summaryrefslogtreecommitdiff
path: root/arch/arm64/crypto/crct10dif-ce-glue.c
diff options
context:
space:
mode:
authorArd Biesheuvel <ard.biesheuvel@linaro.org>2016-12-05 21:42:25 +0300
committerHerbert Xu <herbert@gondor.apana.org.au>2016-12-07 15:01:17 +0300
commit6ef5737f39314907704d68719b74fcca11f4f342 (patch)
tree1ce4d03f889994e39b80aa55df7f31b1c84cbf6a /arch/arm64/crypto/crct10dif-ce-glue.c
parentd31de187acdd7758cbb07c8d7dd3293e8c2d8390 (diff)
downloadlinux-6ef5737f39314907704d68719b74fcca11f4f342.tar.xz
crypto: arm64/crct10dif - port x86 SSE implementation to arm64
This is a transliteration of the Intel algorithm implemented using SSE and PCLMULQDQ instructions that resides in the file arch/x86/crypto/crct10dif-pcl-asm_64.S, but simplified to only operate on buffers that are 16 byte aligned (but of any size) Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Diffstat (limited to 'arch/arm64/crypto/crct10dif-ce-glue.c')
-rw-r--r--arch/arm64/crypto/crct10dif-ce-glue.c95
1 files changed, 95 insertions, 0 deletions
diff --git a/arch/arm64/crypto/crct10dif-ce-glue.c b/arch/arm64/crypto/crct10dif-ce-glue.c
new file mode 100644
index 000000000000..60cb590c2590
--- /dev/null
+++ b/arch/arm64/crypto/crct10dif-ce-glue.c
@@ -0,0 +1,95 @@
+/*
+ * Accelerated CRC-T10DIF using arm64 NEON and Crypto Extensions instructions
+ *
+ * Copyright (C) 2016 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/cpufeature.h>
+#include <linux/crc-t10dif.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/string.h>
+
+#include <crypto/internal/hash.h>
+
+#include <asm/neon.h>
+
+#define CRC_T10DIF_PMULL_CHUNK_SIZE 16U
+
+asmlinkage u16 crc_t10dif_pmull(u16 init_crc, const u8 buf[], u64 len);
+
+static int crct10dif_init(struct shash_desc *desc)
+{
+ u16 *crc = shash_desc_ctx(desc);
+
+ *crc = 0;
+ return 0;
+}
+
+static int crct10dif_update(struct shash_desc *desc, const u8 *data,
+ unsigned int length)
+{
+ u16 *crc = shash_desc_ctx(desc);
+ unsigned int l;
+
+ if (unlikely((u64)data % CRC_T10DIF_PMULL_CHUNK_SIZE)) {
+ l = min_t(u32, length, CRC_T10DIF_PMULL_CHUNK_SIZE -
+ ((u64)data % CRC_T10DIF_PMULL_CHUNK_SIZE));
+
+ *crc = crc_t10dif_generic(*crc, data, l);
+
+ length -= l;
+ data += l;
+ }
+
+ if (length > 0) {
+ kernel_neon_begin_partial(14);
+ *crc = crc_t10dif_pmull(*crc, data, length);
+ kernel_neon_end();
+ }
+
+ return 0;
+}
+
+static int crct10dif_final(struct shash_desc *desc, u8 *out)
+{
+ u16 *crc = shash_desc_ctx(desc);
+
+ *(u16 *)out = *crc;
+ return 0;
+}
+
+static struct shash_alg crc_t10dif_alg = {
+ .digestsize = CRC_T10DIF_DIGEST_SIZE,
+ .init = crct10dif_init,
+ .update = crct10dif_update,
+ .final = crct10dif_final,
+ .descsize = CRC_T10DIF_DIGEST_SIZE,
+
+ .base.cra_name = "crct10dif",
+ .base.cra_driver_name = "crct10dif-arm64-ce",
+ .base.cra_priority = 200,
+ .base.cra_blocksize = CRC_T10DIF_BLOCK_SIZE,
+ .base.cra_module = THIS_MODULE,
+};
+
+static int __init crc_t10dif_mod_init(void)
+{
+ return crypto_register_shash(&crc_t10dif_alg);
+}
+
+static void __exit crc_t10dif_mod_exit(void)
+{
+ crypto_unregister_shash(&crc_t10dif_alg);
+}
+
+module_cpu_feature_match(PMULL, crc_t10dif_mod_init);
+module_exit(crc_t10dif_mod_exit);
+
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");