bpo-33671: efficient zero-copy for shutil.copy* functions (Linux, OSX and Win) (#7160)

* have shutil.copyfileobj use sendfile() if possible

* refactoring: use ctx manager

* add test with non-regular file obj

* emulate case where file size can't be determined

* reference _copyfileobj_sendfile directly

* add test for offset() at certain position

* add test for empty file

* add test for non regular file dst

* small refactoring

* leave copyfileobj() alone in order to not introduce any incompatibility

* minor refactoring

* remove old test

* update docstring

* update docstring; rename exception class

* detect platforms which only support file to socket zero copy

* don't run test on platforms where file-to-file zero copy is not supported

* use tempfiles

* reset verbosity

* add test for smaller chunks

* add big file size test

* add comment

* update doc

* update whatsnew doc

* update doc

* catch Exception

* remove unused import

* add test case for error on second sendfile() call

* turn docstring into comment

* add one more test

* update comment

* add Misc/NEWS entry

* get rid of COPY_BUFSIZE; it belongs to another PR

* update doc

* expose posix._fcopyfile() for OSX

* merge from linux branch

* merge from linux branch

* expose fcopyfile

* arg clinic for the win implementation

* convert path type to path_t

* expose CopyFileW

* fix windows tests

* release GIL

* minor refactoring

* update doc

* update comment

* update docstrings

* rename functions

* rename test classes

* update doc

* update doc

* update docstrings and comments

* avoid do import nt|posix modules if unnecessary

* set nt|posix modules to None if not available

* micro speedup

* update description

* add doc note

* use better wording in doc

* rename function using 'fastcopy' prefix instead of 'zerocopy'

* use :ref: in rst doc

* change wording in doc

* add test to make sure sendfile() doesn't get called aymore in case it doesn't support file to file copies

* move CopyFileW in _winapi and actually expose CopyFileExW instead

* fix line endings

* add tests for mode bits

* add docstring

* remove test file mode class; let's keep it for later when Istart addressing OSX fcopyfile() specific copies

* update doc to reflect new changes

* update doc

* adjust tests on win

* fix argument clinic error

* update doc

* OSX: expose copyfile(3) instead of fcopyfile(3); also expose flags arg to python

* osx / copyfile: use path_t instead of char

* do not set dst name in the OSError exception in order to remain consistent with platforms which cannot do that (e.g. linux)

* add same file test

* add test for same file

* have osx copyfile() pre-emptively check if src and dst are the same, otherwise it will return immedialtey and src file content gets deleted

* turn PermissionError into appropriate SameFileError

* expose ERROR_SHARING_VIOLATION in order to raise more appropriate SameFileError

* honour follow_symlinks arg when using CopyFileEx

* update Misc/NEWS

* expose CreateDirectoryEx mock

* change C type

* CreateDirectoryExW actual implementation

* provide specific makedirs() implementation for win

* fix typo

* skeleton for SetNamedSecurityInfo

* get security info for src path

* finally set security attrs

* add unit tests

* mimick os.makedirs() behavior and raise if dst dir exists

* set 2 paths for OSError object

* set 2 paths for OSError object

* expand windows test

* in case of exception on os.sendfile() set filename and filename2 exception attributes

* set 2 filenames (src, dst) for OSError in case copyfile() fails on OSX

* update doc

* do not use CreateDirectoryEx() in copytree() if source dir is a symlink (breaks test_copytree_symlink_dir); instead just create a plain dir and remain consistent with POSIX implementation

* use bytearray() and readinto()

* use memoryview() with bytearray()

* refactoring + introduce a new _fastcopy_binfileobj() fun

* remove CopyFileEx and other C wrappers

* remove code related to CopyFileEx

* Recognize binary files in copyfileobj()
...and use fastest _fastcopy_binfileobj() when possible

* set 1MB copy bufsize on win; also add a global _COPY_BUFSIZE variable

* use ctx manager for memoryview()

* update doc

* remove outdated doc

* remove last CopyFileEx remnants

* OSX - use fcopyfile(3) instead of copyfile(3)

...as an extra safety measure: in case src/dst are "exotic" files (non
regular or living on a network fs etc.) we better fail on open() instead
of copyfile(3) as we're not quite sure what's gonna happen in that
case.

* update doc

3 files changed, 78 insertions, 2 deletions

diff --git a/Modules/_winapi.c b/Modules/_winapi.c
index c596cba..75d1f06 100644
--- a/Modules/_winapi.c
+++ b/Modules/_winapi.c
@@ -163,6 +163,7 @@ create_converter('LPSECURITY_ATTRIBUTES', '" F_POINTER "')
 create_converter('BOOL', 'i') # F_BOOL used previously (always 'i')
 create_converter('DWORD', 'k') # F_DWORD is always "k" (which is much shorter)
 create_converter('LPCTSTR', 's')
+create_converter('LPCWSTR', 'u')
 create_converter('LPWSTR', 'u')
 create_converter('UINT', 'I') # F_UINT used previously (always 'I')
 
