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, 199 insertions, 0 deletions

diff --git a/fs/sysfs/symlink.c b/fs/sysfs/symlink.c
new file mode 100644
index 000000000..5f9c05fb1
--- /dev/null
+++ b/fs/sysfs/symlink.c
@@ -0,0 +1,199 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * fs/sysfs/symlink.c - sysfs symlink implementation
+ *
+ * Copyright (c) 2001-3 Patrick Mochel
+ * Copyright (c) 2007 SUSE Linux Products GmbH
+ * Copyright (c) 2007 Tejun Heo <teheo@suse.de>
+ *
+ * Please see Documentation/filesystems/sysfs.rst for more information.
+ */
+
+#include <linux/fs.h>
+#include <linux/module.h>
+#include <linux/kobject.h>
+#include <linux/mutex.h>
+#include <linux/security.h>
+
+#include "sysfs.h"
+
+static int sysfs_do_create_link_sd(struct kernfs_node *parent,
+				   struct kobject *target_kobj,
+				   const char *name, int warn)
+{
+	struct kernfs_node *kn, *target = NULL;
+
+	if (WARN_ON(!name || !parent))
+		return -EINVAL;
+
+	/*
+	 * We don't own @target_kobj and it may be removed at any time.
+	 * Synchronize using sysfs_symlink_target_lock.  See
+	 * sysfs_remove_dir() for details.
+	 */
+	spin_lock(&sysfs_symlink_target_lock);
+	if (target_kobj->sd) {
+		target = target_kobj->sd;
+		kernfs_get(target);
+	}
+	spin_unlock(&sysfs_symlink_target_lock);
+
+	if (!target)
+		return -ENOENT;
+
+	kn = kernfs_create_link(parent, name, target);
+	kernfs_put(target);
+
+	if (!IS_ERR(kn))
+		return 0;
+
+	if (warn && PTR_ERR(kn) == -EEXIST)
+		sysfs_warn_dup(parent, name);
+	return PTR_ERR(kn);
+}
+
+/**
+ *	sysfs_create_link_sd - create symlink to a given object.
+ *	@kn:		directory we're creating the link in.
+ *	@target:	object we're pointing to.
+ *	@name:		name of the symlink.
+ */
+int sysfs_create_link_sd(struct kernfs_node *kn, struct kobject *target,
+			 const char *name)
+{
+	return sysfs_do_create_link_sd(kn, target, name, 1);
+}
+
+static int sysfs_do_create_link(struct kobject *kobj, struct kobject *target,
+				const char *name, int warn)
+{
+	struct kernfs_node *parent = NULL;
+
+	if (!kobj)
+		parent = sysfs_root_kn;
+	else
+		parent = kobj->sd;
+
+	if (!parent)
+		return -EFAULT;
+
+	return sysfs_do_create_link_sd(parent, target, name, warn);
+}
+
+/**
+ *	sysfs_create_link - create symlink between two objects.
+ *	@kobj:	object whose directory we're creating the link in.
+ *	@target:	object we're pointing to.
+ *	@name:		name of the symlink.
+ */
+int sysfs_create_link(struct kobject *kobj, struct kobject *target,
+		      const char *name)
+{
+	return sysfs_do_create_link(kobj, target, name, 1);
+}
+EXPORT_SYMBOL_GPL(sysfs_create_link);
+
+/**
+ *	sysfs_create_link_nowarn - create symlink between two objects.
+ *	@kobj:	object whose directory we're creating the link in.
+ *	@target:	object we're pointing to.
+ *	@name:		name of the symlink.
+ *
+ *	This function does the same as sysfs_create_link(), but it
+ *	doesn't warn if the link already exists.
+ */
+int sysfs_create_link_nowarn(struct kobject *kobj, struct kobject *target,
+			     const char *name)
+{
+	return sysfs_do_create_link(kobj, target, name, 0);
+}
+EXPORT_SYMBOL_GPL(sysfs_create_link_nowarn);
+
+/**
+ *	sysfs_delete_link - remove symlink in object's directory.
+ *	@kobj:	object we're acting for.
+ *	@targ:	object we're pointing to.
+ *	@name:	name of the symlink to remove.
+ *
+ *	Unlike sysfs_remove_link sysfs_delete_link has enough information
+ *	to successfully delete symlinks in tagged directories.
+ */
+void sysfs_delete_link(struct kobject *kobj, struct kobject *targ,
+			const char *name)
+{
+	const struct ns_common *ns = NULL;
+
+	/*
+	 * We don't own @target and it may be removed at any time.
+	 * Synchronize using sysfs_symlink_target_lock.  See
+	 * sysfs_remove_dir() for details.
+	 */
+	spin_lock(&sysfs_symlink_target_lock);
+	if (targ->sd && kernfs_ns_enabled(kobj->sd))
+		ns = targ->sd->ns;
+	spin_unlock(&sysfs_symlink_target_lock);
+	kernfs_remove_by_name_ns(kobj->sd, name, ns);
+}
+
+/**
+ *	sysfs_remove_link - remove symlink in object's directory.
+ *	@kobj:	object we're acting for.
+ *	@name:	name of the symlink to remove.
+ */
+void sysfs_remove_link(struct kobject *kobj, const char *name)
+{
+	struct kernfs_node *parent = NULL;
+
+	if (!kobj)
+		parent = sysfs_root_kn;
+	else
+		parent = kobj->sd;
+
+	kernfs_remove_by_name(parent, name);
+}
+EXPORT_SYMBOL_GPL(sysfs_remove_link);
+
+/**
+ *	sysfs_rename_link_ns - rename symlink in object's directory.
+ *	@kobj:	object we're acting for.
+ *	@targ:	object we're pointing to.
+ *	@old:	previous name of the symlink.
+ *	@new:	new name of the symlink.
+ *	@new_ns: new namespace of the symlink.
+ *
+ *	A helper function for the common rename symlink idiom.
+ */
+int sysfs_rename_link_ns(struct kobject *kobj, struct kobject *targ,
+			 const char *old, const char *new,
+			 const struct ns_common *new_ns)
+{
+	struct kernfs_node *parent, *kn = NULL;
+	const struct ns_common *old_ns = NULL;
+	int result;
+
+	if (!kobj)
+		parent = sysfs_root_kn;
+	else
+		parent = kobj->sd;
+
+	if (targ->sd)
+		old_ns = targ->sd->ns;
+
+	result = -ENOENT;
+	kn = kernfs_find_and_get_ns(parent, old, old_ns);
+	if (!kn)
+		goto out;
+
+	result = -EINVAL;
+	if (kernfs_type(kn) != KERNFS_LINK)
+		goto out;
+	if (kn->symlink.target_kn->priv != targ)
+		goto out;
+
+	result = kernfs_rename_ns(kn, parent, new, new_ns);
+
+out:
+	kernfs_put(kn);
+	return result;
+}
+EXPORT_SYMBOL_GPL(sysfs_rename_link_ns);