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, 356 insertions, 0 deletions

diff --git a/include/trace/events/compaction.h b/include/trace/events/compaction.h
new file mode 100644
index 000000000..d05759d18
--- /dev/null
+++ b/include/trace/events/compaction.h
@@ -0,0 +1,356 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM compaction
+
+#if !defined(_TRACE_COMPACTION_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_COMPACTION_H
+
+#include <linux/types.h>
+#include <linux/list.h>
+#include <linux/tracepoint.h>
+#include <trace/events/mmflags.h>
+
+
+DECLARE_EVENT_CLASS(mm_compaction_isolate_template,
+
+	TP_PROTO(
+		unsigned long start_pfn,
+		unsigned long end_pfn,
+		unsigned long nr_scanned,
+		unsigned long nr_taken),
+
+	TP_ARGS(start_pfn, end_pfn, nr_scanned, nr_taken),
+
+	TP_STRUCT__entry(
+		__field(unsigned long, start_pfn)
+		__field(unsigned long, end_pfn)
+		__field(unsigned long, nr_scanned)
+		__field(unsigned long, nr_taken)
+	),
+
+	TP_fast_assign(
+		__entry->start_pfn = start_pfn;
+		__entry->end_pfn = end_pfn;
+		__entry->nr_scanned = nr_scanned;
+		__entry->nr_taken = nr_taken;
+	),
+
+	TP_printk("range=(0x%lx ~ 0x%lx) nr_scanned=%lu nr_taken=%lu",
+		__entry->start_pfn,
+		__entry->end_pfn,
+		__entry->nr_scanned,
+		__entry->nr_taken)
+);
+
+DEFINE_EVENT(mm_compaction_isolate_template, mm_compaction_isolate_migratepages,
+
+	TP_PROTO(
+		unsigned long start_pfn,
+		unsigned long end_pfn,
+		unsigned long nr_scanned,
+		unsigned long nr_taken),
+
+	TP_ARGS(start_pfn, end_pfn, nr_scanned, nr_taken)
+);
+
+DEFINE_EVENT(mm_compaction_isolate_template, mm_compaction_isolate_freepages,
+
+	TP_PROTO(
+		unsigned long start_pfn,
+		unsigned long end_pfn,
+		unsigned long nr_scanned,
+		unsigned long nr_taken),
+
+	TP_ARGS(start_pfn, end_pfn, nr_scanned, nr_taken)
+);
+
+DEFINE_EVENT(mm_compaction_isolate_template, mm_compaction_fast_isolate_freepages,
+
+	TP_PROTO(
+		unsigned long start_pfn,
+		unsigned long end_pfn,
+		unsigned long nr_scanned,
+		unsigned long nr_taken),
+
+	TP_ARGS(start_pfn, end_pfn, nr_scanned, nr_taken)
+);
+
+#ifdef CONFIG_COMPACTION
+TRACE_EVENT(mm_compaction_migratepages,
+
+	TP_PROTO(unsigned int nr_migratepages,
+		unsigned int nr_succeeded),
+
+	TP_ARGS(nr_migratepages, nr_succeeded),
+
+	TP_STRUCT__entry(
+		__field(unsigned long, nr_migrated)
+		__field(unsigned long, nr_failed)
+	),
+
+	TP_fast_assign(
+		__entry->nr_migrated = nr_succeeded;
+		__entry->nr_failed = nr_migratepages - nr_succeeded;
+	),
+
+	TP_printk("nr_migrated=%lu nr_failed=%lu",
+		__entry->nr_migrated,
+		__entry->nr_failed)
+);
+
+TRACE_EVENT(mm_compaction_begin,
+	TP_PROTO(struct compact_control *cc, unsigned long zone_start,
+		unsigned long zone_end, bool sync),
+
+	TP_ARGS(cc, zone_start, zone_end, sync),
+
+	TP_STRUCT__entry(
