Core: updated argon2 to latest release (#23893)

* - updated argon2 to latest release from https://github.com/P-H-C/phc-winner-argon2

- modified CMakeLists.txt to use the reference implementation on aarch64

* fixed indentation

* added ARGON2_NO_THREADS definition to argon2 library

* better indentation

(cherry picked from commit ce916165e2f47446593d2e83a23434702397918f)

6 files changed, 450 insertions, 10 deletions

diff --git a/dep/argon2/CMakeLists.txt b/dep/argon2/CMakeLists.txt
index c8f965c9437..8302406d68b 100644
--- a/dep/argon2/CMakeLists.txt
+++ b/dep/argon2/CMakeLists.txt
@@ -9,18 +9,31 @@
 # implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
 
 file(GLOB_RECURSE sources *.c)
+
+if(CMAKE_SYSTEM_PROCESSOR STREQUAL "aarch64")
+  list(REMOVE_ITEM sources
+    ${CMAKE_CURRENT_SOURCE_DIR}/argon2/opt.c)
+else()
+  list(REMOVE_ITEM sources
+    ${CMAKE_CURRENT_SOURCE_DIR}/argon2/ref.c)
+endif()
+
 add_library(argon2 STATIC
-${sources})
+  ${sources})
+
+target_compile_definitions(argon2
+  PRIVATE
+    -DARGON2_NO_THREADS)
 
 target_include_directories(argon2
-PUBLIC
-  ${CMAKE_CURRENT_SOURCE_DIR})
+  PUBLIC
+    ${CMAKE_CURRENT_SOURCE_DIR})
 
 target_link_libraries(argon2
-PRIVATE
-  trinity-dependency-interface)
+  PRIVATE
+    trinity-dependency-interface)
 
 set_target_properties(argon2
-PROPERTIES
-  FOLDER
-    "dep")
+  PROPERTIES
+    FOLDER
+      "dep")
diff --git a/dep/argon2/argon2/argon2.h b/dep/argon2/argon2/argon2.h
index d5e76a36b82..fc8682c2db4 100644
--- a/dep/argon2/argon2/argon2.h
+++ b/dep/argon2/argon2/argon2.h
@@ -46,6 +46,10 @@ extern "C" {
 #define ARGON2_MIN_LANES UINT32_C(1)
 #define ARGON2_MAX_LANES UINT32_C(0xFFFFFF)
 
+/* Minimum and maximum number of threads */
+#define ARGON2_MIN_THREADS UINT32_C(1)
+#define ARGON2_MAX_THREADS UINT32_C(0xFFFFFF)
+
 /* Number of synchronization points between lanes per pass */
 #define ARGON2_SYNC_POINTS UINT32_C(4)
 
diff --git a/dep/argon2/argon2/core.c b/dep/argon2/argon2/core.c
index b06b25b6ce9..65f05376943 100644
--- a/dep/argon2/argon2/core.c
+++ b/dep/argon2/argon2/core.c
@@ -33,6 +33,7 @@
 #include <string.h>
 
 #include "core.h"
+#include "thread.h"
 #include "blake2/blake2.h"
 #include "blake2/blake2-impl.h"
 
@@ -273,11 +274,115 @@ static int fill_memory_blocks_st(argon2_instance_t *instance) {
     return ARGON2_OK;
 }
 
