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, 95 insertions, 0 deletions

diff --git a/fs/coda/coda_linux.h b/fs/coda/coda_linux.h
new file mode 100644
index 000000000..dd6277d87
--- /dev/null
+++ b/fs/coda/coda_linux.h
@@ -0,0 +1,95 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* 
+ * Coda File System, Linux Kernel module
+ * 
+ * Original version, adapted from cfs_mach.c, (C) Carnegie Mellon University
+ * Linux modifications (C) 1996, Peter J. Braam
+ * Rewritten for Linux 2.1 (C) 1997 Carnegie Mellon University
+ *
+ * Carnegie Mellon University encourages users of this software to
+ * contribute improvements to the Coda project.
+ */
+
+#ifndef _LINUX_CODA_FS
+#define _LINUX_CODA_FS
+
+#ifdef pr_fmt
+#undef pr_fmt
+#endif
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/param.h>
+#include <linux/mm.h>
+#include <linux/vmalloc.h>
+#include <linux/slab.h>
+#include <linux/wait.h>		
+#include <linux/types.h>
+#include <linux/fs.h>
+#include "coda_fs_i.h"
+
+/* operations */
+extern const struct inode_operations coda_dir_inode_operations;
+extern const struct inode_operations coda_file_inode_operations;
+extern const struct inode_operations coda_ioctl_inode_operations;
+
+extern const struct dentry_operations coda_dentry_operations;
+
+extern const struct address_space_operations coda_file_aops;
+extern const struct address_space_operations coda_symlink_aops;
+
+extern const struct file_operations coda_dir_operations;
+extern const struct file_operations coda_file_operations;
+extern const struct file_operations coda_ioctl_operations;
+
+/* operations shared over more than one file */
+int coda_open(struct inode *i, struct file *f);
+int coda_release(struct inode *i, struct file *f);
+int coda_permission(struct mnt_idmap *idmap, struct inode *inode,
+		    int mask);
+int coda_revalidate_inode(struct inode *);
+int coda_getattr(struct mnt_idmap *, const struct path *, struct kstat *,
+		 u32, unsigned int);
+int coda_setattr(struct mnt_idmap *, struct dentry *, struct iattr *);
+
+/* this file:  helpers */
+char *coda_f2s(struct CodaFid *f);
+int coda_iscontrol(const char *name, size_t length);
+
+umode_t coda_inode_type(struct coda_vattr *attr);
+void coda_vattr_to_iattr(struct inode *, struct coda_vattr *);
+void coda_iattr_to_vattr(struct iattr *, struct coda_vattr *);
+unsigned short coda_flags_to_cflags(unsigned short);
+
+/* inode to cnode access functions */
+
+static inline struct coda_inode_info *ITOC(struct inode *inode)
+{
+	return container_of(inode, struct coda_inode_info, vfs_inode);
+}
+
+static __inline__ struct CodaFid *coda_i2f(struct inode *inode)
+{
+	return &(ITOC(inode)->c_fid);
+}
+
+static __inline__ char *coda_i2s(struct inode *inode)
+{
+	return coda_f2s(&(ITOC(inode)->c_fid));
+}
+
+/* this will not zap the inode away */
+static __inline__ void coda_flag_inode(struct inode *inode, int flag)
+{
+	struct coda_inode_info *cii = ITOC(inode);
+
+	if (!inode)
+		return;
+
+	spin_lock(&cii->c_lock);
+	cii->c_flags |= flag;
+	spin_unlock(&cii->c_lock);
+}		
+
+#endif