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, 214 insertions, 0 deletions

diff --git a/fs/fuse/xattr.c b/fs/fuse/xattr.c
new file mode 100644
index 000000000..cab2685ac
--- /dev/null
+++ b/fs/fuse/xattr.c
@@ -0,0 +1,214 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * FUSE: Filesystem in Userspace
+ * Copyright (C) 2001-2016  Miklos Szeredi <miklos@szeredi.hu>
+ */
+
+#include "fuse_i.h"
+
+#include <linux/xattr.h>
+#include <linux/posix_acl_xattr.h>
+
+int fuse_setxattr(struct inode *inode, const char *name, const void *value,
+		  size_t size, int flags, unsigned int extra_flags)
+{
+	struct fuse_mount *fm = get_fuse_mount(inode);
+	FUSE_ARGS(args);
+	struct fuse_setxattr_in inarg;
+	int err;
+
+	if (fm->fc->no_setxattr)
+		return -EOPNOTSUPP;
+
+	memset(&inarg, 0, sizeof(inarg));
+	inarg.size = size;
+	inarg.flags = flags;
+	inarg.setxattr_flags = extra_flags;
+
+	args.opcode = FUSE_SETXATTR;
+	args.nodeid = get_node_id(inode);
+	args.in_numargs = 3;
+	args.in_args[0].size = fm->fc->setxattr_ext ?
+		sizeof(inarg) : FUSE_COMPAT_SETXATTR_IN_SIZE;
+	args.in_args[0].value = &inarg;
+	args.in_args[1].size = strlen(name) + 1;
+	args.in_args[1].value = name;
+	args.in_args[2].size = size;
+	args.in_args[2].value = value;
+	err = fuse_simple_request(fm, &args);
+	if (err == -ENOSYS) {
+		fm->fc->no_setxattr = 1;
+		err = -EOPNOTSUPP;
+	}
+	if (!err)
+		fuse_update_ctime(inode);
+
+	return err;
+}
+
+ssize_t fuse_getxattr(struct inode *inode, const char *name, void *value,
+		      size_t size)
+{
+	struct fuse_mount *fm = get_fuse_mount(inode);
+	FUSE_ARGS(args);
+	struct fuse_getxattr_in inarg;
+	struct fuse_getxattr_out outarg;
+	ssize_t ret;
+
+	if (fm->fc->no_getxattr)
+		return -EOPNOTSUPP;
+
+	memset(&inarg, 0, sizeof(inarg));
+	inarg.size = size;
+	args.opcode = FUSE_GETXATTR;
+	args.nodeid = get_node_id(inode);
+	args.in_numargs = 2;
+	args.in_args[0].size = sizeof(inarg);
+	args.in_args[0].value = &inarg;
+	args.in_args[1].size = strlen(name) + 1;
+	args.in_args[1].value = name;
+	/* This is really two different operations rolled into one */
+	args.out_numargs = 1;
+	if (size) {
+		args.out_argvar = true;
+		args.out_args[0].size = size;
+		args.out_args[0].value = value;
+	} else {
+		args.out_args[0].size = sizeof(outarg);
+		args.out_args[0].value = &outarg;
+	}
+	ret = fuse_simple_request(fm, &args);
+	if (!ret && !size)
+		ret = min_t(size_t, outarg.size, XATTR_SIZE_MAX);
+	if (ret == -ENOSYS) {
+		fm->fc->no_getxattr = 1;
+		ret = -EOPNOTSUPP;
+	}
+	return ret;
+}
+
+static int fuse_verify_xattr_list(char *list, size_t size)
+{
+	size_t origsize = size;
+
+	while (size) {
+		size_t thislen = strnlen(list, size);
+
+		if (!thislen || thislen == size)
+			return -EIO;
+
+		size -= thislen + 1;
+		list += thislen + 1;
+	}
+
+	return origsize;
+}
+
+ssize_t fuse_listxattr(struct dentry *entry, char *list, size_t size)
+{
+	struct inode *inode = d_inode(entry);
+	struct fuse_mount *fm = get_fuse_mount(inode);
+	FUSE_ARGS(args);
+	struct fuse_getxattr_in inarg;
+	struct fuse_getxattr_out outarg;
+	ssize_t ret;
+
+	if (fuse_is_bad(inode))
+		return -EIO;
+
+	if (!fuse_allow_current_process(fm->fc))
+		return -EACCES;
+
+	if (fm->fc->no_listxattr)
+		return -EOPNOTSUPP;
+
+	memset(&inarg, 0, sizeof(inarg));
+	inarg.size = size;
+	args.opcode = FUSE_LISTXATTR;
+	args.nodeid = get_node_id(inode);
+	args.in_numargs = 1;
+	args.in_args[0].size = sizeof(inarg);
+	args.in_args[0].value = &inarg;
+	/* This is really two different operations rolled into one */
+	args.out_numargs = 1;
+	if (size) {
+		args.out_argvar = true;
+		args.out_args[0].size = size;
+		args.out_args[0].value = list;
+	} else {
+		args.out_args[0].size = sizeof(outarg);
+		args.out_args[0].value = &outarg;
+	}
+	ret = fuse_simple_request(fm, &args);
+	if (!ret && !size)
+		ret = min_t(size_t, outarg.size, XATTR_LIST_MAX);
+	if (ret > 0 && size)
+		ret = fuse_verify_xattr_list(list, ret);
+	if (ret == -ENOSYS) {
+		fm->fc->no_listxattr = 1;
+		ret = -EOPNOTSUPP;
+	}
+	return ret;
+}
+
+int fuse_removexattr(struct inode *inode, const char *name)
+{
+	struct fuse_mount *fm = get_fuse_mount(inode);
+	FUSE_ARGS(args);
+	int err;
+
+	if (fm->fc->no_removexattr)
+		return -EOPNOTSUPP;
+
+	args.opcode = FUSE_REMOVEXATTR;
+	args.nodeid = get_node_id(inode);
+	args.in_numargs = 2;
+	fuse_set_zero_arg0(&args);
+	args.in_args[1].size = strlen(name) + 1;
+	args.in_args[1].value = name;
+	err = fuse_simple_request(fm, &args);
+	if (err == -ENOSYS) {
+		fm->fc->no_removexattr = 1;
+		err = -EOPNOTSUPP;
+	}
+	if (!err)
+		fuse_update_ctime(inode);
+
+	return err;
+}
+
+static int fuse_xattr_get(const struct xattr_handler *handler,
+			 struct dentry *dentry, struct inode *inode,
+			 const char *name, void *value, size_t size)
+{
+	if (fuse_is_bad(inode))
+		return -EIO;
+
+	return fuse_getxattr(inode, name, value, size);
+}
+
+static int fuse_xattr_set(const struct xattr_handler *handler,
+			  struct mnt_idmap *idmap,
+			  struct dentry *dentry, struct inode *inode,
+			  const char *name, const void *value, size_t size,
+			  int flags)
+{
+	if (fuse_is_bad(inode))
+		return -EIO;
+
+	if (!value)
+		return fuse_removexattr(inode, name);
+
+	return fuse_setxattr(inode, name, value, size, flags, 0);
+}
+
+static const struct xattr_handler fuse_xattr_handler = {
+	.prefix = "",
+	.get    = fuse_xattr_get,
+	.set    = fuse_xattr_set,
+};
+
+const struct xattr_handler * const fuse_xattr_handlers[] = {
+	&fuse_xattr_handler,
+	NULL
+};