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, 191 insertions, 0 deletions

diff --git a/crypto/xctr.c b/crypto/xctr.c
new file mode 100644
index 000000000..607ab82cb
--- /dev/null
+++ b/crypto/xctr.c
@@ -0,0 +1,191 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * XCTR: XOR Counter mode - Adapted from ctr.c
+ *
+ * (C) Copyright IBM Corp. 2007 - Joy Latten <latten@us.ibm.com>
+ * Copyright 2021 Google LLC
+ */
+
+/*
+ * XCTR mode is a blockcipher mode of operation used to implement HCTR2. XCTR is
+ * closely related to the CTR mode of operation; the main difference is that CTR
+ * generates the keystream using E(CTR + IV) whereas XCTR generates the
+ * keystream using E(CTR ^ IV). This allows implementations to avoid dealing
+ * with multi-limb integers (as is required in CTR mode). XCTR is also specified
+ * using little-endian arithmetic which makes it slightly faster on LE machines.
+ *
+ * See the HCTR2 paper for more details:
+ *	Length-preserving encryption with HCTR2
+ *      (https://eprint.iacr.org/2021/1441.pdf)
+ */
+
+#include <crypto/algapi.h>
+#include <crypto/internal/cipher.h>
+#include <crypto/internal/skcipher.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+
+/* For now this implementation is limited to 16-byte blocks for simplicity */
+#define XCTR_BLOCKSIZE 16
+
+static void crypto_xctr_crypt_final(struct skcipher_walk *walk,
+				   struct crypto_cipher *tfm, u32 byte_ctr)
+{
+	u8 keystream[XCTR_BLOCKSIZE];
+	const u8 *src = walk->src.virt.addr;
+	u8 *dst = walk->dst.virt.addr;
+	unsigned int nbytes = walk->nbytes;
+	__le32 ctr32 = cpu_to_le32(byte_ctr / XCTR_BLOCKSIZE + 1);
+
+	crypto_xor(walk->iv, (u8 *)&ctr32, sizeof(ctr32));
+	crypto_cipher_encrypt_one(tfm, keystream, walk->iv);
+	crypto_xor_cpy(dst, keystream, src, nbytes);
+	crypto_xor(walk->iv, (u8 *)&ctr32, sizeof(ctr32));
+}
+
+static int crypto_xctr_crypt_segment(struct skcipher_walk *walk,
+				    struct crypto_cipher *tfm, u32 byte_ctr)
+{
+	void (*fn)(struct crypto_tfm *, u8 *, const u8 *) =
+		   crypto_cipher_alg(tfm)->cia_encrypt;
+	const u8 *src = walk->src.virt.addr;
+	u8 *dst = walk->dst.virt.addr;
+	unsigned int nbytes = walk->nbytes;
+	__le32 ctr32 = cpu_to_le32(byte_ctr / XCTR_BLOCKSIZE + 1);
+
+	do {
+		crypto_xor(walk->iv, (u8 *)&ctr32, sizeof(ctr32));
+		fn(crypto_cipher_tfm(tfm), dst, walk->iv);
+		crypto_xor(dst, src, XCTR_BLOCKSIZE);
+		crypto_xor(walk->iv, (u8 *)&ctr32, sizeof(ctr32));
+
+		le32_add_cpu(&ctr32, 1);
+
+		src += XCTR_BLOCKSIZE;
+		dst += XCTR_BLOCKSIZE;
+	} while ((nbytes -= XCTR_BLOCKSIZE) >= XCTR_BLOCKSIZE);
+
+	return nbytes;
+}
+
+static int crypto_xctr_crypt_inplace(struct skcipher_walk *walk,
+				    struct crypto_cipher *tfm, u32 byte_ctr)
+{
+	void (*fn)(struct crypto_tfm *, u8 *, const u8 *) =
+		   crypto_cipher_alg(tfm)->cia_encrypt;
+	unsigned long alignmask = crypto_cipher_alignmask(tfm);
