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, 133 insertions, 0 deletions

diff --git a/fs/nfs/getroot.c b/fs/nfs/getroot.c
new file mode 100644
index 000000000..ff7424bc4
--- /dev/null
+++ b/fs/nfs/getroot.c
@@ -0,0 +1,133 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* getroot.c: get the root dentry for an NFS mount
+ *
+ * Copyright (C) 2006 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+
+#include <linux/time.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/string.h>
+#include <linux/stat.h>
+#include <linux/errno.h>
+#include <linux/unistd.h>
+#include <linux/sunrpc/clnt.h>
+#include <linux/sunrpc/stats.h>
+#include <linux/nfs_fs.h>
+#include <linux/nfs_mount.h>
+#include <linux/lockd/bind.h>
+#include <linux/seq_file.h>
+#include <linux/mount.h>
+#include <linux/vfs.h>
+#include <linux/namei.h>
+#include <linux/security.h>
+
+#include <linux/uaccess.h>
+
+#include "internal.h"
+
+#define NFSDBG_FACILITY		NFSDBG_CLIENT
+
+/*
+ * get a root dentry from the root filehandle
+ */
+int nfs_get_root(struct super_block *s, struct fs_context *fc)
+{
+	struct nfs_fs_context *ctx = nfs_fc2context(fc);
+	struct nfs_server *server = NFS_SB(s), *clone_server;
+	struct nfs_fsinfo fsinfo;
+	struct dentry *root;
+	struct inode *inode;
+	char *name;
+	int error = -ENOMEM;
+	unsigned long kflags = 0, kflags_out = 0;
+
+	name = kstrdup(fc->source, GFP_KERNEL);
+	if (!name)
+		goto out;
+
+	/* get the actual root for this mount */
+	fsinfo.fattr = nfs_alloc_fattr_with_label(server);
+	if (fsinfo.fattr == NULL)
+		goto out_name;
+
+	error = server->nfs_client->rpc_ops->getroot(server, ctx->mntfh, &fsinfo);
+	if (error < 0) {
+		dprintk("nfs_get_root: getattr error = %d\n", -error);
+		nfs_errorf(fc, "NFS: Couldn't getattr on root");
+		goto out_fattr;
+	}
+
+	inode = nfs_fhget(s, ctx->mntfh, fsinfo.fattr);
+	if (IS_ERR(inode)) {
+		dprintk("nfs_get_root: get root inode failed\n");
+		error = PTR_ERR(inode);
+		nfs_errorf(fc, "NFS: Couldn't get root inode");
+		goto out_fattr;
+	}
+
+	/* root dentries normally start off anonymous and get spliced in later
+	 * if the dentry tree reaches them; however if the dentry already
+	 * exists, we'll pick it up at this point and use it as the root
+	 */
+	root = d_obtain_root(inode);
+	if (IS_ERR(root)) {
+		dprintk("nfs_get_root: get root dentry failed\n");
+		error = PTR_ERR(root);
+		nfs_errorf(fc, "NFS: Couldn't get root dentry");
+		goto out_fattr;
+	}
+
+	security_d_instantiate(root, inode);
+	spin_lock(&root->d_lock);
+	if (IS_ROOT(root) && !root->d_fsdata &&
+	    !(root->d_flags & DCACHE_NFSFS_RENAMED)) {
+		root->d_fsdata = name;
+		name = NULL;
+	}
+	spin_unlock(&root->d_lock);
+	if (!s->s_root)
+		s->s_root = dget(root);
+	fc->root = root;
+	if (server->caps & NFS_CAP_SECURITY_LABEL)
+		kflags |= SECURITY_LSM_NATIVE_LABELS;
+	if (ctx->clone_data.sb) {
+		if (d_inode(fc->root)->i_fop != &nfs_dir_operations) {
+			error = -ESTALE;
+			goto error_splat_root;
+		}
+		/* clone lsm security options from the parent to the new sb */
+		error = security_sb_clone_mnt_opts(ctx->clone_data.sb,
+						   s, kflags, &kflags_out);
+		if (error)
+			goto error_splat_root;
+		clone_server = NFS_SB(ctx->clone_data.sb);
+		server->has_sec_mnt_opts = clone_server->has_sec_mnt_opts;
+	} else {
+		error = security_sb_set_mnt_opts(s, fc->security,
+							kflags, &kflags_out);
+	}
+	if (error)
+		goto error_splat_root;
+	if (server->caps & NFS_CAP_SECURITY_LABEL &&
+		!(kflags_out & SECURITY_LSM_NATIVE_LABELS))
+		server->caps &= ~NFS_CAP_SECURITY_LABEL;
+
+	nfs_setsecurity(inode, fsinfo.fattr);
+	error = 0;
+
+out_fattr:
+	nfs_free_fattr(fsinfo.fattr);
+out_name:
+	kfree(name);
+out:
+	return error;
+error_splat_root:
+	dput(fc->root);
+	fc->root = NULL;
+	goto out_fattr;
+}