+#if !defined(ARGON2_NO_THREADS)
+
+#ifdef _WIN32
+static unsigned __stdcall fill_segment_thr(void *thread_data)
+#else
+static void *fill_segment_thr(void *thread_data)
+#endif
+{
+    argon2_thread_data *my_data = thread_data;
+    fill_segment(my_data->instance_ptr, my_data->pos);
+    argon2_thread_exit();
+    return 0;
+}
+
+/* Multi-threaded version for p > 1 case */
+static int fill_memory_blocks_mt(argon2_instance_t *instance) {
+    uint32_t r, s;
+    argon2_thread_handle_t *thread = NULL;
+    argon2_thread_data *thr_data = NULL;
+    int rc = ARGON2_OK;
+
+    /* 1. Allocating space for threads */
+    thread = calloc(instance->lanes, sizeof(argon2_thread_handle_t));
+    if (thread == NULL) {
+        rc = ARGON2_MEMORY_ALLOCATION_ERROR;
+        goto fail;
+    }
+
+    thr_data = calloc(instance->lanes, sizeof(argon2_thread_data));
+    if (thr_data == NULL) {
+        rc = ARGON2_MEMORY_ALLOCATION_ERROR;
+        goto fail;
+    }
+
+    for (r = 0; r < instance->passes; ++r) {
+        for (s = 0; s < ARGON2_SYNC_POINTS; ++s) {
+            uint32_t l, ll;
+
+            /* 2. Calling threads */
+            for (l = 0; l < instance->lanes; ++l) {
+                argon2_position_t position;
+
+                /* 2.1 Join a thread if limit is exceeded */
+                if (l >= instance->threads) {
+                    if (argon2_thread_join(thread[l - instance->threads])) {
+                        rc = ARGON2_THREAD_FAIL;
+                        goto fail;
+                    }
+                }
+
+                /* 2.2 Create thread */
+                position.pass = r;
+                position.lane = l;
+                position.slice = (uint8_t)s;
+                position.index = 0;
+                thr_data[l].instance_ptr =
+                    instance; /* preparing the thread input */
+                memcpy(&(thr_data[l].pos), &position,
+                       sizeof(argon2_position_t));
+                if (argon2_thread_create(&thread[l], &fill_segment_thr,
+                                         (void *)&thr_data[l])) {
+                    /* Wait for already running threads */
+                    for (ll = 0; ll < l; ++ll)
+                        argon2_thread_join(thread[ll]);
+                    rc = ARGON2_THREAD_FAIL;
+                    goto fail;
+                }
+
+                /* fill_segment(instance, position); */
+                /*Non-thread equivalent of the lines above */
+            }
+
+            /* 3. Joining remaining threads */
+            for (l = instance->lanes - instance->threads; l < instance->lanes;
+                 ++l) {
+                if (argon2_thread_join(thread[l])) {
+                    rc = ARGON2_THREAD_FAIL;
+                    goto fail;
+                }
+            }
+        }
+
+#ifdef GENKAT
+        internal_kat(instance, r); /* Print all memory blocks */
+#endif
+    }
+
+fail:
+    if (thread != NULL) {
+        free(thread);
+    }
+    if (thr_data != NULL) {
+        free(thr_data);
+    }
+    return rc;
+}
+
+#endif /* ARGON2_NO_THREADS */
+
 int fill_memory_blocks(argon2_instance_t *instance) {
 	if (instance == NULL || instance->lanes == 0) {
 	    return ARGON2_INCORRECT_PARAMETER;
     }
+#if defined(ARGON2_NO_THREADS)
     return fill_memory_blocks_st(instance);
+#else
+    return instance->threads == 1 ?
+			fill_memory_blocks_st(instance) : fill_memory_blocks_mt(instance);
+#endif
 }
 
 int validate_inputs(const argon2_context *context) {
@@ -388,11 +493,11 @@ int validate_inputs(const argon2_context *context) {
     }
 
     /* Validate threads */
-    if (1 > context->threads) {
+    if (ARGON2_MIN_THREADS > context->threads) {
         return ARGON2_THREADS_TOO_FEW;
     }
 
-    if (1 < context->threads) {
+    if (ARGON2_MAX_THREADS < context->threads) {
         return ARGON2_THREADS_TOO_MANY;
     }
 
