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, 84 insertions, 0 deletions

diff --git a/include/net/gen_stats.h b/include/net/gen_stats.h
new file mode 100644
index 000000000..856b5e90f
--- /dev/null
+++ b/include/net/gen_stats.h
@@ -0,0 +1,84 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __NET_GEN_STATS_H
+#define __NET_GEN_STATS_H
+
+#include <linux/gen_stats.h>
+#include <linux/socket.h>
+#include <linux/rtnetlink.h>
+#include <linux/pkt_sched.h>
+
+/* Throughput stats.
+ * Must be initialized beforehand with gnet_stats_basic_sync_init().
+ *
+ * If no reads can ever occur parallel to writes (e.g. stack-allocated
+ * bstats), then the internal stat values can be written to and read
+ * from directly. Otherwise, use _bstats_set/update() for writes and
+ * gnet_stats_add_basic() for reads.
+ */
+struct gnet_stats_basic_sync {
+	u64_stats_t bytes;
+	u64_stats_t packets;
+	struct u64_stats_sync syncp;
+} __aligned(2 * sizeof(u64));
+
+struct net_rate_estimator;
+
+struct gnet_dump {
+	spinlock_t *      lock;
+	struct sk_buff *  skb;
+	struct nlattr *   tail;
+
+	/* Backward compatibility */
+	int               compat_tc_stats;
+	int               compat_xstats;
+	int               padattr;
+	void *            xstats;
+	int               xstats_len;
+	struct tc_stats   tc_stats;
+};
+
+void gnet_stats_basic_sync_init(struct gnet_stats_basic_sync *b);
+int gnet_stats_start_copy(struct sk_buff *skb, int type, spinlock_t *lock,
+			  struct gnet_dump *d, int padattr);
+
+int gnet_stats_start_copy_compat(struct sk_buff *skb, int type,
+				 int tc_stats_type, int xstats_type,
+				 spinlock_t *lock, struct gnet_dump *d,
+				 int padattr);
+
+int gnet_stats_copy_basic(struct gnet_dump *d,
+			  const struct gnet_stats_basic_sync __percpu *cpu,
+			  const struct gnet_stats_basic_sync *b, bool running);
+void gnet_stats_add_basic(struct gnet_stats_basic_sync *bstats,
+			  const struct gnet_stats_basic_sync __percpu *cpu,
+			  const struct gnet_stats_basic_sync *b, bool running);
+int gnet_stats_copy_basic_hw(struct gnet_dump *d,
+			     const struct gnet_stats_basic_sync __percpu *cpu,
+			     const struct gnet_stats_basic_sync *b, bool running);
+int gnet_stats_copy_rate_est(struct gnet_dump *d,
+			     struct net_rate_estimator __rcu **ptr);
+int gnet_stats_copy_queue(struct gnet_dump *d,
+			  const struct gnet_stats_queue __percpu *cpu_q,
+			  const struct gnet_stats_queue *q, __u32 qlen);
+void gnet_stats_add_queue(struct gnet_stats_queue *qstats,
+			  const struct gnet_stats_queue __percpu *cpu_q,
+			  const struct gnet_stats_queue *q);
+int gnet_stats_copy_app(struct gnet_dump *d, void *st, int len);
+
+int gnet_stats_finish_copy(struct gnet_dump *d);
+
+int gen_new_estimator(struct gnet_stats_basic_sync *bstats,
+		      struct gnet_stats_basic_sync __percpu *cpu_bstats,
+		      struct net_rate_estimator __rcu **rate_est,
+		      spinlock_t *lock,
+		      bool running, struct nlattr *opt);
+void gen_kill_estimator(struct net_rate_estimator __rcu **ptr);
+int gen_replace_estimator(struct gnet_stats_basic_sync *bstats,
+			  struct gnet_stats_basic_sync __percpu *cpu_bstats,
+			  struct net_rate_estimator __rcu **ptr,
+			  spinlock_t *lock,
+			  bool running, struct nlattr *opt);
+bool gen_estimator_active(struct net_rate_estimator __rcu **ptr);
+bool gen_estimator_read(struct net_rate_estimator __rcu **ptr,
+			struct gnet_stats_rate_est64 *sample);
+#endif