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, 124 insertions, 0 deletions

diff --git a/include/trace/events/timestamp.h b/include/trace/events/timestamp.h
new file mode 100644
index 000000000..d6503612d
--- /dev/null
+++ b/include/trace/events/timestamp.h
@@ -0,0 +1,124 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM timestamp
+
+#if !defined(_TRACE_TIMESTAMP_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_TIMESTAMP_H
+
+#include <linux/tracepoint.h>
+#include <linux/fs.h>
+
+#define CTIME_QUERIED_FLAGS \
+	{ I_CTIME_QUERIED, "Q" }
+
+DECLARE_EVENT_CLASS(ctime,
+	TP_PROTO(struct inode *inode,
+		 struct timespec64 *ctime),
+
+	TP_ARGS(inode, ctime),
+
+	TP_STRUCT__entry(
+		__field(u64,		ino)
+		__field(time64_t,	ctime_s)
+		__field(dev_t,		dev)
+		__field(u32,		ctime_ns)
+		__field(u32,		gen)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= inode->i_sb->s_dev;
+		__entry->ino		= inode->i_ino;
+		__entry->gen		= inode->i_generation;
+		__entry->ctime_s	= ctime->tv_sec;
+		__entry->ctime_ns	= ctime->tv_nsec;
+	),
+
+	TP_printk("ino=%d:%d:%llu:%u ctime=%lld.%u",
+		MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->gen,
+		__entry->ctime_s, __entry->ctime_ns
+	)
+);
+
+DEFINE_EVENT(ctime, inode_set_ctime_to_ts,
+		TP_PROTO(struct inode *inode,
+			 struct timespec64 *ctime),
+		TP_ARGS(inode, ctime));
+
+DEFINE_EVENT(ctime, ctime_xchg_skip,
+		TP_PROTO(struct inode *inode,
+			 struct timespec64 *ctime),
+		TP_ARGS(inode, ctime));
+
+TRACE_EVENT(ctime_ns_xchg,
+	TP_PROTO(struct inode *inode,
+		 u32 old,
+		 u32 new,
+		 u32 cur),
+
+	TP_ARGS(inode, old, new, cur),
+
+	TP_STRUCT__entry(
+		__field(u64,		ino)
+		__field(dev_t,		dev)
+		__field(u32,		gen)
+		__field(u32,		old)
+		__field(u32,		new)
+		__field(u32,		cur)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= inode->i_sb->s_dev;
+		__entry->ino		= inode->i_ino;
+		__entry->gen		= inode->i_generation;
+		__entry->old		= old;
+		__entry->new		= new;
+		__entry->cur		= cur;
+	),
+
+	TP_printk("ino=%d:%d:%llu:%u old=%u:%s new=%u cur=%u:%s",
+		MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->gen,
+		__entry->old & ~I_CTIME_QUERIED,
+		__print_flags(__entry->old & I_CTIME_QUERIED, "|", CTIME_QUERIED_FLAGS),
+		__entry->new,
+		__entry->cur & ~I_CTIME_QUERIED,
+		__print_flags(__entry->cur & I_CTIME_QUERIED, "|", CTIME_QUERIED_FLAGS)
+	)
+);
+
+TRACE_EVENT(fill_mg_cmtime,
+	TP_PROTO(struct inode *inode,
+		 struct timespec64 *ctime,
+		 struct timespec64 *mtime),
+
+	TP_ARGS(inode, ctime, mtime),
+
+	TP_STRUCT__entry(
+		__field(u64,		ino)
+		__field(time64_t,	ctime_s)
+		__field(time64_t,	mtime_s)
+		__field(dev_t,		dev)
+		__field(u32,		ctime_ns)
+		__field(u32,		mtime_ns)
+		__field(u32,		gen)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= inode->i_sb->s_dev;
+		__entry->ino		= inode->i_ino;
+		__entry->gen		= inode->i_generation;
+		__entry->ctime_s	= ctime->tv_sec;
+		__entry->mtime_s	= mtime->tv_sec;
+		__entry->ctime_ns	= ctime->tv_nsec;
+		__entry->mtime_ns	= mtime->tv_nsec;
+	),
+
+	TP_printk("ino=%d:%d:%llu:%u ctime=%lld.%u mtime=%lld.%u",
+		MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->gen,
+		__entry->ctime_s, __entry->ctime_ns,
+		__entry->mtime_s, __entry->mtime_ns
+	)
+);
+#endif /* _TRACE_TIMESTAMP_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>