Windows: Readlink improvements (#6745)

* Windows: Use readlink emulation for File.readlink

This fixes readlink emulation for the ERROR_MORE_DATA case and general error reporting.
It now releases GVL while readlink IO operation.

The dedicated rb_readlink was introduced in commit 2ffb87995a33cdc7ba609a4b867f03f18da0c3b3
in order to improve encoding and buffer allocation.
However the encoding issues are solved since ruby-3.0 switched to UTF-8
and the buffer allocation will be improved in a later commit.

* Windows: Increase the default buffer size for reparse point info

So far nearly all queries of reparse points needed two attempts to get enough buffer.

* Windows: Remove declaration of rb_w32_wreadlink

It was removed in commit 2f6fdd3aebdee2ce04d003b206f6da78120e8235

file.c

@@ -115,6 +115,8 @@ int flock(int, int);
 # define link(f, t)      rb_w32_ulink((f), (t))
 # undef unlink
 # define unlink(p)       rb_w32_uunlink(p)
+# undef readlink
+# define readlink(f, t, l)    rb_w32_ureadlink((f), (t), (l))
 # undef rename
 # define rename(f, t)    rb_w32_urename((f), (t))
 # undef symlink
@@ -3152,7 +3154,6 @@ rb_file_s_readlink(VALUE klass, VALUE path)
     return rb_readlink(path, rb_filesystem_encoding());
 }
 
-#ifndef _WIN32
 struct readlink_arg {
     const char *path;
     char *buf;
@@ -3208,7 +3209,6 @@ rb_readlink(VALUE path, rb_encoding *enc)
 
     return v;
 }
-#endif
 #else
 #define rb_file_s_readlink rb_f_notimplement
 #endif

include/ruby/win32.h

@@ -302,7 +302,6 @@ extern DWORD  rb_w32_osver(void);
 extern int rb_w32_uchown(const char *, int, int);
 extern int rb_w32_ulink(const char *, const char *);
 extern ssize_t rb_w32_ureadlink(const char *, char *, size_t);
-extern ssize_t rb_w32_wreadlink(const WCHAR *, WCHAR *, size_t);
 extern int rb_w32_usymlink(const char *src, const char *link);
 extern int gettimeofday(struct timeval *, struct timezone *);
 extern int clock_gettime(clockid_t, struct timespec *);

win32/file.c

@@ -591,50 +591,6 @@ rb_file_expand_path_internal(VALUE fname, VALUE dname, int abs_mode, int long_na
     return result;
 }
 
-VALUE
-rb_readlink(VALUE path, rb_encoding *resultenc)
-{
-    DWORD len;
-    VALUE wtmp = 0, wpathbuf, str;
-    rb_w32_reparse_buffer_t rbuf, *rp = &rbuf;
-    WCHAR *wpath, *wbuf;
-    rb_encoding *enc;
-    UINT cp, path_cp;
-    int e;
-
-    FilePathValue(path);
-    enc = rb_enc_get(path);
-    cp = path_cp = code_page(enc);
-    if (cp == INVALID_CODE_PAGE) {
-        path = fix_string_encoding(path, enc);
-        cp = CP_UTF8;
-    }
-    len = MultiByteToWideChar(cp, 0, RSTRING_PTR(path), RSTRING_LEN(path), NULL, 0);
-    wpath = ALLOCV_N(WCHAR, wpathbuf, len+1);
-    MultiByteToWideChar(cp, 0, RSTRING_PTR(path), RSTRING_LEN(path), wpath, len);
-    wpath[len] = L'\0';
-    e = rb_w32_read_reparse_point(wpath, rp, sizeof(rbuf), &wbuf, &len);
-    if (e == ERROR_MORE_DATA) {
-        size_t size = rb_w32_reparse_buffer_size(len + 1);
-        rp = ALLOCV(wtmp, size);
-        e = rb_w32_read_reparse_point(wpath, rp, size, &wbuf, &len);
-    }
-    ALLOCV_END(wpathbuf);
-    if (e) {
-        ALLOCV_END(wtmp);
-        if (e != -1)
-            rb_syserr_fail_path(rb_w32_map_errno(e), path);
-        else /* not symlink; maybe volume mount point */
-            rb_syserr_fail_path(EINVAL, path);
-    }
-    enc = resultenc;
-    path_cp = code_page(enc);
-    len = lstrlenW(wbuf);
-    str = append_wstr(rb_enc_str_new(0, 0, enc), wbuf, len, path_cp, enc);
-    ALLOCV_END(wtmp);
-    return str;
-}
-
 int
 rb_file_load_ok(const char *path)
 {