+		__field(unsigned long, zone_start)
+		__field(unsigned long, migrate_pfn)
+		__field(unsigned long, free_pfn)
+		__field(unsigned long, zone_end)
+		__field(bool, sync)
+	),
+
+	TP_fast_assign(
+		__entry->zone_start = zone_start;
+		__entry->migrate_pfn = cc->migrate_pfn;
+		__entry->free_pfn = cc->free_pfn;
+		__entry->zone_end = zone_end;
+		__entry->sync = sync;
+	),
+
+	TP_printk("zone_start=0x%lx migrate_pfn=0x%lx free_pfn=0x%lx zone_end=0x%lx, mode=%s",
+		__entry->zone_start,
+		__entry->migrate_pfn,
+		__entry->free_pfn,
+		__entry->zone_end,
+		__entry->sync ? "sync" : "async")
+);
+
+TRACE_EVENT(mm_compaction_end,
+	TP_PROTO(struct compact_control *cc, unsigned long zone_start,
+		unsigned long zone_end, bool sync,
+		int status),
+
+	TP_ARGS(cc, zone_start, zone_end, sync, status),
+
+	TP_STRUCT__entry(
+		__field(unsigned long, zone_start)
+		__field(unsigned long, migrate_pfn)
+		__field(unsigned long, free_pfn)
+		__field(unsigned long, zone_end)
+		__field(bool, sync)
+		__field(int, status)
+	),
+
+	TP_fast_assign(
+		__entry->zone_start = zone_start;
+		__entry->migrate_pfn = cc->migrate_pfn;
+		__entry->free_pfn = cc->free_pfn;
+		__entry->zone_end = zone_end;
+		__entry->sync = sync;
+		__entry->status = status;
+	),
+
+	TP_printk("zone_start=0x%lx migrate_pfn=0x%lx free_pfn=0x%lx zone_end=0x%lx, mode=%s status=%s",
+		__entry->zone_start,
+		__entry->migrate_pfn,
+		__entry->free_pfn,
+		__entry->zone_end,
+		__entry->sync ? "sync" : "async",
+		__print_symbolic(__entry->status, COMPACTION_STATUS))
+);
+
+TRACE_EVENT(mm_compaction_try_to_compact_pages,
+
+	TP_PROTO(
+		int order,
+		gfp_t gfp_mask,
+		int prio),
+
+	TP_ARGS(order, gfp_mask, prio),
+
+	TP_STRUCT__entry(
+		__field(int, order)
+		__field(unsigned long, gfp_mask)
+		__field(int, prio)
+	),
+
+	TP_fast_assign(
+		__entry->order = order;
+		__entry->gfp_mask = (__force unsigned long)gfp_mask;
+		__entry->prio = prio;
+	),
+
+	TP_printk("order=%d gfp_mask=%s priority=%d",
+		__entry->order,
+		show_gfp_flags(__entry->gfp_mask),
+		__entry->prio)
+);
+
+DECLARE_EVENT_CLASS(mm_compaction_suitable_template,
+
+	TP_PROTO(struct zone *zone,
+		int order,
+		int ret),
+
+	TP_ARGS(zone, order, ret),
+
+	TP_STRUCT__entry(
+		__field(int, nid)
+		__field(enum zone_type, idx)
+		__field(int, order)
+		__field(int, ret)
+	),
+
+	TP_fast_assign(
+		__entry->nid = zone_to_nid(zone);
+		__entry->idx = zone_idx(zone);
+		__entry->order = order;
+		__entry->ret = ret;
+	),
+
+	TP_printk("node=%d zone=%-8s order=%d ret=%s",
+		__entry->nid,
+		__print_symbolic(__entry->idx, ZONE_TYPE),
+		__entry->order,
+		__print_symbolic(__entry->ret, COMPACTION_STATUS))
+);
+
+DEFINE_EVENT(mm_compaction_suitable_template, mm_compaction_finished,
+
+	TP_PROTO(struct zone *zone,
+		int order,
+		int ret),
+
+	TP_ARGS(zone, order, ret)
+);
+
