Issue #13703: add a way to randomize the hash values of basic types (str, bytes, datetime)

in order to make algorithmic complexity attacks on (e.g.) web apps much more complicated.

The environment variable PYTHONHASHSEED and the new command line flag -R control this
behavior.

3 files changed, 314 insertions, 2 deletions

diff --git a/Python/pythonrun.c b/Python/pythonrun.c
index c4ae921..4474e79 100644
--- a/Python/pythonrun.c
+++ b/Python/pythonrun.c
@@ -73,6 +73,7 @@ extern void _PyUnicode_Init(void);
 extern void _PyUnicode_Fini(void);
 extern int _PyLong_Init(void);
 extern void PyLong_Fini(void);
+extern void _PyRandom_Init(void);
 
 #ifdef WITH_THREAD
 extern void _PyGILState_Init(PyInterpreterState *, PyThreadState *);
@@ -91,6 +92,7 @@ int Py_FrozenFlag; /* Needed by getpath.c */
 int Py_IgnoreEnvironmentFlag; /* e.g. PYTHONPATH, PYTHONHOME */
 int Py_NoUserSiteDirectory = 0; /* for -s and site.py */
 int Py_UnbufferedStdioFlag = 0; /* Unbuffered binary std{in,out,err} */
+int Py_HashRandomizationFlag = 0; /* for -R and PYTHONHASHSEED */
 
 /* PyModule_GetWarningsModule is no longer necessary as of 2.6
 since _warnings is builtin.  This API should not be used. */
@@ -195,6 +197,12 @@ Py_InitializeEx(int install_sigs)
         Py_OptimizeFlag = add_flag(Py_OptimizeFlag, p);
     if ((p = Py_GETENV("PYTHONDONTWRITEBYTECODE")) && *p != '\0')
         Py_DontWriteBytecodeFlag = add_flag(Py_DontWriteBytecodeFlag, p);
+    /* The variable is only tested for existence here; _PyRandom_Init will
+       check its value further. */
+    if ((p = Py_GETENV("PYTHONHASHSEED")) && *p != '\0')
+        Py_HashRandomizationFlag = add_flag(Py_HashRandomizationFlag, p);
+
+    _PyRandom_Init();
 
