Automatic downtune problem:

In the automatic downtune routine, hashcat prepares a fixed 512MiB host
buffer that is known to be allocated by the compute runtimes (CUDA, HIP,
OpenCL, Metal), and over which hashcat has no control.

However, hashcat still divides the maximum available host memory by the
active device count to automatically as a preparation to later downtune
the -n and -T parameters when memory is limited.

Hashcat reserves 512MiB per active device. With bridges, the active
devices become bridge units, which for modes 70000, 70100, and 70200
equals the CPU core count. On a 32-core CPU, this multiplies to 16GiB,
even though the memory is actually shared because of threading.
This leads to an overestimation of memory usage.

A simple fix is to divide the 512MiB buffer by the active device count.
This keeps the full 512MiB for a single GPU but avoids overestimating
memory usage with many virtual devices.

Fix code handling kernel-accel value in argon2_common.c for CPU,
which was accidentally removed during previous refactoring.

Set thread count to 1 for hash-mode 70000. Oversubscribing the CPU isn't
useful here. This allows to keep the wordlist count low, which is very
welcome for slow hashes like Argon2id.

Fix unit test for 20011/20012/20013 (DiskCryptor) by adding setuptools
to install_modules.sh and replacing AES.MODE_XTS with python_AES.MODE_XTS.

Fix false negative for kernel 32800, which only occurred if all
conditions were true: multihash, -a 3, optimized mode, and password
length between 16 and 31.

Fix Python package name in BUILD_WSL.md command line example.