+DEFINE_EVENT(mm_compaction_suitable_template, mm_compaction_suitable,
+
+	TP_PROTO(struct zone *zone,
+		int order,
+		int ret),
+
+	TP_ARGS(zone, order, ret)
+);
+
+DECLARE_EVENT_CLASS(mm_compaction_defer_template,
+
+	TP_PROTO(struct zone *zone, int order),
+
+	TP_ARGS(zone, order),
+
+	TP_STRUCT__entry(
+		__field(int, nid)
+		__field(enum zone_type, idx)
+		__field(int, order)
+		__field(unsigned int, considered)
+		__field(unsigned int, defer_shift)
+		__field(int, order_failed)
+	),
+
+	TP_fast_assign(
+		__entry->nid = zone_to_nid(zone);
+		__entry->idx = zone_idx(zone);
+		__entry->order = order;
+		__entry->considered = zone->compact_considered;
+		__entry->defer_shift = zone->compact_defer_shift;
+		__entry->order_failed = zone->compact_order_failed;
+	),
+
+	TP_printk("node=%d zone=%-8s order=%d order_failed=%d consider=%u limit=%lu",
+		__entry->nid,
+		__print_symbolic(__entry->idx, ZONE_TYPE),
+		__entry->order,
+		__entry->order_failed,
+		__entry->considered,
+		1UL << __entry->defer_shift)
+);
+
+DEFINE_EVENT(mm_compaction_defer_template, mm_compaction_deferred,
+
+	TP_PROTO(struct zone *zone, int order),
+
+	TP_ARGS(zone, order)
+);
+
+DEFINE_EVENT(mm_compaction_defer_template, mm_compaction_defer_compaction,
+
+	TP_PROTO(struct zone *zone, int order),
+
+	TP_ARGS(zone, order)
+);
+
+DEFINE_EVENT(mm_compaction_defer_template, mm_compaction_defer_reset,
+
+	TP_PROTO(struct zone *zone, int order),
+
+	TP_ARGS(zone, order)
+);
+
+TRACE_EVENT(mm_compaction_kcompactd_sleep,
+
+	TP_PROTO(int nid),
+
+	TP_ARGS(nid),
+
+	TP_STRUCT__entry(
+		__field(int, nid)
+	),
+
+	TP_fast_assign(
+		__entry->nid = nid;
+	),
+
+	TP_printk("nid=%d", __entry->nid)
+);
+
+DECLARE_EVENT_CLASS(kcompactd_wake_template,
+
+	TP_PROTO(int nid, int order, enum zone_type highest_zoneidx),
+
+	TP_ARGS(nid, order, highest_zoneidx),
+
+	TP_STRUCT__entry(
+		__field(int, nid)
+		__field(int, order)
+		__field(enum zone_type, highest_zoneidx)
+	),
+
+	TP_fast_assign(
+		__entry->nid = nid;
+		__entry->order = order;
+		__entry->highest_zoneidx = highest_zoneidx;
+	),
+
+	/*
+	 * classzone_idx is previous name of the highest_zoneidx.
+	 * Reason not to change it is the ABI requirement of the tracepoint.
+	 */
+	TP_printk("nid=%d order=%d classzone_idx=%-8s",
+		__entry->nid,
+		__entry->order,
+		__print_symbolic(__entry->highest_zoneidx, ZONE_TYPE))
+);
+
+DEFINE_EVENT(kcompactd_wake_template, mm_compaction_wakeup_kcompactd,
+
+	TP_PROTO(int nid, int order, enum zone_type highest_zoneidx),
+
+	TP_ARGS(nid, order, highest_zoneidx)
+);
+
+DEFINE_EVENT(kcompactd_wake_template, mm_compaction_kcompactd_wake,
+
+	TP_PROTO(int nid, int order, enum zone_type highest_zoneidx),
+
+	TP_ARGS(nid, order, highest_zoneidx)
+);
+#endif
+
+#endif /* _TRACE_COMPACTION_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>