diff --git a/dep/argon2/argon2/ref.c b/dep/argon2/argon2/ref.c
new file mode 100644
index 00000000000..ad1cf461f96
--- /dev/null
+++ b/dep/argon2/argon2/ref.c
@@ -0,0 +1,194 @@
+/*
+ * Argon2 reference source code package - reference C implementations
+ *
+ * Copyright 2015
+ * Daniel Dinu, Dmitry Khovratovich, Jean-Philippe Aumasson, and Samuel Neves
+ *
+ * You may use this work under the terms of a Creative Commons CC0 1.0
+ * License/Waiver or the Apache Public License 2.0, at your option. The terms of
+ * these licenses can be found at:
+ *
+ * - CC0 1.0 Universal : http://creativecommons.org/publicdomain/zero/1.0
+ * - Apache 2.0        : http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * You should have received a copy of both of these licenses along with this
+ * software. If not, they may be obtained at the above URLs.
+ */
+
+#include <stdint.h>
+#include <string.h>
+#include <stdlib.h>
+
+#include "argon2.h"
+#include "core.h"
+
+#include "blake2/blamka-round-ref.h"
+#include "blake2/blake2-impl.h"
+#include "blake2/blake2.h"
+
+
+/*
+ * Function fills a new memory block and optionally XORs the old block over the new one.
+ * @next_block must be initialized.
+ * @param prev_block Pointer to the previous block
+ * @param ref_block Pointer to the reference block
+ * @param next_block Pointer to the block to be constructed
+ * @param with_xor Whether to XOR into the new block (1) or just overwrite (0)
+ * @pre all block pointers must be valid
+ */
+static void fill_block(const block *prev_block, const block *ref_block,
+                       block *next_block, int with_xor) {
+    block blockR, block_tmp;
+    unsigned i;
+
+    copy_block(&blockR, ref_block);
+    xor_block(&blockR, prev_block);
+    copy_block(&block_tmp, &blockR);
+    /* Now blockR = ref_block + prev_block and block_tmp = ref_block + prev_block */
+    if (with_xor) {
+        /* Saving the next block contents for XOR over: */
+        xor_block(&block_tmp, next_block);
+        /* Now blockR = ref_block + prev_block and
+           block_tmp = ref_block + prev_block + next_block */
+    }
+
+    /* Apply Blake2 on columns of 64-bit words: (0,1,...,15) , then
+       (16,17,..31)... finally (112,113,...127) */
+    for (i = 0; i < 8; ++i) {
+        BLAKE2_ROUND_NOMSG(
+            blockR.v[16 * i], blockR.v[16 * i + 1], blockR.v[16 * i + 2],
+            blockR.v[16 * i + 3], blockR.v[16 * i + 4], blockR.v[16 * i + 5],
+            blockR.v[16 * i + 6], blockR.v[16 * i + 7], blockR.v[16 * i + 8],
+            blockR.v[16 * i + 9], blockR.v[16 * i + 10], blockR.v[16 * i + 11],
+            blockR.v[16 * i + 12], blockR.v[16 * i + 13], blockR.v[16 * i + 14],
+            blockR.v[16 * i + 15]);
+    }
+
+    /* Apply Blake2 on rows of 64-bit words: (0,1,16,17,...112,113), then
+       (2,3,18,19,...,114,115).. finally (14,15,30,31,...,126,127) */
+    for (i = 0; i < 8; i++) {
+        BLAKE2_ROUND_NOMSG(
+            blockR.v[2 * i], blockR.v[2 * i + 1], blockR.v[2 * i + 16],
+            blockR.v[2 * i + 17], blockR.v[2 * i + 32], blockR.v[2 * i + 33],
+            blockR.v[2 * i + 48], blockR.v[2 * i + 49], blockR.v[2 * i + 64],
+            blockR.v[2 * i + 65], blockR.v[2 * i + 80], blockR.v[2 * i + 81],
+            blockR.v[2 * i + 96], blockR.v[2 * i + 97], blockR.v[2 * i + 112],
+            blockR.v[2 * i + 113]);
+    }
+
+    copy_block(next_block, &block_tmp);
+    xor_block(next_block, &blockR);
+}
+
+static void next_addresses(block *address_block, block *input_block,
+                           const block *zero_block) {
+    input_block->v[6]++;
+    fill_block(zero_block, input_block, address_block, 0);
+    fill_block(zero_block, address_block, address_block, 0);
+}
+
+void fill_segment(const argon2_instance_t *instance,
+                  argon2_position_t position) {
+    block *ref_block = NULL, *curr_block = NULL;
+    block address_block, input_block, zero_block;
+    uint64_t pseudo_rand, ref_index, ref_lane;
+    uint32_t prev_offset, curr_offset;
