ARM: 9485/1: mm: acquire mmap write lock around show_pte() for user faultsgrafted

When CONFIG_DEBUG_USER=y, and cmdline "user_debug=31" is set,
a user fault may trigger show_pte() without any lock.
If another thread in the same process concurrently calls munmap(),
the page table pages may be freed while show_pte() is still traversing
them, causing a use-after-free in show_pte().

If CONFIG_ARM_LPAE=y, this may cause a kernel panic if the pages table
of PMD are freed when show_pte() is running.

Acquire mmap_write_lock() around show_pte() for user faults to fix the
contention.

For user faults, additionally restrict that show_pte() is called only
when the addr is a user-space address (addr < TASK_SIZE). This is because
the lock of tsk->mm only protects the virtual memory of user address space,
furthermore, dumping the page tables of a kernel-space address for user
faults is unnecessary and may have security implications.

Keep everything unchanged for kernel faults, because the kernel is
already in the "oops" state, acquiring a lock may risk a deadlock.

Co-developed-by: Qi Xi <xiqi2@huawei.com>

Fixes: 6d021b724481 ("ARM: dump pgd, pmd and pte states on unhandled data abort faults")
Link: https://lore.kernel.org/20260716014022.2823-1-xieyuanbin1@huawei.com
Acked-by: Lorenzo Stoakes (ARM) <ljs@kernel.org>
Reviewed-by: Linus Walleij <linusw@kernel.org>
Signed-off-by: Qi Xi <xiqi2@huawei.com>
Signed-off-by: Xie Yuanbin <xieyuanbin1@huawei.com>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>

1 files changed, 76 insertions, 0 deletions

diff --git a/fs/ecryptfs/dentry.c b/fs/ecryptfs/dentry.c
new file mode 100644
index 000000000..6648a924e
--- /dev/null
+++ b/fs/ecryptfs/dentry.c
@@ -0,0 +1,76 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * eCryptfs: Linux filesystem encryption layer
+ *
+ * Copyright (C) 1997-2003 Erez Zadok
+ * Copyright (C) 2001-2003 Stony Brook University
+ * Copyright (C) 2004-2006 International Business Machines Corp.
+ *   Author(s): Michael A. Halcrow <mahalcro@us.ibm.com>
+ */
+
+#include <linux/dcache.h>
+#include <linux/namei.h>
+#include <linux/mount.h>
+#include <linux/fs_stack.h>
+#include <linux/slab.h>
+#include "ecryptfs_kernel.h"
+
+/**
+ * ecryptfs_d_revalidate - revalidate an ecryptfs dentry
+ * @dir: inode of expected parent
+ * @name: expected name
+ * @dentry: dentry to revalidate
+ * @flags: lookup flags
+ *
+ * Called when the VFS needs to revalidate a dentry. This
+ * is called whenever a name lookup finds a dentry in the
+ * dcache. Most filesystems leave this as NULL, because all their
+ * dentries in the dcache are valid.
+ *
+ * Returns 1 if valid, 0 otherwise.
+ *
+ */
+static int ecryptfs_d_revalidate(struct inode *dir, const struct qstr *name,
+				 struct dentry *dentry, unsigned int flags)
+{
+	struct dentry *lower_dentry = ecryptfs_dentry_to_lower(dentry);
+	int rc = 1;
+
+	if (flags & LOOKUP_RCU)
+		return -ECHILD;
+
+	if (lower_dentry->d_flags & DCACHE_OP_REVALIDATE) {
+		struct inode *lower_dir = ecryptfs_inode_to_lower(dir);
+		struct name_snapshot n;
+
+		take_dentry_name_snapshot(&n, lower_dentry);
+		rc = lower_dentry->d_op->d_revalidate(lower_dir, &n.name,
+						      lower_dentry, flags);
+		release_dentry_name_snapshot(&n);
+	}
+
+	if (d_really_is_positive(dentry)) {
+		struct inode *inode = d_inode(dentry);
+
+		fsstack_copy_attr_all(inode, ecryptfs_inode_to_lower(inode));
+		if (!inode->i_nlink)
+			return 0;
+	}
+	return rc;
+}
+
+/**
+ * ecryptfs_d_release
+ * @dentry: The ecryptfs dentry
+ *
+ * Called when a dentry is really deallocated.
+ */
+static void ecryptfs_d_release(struct dentry *dentry)
+{
+	dput(dentry->d_fsdata);
+}
+
+const struct dentry_operations ecryptfs_dops = {
+	.d_revalidate = ecryptfs_d_revalidate,
+	.d_release = ecryptfs_d_release,
+};