Update BLAKE3 for using the new impl handling

This commit changes the BLAKE3 implementation handling and
also the calls to it from the ztest command.

Signed-off-by: Tino Reichardt <[email protected]>

Author: mcmilk

cmd/ztest.c

@@ -135,6 +135,7 @@
 #include <libnvpair.h>
 #include <libzutil.h>
 #include <sys/crypto/icp.h>
+#include <sys/zfs_impl.h>
 #if (__GLIBC__ && !__UCLIBC__)
 #include <execinfo.h> /* for backtrace() */
 #endif
@@ -6389,6 +6390,7 @@ ztest_blake3(ztest_ds_t *zd, uint64_t id)
 	int i, *ptr;
 	uint32_t size;
 	BLAKE3_CTX ctx;
+	const zfs_impl_t *blake3 = zfs_impl_get_ops("blake3");
 
 	size = ztest_random_blocksize();
 	buf = umem_alloc(size, UMEM_NOFAIL);
@@ -6413,7 +6415,7 @@ ztest_blake3(ztest_ds_t *zd, uint64_t id)
 		void *res2 = &zc_res2;
 
 		/* BLAKE3_KEY_LEN = 32 */
-		VERIFY0(blake3_set_impl_name("generic"));
+		VERIFY0(blake3->setname("generic"));
 		templ = abd_checksum_blake3_tmpl_init(&salt);
 		Blake3_InitKeyed(&ctx, salt_ptr);
 		Blake3_Update(&ctx, buf, size);
@@ -6422,7 +6424,7 @@ ztest_blake3(ztest_ds_t *zd, uint64_t id)
 		ZIO_CHECKSUM_BSWAP(&zc_ref2);
 		abd_checksum_blake3_tmpl_free(templ);
 
-		VERIFY0(blake3_set_impl_name("cycle"));
+		VERIFY0(blake3->setname("cycle"));
 		while (run_count-- > 0) {
 
 			/* Test current implementation */

include/sys/blake3.h

@@ -22,11 +22,11 @@
 /*
  * Based on BLAKE3 v1.3.1, https://github.com/BLAKE3-team/BLAKE3
  * Copyright (c) 2019-2020 Samuel Neves and Jack O'Connor
- * Copyright (c) 2021 Tino Reichardt <[email protected]>
+ * Copyright (c) 2021-2022 Tino Reichardt <[email protected]>
  */
 
-#ifndef BLAKE3_H
-#define	BLAKE3_H
+#ifndef	_SYS_BLAKE3_H
+#define	_SYS_BLAKE3_H
 
 #ifdef  _KERNEL
 #include <sys/types.h>
@@ -72,7 +72,7 @@ typedef struct {
 	 */
 	uint8_t cv_stack[(BLAKE3_MAX_DEPTH + 1) * BLAKE3_OUT_LEN];
 
-	/* const blake3_impl_ops_t *ops */
+	/* const blake3_ops_t *ops */
 	const void *ops;
 } BLAKE3_CTX;
 
@@ -97,29 +97,8 @@ extern void **blake3_per_cpu_ctx;
 extern void blake3_per_cpu_ctx_init(void);
 extern void blake3_per_cpu_ctx_fini(void);
 
-/* return number of supported implementations */
-extern int blake3_get_impl_count(void);
-
-/* return id of selected implementation */
-extern int blake3_get_impl_id(void);
-
-/* return name of selected implementation */
-extern const char *blake3_get_impl_name(void);
-
-/* setup id as fastest implementation */
-extern void blake3_set_impl_fastest(uint32_t id);
-
-/* set implementation by id */
-extern void blake3_set_impl_id(uint32_t id);
-
-/* set implementation by name */
-extern int blake3_set_impl_name(const char *name);
-
-/* set startup implementation */
-extern void blake3_setup_impl(void);
-
 #ifdef __cplusplus
 }
 #endif
 
-#endif	/* BLAKE3_H */
+#endif	/* _SYS_BLAKE3_H */

module/icp/algs/blake3/blake3.c

@@ -129,7 +129,7 @@ static output_t make_output(const uint32_t input_cv[8],
  * bytes. For that reason, chaining values in the CV stack are represented as
  * bytes.
  */
-static void output_chaining_value(const blake3_impl_ops_t *ops,
+static void output_chaining_value(const blake3_ops_t *ops,
     const output_t *ctx, uint8_t cv[32])
 {
 	uint32_t cv_words[8];
@@ -139,7 +139,7 @@ static void output_chaining_value(const blake3_impl_ops_t *ops,
 	store_cv_words(cv, cv_words);
 }
 