@@ -186,7 +187,7 @@ class DWORD_return_converter(CReturnConverter):
         data.return_conversion.append(
             'return_value = Py_BuildValue("k", _return_value);\n')
 [python start generated code]*/
-/*[python end generated code: output=da39a3ee5e6b4b0d input=4527052fe06e5823]*/
+/*[python end generated code: output=da39a3ee5e6b4b0d input=27456f8555228b62]*/
 
 #include "clinic/_winapi.c.h"
 
diff --git a/Modules/clinic/posixmodule.c.h b/Modules/clinic/posixmodule.c.h
index e4bbd08..c41d131 100644
--- a/Modules/clinic/posixmodule.c.h
+++ b/Modules/clinic/posixmodule.c.h
@@ -3853,6 +3853,40 @@ exit:
     return return_value;
 }
 
+#if defined(__APPLE__)
+
+PyDoc_STRVAR(os__fcopyfile__doc__,
+"_fcopyfile($module, infd, outfd, flags, /)\n"
+"--\n"
+"\n"
+"Efficiently copy content or metadata of 2 regular file descriptors (OSX).");
+
+#define OS__FCOPYFILE_METHODDEF    \
+    {"_fcopyfile", (PyCFunction)os__fcopyfile, METH_FASTCALL, os__fcopyfile__doc__},
+
+static PyObject *
+os__fcopyfile_impl(PyObject *module, int infd, int outfd, int flags);
+
+static PyObject *
+os__fcopyfile(PyObject *module, PyObject *const *args, Py_ssize_t nargs)
+{
+    PyObject *return_value = NULL;
+    int infd;
+    int outfd;
+    int flags;
+
+    if (!_PyArg_ParseStack(args, nargs, "iii:_fcopyfile",
+        &infd, &outfd, &flags)) {
+        goto exit;
+    }
+    return_value = os__fcopyfile_impl(module, infd, outfd, flags);
+
+exit:
+    return return_value;
+}
+
+#endif /* defined(__APPLE__) */
+
 PyDoc_STRVAR(os_fstat__doc__,
 "fstat($module, /, fd)\n"
 "--\n"
@@ -6414,6 +6448,10 @@ exit:
     #define OS_PREADV_METHODDEF
 #endif /* !defined(OS_PREADV_METHODDEF) */
 
+#ifndef OS__FCOPYFILE_METHODDEF
+    #define OS__FCOPYFILE_METHODDEF
+#endif /* !defined(OS__FCOPYFILE_METHODDEF) */
+
 #ifndef OS_PIPE_METHODDEF
     #define OS_PIPE_METHODDEF
 #endif /* !defined(OS_PIPE_METHODDEF) */
@@ -6589,4 +6627,4 @@ exit:
 #ifndef OS_GETRANDOM_METHODDEF
     #define OS_GETRANDOM_METHODDEF
 #endif /* !defined(OS_GETRANDOM_METHODDEF) */
-/*[clinic end generated code: output=8d3d9dddf254c3c2 input=a9049054013a1b77]*/
+/*[clinic end generated code: output=b5d1ec71bc6f0651 input=a9049054013a1b77]*/
diff --git a/Modules/posixmodule.c b/Modules/posixmodule.c
index 247af1b..24d8be6 100644
--- a/Modules/posixmodule.c
+++ b/Modules/posixmodule.c
@@ -97,6 +97,10 @@ corresponding Unix manual entries for more information on calls.");
 #include <sys/sendfile.h>
 #endif
 
+#if defined(__APPLE__)
+#include <copyfile.h>
+#endif
+
 #ifdef HAVE_SCHED_H
 #include <sched.h>
 #endif
@@ -8742,6 +8746,34 @@ done:
 #endif /* HAVE_SENDFILE */
 
 
+#if defined(__APPLE__)
+/*[clinic input]
+os._fcopyfile
+
+    infd: int
+    outfd: int
+    flags: int
+    /
+
+Efficiently copy content or metadata of 2 regular file descriptors (OSX).
+[clinic start generated code]*/
+
+static PyObject *
+os__fcopyfile_impl(PyObject *module, int infd, int outfd, int flags)
+/*[clinic end generated code: output=8e8885c721ec38e3 input=aeb9456804eec879]*/
+{
+    int ret;
+
+    Py_BEGIN_ALLOW_THREADS
+    ret = fcopyfile(infd, outfd, NULL, flags);
+    Py_END_ALLOW_THREADS
+    if (ret < 0)
+        return posix_error();
+    Py_RETURN_NONE;
+}
+#endif
+
+
 /*[clinic input]
 os.fstat
 
@@ -12918,6 +12950,7 @@ static PyMethodDef posix_methods[] = {
     OS_UTIME_METHODDEF
     OS_TIMES_METHODDEF
     OS__EXIT_METHODDEF
+    OS__FCOPYFILE_METHODDEF
     OS_EXECV_METHODDEF
     OS_EXECVE_METHODDEF
     OS_SPAWNV_METHODDEF
@@ -13537,6 +13570,10 @@ all_ins(PyObject *m)
     if (PyModule_AddIntMacro(m, GRND_NONBLOCK)) return -1;
 #endif
 
+#if defined(__APPLE__)
+    if (PyModule_AddIntConstant(m, "_COPYFILE_DATA", COPYFILE_DATA)) return -1;
+#endif
+
     return 0;
 }