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, 102 insertions, 0 deletions

diff --git a/include/crypto/chacha.h b/include/crypto/chacha.h
new file mode 100644
index 000000000..1cc301a48
--- /dev/null
+++ b/include/crypto/chacha.h
@@ -0,0 +1,102 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Common values and helper functions for the ChaCha and XChaCha stream ciphers.
+ *
+ * XChaCha extends ChaCha's nonce to 192 bits, while provably retaining ChaCha's
+ * security.  Here they share the same key size, tfm context, and setkey
+ * function; only their IV size and encrypt/decrypt function differ.
+ *
+ * The ChaCha paper specifies 20, 12, and 8-round variants.  In general, it is
+ * recommended to use the 20-round variant ChaCha20.  However, the other
+ * variants can be needed in some performance-sensitive scenarios.  The generic
+ * ChaCha code currently allows only the 20 and 12-round variants.
+ */
+
+#ifndef _CRYPTO_CHACHA_H
+#define _CRYPTO_CHACHA_H
+
+#include <linux/unaligned.h>
+#include <linux/string.h>
+#include <linux/types.h>
+
+/* 32-bit stream position, then 96-bit nonce (RFC7539 convention) */
+#define CHACHA_IV_SIZE		16
+
+#define CHACHA_KEY_SIZE		32
+#define CHACHA_BLOCK_SIZE	64
+#define CHACHAPOLY_IV_SIZE	12
+
+#define CHACHA_KEY_WORDS	8
+#define CHACHA_STATE_WORDS	16
+#define HCHACHA_OUT_WORDS	8
+
+/* 192-bit nonce, then 64-bit stream position */
+#define XCHACHA_IV_SIZE		32
+
+struct chacha_state {
+	u32 x[CHACHA_STATE_WORDS];
+};
+
+void chacha_block_generic(struct chacha_state *state,
+			  u8 out[at_least CHACHA_BLOCK_SIZE], int nrounds);
+static inline void chacha20_block(struct chacha_state *state,
+				  u8 out[at_least CHACHA_BLOCK_SIZE])
+{
+	chacha_block_generic(state, out, 20);
+}
+
+void hchacha_block_generic(const struct chacha_state *state,
+			   u32 out[at_least HCHACHA_OUT_WORDS], int nrounds);
+
+void hchacha_block(const struct chacha_state *state,
+		   u32 out[at_least HCHACHA_OUT_WORDS], int nrounds);
+
+enum chacha_constants { /* expand 32-byte k */
+	CHACHA_CONSTANT_EXPA = 0x61707865U,
+	CHACHA_CONSTANT_ND_3 = 0x3320646eU,
+	CHACHA_CONSTANT_2_BY = 0x79622d32U,
+	CHACHA_CONSTANT_TE_K = 0x6b206574U
+};
+
+static inline void chacha_init_consts(struct chacha_state *state)
+{
+	state->x[0]  = CHACHA_CONSTANT_EXPA;
+	state->x[1]  = CHACHA_CONSTANT_ND_3;
+	state->x[2]  = CHACHA_CONSTANT_2_BY;
+	state->x[3]  = CHACHA_CONSTANT_TE_K;
+}
+
+static inline void chacha_init(struct chacha_state *state,
+			       const u32 key[at_least CHACHA_KEY_WORDS],
+			       const u8 iv[at_least CHACHA_IV_SIZE])
+{
+	chacha_init_consts(state);
+	state->x[4]  = key[0];
+	state->x[5]  = key[1];
+	state->x[6]  = key[2];
+	state->x[7]  = key[3];
+	state->x[8]  = key[4];
+	state->x[9]  = key[5];
+	state->x[10] = key[6];
+	state->x[11] = key[7];
+	state->x[12] = get_unaligned_le32(iv +  0);
+	state->x[13] = get_unaligned_le32(iv +  4);
+	state->x[14] = get_unaligned_le32(iv +  8);
+	state->x[15] = get_unaligned_le32(iv + 12);
+}
+
+void chacha_crypt(struct chacha_state *state, u8 *dst, const u8 *src,
+		  unsigned int bytes, int nrounds);
+
+static inline void chacha20_crypt(struct chacha_state *state,
+				  u8 *dst, const u8 *src, unsigned int bytes)
+{
+	chacha_crypt(state, dst, src, bytes, 20);
+}
+
+static inline void chacha_zeroize_state(struct chacha_state *state)
+{
+	memzero_explicit(state, sizeof(*state));
+}
+
+#endif /* _CRYPTO_CHACHA_H */