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/9p/cache.c b/fs/9p/cache.c
new file mode 100644
index 000000000..12c0ae29f
--- /dev/null
+++ b/fs/9p/cache.c
@@ -0,0 +1,76 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * V9FS cache definitions.
+ *
+ *  Copyright (C) 2009 by Abhishek Kulkarni <adkulkar@umail.iu.edu>
+ */
+
+#include <linux/jiffies.h>
+#include <linux/file.h>
+#include <linux/slab.h>
+#include <linux/stat.h>
+#include <linux/sched.h>
+#include <linux/fs.h>
+#include <net/9p/9p.h>
+
+#include "v9fs.h"
+#include "cache.h"
+
+int v9fs_cache_session_get_cookie(struct v9fs_session_info *v9ses,
+				  const char *dev_name)
+{
+	struct fscache_volume *vcookie;
+	char *name, *p;
+
+	name = kasprintf(GFP_KERNEL, "9p,%s,%s",
+			 dev_name, v9ses->cachetag ?: v9ses->aname);
+	if (!name)
+		return -ENOMEM;
+
+	for (p = name; *p; p++)
+		if (*p == '/')
+			*p = ';';
+
+	vcookie = fscache_acquire_volume(name, NULL, NULL, 0);
+	p9_debug(P9_DEBUG_FSC, "session %p get volume %p (%s)\n",
+		 v9ses, vcookie, name);
+	if (IS_ERR(vcookie)) {
+		if (vcookie != ERR_PTR(-EBUSY)) {
+			kfree(name);
+			return PTR_ERR(vcookie);
+		}
+		pr_err("Cache volume key already in use (%s)\n", name);
+		vcookie = NULL;
+	}
+	v9ses->fscache = vcookie;
+	kfree(name);
+	return 0;
+}
+
+void v9fs_cache_inode_get_cookie(struct inode *inode)
+{
+	struct v9fs_inode *v9inode = V9FS_I(inode);
+	struct v9fs_session_info *v9ses;
+	__le32 version;
+	__le64 path;
+
+	if (!S_ISREG(inode->i_mode))
+		return;
+	if (WARN_ON(v9fs_inode_cookie(v9inode)))
+		return;
+
+	version = cpu_to_le32(v9inode->qid.version);
+	path = cpu_to_le64(v9inode->qid.path);
+	v9ses = v9fs_inode2v9ses(inode);
+	v9inode->netfs.cache =
+		fscache_acquire_cookie(v9fs_session_cache(v9ses),
+				       0,
+				       &path, sizeof(path),
+				       &version, sizeof(version),
+				       i_size_read(&v9inode->netfs.inode));
+	if (v9inode->netfs.cache)
+		mapping_set_release_always(inode->i_mapping);
+
+	p9_debug(P9_DEBUG_FSC, "inode %p get cookie %p\n",
+		 inode, v9fs_inode_cookie(v9inode));
+}