN        (unlikely to be supported any time soon)
+ *    MIMETYPE      (unlikely to be supported any time soon)
+ *    QUOTA_*       (unlikely to be supported any time soon)
+ *    SYSTEM        (unlikely to be supported any time soon)
+ *    TIME_BACKUP   (unlikely to be supported any time soon)
+ */
+#define NFSD4_SUPPORTED_ATTRS_WORD0                                                         \
+(FATTR4_WORD0_SUPPORTED_ATTRS   | FATTR4_WORD0_TYPE         | FATTR4_WORD0_FH_EXPIRE_TYPE   \
+ | FATTR4_WORD0_CHANGE          | FATTR4_WORD0_SIZE         | FATTR4_WORD0_LINK_SUPPORT     \
+ | FATTR4_WORD0_SYMLINK_SUPPORT | FATTR4_WORD0_NAMED_ATTR   | FATTR4_WORD0_FSID             \
+ | FATTR4_WORD0_UNIQUE_HANDLES  | FATTR4_WORD0_LEASE_TIME   | FATTR4_WORD0_RDATTR_ERROR     \
+ | FATTR4_WORD0_ACLSUPPORT      | FATTR4_WORD0_CANSETTIME   | FATTR4_WORD0_CASE_INSENSITIVE \
+ | FATTR4_WORD0_CASE_PRESERVING | FATTR4_WORD0_CHOWN_RESTRICTED                             \
+ | FATTR4_WORD0_FILEHANDLE      | FATTR4_WORD0_FILEID       | FATTR4_WORD0_FILES_AVAIL      \
+ | FATTR4_WORD0_FILES_FREE      | FATTR4_WORD0_FILES_TOTAL  | FATTR4_WORD0_FS_LOCATIONS | FATTR4_WORD0_HOMOGENEOUS      \
+ | FATTR4_WORD0_MAXFILESIZE     | FATTR4_WORD0_MAXLINK      | FATTR4_WORD0_MAXNAME          \
+ | FATTR4_WORD0_MAXREAD         | FATTR4_WORD0_MAXWRITE     | FATTR4_WORD0_ACL)
+
+#define NFSD4_SUPPORTED_ATTRS_WORD1                                                         \
+(FATTR4_WORD1_MODE              | FATTR4_WORD1_NO_TRUNC     | FATTR4_WORD1_NUMLINKS         \
+ | FATTR4_WORD1_OWNER	        | FATTR4_WORD1_OWNER_GROUP  | FATTR4_WORD1_RAWDEV           \
+ | FATTR4_WORD1_SPACE_AVAIL     | FATTR4_WORD1_SPACE_FREE   | FATTR4_WORD1_SPACE_TOTAL      \
+ | FATTR4_WORD1_SPACE_USED      | FATTR4_WORD1_TIME_ACCESS  | FATTR4_WORD1_TIME_ACCESS_SET  \
+ | FATTR4_WORD1_TIME_DELTA      | FATTR4_WORD1_TIME_METADATA   | FATTR4_WORD1_TIME_CREATE      \
+ | FATTR4_WORD1_TIME_MODIFY     | FATTR4_WORD1_TIME_MODIFY_SET | FATTR4_WORD1_MOUNTED_ON_FILEID)
+
+#define NFSD4_SUPPORTED_ATTRS_WORD2 0
+
+/* 4.1 */
+#ifdef CONFIG_NFSD_PNFS
+#define PNFSD_SUPPORTED_ATTRS_WORD1	FATTR4_WORD1_FS_LAYOUT_TYPES
+#define PNFSD_SUPPORTED_ATTRS_WORD2 \
+(FATTR4_WORD2_LAYOUT_BLKSIZE	| FATTR4_WORD2_LAYOUT_TYPES)
+#else
+#define PNFSD_SUPPORTED_ATTRS_WORD1	0
+#define PNFSD_SUPPORTED_ATTRS_WORD2	0
+#endif /* CONFIG_NFSD_PNFS */
+
+#define NFSD4_1_SUPPORTED_ATTRS_WORD0 \
+	NFSD4_SUPPORTED_ATTRS_WORD0
+
+#define NFSD4_1_SUPPORTED_ATTRS_WORD1 \
+	(NFSD4_SUPPORTED_ATTRS_WORD1	| PNFSD_SUPPORTED_ATTRS_WORD1)
+
+#define NFSD4_1_SUPPORTED_ATTRS_WORD2 \
+	(NFSD4_SUPPORTED_ATTRS_WORD2	| PNFSD_SUPPORTED_ATTRS_WORD2 | \
+	 FATTR4_WORD2_SUPPATTR_EXCLCREAT)
+
+/* 4.2 */
+#ifdef CONFIG_NFSD_V4_SECURITY_LABEL
+#define NFSD4_2_SECURITY_ATTRS		FATTR4_WORD2_SECURITY_LABEL
+#else
+#define NFSD4_2_SECURITY_ATTRS		0
+#endif
+
+#ifdef CONFIG_NFSD_V4_POSIX_ACLS
+#define NFSD4_2_POSIX_ACL_ATTRS \
+	(FATTR4_WORD2_ACL_TRUEFORM | \
+	FATTR4_WORD2_ACL_TRUEFORM_SCOPE | \
+	FATTR4_WORD2_POSIX_DEFAULT_ACL | \
+	FATTR4_WORD2_POSIX_ACCESS_ACL)
+#else
+#define NFSD4_2_POSIX_ACL_ATTRS		0
+#endif
+
+#define NFSD4_2_SUPPORTED_ATTRS_WORD2 \
+	(NFSD4_1_SUPPORTED_ATTRS_WORD2 | \
+	FATTR4_WORD2_MODE_UMASK | \
+	FATTR4_WORD2_CLONE_BLKSIZE | \
+	NFSD4_2_SECURITY_ATTRS | \
+	FATTR4_WORD2_XATTR_SUPPORT | \
+	FATTR4_WORD2_TIME_DELEG_ACCESS | \
+	FATTR4_WORD2_TIME_DELEG_MODIFY | \
+	FATTR4_WORD2_OPEN_ARGUMENTS | \
+	NFSD4_2_POSIX_ACL_ATTRS)
+
+/* These will return ERR_INVAL if specified in GETATTR or READDIR. */
+#define NFSD_WRITEONLY_ATTRS_WORD1 \
+	(FATTR4_WORD1_TIME_ACCESS_SET   | FATTR4_WORD1_TIME_MODIFY_SET)
+
+/*
+ * These are the only attrs allowed in CREATE/OPEN/SETATTR. Don't add
+ * a writeable attribute here without also adding code to parse it to
+ * nfsd4_decode_fattr4().
