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, 194 insertions, 0 deletions

diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c
new file mode 100644
index 000000000..68290fe0e
--- /dev/null
+++ b/fs/configfs/inode.c
@@ -0,0 +1,194 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * inode.c - basic inode and dentry operations.
+ *
+ * Based on sysfs:
+ * 	sysfs is Copyright (C) 2001, 2002, 2003 Patrick Mochel
+ *
+ * configfs Copyright (C) 2005 Oracle.  All rights reserved.
+ *
+ * Please see Documentation/filesystems/configfs.rst for more
+ * information.
+ */
+
+#undef DEBUG
+
+#include <linux/pagemap.h>
+#include <linux/namei.h>
+#include <linux/backing-dev.h>
+#include <linux/capability.h>
+#include <linux/sched.h>
+#include <linux/lockdep.h>
+#include <linux/slab.h>
+
+#include <linux/configfs.h>
+#include "configfs_internal.h"
+
+#ifdef CONFIG_LOCKDEP
+static struct lock_class_key default_group_class[MAX_LOCK_DEPTH];
+#endif
+
+static const struct inode_operations configfs_inode_operations ={
+	.setattr	= configfs_setattr,
+};
+
+int configfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
+		     struct iattr *iattr)
+{
+	struct inode * inode = d_inode(dentry);
+	struct configfs_dirent * sd = dentry->d_fsdata;
+	struct iattr * sd_iattr;
+	unsigned int ia_valid = iattr->ia_valid;
+	int error;
+
+	if (!sd)
+		return -EINVAL;
+
+	sd_iattr = sd->s_iattr;
+	if (!sd_iattr) {
+		/* setting attributes for the first time, allocate now */
+		sd_iattr = kzalloc_obj(struct iattr);
+		if (!sd_iattr)
+			return -ENOMEM;
+		/* assign default attributes */
+		sd_iattr->ia_mode = sd->s_mode;
+		sd_iattr->ia_uid = GLOBAL_ROOT_UID;
+		sd_iattr->ia_gid = GLOBAL_ROOT_GID;
+		sd_iattr->ia_atime = sd_iattr->ia_mtime =
+			sd_iattr->ia_ctime = current_time(inode);
+		sd->s_iattr = sd_iattr;
+	}
+	/* attributes were changed atleast once in past */
+
+	error = simple_setattr(idmap, dentry, iattr);
+	if (error)
+		return error;
+
+	if (ia_valid & ATTR_UID)
+		sd_iattr->ia_uid = iattr->ia_uid;
+	if (ia_valid & ATTR_GID)
+		sd_iattr->ia_gid = iattr->ia_gid;
+	if (ia_valid & ATTR_ATIME)
+		sd_iattr->ia_atime = iattr->ia_atime;
+	if (ia_valid & ATTR_MTIME)
+		sd_iattr->ia_mtime = iattr->ia_mtime;
+	if (ia_valid & ATTR_CTIME)
+		sd_iattr->ia_ctime = iattr->ia_ctime;
+	if (ia_valid & ATTR_MODE) {
+		umode_t mode = iattr->ia_mode;
+
+		if (!in_group_p(inode->i_gid) && !capable(CAP_FSETID))
+			mode &= ~S_ISGID;
+		sd_iattr->ia_mode = sd->s_mode = mode;
+	}
+
+	return error;
+}
+
+static inline void set_default_inode_attr(struct inode * inode, umode_t mode)
+{
+	inode->i_mode = mode;
+	simple_inode_init_ts(inode);
+}
+
+static inline void set_inode_attr(struct inode * inode, struct iattr * iattr)
+{
+	inode->i_mode = iattr->ia_mode;
+	inode->i_uid = iattr->ia_uid;
+	inode->i_gid = iattr->ia_gid;
+	inode_set_atime_to_ts(inode, iattr->ia_atime);
+	inode_set_mtime_to_ts(inode, iattr->ia_mtime);
+	inode_set_ctime_to_ts(inode, iattr->ia_ctime);
+}
+
+struct inode *configfs_new_inode(umode_t mode, struct configfs_dirent *sd,
+				 struct super_block *s)
+{
+	struct inode * inode = new_inode(s);
+	if (inode) {
+		inode->i_ino = get_next_ino();
+		inode->i_mapping->a_ops = &ram_aops;
+		inode->i_op = &configfs_inode_operations;
+
+		if (sd->s_iattr) {
+			/* sysfs_dirent has non-default attributes
+			 * get them for the new inode from persistent copy
+			 * in sysfs_dirent
+			 */
+			set_inode_attr(inode, sd->s_iattr);
+		} else
+			set_default_inode_attr(inode, mode);
+	}
+	return inode;
+}
+
+#ifdef CONFIG_LOCKDEP
+
+static void configfs_set_inode_lock_class(struct configfs_dirent *sd,
+					  struct inode *inode)
+{
+	int depth = sd->s_depth;
+
+	if (depth > 0) {
+		if (depth <= ARRAY_SIZE(default_group_class)) {
+			lockdep_set_class(&inode->i_rwsem,
+					  &default_group_class[depth - 1]);
+		} else {
+			/*
+			 * In practice the maximum level of locking depth is
+			 * already reached. Just inform about possible reasons.
+			 */
+			pr_info("Too many levels of inodes for the locking correctness validator.\n");
+			pr_info("Spurious warnings may appear.\n");
+		}
+	}
+}
+
+#else /* CONFIG_LOCKDEP */
+
+static void configfs_set_inode_lock_class(struct configfs_dirent *sd,
+					  struct inode *inode)
+{
+}
+
+#endif /* CONFIG_LOCKDEP */
+
+struct inode *configfs_create(struct dentry *dentry, umode_t mode)
+{
+	struct inode *inode = NULL;
+	struct configfs_dirent *sd;
+
+	if (!dentry)
+		return ERR_PTR(-ENOENT);
+
+	if (d_really_is_positive(dentry))
+		return ERR_PTR(-EEXIST);
+
+	sd = dentry->d_fsdata;
+	inode = configfs_new_inode(mode, sd, dentry->d_sb);
+	if (!inode)
+		return ERR_PTR(-ENOMEM);
+
+	configfs_set_inode_lock_class(sd, inode);
+	return inode;
+}
+
+/*
+ * Get the name for corresponding element represented by the given configfs_dirent
+ */
+const unsigned char * configfs_get_name(struct configfs_dirent *sd)
+{
+	struct configfs_attribute *attr;
+
+	BUG_ON(!sd || !sd->s_element);
+
+	/* These always have a dentry, so use that */
+	if (sd->s_type & (CONFIGFS_DIR | CONFIGFS_ITEM_LINK))
+		return sd->s_dentry->d_name.name;
+
+	if (sd->s_type & (CONFIGFS_ITEM_ATTR | CONFIGFS_ITEM_BIN_ATTR)) {
+		attr = sd->s_element;
+		return attr->ca_name;
+	}
+	return NULL;
+}