Author: jsteube

BUILD_WSL.md

@@ -21,7 +21,7 @@ sudo make install
 cd ../
 wget https://repo.msys2.org/mingw/mingw64/mingw-w64-x86_64-python-3.12.11-1-any.pkg.tar.zst
 sudo mkdir /opt/win-python
-sudo tar --zstd -xf mingw-w64-x86_64-python-3.12.10-1-any.pkg.tar.zst -C /opt/win-python
+sudo tar --zstd -xf mingw-w64-x86_64-python-3.12.11-1-any.pkg.tar.zst -C /opt/win-python
 ```
 
 ### Building ###

OpenCL/m32800_a3-optimized.cl

@@ -917,8 +917,8 @@ KERNEL_FQ KERNEL_FA void m32800_m08 (KERN_ATTR_BASIC ())
 
   w3[0] = 0;
   w3[1] = 0;
-  w3[2] = 0;
-  w3[3] = pws[gid].i[15];
+  w3[2] = pws[gid].i[14];
+  w3[3] = 0;
 
   const u32 pw_len = pws[gid].pw_len & 63;
 

src/backend.c

@@ -16425,7 +16425,7 @@ int backend_session_begin (hashcat_ctx_t *hashcat_ctx)
 
       if (size_total > device_param->device_available_mem) memory_limit_hit = 1;
 
-      const u64 size_host_extra = (512 * 1024 * 1024);
+      const u64 size_host_extra = (512 * 1024 * 1024) / backend_ctx->backend_devices_active;
 
       const u64 size_total_host
         = size_pws_comp

src/bridges/bridge_argon2id_reference.c

@@ -25,7 +25,7 @@
 // and therefore it's easier for hashcat to parallelize if this multiplier is low.
 // in the end, it's a trade-off.
 
-#define N_ACCEL 8
+#define N_ACCEL 32
 
 typedef struct
 {

src/modules/argon2_common.c

@@ -71,9 +71,17 @@ const char *argon2_module_extra_tuningdb_block (MAYBE_UNUSED const hashconfig_t
   }
   else
   {
-    kernel_accel_new = kernel_accel_max;
+    if (device_param->opencl_device_type & CL_DEVICE_TYPE_CPU)
+    {
+      kernel_accel_new = MIN (device_processors, kernel_accel_max);
+    }
+    else
+    {
+      kernel_accel_new = kernel_accel_max;
+    }
   }
 
+
   char *new_device_name = hcstrdup (device_param->device_name);
 
   for (size_t i = 0; i < strlen (new_device_name); i++)

src/modules/module_70000.c

@@ -77,6 +77,20 @@ typedef struct
 
 static const char *SIGNATURE_ARGON2ID= "$argon2id$";
 
+u32 module_kernel_threads_min (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra)
+{
+  const u32 kernel_threads_min = 1;
+
+  return kernel_threads_min;
+}
+
+u32 module_kernel_threads_max (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra)
+{
+  const u32 kernel_threads_max = 1;
+
+  return kernel_threads_max;
+}
+
 u64 module_esalt_size (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra)
 {
   const u64 esalt_size = (const u64) sizeof (argon2_t);
@@ -300,8 +314,8 @@ void module_init (module_ctx_t *module_ctx)
   module_ctx->module_kernel_accel_min         = MODULE_DEFAULT;
   module_ctx->module_kernel_loops_max         = MODULE_DEFAULT;
   module_ctx->module_kernel_loops_min         = MODULE_DEFAULT;
-  module_ctx->module_kernel_threads_max       = MODULE_DEFAULT;
-  module_ctx->module_kernel_threads_min       = MODULE_DEFAULT;
+  module_ctx->module_kernel_threads_max       = module_kernel_threads_max;
+  module_ctx->module_kernel_threads_min       = module_kernel_threads_min;
   module_ctx->module_kern_type                = module_kern_type;
   module_ctx->module_kern_type_dynamic        = MODULE_DEFAULT;
   module_ctx->module_opti_type                = module_opti_type;

tools/install_modules.sh

@@ -164,6 +164,9 @@ else
   pip3 install cryptography
   ERRORS=$((ERRORS+$?))
 
+  pip3 install setuptools
+  ERRORS=$((ERRORS+$?))
+
 fi
 
 echo

tools/test_modules/m13600.pm

@@ -86,7 +86,7 @@ sub module_generate_hash
 
   my $key = $pbkdf2->PBKDF2_hex ($salt_bin, $word);
 
-  my $verify_bytes = substr ($key, -4); $verify_bytes =~ s/^0+//; #lol
+  my $verify_bytes = substr ($key, -4); #$verify_bytes =~ s/^0+//; #lol
 
   $key = substr ($key, $key_len, $key_len);
 

tools/test_modules/m20011.pm

@@ -24,15 +24,15 @@ sub aes_encrypt
 
   my $python_code = <<'END_CODE';
 
-from CryptoPlus.Cipher import AES
+from CryptoPlus.Cipher import python_AES
 import base64
 
 key1 = base64.b64decode (key_main)
 key2 = base64.b64decode (key_tweak)
 
 key = (key1, key2)
 
-cipher = AES.new (key, AES.MODE_XTS)
+cipher = python_AES.new (key, python_AES.MODE_XTS)
 
 sequence = b"\x01"
 
@@ -67,15 +67,15 @@ sub aes_decrypt
 
   my $python_code = <<'END_CODE';
 
-from CryptoPlus.Cipher import AES
+from CryptoPlus.Cipher import python_AES
 import base64
 
 key1 = base64.b64decode (key_main)
 key2 = base64.b64decode (key_tweak)
 
 key = (key1, key2)
 
-cipher = AES.new (key, AES.MODE_XTS)
+cipher = python_AES.new (key, python_AES.MODE_XTS)
 
 sequence = b"\x01"
 

tools/test_modules/m20012.pm

@@ -24,15 +24,15 @@ sub aes_encrypt
 
   my $python_code = <<'END_CODE';
 
-from CryptoPlus.Cipher import AES
+from CryptoPlus.Cipher import python_AES
 import base64
 
 key1 = base64.b64decode (key_main)
 key2 = base64.b64decode (key_tweak)
 
 key = (key1, key2)
 
-cipher = AES.new (key, AES.MODE_XTS)
+cipher = python_AES.new (key, python_AES.MODE_XTS)
 
 sequence = b"\x01"
 
@@ -67,15 +67,15 @@ sub aes_decrypt
 
   my $python_code = <<'END_CODE';
 
-from CryptoPlus.Cipher import AES
+from CryptoPlus.Cipher import python_AES
 import base64
 
 key1 = base64.b64decode (key_main)
 key2 = base64.b64decode (key_tweak)
 
 key = (key1, key2)
 
-cipher = AES.new (key, AES.MODE_XTS)
+cipher = python_AES.new (key, python_AES.MODE_XTS)
 
 sequence = b"\x01"