+    uint32_t starting_index;
+    uint32_t i;
+    int data_independent_addressing;
+
+    if (instance == NULL) {
+        return;
+    }
+
+    data_independent_addressing =
+        (instance->type == Argon2_i) ||
+        (instance->type == Argon2_id && (position.pass == 0) &&
+         (position.slice < ARGON2_SYNC_POINTS / 2));
+
+    if (data_independent_addressing) {
+        init_block_value(&zero_block, 0);
+        init_block_value(&input_block, 0);
+
+        input_block.v[0] = position.pass;
+        input_block.v[1] = position.lane;
+        input_block.v[2] = position.slice;
+        input_block.v[3] = instance->memory_blocks;
+        input_block.v[4] = instance->passes;
+        input_block.v[5] = instance->type;
+    }
+
+    starting_index = 0;
+
+    if ((0 == position.pass) && (0 == position.slice)) {
+        starting_index = 2; /* we have already generated the first two blocks */
+
+        /* Don't forget to generate the first block of addresses: */
+        if (data_independent_addressing) {
+            next_addresses(&address_block, &input_block, &zero_block);
+        }
+    }
+
+    /* Offset of the current block */
+    curr_offset = position.lane * instance->lane_length +
+                  position.slice * instance->segment_length + starting_index;
+
+    if (0 == curr_offset % instance->lane_length) {
+        /* Last block in this lane */
+        prev_offset = curr_offset + instance->lane_length - 1;
+    } else {
+        /* Previous block */
+        prev_offset = curr_offset - 1;
+    }
+
+    for (i = starting_index; i < instance->segment_length;
+         ++i, ++curr_offset, ++prev_offset) {
+        /*1.1 Rotating prev_offset if needed */
+        if (curr_offset % instance->lane_length == 1) {
+            prev_offset = curr_offset - 1;
+        }
+
+        /* 1.2 Computing the index of the reference block */
+        /* 1.2.1 Taking pseudo-random value from the previous block */
+        if (data_independent_addressing) {
+            if (i % ARGON2_ADDRESSES_IN_BLOCK == 0) {
+                next_addresses(&address_block, &input_block, &zero_block);
+            }
+            pseudo_rand = address_block.v[i % ARGON2_ADDRESSES_IN_BLOCK];
+        } else {
+            pseudo_rand = instance->memory[prev_offset].v[0];
+        }
+
+        /* 1.2.2 Computing the lane of the reference block */
+        ref_lane = ((pseudo_rand >> 32)) % instance->lanes;
+
+        if ((position.pass == 0) && (position.slice == 0)) {
+            /* Can not reference other lanes yet */
+            ref_lane = position.lane;
+        }
+
+        /* 1.2.3 Computing the number of possible reference block within the
+         * lane.
+         */
+        position.index = i;
+        ref_index = index_alpha(instance, &position, pseudo_rand & 0xFFFFFFFF,
+                                ref_lane == position.lane);
+
+        /* 2 Creating a new block */
+        ref_block =
+            instance->memory + instance->lane_length * ref_lane + ref_index;
+        curr_block = instance->memory + curr_offset;
+        if (ARGON2_VERSION_10 == instance->version) {
+            /* version 1.2.1 and earlier: overwrite, not XOR */
+            fill_block(instance->memory + prev_offset, ref_block, curr_block, 0);
+        } else {
+            if(0 == position.pass) {
+                fill_block(instance->memory + prev_offset, ref_block,
+                           curr_block, 0);
+            } else {
+                fill_block(instance->memory + prev_offset, ref_block,
+                           curr_block, 1);
+            }
+        }
+    }
+}
diff --git a/dep/argon2/argon2/thread.c b/dep/argon2/argon2/thread.c
new file mode 100644
index 00000000000..e099a00d217
--- /dev/null
+++ b/dep/argon2/argon2/thread.c
@@ -0,0 +1,57 @@
+/*
+ * Argon2 reference source code package - reference C implementations
+ *
+ * Copyright 2015
+ * Daniel Dinu, Dmitry Khovratovich, Jean-Philippe Aumasson, and Samuel Neves
+ *
+ * You may use this work under the terms of a Creative Commons CC0 1.0