     interp = PyInterpreterState_New();
     if (interp == NULL)
diff --git a/Python/random.c b/Python/random.c
new file mode 100644
index 0000000..327166e
--- /dev/null
+++ b/Python/random.c
@@ -0,0 +1,302 @@
+#include "Python.h"
+#ifdef MS_WINDOWS
+#include <windows.h>
+#else
+#include <fcntl.h>
+#endif
+
+static int random_initialized = 0;
+
+#ifdef MS_WINDOWS
+typedef BOOL (WINAPI *CRYPTACQUIRECONTEXTA)(HCRYPTPROV *phProv,\
+              LPCSTR pszContainer, LPCSTR pszProvider, DWORD dwProvType,\
+              DWORD dwFlags );
+typedef BOOL (WINAPI *CRYPTGENRANDOM)(HCRYPTPROV hProv, DWORD dwLen,\
+              BYTE *pbBuffer );
+
+static CRYPTGENRANDOM pCryptGenRandom = NULL;
+/* This handle is never explicitly released. Instead, the operating
+   system will release it when the process terminates. */
+static HCRYPTPROV hCryptProv = 0;
+
+static int
+win32_urandom_init(int raise)
+{
+    HINSTANCE hAdvAPI32 = NULL;
+    CRYPTACQUIRECONTEXTA pCryptAcquireContext = NULL;
+
+    /* Obtain handle to the DLL containing CryptoAPI. This should not fail. */
+    hAdvAPI32 = GetModuleHandle("advapi32.dll");
+    if(hAdvAPI32 == NULL)
+        goto error;
+
+    /* Obtain pointers to the CryptoAPI functions. This will fail on some early
+       versions of Win95. */
+    pCryptAcquireContext = (CRYPTACQUIRECONTEXTA)GetProcAddress(
+                               hAdvAPI32, "CryptAcquireContextA");
+    if (pCryptAcquireContext == NULL)
+        goto error;
+
+    pCryptGenRandom = (CRYPTGENRANDOM)GetProcAddress(hAdvAPI32,
+                                                     "CryptGenRandom");
+    if (pCryptGenRandom == NULL)
+        goto error;
+
+    /* Acquire context */
+    if (! pCryptAcquireContext(&hCryptProv, NULL, NULL,
+                               PROV_RSA_FULL, CRYPT_VERIFYCONTEXT))
+        goto error;
+
+    return 0;
+
+error:
+    if (raise)
+        PyErr_SetFromWindowsErr(0);
+    else
+        Py_FatalError("Failed to initialize Windows random API (CryptoGen)");
+    return -1;
+}
+
+/* Fill buffer with size pseudo-random bytes generated by the Windows CryptoGen
+   API. Return 0 on success, or -1 on error. */
+static int
+win32_urandom(unsigned char *buffer, Py_ssize_t size, int raise)
+{
+    Py_ssize_t chunk;
+
+    if (hCryptProv == 0)
+    {
+        if (win32_urandom_init(raise) == -1)
+            return -1;
+    }
+
+    while (size > 0)
+    {
+        chunk = size > INT_MAX ? INT_MAX : size;
+        if (!pCryptGenRandom(hCryptProv, chunk, buffer))
+        {
+            /* CryptGenRandom() failed */
+            if (raise)
+                PyErr_SetFromWindowsErr(0);
+            else
+                Py_FatalError("Failed to initialized the randomized hash "
+                        "secret using CryptoGen)");
+            return -1;
+        }
+        buffer += chunk;
+        size -= chunk;
+    }
+    return 0;
+}
+#endif /* MS_WINDOWS */
+
+
+#ifdef __VMS
+/* Use openssl random routine */
+#include <openssl/rand.h>
+static int
+vms_urandom(unsigned char *buffer, Py_ssize_t size, int raise)
+{
+    if (RAND_pseudo_bytes(buffer, size) < 0) {
+        if (raise) {
+            PyErr_Format(PyExc_ValueError,
+                         "RAND_pseudo_bytes");
+        } else {
+            Py_FatalError("Failed to initialize the randomized hash "
+                          "secret using RAND_pseudo_bytes");
+        }
+        return -1;
+    }
+    return 0;
+}
+#endif /* __VMS */
+
+
+#if !defined(MS_WINDOWS) && !defined(__VMS)
+
+/* Read size bytes from /dev/urandom into buffer.
+   Call Py_FatalError() on error. */
+static void
+dev_urandom_noraise(char *buffer, Py_ssize_t size)
+{
+    int fd;
+    Py_ssize_t n;
+
+    assert (0 < size);
+
+    fd = open("/dev/urandom", O_RDONLY);
+    if (fd < 0)
+        Py_FatalError("Failed to open /dev/urandom");
+
+    while (0 < size)
+    {
+        do {
+            n = read(fd, buffer, (size_t)size);
+        } while (n < 0 && errno == EINTR);
+        if (n <= 0)
+        {
+            /* stop on error or if read(size) returned 0 */
+            Py_FatalError("Failed to read bytes from /dev/urandom");
+            break;
+        }
+        buffer += n;
+        size -= (Py_ssize_t)n;
+    }
+    close(fd);
+}
+
+/* Read size bytes from /dev/urandom into buffer.
+   Return 0 on success, raise an exception and return -1 on error. */
+static int
+dev_urandom_python(char *buffer, Py_ssize_t size)
+{
+    int fd;
+    Py_ssize_t n;
+
+    if (size <= 0)
+        return 0;
+
+    Py_BEGIN_ALLOW_THREADS
+    fd = open("/dev/urandom", O_RDONLY);
