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, 101 insertions, 0 deletions

diff --git a/include/net/fq.h b/include/net/fq.h
new file mode 100644
index 000000000..99fbe4127
--- /dev/null
+++ b/include/net/fq.h
@@ -0,0 +1,101 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2016 Qualcomm Atheros, Inc
+ *
+ * Based on net/sched/sch_fq_codel.c
+ */
+#ifndef __NET_SCHED_FQ_H
+#define __NET_SCHED_FQ_H
+
+#include <linux/skbuff.h>
+#include <linux/spinlock.h>
+#include <linux/types.h>
+
+struct fq_tin;
+
+/**
+ * struct fq_flow - per traffic flow queue
+ *
+ * @tin: owner of this flow. Used to manage collisions, i.e. when a packet
+ *	hashes to an index which points to a flow that is already owned by a
+ *	different tin the packet is destined to. In such case the implementer
+ *	must provide a fallback flow
+ * @flowchain: can be linked to fq_tin's new_flows or old_flows. Used for DRR++
+ *	(deficit round robin) based round robin queuing similar to the one
+ *	found in net/sched/sch_fq_codel.c
+ * @queue: sk_buff queue to hold packets
+ * @backlog: number of bytes pending in the queue. The number of packets can be
+ *	found in @queue.qlen
+ * @deficit: used for DRR++
+ */
+struct fq_flow {
+	struct fq_tin *tin;
+	struct list_head flowchain;
+	struct sk_buff_head queue;
+	u32 backlog;
+	int deficit;
+};
+
+/**
+ * struct fq_tin - a logical container of fq_flows
+ *
+ * Used to group fq_flows into a logical aggregate. DRR++ scheme is used to
+ * pull interleaved packets out of the associated flows.
+ *
+ * @new_flows: linked list of fq_flow
+ * @old_flows: linked list of fq_flow
+ */
+struct fq_tin {
+	struct list_head new_flows;
+	struct list_head old_flows;
+	struct list_head tin_list;
+	struct fq_flow default_flow;
+	u32 backlog_bytes;
+	u32 backlog_packets;
+	u32 overlimit;
+	u32 collisions;
+	u32 flows;
+	u32 tx_bytes;
+	u32 tx_packets;
+};
+
+/**
+ * struct fq - main container for fair queuing purposes
+ *
+ * @limit: max number of packets that can be queued across all flows
+ * @backlog: number of packets queued across all flows
+ */
+struct fq {
+	struct fq_flow *flows;
+	unsigned long *flows_bitmap;
+
+	struct list_head tin_backlog;
+	spinlock_t lock;
+	u32 flows_cnt;
+	u32 limit;
+	u32 memory_limit;
+	u32 memory_usage;
+	u32 quantum;
+	u32 backlog;
+	u32 overlimit;
+	u32 overmemory;
+	u32 collisions;
+};
+
+typedef struct sk_buff *fq_tin_dequeue_t(struct fq *,
+					 struct fq_tin *,
+					 struct fq_flow *flow);
+
+typedef void fq_skb_free_t(struct fq *,
+			   struct fq_tin *,
+			   struct fq_flow *,
+			   struct sk_buff *);
+
+/* Return %true to filter (drop) the frame. */
+typedef bool fq_skb_filter_t(struct fq *,
+			     struct fq_tin *,
+			     struct fq_flow *,
+			     struct sk_buff *,
+			     void *);
+
+#endif