+	unsigned int nbytes = walk->nbytes;
+	u8 *data = walk->dst.virt.addr;
+	u8 tmp[XCTR_BLOCKSIZE + MAX_CIPHER_ALIGNMASK];
+	u8 *keystream = PTR_ALIGN(tmp + 0, alignmask + 1);
+	__le32 ctr32 = cpu_to_le32(byte_ctr / XCTR_BLOCKSIZE + 1);
+
+	do {
+		crypto_xor(walk->iv, (u8 *)&ctr32, sizeof(ctr32));
+		fn(crypto_cipher_tfm(tfm), keystream, walk->iv);
+		crypto_xor(data, keystream, XCTR_BLOCKSIZE);
+		crypto_xor(walk->iv, (u8 *)&ctr32, sizeof(ctr32));
+
+		le32_add_cpu(&ctr32, 1);
+
+		data += XCTR_BLOCKSIZE;
+	} while ((nbytes -= XCTR_BLOCKSIZE) >= XCTR_BLOCKSIZE);
+
+	return nbytes;
+}
+
+static int crypto_xctr_crypt(struct skcipher_request *req)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct crypto_cipher *cipher = skcipher_cipher_simple(tfm);
+	struct skcipher_walk walk;
+	unsigned int nbytes;
+	int err;
+	u32 byte_ctr = 0;
+
+	err = skcipher_walk_virt(&walk, req, false);
+
+	while (walk.nbytes >= XCTR_BLOCKSIZE) {
+		if (walk.src.virt.addr == walk.dst.virt.addr)
+			nbytes = crypto_xctr_crypt_inplace(&walk, cipher,
+							   byte_ctr);
+		else
+			nbytes = crypto_xctr_crypt_segment(&walk, cipher,
+							   byte_ctr);
+
+		byte_ctr += walk.nbytes - nbytes;
+		err = skcipher_walk_done(&walk, nbytes);
+	}
+
+	if (walk.nbytes) {
+		crypto_xctr_crypt_final(&walk, cipher, byte_ctr);
+		err = skcipher_walk_done(&walk, 0);
+	}
+
+	return err;
+}
+
+static int crypto_xctr_create(struct crypto_template *tmpl, struct rtattr **tb)
+{
+	struct skcipher_instance *inst;
+	struct crypto_alg *alg;
+	int err;
+
+	inst = skcipher_alloc_instance_simple(tmpl, tb);
+	if (IS_ERR(inst))
+		return PTR_ERR(inst);
+
+	alg = skcipher_ialg_simple(inst);
+
+	/* Block size must be 16 bytes. */
+	err = -EINVAL;
+	if (alg->cra_blocksize != XCTR_BLOCKSIZE)
+		goto out_free_inst;
+
+	/* XCTR mode is a stream cipher. */
+	inst->alg.base.cra_blocksize = 1;
+
+	/*
+	 * To simplify the implementation, configure the skcipher walk to only
+	 * give a partial block at the very end, never earlier.
+	 */
+	inst->alg.chunksize = alg->cra_blocksize;
+
+	inst->alg.encrypt = crypto_xctr_crypt;
+	inst->alg.decrypt = crypto_xctr_crypt;
+
+	err = skcipher_register_instance(tmpl, inst);
+	if (err) {
+out_free_inst:
+		inst->free(inst);
+	}
+
+	return err;
+}
+
+static struct crypto_template crypto_xctr_tmpl = {
+	.name = "xctr",
+	.create = crypto_xctr_create,
+	.module = THIS_MODULE,
+};
+
+static int __init crypto_xctr_module_init(void)
+{
+	return crypto_register_template(&crypto_xctr_tmpl);
+}
+
+static void __exit crypto_xctr_module_exit(void)
+{
+	crypto_unregister_template(&crypto_xctr_tmpl);
+}
+
+module_init(crypto_xctr_module_init);
+module_exit(crypto_xctr_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("XCTR block cipher mode of operation");
+MODULE_ALIAS_CRYPTO("xctr");
+MODULE_IMPORT_NS("CRYPTO_INTERNAL");