+    Py_END_ALLOW_THREADS
+    if (fd < 0)
+    {
+        PyErr_SetFromErrnoWithFilename(PyExc_OSError, "/dev/urandom");
+        return -1;
+    }
+
+    Py_BEGIN_ALLOW_THREADS
+    do {
+        do {
+            n = read(fd, buffer, (size_t)size);
+        } while (n < 0 && errno == EINTR);
+        if (n <= 0)
+            break;
+        buffer += n;
+        size -= (Py_ssize_t)n;
+    } while (0 < size);
+    Py_END_ALLOW_THREADS
+
+    if (n <= 0)
+    {
+        /* stop on error or if read(size) returned 0 */
+        if (n < 0)
+            PyErr_SetFromErrno(PyExc_OSError);
+        else
+            PyErr_Format(PyExc_RuntimeError,
+                         "Failed to read %zi bytes from /dev/urandom",
+                         size);
+        close(fd);
+        return -1;
+    }
+    close(fd);
+    return 0;
+}
+#endif /* !defined(MS_WINDOWS) && !defined(__VMS) */
+
+/* Fill buffer with pseudo-random bytes generated by a linear congruent
+   generator (LCG):
+
+       x(n+1) = (x(n) * 214013 + 2531011) % 2^32
+
+   Use bits 23..16 of x(n) to generate a byte. */
+static void
+lcg_urandom(unsigned int x0, unsigned char *buffer, size_t size)
+{
+    size_t index;
+    unsigned int x;
+
+    x = x0;
+    for (index=0; index < size; index++) {
+        x *= 214013;
+        x += 2531011;
+        /* modulo 2 ^ (8 * sizeof(int)) */
+        buffer[index] = (x >> 16) & 0xff;
+    }
+}
+
+/* Fill buffer with size pseudo-random bytes, not suitable for cryptographic
+   use, from the operating random number generator (RNG).
+
+   Return 0 on success, raise an exception and return -1 on error. */
+int
+_PyOS_URandom(void *buffer, Py_ssize_t size)
+{
+    if (size < 0) {
+        PyErr_Format(PyExc_ValueError,
+                     "negative argument not allowed");
+        return -1;
+    }
+    if (size == 0)
+        return 0;
+
+#ifdef MS_WINDOWS
+    return win32_urandom((unsigned char *)buffer, size, 1);
+#else
+# ifdef __VMS
+    return vms_urandom((unsigned char *)buffer, size, 1);
+# else
+    return dev_urandom_python((char*)buffer, size);
+# endif
+#endif
+}
+
+void
+_PyRandom_Init(void)
+{
+    char *env;
+    void *secret = &_Py_HashSecret;
+    Py_ssize_t secret_size = sizeof(_Py_HashSecret);
+
+    if (random_initialized)
+        return;
+    random_initialized = 1;
+
+    /*
+      By default, hash randomization is disabled, and only
+      enabled if PYTHONHASHSEED is set to non-empty or if
+      "-R" is provided at the command line:
+    */
+    if (!Py_HashRandomizationFlag) {
+        /* Disable the randomized hash: */
+        memset(secret, 0, secret_size);
+        return;
+    }
+
+    /*
+      Hash randomization is enabled.  Generate a per-process secret,
+      using PYTHONHASHSEED if provided.
+    */
+
+    env = Py_GETENV("PYTHONHASHSEED");
+    if (env && *env != '\0' & strcmp(env, "random") != 0) {
+        char *endptr = env;
+        unsigned long seed;
+        seed = strtoul(env, &endptr, 10);
+        if (*endptr != '\0'
+            || seed > 4294967295UL
+            || (errno == ERANGE && seed == ULONG_MAX))
+        {
+            Py_FatalError("PYTHONHASHSEED must be \"random\" or an integer "
+                          "in range [0; 4294967295]");
+        }
+        if (seed == 0) {
+            /* disable the randomized hash */
+            memset(secret, 0, secret_size);
+        }
+        else {
+            lcg_urandom(seed, (unsigned char*)secret, secret_size);
+        }
+    }
+    else {
+#ifdef MS_WINDOWS
+        (void)win32_urandom((unsigned char *)secret, secret_size, 0);
+#else /* #ifdef MS_WINDOWS */
+# ifdef __VMS
+        vms_urandom((unsigned char *)secret, secret_size, 0);
+# else
+        dev_urandom_noraise((char*)secret, secret_size);
+# endif
+#endif
+    }
+}
diff --git a/Python/sysmodule.c b/Python/sysmodule.c
index c688172..6a7e914 100644
--- a/Python/sysmodule.c
+++ b/Python/sysmodule.c
@@ -1126,6 +1126,7 @@ static PyStructSequence_Field flags_fields[] = {
     /* {"unbuffered",                   "-u"}, */
     /* {"skip_first",                   "-x"}, */
     {"bytes_warning", "-b"},
+    {"hash_randomization", "-R"},
     {0}
 };
 
@@ -1134,9 +1135,9 @@ static PyStructSequence_Desc flags_desc = {
     flags__doc__,       /* doc */
     flags_fields,       /* fields */
 #ifdef RISCOS
-    12
+    13
 #else
-    11
+    12
 #endif
 };
 
@@ -1169,6 +1170,7 @@ make_flags(void)
     /* SetFlag(saw_unbuffered_flag); */
     /* SetFlag(skipfirstline); */
     SetFlag(Py_BytesWarningFlag);
+    SetFlag(Py_HashRandomizationFlag);
 #undef SetFlag
 
     if (PyErr_Occurred()) {