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, 61 insertions, 0 deletions

diff --git a/include/uapi/asm-generic/shmbuf.h b/include/uapi/asm-generic/shmbuf.h
new file mode 100644
index 000000000..2979b6dd2
--- /dev/null
+++ b/include/uapi/asm-generic/shmbuf.h
@@ -0,0 +1,61 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __ASM_GENERIC_SHMBUF_H
+#define __ASM_GENERIC_SHMBUF_H
+
+#include <asm/bitsperlong.h>
+#include <asm/ipcbuf.h>
+#include <asm/posix_types.h>
+
+/*
+ * The shmid64_ds structure for x86 architecture.
+ * Note extra padding because this structure is passed back and forth
+ * between kernel and user space.
+ *
+ * shmid64_ds was originally meant to be architecture specific, but
+ * everyone just ended up making identical copies without specific
+ * optimizations, so we may just as well all use the same one.
+ *
+ * 64 bit architectures use a 64-bit long time field here, while
+ * 32 bit architectures have a pair of unsigned long values.
+ * On big-endian systems, the lower half is in the wrong place.
+ *
+ *
+ * Pad space is left for:
+ * - 2 miscellaneous 32-bit values
+ */
+
+struct shmid64_ds {
+	struct ipc64_perm	shm_perm;	/* operation perms */
+	__kernel_size_t		shm_segsz;	/* size of segment (bytes) */
+#if __BITS_PER_LONG == 64
+	long			shm_atime;	/* last attach time */
+	long			shm_dtime;	/* last detach time */
+	long			shm_ctime;	/* last change time */
+#else
+	unsigned long		shm_atime;	/* last attach time */
+	unsigned long		shm_atime_high;
+	unsigned long		shm_dtime;	/* last detach time */
+	unsigned long		shm_dtime_high;
+	unsigned long		shm_ctime;	/* last change time */
+	unsigned long		shm_ctime_high;
+#endif
+	__kernel_pid_t		shm_cpid;	/* pid of creator */
+	__kernel_pid_t		shm_lpid;	/* pid of last operator */
+	unsigned long		shm_nattch;	/* no. of current attaches */
+	unsigned long		__unused4;
+	unsigned long		__unused5;
+};
+
+struct shminfo64 {
+	unsigned long		shmmax;
+	unsigned long		shmmin;
+	unsigned long		shmmni;
+	unsigned long		shmseg;
+	unsigned long		shmall;
+	unsigned long		__unused1;
+	unsigned long		__unused2;
+	unsigned long		__unused3;
+	unsigned long		__unused4;
+};
+
+#endif /* __ASM_GENERIC_SHMBUF_H */