+ */
+#define NFSD_WRITEABLE_ATTRS_WORD0 \
+	(FATTR4_WORD0_SIZE | FATTR4_WORD0_ACL)
+#define NFSD_WRITEABLE_ATTRS_WORD1 \
+	(FATTR4_WORD1_MODE | FATTR4_WORD1_OWNER | FATTR4_WORD1_OWNER_GROUP \
+	| FATTR4_WORD1_TIME_ACCESS_SET | FATTR4_WORD1_TIME_CREATE \
+	| FATTR4_WORD1_TIME_MODIFY_SET)
+#ifdef CONFIG_NFSD_V4_SECURITY_LABEL
+#define MAYBE_FATTR4_WORD2_SECURITY_LABEL \
+	FATTR4_WORD2_SECURITY_LABEL
+#else
+#define MAYBE_FATTR4_WORD2_SECURITY_LABEL 0
+#endif
+#ifdef CONFIG_NFSD_V4_POSIX_ACLS
+#define MAYBE_FATTR4_WORD2_POSIX_ACL_ATTRS \
+	FATTR4_WORD2_POSIX_DEFAULT_ACL | FATTR4_WORD2_POSIX_ACCESS_ACL
+#else
+#define MAYBE_FATTR4_WORD2_POSIX_ACL_ATTRS 0
+#endif
+#define NFSD_WRITEABLE_ATTRS_WORD2 \
+	(FATTR4_WORD2_MODE_UMASK \
+	| MAYBE_FATTR4_WORD2_SECURITY_LABEL \
+	| FATTR4_WORD2_TIME_DELEG_ACCESS \
+	| FATTR4_WORD2_TIME_DELEG_MODIFY \
+	| MAYBE_FATTR4_WORD2_POSIX_ACL_ATTRS \
+	)
+
+#define NFSD_SUPPATTR_EXCLCREAT_WORD0 \
+	NFSD_WRITEABLE_ATTRS_WORD0
+/*
+ * we currently store the exclusive create verifier in the v_{a,m}time
+ * attributes so the client can't set these at create time using EXCLUSIVE4_1
+ */
+#define NFSD_SUPPATTR_EXCLCREAT_WORD1 \
+	(NFSD_WRITEABLE_ATTRS_WORD1 & \
+	 ~(FATTR4_WORD1_TIME_ACCESS_SET | FATTR4_WORD1_TIME_MODIFY_SET))
+/*
+ * The FATTR4_WORD2_TIME_DELEG attributes are not to be allowed for
+ * OPEN(create) with EXCLUSIVE4_1. It doesn't make sense to set a
+ * delegated timestamp on a new file.
+ *
+ * This mask includes NFSv4.2-only attributes (e.g., POSIX ACLs).
+ * Version filtering occurs via nfsd_suppattrs[] before this mask
+ * is applied, so pre-4.2 clients never see unsupported attributes.
+ */
+#define NFSD_SUPPATTR_EXCLCREAT_WORD2 \
+	(NFSD_WRITEABLE_ATTRS_WORD2 & \
+	~(FATTR4_WORD2_TIME_DELEG_ACCESS | FATTR4_WORD2_TIME_DELEG_MODIFY))
+
+extern const u32 nfsd_suppattrs[3][3];
+
+static inline bool bmval_is_subset(const u32 *bm1, const u32 *bm2)
+{
+	return !((bm1[0] & ~bm2[0]) ||
+	         (bm1[1] & ~bm2[1]) ||
+		 (bm1[2] & ~bm2[2]));
+}
+
+static inline bool nfsd_attrs_supported(u32 minorversion, const u32 *bmval)
+{
+	return bmval_is_subset(bmval, nfsd_suppattrs[minorversion]);
+}
+
+#endif /* _LINUX_NFSD_ATTR4_H */