win32/file.h

@@ -1,10 +1,8 @@
 #ifndef RUBY_WIN32_FILE_H
 #define RUBY_WIN32_FILE_H
 
-#define MAX_REPARSE_PATH_LEN 4092
-
 enum {
-    MINIMUM_REPARSE_BUFFER_PATH_LEN = 4
+    MINIMUM_REPARSE_BUFFER_PATH_LEN = 100
 };
 /* License: Ruby's */
 typedef struct {
@@ -18,14 +16,14 @@ typedef struct {
             USHORT PrintNameOffset;
             USHORT PrintNameLength;
             ULONG  Flags;
-            WCHAR  PathBuffer[4];
+            WCHAR  PathBuffer[MINIMUM_REPARSE_BUFFER_PATH_LEN];
         } SymbolicLinkReparseBuffer;
         struct {
             USHORT SubstituteNameOffset;
             USHORT SubstituteNameLength;
             USHORT PrintNameOffset;
             USHORT PrintNameLength;
-            WCHAR  PathBuffer[4];
+            WCHAR  PathBuffer[MINIMUM_REPARSE_BUFFER_PATH_LEN];
         } MountPointReparseBuffer;
     };
 } rb_w32_reparse_buffer_t;

win32/win32.c

@@ -5144,32 +5144,35 @@ rb_w32_read_reparse_point(const WCHAR *path, rb_w32_reparse_buffer_t *rp,
 static ssize_t
 w32_readlink(UINT cp, const char *path, char *buf, size_t bufsize)
 {
-    VALUE wtmp;
+    VALUE rp_buf, rp_buf_bigger = 0;
     DWORD len = MultiByteToWideChar(cp, 0, path, -1, NULL, 0);
-    size_t size = rb_w32_reparse_buffer_size(len);
+    size_t size = rb_w32_reparse_buffer_size(bufsize);
-    WCHAR *wname, *wpath = ALLOCV(wtmp, size + sizeof(WCHAR) * len);
+    WCHAR *wname;
+    WCHAR *wpath = ALLOCV(rp_buf, sizeof(WCHAR) * len + size);
     rb_w32_reparse_buffer_t *rp = (void *)(wpath + len);
     ssize_t ret;
     int e;
 
     MultiByteToWideChar(cp, 0, path, -1, wpath, len);
     e = rb_w32_read_reparse_point(wpath, rp, size, &wname, &len);
-    if (e && e != ERROR_MORE_DATA) {
+    if (e == ERROR_MORE_DATA) {
-        ALLOCV_END(wtmp);
+        size = rb_w32_reparse_buffer_size(len + 1);
-        errno = map_errno(e);
+        rp = ALLOCV(rp_buf_bigger, size);
+        e = rb_w32_read_reparse_point(wpath, rp, size, &wname, &len);
+    }
+    if (e) {
+        ALLOCV_END(rp_buf);
+        ALLOCV_END(rp_buf_bigger);
+        errno = e == -1 ? EINVAL : map_errno(e);
         return -1;
     }
-    len = lstrlenW(wname) + 1;
+    len = lstrlenW(wname);
     ret = WideCharToMultiByte(cp, 0, wname, len, buf, bufsize, NULL, NULL);
-    ALLOCV_END(wtmp);
+    ALLOCV_END(rp_buf);
-    if (e) {
+    ALLOCV_END(rp_buf_bigger);
+    if (!ret) {
         ret = bufsize;
     }
-    else if (!ret) {
-        e = GetLastError();
-        errno = map_errno(e);
-        ret = -1;
-    }
     return ret;
 }