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, 196 insertions, 0 deletions

diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c
new file mode 100644
index 000000000..ea6ec61a0
--- /dev/null
+++ b/fs/proc/namespaces.c
@@ -0,0 +1,196 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/proc_fs.h>
+#include <linux/nsproxy.h>
+#include <linux/ptrace.h>
+#include <linux/namei.h>
+#include <linux/file.h>
+#include <linux/utsname.h>
+#include <net/net_namespace.h>
+#include <linux/ipc_namespace.h>
+#include <linux/pid_namespace.h>
+#include <linux/user_namespace.h>
+#include "internal.h"
+
+
+static const struct proc_ns_operations *const ns_entries[] = {
+#ifdef CONFIG_NET_NS
+	&netns_operations,
+#endif
+#ifdef CONFIG_UTS_NS
+	&utsns_operations,
+#endif
+#ifdef CONFIG_IPC_NS
+	&ipcns_operations,
+#endif
+#ifdef CONFIG_PID_NS
+	&pidns_operations,
+	&pidns_for_children_operations,
+#endif
+#ifdef CONFIG_USER_NS
+	&userns_operations,
+#endif
+	&mntns_operations,
+#ifdef CONFIG_CGROUPS
+	&cgroupns_operations,
+#endif
+#ifdef CONFIG_TIME_NS
+	&timens_operations,
+	&timens_for_children_operations,
+#endif
+};
+
+static const char *proc_ns_get_link(struct dentry *dentry,
+				    struct inode *inode,
+				    struct delayed_call *done)
+{
+	const struct proc_ns_operations *ns_ops = PROC_I(inode)->ns_ops;
+	struct task_struct *task;
+	struct path ns_path;
+	int error;
+
+	if (!dentry)
+		return ERR_PTR(-ECHILD);
+
+	task = get_proc_task(inode);
+	if (!task)
+		return ERR_PTR(-EACCES);
+
+	error = down_read_killable(&task->signal->exec_update_lock);
+	if (error)
+		goto out_put_task;
+
+	error = -EACCES;
+	if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS))
+		goto out;
+
+	error = ns_get_path(&ns_path, task, ns_ops);
+	if (error)
+		goto out;
+
+	error = nd_jump_link(&ns_path);
+out:
+	up_read(&task->signal->exec_update_lock);
+out_put_task:
+	put_task_struct(task);
+	return ERR_PTR(error);
+}
+
+static int proc_ns_readlink(struct dentry *dentry, char __user *buffer, int buflen)
+{
+	struct inode *inode = d_inode(dentry);
+	const struct proc_ns_operations *ns_ops = PROC_I(inode)->ns_ops;
+	struct task_struct *task;
+	char name[50];
+	int res = -EACCES;
+
+	task = get_proc_task(inode);
+	if (!task)
+		return res;
+
+	res = down_read_killable(&task->signal->exec_update_lock);
+	if (res)
+		goto out_put_task;
+
+	res = -EACCES;
+	if (ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) {
+		res = ns_get_name(name, sizeof(name), task, ns_ops);
+		if (res >= 0)
+			res = readlink_copy(buffer, buflen, name, strlen(name));
+	}
+	up_read(&task->signal->exec_update_lock);
+out_put_task:
+	put_task_struct(task);
+	return res;
+}
+
+static const struct inode_operations proc_ns_link_inode_operations = {
+	.readlink	= proc_ns_readlink,
+	.get_link	= proc_ns_get_link,
+	.setattr	= proc_nochmod_setattr,
+};
+
+static struct dentry *proc_ns_instantiate(struct dentry *dentry,
+	struct task_struct *task, const void *ptr)
+{
+	const struct proc_ns_operations *ns_ops = ptr;
+	struct inode *inode;
+	struct proc_inode *ei;
+
+	inode = proc_pid_make_inode(dentry->d_sb, task, S_IFLNK | S_IRWXUGO);
+	if (!inode)
+		return ERR_PTR(-ENOENT);
+
+	ei = PROC_I(inode);
+	inode->i_op = &proc_ns_link_inode_operations;
+	ei->ns_ops = ns_ops;
+	pid_update_inode(task, inode);
+
+	return d_splice_alias_ops(inode, dentry, &pid_dentry_operations);
+}
+
+static int proc_ns_dir_readdir(struct file *file, struct dir_context *ctx)
+{
+	struct task_struct *task = get_proc_task(file_inode(file));
+	const struct proc_ns_operations *const *entry, *const *last;
+
+	if (!task)
+		return -ENOENT;
+
+	if (!dir_emit_dots(file, ctx))
+		goto out;
+	if (ctx->pos >= 2 + ARRAY_SIZE(ns_entries))
+		goto out;
+	entry = ns_entries + (ctx->pos - 2);
+	last = &ns_entries[ARRAY_SIZE(ns_entries) - 1];
+	while (entry <= last) {
+		const struct proc_ns_operations *ops = *entry;
+		if (!proc_fill_cache(file, ctx, ops->name, strlen(ops->name),
+				     proc_ns_instantiate, task, ops))
+			break;
+		ctx->pos++;
+		entry++;
+	}
+out:
+	put_task_struct(task);
+	return 0;
+}
+
+const struct file_operations proc_ns_dir_operations = {
+	.read		= generic_read_dir,
+	.iterate_shared	= proc_ns_dir_readdir,
+	.llseek		= generic_file_llseek,
+};
+
+static struct dentry *proc_ns_dir_lookup(struct inode *dir,
+				struct dentry *dentry, unsigned int flags)
+{
+	struct task_struct *task = get_proc_task(dir);
+	const struct proc_ns_operations *const *entry, *const *last;
+	unsigned int len = dentry->d_name.len;
+	struct dentry *res = ERR_PTR(-ENOENT);
+
+	if (!task)
+		goto out_no_task;
+
+	last = &ns_entries[ARRAY_SIZE(ns_entries)];
+	for (entry = ns_entries; entry < last; entry++) {
+		if (strlen((*entry)->name) != len)
+			continue;
+		if (!memcmp(dentry->d_name.name, (*entry)->name, len))
+			break;
+	}
+	if (entry == last)
+		goto out;
+
+	res = proc_ns_instantiate(dentry, task, *entry);
+out:
+	put_task_struct(task);
+out_no_task:
+	return res;
+}
+
+const struct inode_operations proc_ns_dir_inode_operations = {
+	.lookup		= proc_ns_dir_lookup,
+	.getattr	= pid_getattr,
+	.setattr	= proc_nochmod_setattr,
+};