[3.6] bpo-24658: Fix read/write greater than 2 GiB on macOS (GH-1705) (GH-9937)

On macOS, fix reading from and writing into a file with a size larger than 2 GiB.

(cherry picked from commit 74a8b6ea7e0a8508b13a1c75ec9b91febd8b5557)

diff --git a/Include/fileutils.h b/Include/fileutils.h
index 9fce7d23cf0efa1ee307cb7ba0969c9c74c645e9..4efcf13219c3987a034d3414114f96c0b4edbeb0 100644 (file)
--- a/Include/fileutils.h
+++ b/Include/fileutils.h
@@ -29,6 +29,19 @@ PyAPI_FUNC(char*) _Py_EncodeLocaleEx(
 
 PyAPI_FUNC(PyObject *) _Py_device_encoding(int);
 
+#if defined(MS_WINDOWS) || defined(__APPLE__)
+    /* On Windows, the count parameter of read() is an int (bpo-9015, bpo-9611).
+       On macOS 10.13, read() and write() with more than INT_MAX bytes
+       fail with EINVAL (bpo-24658). */
+#   define _PY_READ_MAX  INT_MAX
+#   define _PY_WRITE_MAX INT_MAX
+#else
+    /* write() should truncate the input to PY_SSIZE_T_MAX bytes,
+       but it's safer to do it ourself to have a portable behaviour */
+#   define _PY_READ_MAX  PY_SSIZE_T_MAX
+#   define _PY_WRITE_MAX PY_SSIZE_T_MAX
+#endif
+
 #ifdef MS_WINDOWS
 struct _Py_stat_struct {
     unsigned long st_dev;

diff --git a/Lib/test/test_largefile.py b/Lib/test/test_largefile.py
index d07bb8eee5a7921ac250a6917e219ceeafc3c8fe..fd2cc03259e832c32530677f9b35a4bf6e12e832 100644 (file)
--- a/Lib/test/test_largefile.py
+++ b/Lib/test/test_largefile.py
@@ -5,12 +5,12 @@ import os
 import stat
 import sys
 import unittest
-from test.support import TESTFN, requires, unlink
+from test.support import TESTFN, requires, unlink, bigmemtest
 import io  # C implementation of io
 import _pyio as pyio # Python implementation of io
 
-# size of file to create (>2GB; 2GB == 2147483648 bytes)
-size = 2500000000
+# size of file to create (>2 GiB; 2 GiB == 2,147,483,648 bytes)
+size = 2_500_000_000
 
 class LargeFileTest:
     """Test that each file function works as expected for large
@@ -45,6 +45,15 @@ class LargeFileTest:
             raise cls.failureException('File was not truncated by opening '
                                        'with mode "wb"')
 
+    # _pyio.FileIO.readall() uses a temporary bytearray then casted to bytes,
+    # so memuse=2 is needed
+    @bigmemtest(size=size, memuse=2, dry_run=False)
+    def test_large_read(self, _size):
+        # bpo-24658: Test that a read greater than 2GB does not fail.
+        with self.open(TESTFN, "rb") as f:
+            self.assertEqual(len(f.read()), size + 1)
+            self.assertEqual(f.tell(), size + 1)
+
     def test_osstat(self):
         self.assertEqual(os.stat(TESTFN)[stat.ST_SIZE], size+1)
 

diff --git a/Misc/NEWS.d/next/macOS/2018-10-17-14-36-08.bpo-24658.Naddgx.rst b/Misc/NEWS.d/next/macOS/2018-10-17-14-36-08.bpo-24658.Naddgx.rst
new file mode 100644 (file)
index 0000000..ff660a1
--- /dev/null
+++ b/Misc/NEWS.d/next/macOS/2018-10-17-14-36-08.bpo-24658.Naddgx.rst
@@ -0,0 +1 @@
+On macOS, fix reading from and writing into a file with a size larger than 2 GiB.
\ No newline at end of file

diff --git a/Modules/_io/fileio.c b/Modules/_io/fileio.c
index 52cbb94b24b6b572e038d4c00caeb73108495606..e014552887fa4ebe84116e86add84a355cbbaa49 100644 (file)
--- a/Modules/_io/fileio.c
+++ b/Modules/_io/fileio.c
@@ -799,11 +799,9 @@ _io_FileIO_read_impl(fileio *self, Py_ssize_t size)
     if (size < 0)
         return _io_FileIO_readall_impl(self);
 
-#ifdef MS_WINDOWS
-    /* On Windows, the count parameter of read() is an int */
-    if (size > INT_MAX)
-        size = INT_MAX;
-#endif
+    if (size > _PY_READ_MAX) {
+        size = _PY_READ_MAX;
+    }
 
     bytes = PyBytes_FromStringAndSize(NULL, size);
     if (bytes == NULL)

diff --git a/Python/fileutils.c b/Python/fileutils.c
index b8e489125e3c69ff760e0283a5023e2301e3e528..306838ecce44d771c422f1466878c8504990c335 100644 (file)
--- a/Python/fileutils.c
+++ b/Python/fileutils.c
@@ -1263,18 +1263,9 @@ _Py_read(int fd, void *buf, size_t count)
      * handler raised an exception. */
     assert(!PyErr_Occurred());
 
-#ifdef MS_WINDOWS
-    if (count > INT_MAX) {
-        /* On Windows, the count parameter of read() is an int */
-        count = INT_MAX;
-    }
-#else
-    if (count > PY_SSIZE_T_MAX) {
-        /* if count is greater than PY_SSIZE_T_MAX,
-         * read() result is undefined */
-        count = PY_SSIZE_T_MAX;
+    if (count > _PY_READ_MAX) {
+        count = _PY_READ_MAX;
     }
-#endif
 
     _Py_BEGIN_SUPPRESS_IPH
     do {
@@ -1325,15 +1316,10 @@ _Py_write_impl(int fd, const void *buf, size_t count, int gil_held)
            depending on heap usage). */
         count = 32767;
     }
-    else if (count > INT_MAX)
-        count = INT_MAX;
-#else
-    if (count > PY_SSIZE_T_MAX) {
-        /* write() should truncate count to PY_SSIZE_T_MAX, but it's safer
-         * to do it ourself to have a portable behaviour. */
-        count = PY_SSIZE_T_MAX;
-    }
 #endif
+    if (count > _PY_WRITE_MAX) {
+        count = _PY_WRITE_MAX;
+    }
 
     if (gil_held) {
         do {