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, 135 insertions, 0 deletions

diff --git a/include/net/pie.h b/include/net/pie.h
new file mode 100644
index 000000000..1f3db0c35
--- /dev/null
+++ b/include/net/pie.h
@@ -0,0 +1,135 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef __NET_SCHED_PIE_H
+#define __NET_SCHED_PIE_H
+
+#include <linux/ktime.h>
+#include <linux/skbuff.h>
+#include <linux/types.h>
+#include <net/inet_ecn.h>
+#include <net/pkt_sched.h>
+
+#define MAX_PROB	(U64_MAX >> BITS_PER_BYTE)
+#define DTIME_INVALID	U64_MAX
+#define QUEUE_THRESHOLD	16384
+#define DQCOUNT_INVALID	-1
+#define PIE_SCALE	8
+
+/**
+ * struct pie_params - contains pie parameters
+ * @target:		target delay in pschedtime
+ * @tupdate:		interval at which drop probability is calculated
+ * @limit:		total number of packets that can be in the queue
+ * @alpha:		parameter to control drop probability
+ * @beta:		parameter to control drop probability
+ * @ecn:		is ECN marking of packets enabled
+ * @bytemode:		is drop probability scaled based on pkt size
+ * @dq_rate_estimator:	is Little's law used for qdelay calculation
+ */
+struct pie_params {
+	psched_time_t target;
+	u32 tupdate;
+	u32 limit;
+	u32 alpha;
+	u32 beta;
+	u8 ecn;
+	u8 bytemode;
+	u8 dq_rate_estimator;
+};
+
+/**
+ * struct pie_vars - contains pie variables
+ * @qdelay:		current queue delay
+ * @qdelay_old:		queue delay in previous qdelay calculation
+ * @burst_time:		burst time allowance
+ * @dq_tstamp:		timestamp at which dq rate was last calculated
+ * @prob:		drop probability
+ * @accu_prob:		accumulated drop probability
+ * @dq_count:		number of bytes dequeued in a measurement cycle
+ * @avg_dq_rate:	calculated average dq rate
+ * @backlog_old:	queue backlog during previous qdelay calculation
+ */
+struct pie_vars {
+	psched_time_t qdelay;
+	psched_time_t qdelay_old;
+	psched_time_t burst_time;
+	psched_time_t dq_tstamp;
+	u64 prob;
+	u64 accu_prob;
+	u64 dq_count;
+	u32 avg_dq_rate;
+	u32 backlog_old;
+};
+
+/**
+ * struct pie_stats - contains pie stats
+ * @packets_in:	total number of packets enqueued
+ * @dropped:	packets dropped due to pie action
+ * @overlimit:	packets dropped due to lack of space in queue
+ * @ecn_mark:	packets marked with ECN
+ * @maxq:	maximum queue size
+ */
+struct pie_stats {
+	u32 packets_in;
+	u32 dropped;
+	u32 overlimit;
+	u32 ecn_mark;
+	u32 maxq;
+};
+
+/**
+ * struct pie_skb_cb - contains private skb vars
+ * @enqueue_time:	timestamp when the packet is enqueued
+ * @mem_usage:		size of the skb during enqueue
+ */
+struct pie_skb_cb {
+	psched_time_t enqueue_time;
+	u32 mem_usage;
+};
+
+static inline void pie_params_init(struct pie_params *params)
+{
+	params->target = PSCHED_NS2TICKS(15 * NSEC_PER_MSEC);	/* 15 ms */
+	params->tupdate = usecs_to_jiffies(15 * USEC_PER_MSEC);	/* 15 ms */
+	params->limit = 1000;
+	params->alpha = 2;
+	params->beta = 20;
+	params->ecn = false;
+	params->bytemode = false;
+	params->dq_rate_estimator = false;
+}
+
+static inline void pie_vars_init(struct pie_vars *vars)
+{
+	vars->burst_time = PSCHED_NS2TICKS(150 * NSEC_PER_MSEC); /* 150 ms */
+	vars->dq_tstamp = DTIME_INVALID;
+	vars->accu_prob = 0;
+	vars->dq_count = DQCOUNT_INVALID;
+	WRITE_ONCE(vars->avg_dq_rate, 0);
+}
+
+static inline struct pie_skb_cb *get_pie_cb(const struct sk_buff *skb)
+{
+	qdisc_cb_private_validate(skb, sizeof(struct pie_skb_cb));
+	return (struct pie_skb_cb *)qdisc_skb_cb(skb)->data;
+}
+
+static inline psched_time_t pie_get_enqueue_time(const struct sk_buff *skb)
+{
+	return get_pie_cb(skb)->enqueue_time;
+}
+
+static inline void pie_set_enqueue_time(struct sk_buff *skb)
+{
+	get_pie_cb(skb)->enqueue_time = psched_get_time();
+}
+
+bool pie_drop_early(struct Qdisc *sch, struct pie_params *params,
+		    struct pie_vars *vars, u32 backlog, u32 packet_size);
+
+void pie_process_dequeue(struct sk_buff *skb, struct pie_params *params,
+			 struct pie_vars *vars, u32 backlog);
+
+void pie_calculate_probability(struct pie_params *params, struct pie_vars *vars,
+			       u32 backlog);
+
+#endif