+ * License/Waiver or the Apache Public License 2.0, at your option. The terms of
+ * these licenses can be found at:
+ *
+ * - CC0 1.0 Universal : http://creativecommons.org/publicdomain/zero/1.0
+ * - Apache 2.0        : http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * You should have received a copy of both of these licenses along with this
+ * software. If not, they may be obtained at the above URLs.
+ */
+
+#if !defined(ARGON2_NO_THREADS)
+
+#include "thread.h"
+#if defined(_WIN32)
+#include <windows.h>
+#endif
+
+int argon2_thread_create(argon2_thread_handle_t *handle,
+                         argon2_thread_func_t func, void *args) {
+    if (NULL == handle || func == NULL) {
+        return -1;
+    }
+#if defined(_WIN32)
+    *handle = _beginthreadex(NULL, 0, func, args, 0, NULL);
+    return *handle != 0 ? 0 : -1;
+#else
+    return pthread_create(handle, NULL, func, args);
+#endif
+}
+
+int argon2_thread_join(argon2_thread_handle_t handle) {
+#if defined(_WIN32)
+    if (WaitForSingleObject((HANDLE)handle, INFINITE) == WAIT_OBJECT_0) {
+        return CloseHandle((HANDLE)handle) != 0 ? 0 : -1;
+    }
+    return -1;
+#else
+    return pthread_join(handle, NULL);
+#endif
+}
+
+void argon2_thread_exit(void) {
+#if defined(_WIN32)
+    _endthreadex(0);
+#else
+    pthread_exit(NULL);
+#endif
+}
+
+#endif /* ARGON2_NO_THREADS */
diff --git a/dep/argon2/argon2/thread.h b/dep/argon2/argon2/thread.h
new file mode 100644
index 00000000000..49d88367b4f
--- /dev/null
+++ b/dep/argon2/argon2/thread.h
@@ -0,0 +1,67 @@
+/*
+ * Argon2 reference source code package - reference C implementations
+ *
+ * Copyright 2015
+ * Daniel Dinu, Dmitry Khovratovich, Jean-Philippe Aumasson, and Samuel Neves
+ *
+ * You may use this work under the terms of a Creative Commons CC0 1.0
+ * License/Waiver or the Apache Public License 2.0, at your option. The terms of
+ * these licenses can be found at:
+ *
+ * - CC0 1.0 Universal : http://creativecommons.org/publicdomain/zero/1.0
+ * - Apache 2.0        : http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * You should have received a copy of both of these licenses along with this
+ * software. If not, they may be obtained at the above URLs.
+ */
+
+#ifndef ARGON2_THREAD_H
+#define ARGON2_THREAD_H
+
+#if !defined(ARGON2_NO_THREADS)
+
+/*
+        Here we implement an abstraction layer for the simpĺe requirements
+        of the Argon2 code. We only require 3 primitives---thread creation,
+        joining, and termination---so full emulation of the pthreads API
+        is unwarranted. Currently we wrap pthreads and Win32 threads.
+
+        The API defines 2 types: the function pointer type,
+   argon2_thread_func_t,
+        and the type of the thread handle---argon2_thread_handle_t.
+*/
+#if defined(_WIN32)
+#include <process.h>
+typedef unsigned(__stdcall *argon2_thread_func_t)(void *);
+typedef uintptr_t argon2_thread_handle_t;
+#else
+#include <pthread.h>
+typedef void *(*argon2_thread_func_t)(void *);
+typedef pthread_t argon2_thread_handle_t;
+#endif
+
+/* Creates a thread
+ * @param handle pointer to a thread handle, which is the output of this
+ * function. Must not be NULL.
+ * @param func A function pointer for the thread's entry point. Must not be
+ * NULL.
+ * @param args Pointer that is passed as an argument to @func. May be NULL.
+ * @return 0 if @handle and @func are valid pointers and a thread is successfully
+ * created.
+ */
+int argon2_thread_create(argon2_thread_handle_t *handle,
+                         argon2_thread_func_t func, void *args);
+
+/* Waits for a thread to terminate
+ * @param handle Handle to a thread created with argon2_thread_create.
+ * @return 0 if @handle is a valid handle, and joining completed successfully.
+*/
+int argon2_thread_join(argon2_thread_handle_t handle);
+
+/* Terminate the current thread. Must be run inside a thread created by
+ * argon2_thread_create.
+*/
+void argon2_thread_exit(void);
+
+#endif /* ARGON2_NO_THREADS */
+#endif