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, 155 insertions, 0 deletions

diff --git a/fs/fs_struct.c b/fs/fs_struct.c
new file mode 100644
index 000000000..394875d06
--- /dev/null
+++ b/fs/fs_struct.c
@@ -0,0 +1,155 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/export.h>
+#include <linux/sched/signal.h>
+#include <linux/sched/task.h>
+#include <linux/fs.h>
+#include <linux/path.h>
+#include <linux/slab.h>
+#include <linux/fs_struct.h>
+#include <linux/init_task.h>
+#include "internal.h"
+
+/*
+ * Replace the fs->{rootmnt,root} with {mnt,dentry}. Put the old values.
+ * It can block.
+ */
+void set_fs_root(struct fs_struct *fs, const struct path *path)
+{
+	struct path old_root;
+
+	path_get(path);
+	write_seqlock(&fs->seq);
+	old_root = fs->root;
+	fs->root = *path;
+	write_sequnlock(&fs->seq);
+	if (old_root.dentry)
+		path_put(&old_root);
+}
+
+/*
+ * Replace the fs->{pwdmnt,pwd} with {mnt,dentry}. Put the old values.
+ * It can block.
+ */
+void set_fs_pwd(struct fs_struct *fs, const struct path *path)
+{
+	struct path old_pwd;
+
+	path_get(path);
+	write_seqlock(&fs->seq);
+	old_pwd = fs->pwd;
+	fs->pwd = *path;
+	write_sequnlock(&fs->seq);
+
+	if (old_pwd.dentry)
+		path_put(&old_pwd);
+}
+
+static inline int replace_path(struct path *p, const struct path *old, const struct path *new)
+{
+	if (likely(p->dentry != old->dentry || p->mnt != old->mnt))
+		return 0;
+	*p = *new;
+	return 1;
+}
+
+void chroot_fs_refs(const struct path *old_root, const struct path *new_root)
+{
+	struct task_struct *g, *p;
+	struct fs_struct *fs;
+	int count = 0;
+
+	read_lock(&tasklist_lock);
+	for_each_process_thread(g, p) {
+		task_lock(p);
+		fs = p->fs;
+		if (fs) {
+			int hits = 0;
+			write_seqlock(&fs->seq);
+			hits += replace_path(&fs->root, old_root, new_root);
+			hits += replace_path(&fs->pwd, old_root, new_root);
+			while (hits--) {
+				count++;
+				path_get(new_root);
+			}
+			write_sequnlock(&fs->seq);
+		}
+		task_unlock(p);
+	}
+	read_unlock(&tasklist_lock);
+	while (count--)
+		path_put(old_root);
+}
+
+void free_fs_struct(struct fs_struct *fs)
+{
+	path_put(&fs->root);
+	path_put(&fs->pwd);
+	kmem_cache_free(fs_cachep, fs);
+}
+
+void exit_fs(struct task_struct *tsk)
+{
+	struct fs_struct *fs = tsk->fs;
+
+	if (fs) {
+		int kill;
+		task_lock(tsk);
+		read_seqlock_excl(&fs->seq);
+		tsk->fs = NULL;
+		kill = !--fs->users;
+		read_sequnlock_excl(&fs->seq);
+		task_unlock(tsk);
+		if (kill)
+			free_fs_struct(fs);
+	}
+}
+
+struct fs_struct *copy_fs_struct(struct fs_struct *old)
+{
+	struct fs_struct *fs = kmem_cache_alloc(fs_cachep, GFP_KERNEL);
+	/* We don't need to lock fs - think why ;-) */
+	if (fs) {
+		fs->users = 1;
+		fs->in_exec = 0;
+		seqlock_init(&fs->seq);
+		fs->umask = old->umask;
+
+		read_seqlock_excl(&old->seq);
+		fs->root = old->root;
+		path_get(&fs->root);
+		fs->pwd = old->pwd;
+		path_get(&fs->pwd);
+		read_sequnlock_excl(&old->seq);
+	}
+	return fs;
+}
+
+int unshare_fs_struct(void)
+{
+	struct fs_struct *fs = current->fs;
+	struct fs_struct *new_fs = copy_fs_struct(fs);
+	int kill;
+
+	if (!new_fs)
+		return -ENOMEM;
+
+	task_lock(current);
+	read_seqlock_excl(&fs->seq);
+	kill = !--fs->users;
+	current->fs = new_fs;
+	read_sequnlock_excl(&fs->seq);
+	task_unlock(current);
+
+	if (kill)
+		free_fs_struct(fs);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(unshare_fs_struct);
+
+/* to be mentioned only in INIT_TASK */
+struct fs_struct init_fs = {
+	.users		= 1,
+	.seq		= __SEQLOCK_UNLOCKED(init_fs.seq),
+	.umask		= 0022,
+};