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, 80 insertions, 0 deletions

diff --git a/include/uapi/misc/ocxl.h b/include/uapi/misc/ocxl.h
new file mode 100644
index 000000000..6d29a60a8
--- /dev/null
+++ b/include/uapi/misc/ocxl.h
@@ -0,0 +1,80 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/* Copyright 2017 IBM Corp. */
+#ifndef _UAPI_MISC_OCXL_H
+#define _UAPI_MISC_OCXL_H
+
+#include <linux/types.h>
+#include <linux/ioctl.h>
+
+enum ocxl_event_type {
+	OCXL_AFU_EVENT_XSL_FAULT_ERROR = 0,
+};
+
+#define OCXL_KERNEL_EVENT_FLAG_LAST 0x0001  /* This is the last event pending */
+
+struct ocxl_kernel_event_header {
+	__u16 type;
+	__u16 flags;
+	__u32 reserved;
+};
+
+struct ocxl_kernel_event_xsl_fault_error {
+	__u64 addr;
+	__u64 dsisr;
+	__u64 count;
+	__u64 reserved;
+};
+
+struct ocxl_ioctl_attach {
+	__u64 amr;
+	__u64 reserved1;
+	__u64 reserved2;
+	__u64 reserved3;
+};
+
+struct ocxl_ioctl_metadata {
+	__u16 version; /* struct version, always backwards compatible */
+
+	/* Version 0 fields */
+	__u8  afu_version_major;
+	__u8  afu_version_minor;
+	__u32 pasid;		/* PASID assigned to the current context */
+
+	__u64 pp_mmio_size;	/* Per PASID MMIO size */
+	__u64 global_mmio_size;
+
+	/* End version 0 fields */
+
+	__u64 reserved[13]; /* Total of 16*u64 */
+};
+
+struct ocxl_ioctl_p9_wait {
+	__u16 thread_id; /* The thread ID required to wake this thread */
+	__u16 reserved1;
+	__u32 reserved2;
+	__u64 reserved3[3];
+};
+
+#define OCXL_IOCTL_FEATURES_FLAGS0_P9_WAIT	0x01
+struct ocxl_ioctl_features {
+	__u64 flags[4];
+};
+
+struct ocxl_ioctl_irq_fd {
+	__u64 irq_offset;
+	__s32 eventfd;
+	__u32 reserved;
+};
+
+/* ioctl numbers */
+#define OCXL_MAGIC 0xCA
+/* AFU devices */
+#define OCXL_IOCTL_ATTACH	_IOW(OCXL_MAGIC, 0x10, struct ocxl_ioctl_attach)
+#define OCXL_IOCTL_IRQ_ALLOC	_IOR(OCXL_MAGIC, 0x11, __u64)
+#define OCXL_IOCTL_IRQ_FREE	_IOW(OCXL_MAGIC, 0x12, __u64)
+#define OCXL_IOCTL_IRQ_SET_FD	_IOW(OCXL_MAGIC, 0x13, struct ocxl_ioctl_irq_fd)
+#define OCXL_IOCTL_GET_METADATA _IOR(OCXL_MAGIC, 0x14, struct ocxl_ioctl_metadata)
+#define OCXL_IOCTL_ENABLE_P9_WAIT	_IOR(OCXL_MAGIC, 0x15, struct ocxl_ioctl_p9_wait)
+#define OCXL_IOCTL_GET_FEATURES _IOR(OCXL_MAGIC, 0x16, struct ocxl_ioctl_features)
+
+#endif /* _UAPI_MISC_OCXL_H */