-static void output_root_bytes(const blake3_impl_ops_t *ops, const output_t *ctx,
+static void output_root_bytes(const blake3_ops_t *ops, const output_t *ctx,
     uint64_t seek, uint8_t *out, size_t out_len)
 {
 	uint64_t output_block_counter = seek / 64;
@@ -163,7 +163,7 @@ static void output_root_bytes(const blake3_impl_ops_t *ops, const output_t *ctx,
 	}
 }
 
-static void chunk_state_update(const blake3_impl_ops_t *ops,
+static void chunk_state_update(const blake3_ops_t *ops,
     blake3_chunk_state_t *ctx, const uint8_t *input, size_t input_len)
 {
 	if (ctx->buf_len > 0) {
@@ -230,7 +230,7 @@ static size_t left_len(size_t content_len)
  * number of chunks hashed. These chunks are never the root and never empty;
  * those cases use a different codepath.
  */
-static size_t compress_chunks_parallel(const blake3_impl_ops_t *ops,
+static size_t compress_chunks_parallel(const blake3_ops_t *ops,
     const uint8_t *input, size_t input_len, const uint32_t key[8],
     uint64_t chunk_counter, uint8_t flags, uint8_t *out)
 {
@@ -274,7 +274,7 @@ static size_t compress_chunks_parallel(const blake3_impl_ops_t *ops,
  * return it as an additional output.) These parents are never the root and
  * never empty; those cases use a different codepath.
  */
-static size_t compress_parents_parallel(const blake3_impl_ops_t *ops,
+static size_t compress_parents_parallel(const blake3_ops_t *ops,
     const uint8_t *child_chaining_values, size_t num_chaining_values,
     const uint32_t key[8], uint8_t flags, uint8_t *out)
 {
@@ -320,7 +320,7 @@ static size_t compress_parents_parallel(const blake3_impl_ops_t *ops,
  * of implementing this special rule? Because we don't want to limit SIMD or
  * multi-threading parallelism for that update().
  */
-static size_t blake3_compress_subtree_wide(const blake3_impl_ops_t *ops,
+static size_t blake3_compress_subtree_wide(const blake3_ops_t *ops,
     const uint8_t *input, size_t input_len, const uint32_t key[8],
     uint64_t chunk_counter, uint8_t flags, uint8_t *out)
 {
@@ -406,7 +406,7 @@ static size_t blake3_compress_subtree_wide(const blake3_impl_ops_t *ops,
  * As with compress_subtree_wide(), this function is not used on inputs of 1
  * chunk or less. That's a different codepath.
  */
-static void compress_subtree_to_parent_node(const blake3_impl_ops_t *ops,
+static void compress_subtree_to_parent_node(const blake3_ops_t *ops,
     const uint8_t *input, size_t input_len, const uint32_t key[8],
     uint64_t chunk_counter, uint8_t flags, uint8_t out[2 * BLAKE3_OUT_LEN])
 {
@@ -434,7 +434,7 @@ static void hasher_init_base(BLAKE3_CTX *ctx, const uint32_t key[8],
 	memcpy(ctx->key, key, BLAKE3_KEY_LEN);
 	chunk_state_init(&ctx->chunk, key, flags);
 	ctx->cv_stack_len = 0;
-	ctx->ops = blake3_impl_get_ops();
+	ctx->ops = blake3_get_ops();
 }
 
 /*

module/icp/algs/blake3/blake3_generic.c

@@ -187,16 +187,17 @@ static inline void blake3_hash_many_generic(const uint8_t * const *inputs,
 	}
 }
 
-static inline boolean_t blake3_is_generic_supported(void)
+/* the generic implementation is always okay */
+static boolean_t blake3_is_supported(void)
 {
 	return (B_TRUE);
 }
 
-const blake3_impl_ops_t blake3_generic_impl = {
+const blake3_ops_t blake3_generic_impl = {
 	.compress_in_place = blake3_compress_in_place_generic,
 	.compress_xof = blake3_compress_xof_generic,
 	.hash_many = blake3_hash_many_generic,
-	.is_supported = blake3_is_generic_supported,
+	.is_supported = blake3_is_supported,
 	.degree = 4,
 	.name = "generic"
 };