Windows: add fallback if canonicalize fails

library/std/src/lib.rs

@@ -390,6 +390,7 @@
 #![feature(str_internals)]
 #![feature(sync_unsafe_cell)]
 #![feature(temporary_niche_types)]
+#![feature(trim_prefix_suffix)]
 #![feature(ub_checks)]
 #![feature(uint_carryless_mul)]
 #![feature(used_with_arg)]

library/std/src/sys/fs/windows.rs

@@ -6,6 +6,7 @@ use crate::ffi::{OsStr, OsString, c_void};
 use crate::fs::TryLockError;
 use crate::io::{self, BorrowedCursor, Error, IoSlice, IoSliceMut, SeekFrom};
 use crate::mem::{self, MaybeUninit, offset_of};
+use crate::os::windows::ffi::{OsStrExt, OsStringExt};
 use crate::os::windows::io::{AsHandle, BorrowedHandle};
 use crate::os::windows::prelude::*;
 use crate::path::{Path, PathBuf};
@@ -18,6 +19,9 @@ use crate::sys::time::SystemTime;
 use crate::sys::{Align8, AsInner, FromInner, IntoInner, c, cvt};
 use crate::{fmt, ptr, slice};
 
+#[cfg(test)]
+mod tests;
+
 mod dir;
 pub use dir::Dir;
 mod remove_dir_all;
@@ -1591,14 +1595,75 @@ pub fn set_times_nofollow(p: &WCStr, times: FileTimes) -> io::Result<()> {
 }
 
 fn get_path(f: impl AsRawHandle) -> io::Result<PathBuf> {
+    let h = f.as_raw_handle();
+    // If getting the canonical path fails with ERROR_INVALID_FUNCTION
+    // then it's likely it failed to resolve the path's drive.
+    // In that case, use the fallback method to resolve it.
+    let invalid_function = Some(c::ERROR_INVALID_FUNCTION as i32);
+    match get_path_canonical(h) {
+        Err(e) if e.raw_os_error() == invalid_function => get_path_fallback(h).ok_or(e),
+        result => result,
+    }
+}
+
+fn get_path_canonical(handle: c::HANDLE) -> io::Result<PathBuf> {
     fill_utf16_buf(
-        |buf, sz| unsafe {
-            c::GetFinalPathNameByHandleW(f.as_raw_handle(), buf, sz, c::VOLUME_NAME_DOS)
-        },
+        |buf, sz| unsafe { c::GetFinalPathNameByHandleW(handle, buf, sz, c::VOLUME_NAME_DOS) },
         |buf| PathBuf::from(OsString::from_wide(buf)),
     )
 }
 
+/// Fallback in case `get_path_canonical` fails.
+///
+/// `get_path_canonical` can fail if the Win32 drive name cannot be resolved.
+/// This can happen with certain third party drivers that don't integrate
+/// with the mount manager.
+///
+/// Instead we manually do the same job by getting the NT path
+/// and then finding the first drive letter that points to a prefix of
+/// that path. From there we can construct a Win32 path.
+///
+/// It's implemented by first getting the NT path, which should always succeed.
+/// Then we use [`GetLogicalDrives`] to get a bit array of win32 drive letters
+/// from 'A' to 'Z'. If the corresponding bit is set then it means that drive exists.
+/// E.g. bit 2 being set means there's a `C:` drive.
+///
+/// Then for each drive we use [`QueryDosDeviceW`] to see the NT path that drive resolves to.
+/// If that path is a prefix to the path we got initially then we treat that as the canonical drive letter.
+/// So in the unlikely even two drives point to the same device, the lowest one is considered canonical.
+///
+/// [`GetLogicalDrives`]: https://learn.microsoft.com/en-us/windows/win32/api/fileapi/nf-fileapi-getlogicaldrives
+/// [`QueryDosDeviceW`]:
+fn get_path_fallback(handle: c::HANDLE) -> Option<PathBuf> {
+    fill_utf16_buf(
+        |buf, sz| unsafe { c::GetFinalPathNameByHandleW(handle, buf, sz, c::VOLUME_NAME_NT) },
+        |nt_path| {
+            let mut buf = [0_u16; c::MAX_PATH as usize];
+            for letter in api::get_logical_drives() {
+                let device_name = [letter as u16, b':' as u16, 0];
+                // SAFETY: `device_name` is a null terminated u16 string
+                if let Some(drive_path) = unsafe { api::query_dos_device(&device_name, &mut buf) } {
+                    if let Some(nt_path) = nt_path.strip_prefix(drive_path) {
+                        // Reserve approximately enough space for the drive + path.
+                        let mut path = Vec::with_capacity(r"\\?\C:".len() + nt_path.len());
+                        // Create a verbatim drive root (e.g. \\?\C:)
+                        path.extend_from_slice(&[b'\\', b'\\', b'?', b'\\', letter, b':']);
+                        path.extend(OsString::from_wide(nt_path).into_encoded_bytes());
+                        // SAFETY: All characters are either in the ASCII range (the prefix)
+                        // or else came from an OsString.
+                        unsafe {
+                            return Some(OsString::from_encoded_bytes_unchecked(path).into());
+                        }
+                    }
+                }
+            }
+            None
+        },
+    )
+    .ok()
+    .flatten()
+}
+
 pub fn canonicalize(p: &WCStr) -> io::Result<PathBuf> {
     let mut opts = OpenOptions::new();
     // No read or write permissions are necessary

library/std/src/sys/fs/windows/tests.rs

@@ -0,0 +1,21 @@
+use super::{get_path_canonical, get_path_fallback};
+use crate::env;
+use crate::fs::{File, canonicalize};
+use crate::os::windows::io::AsRawHandle;
+use crate::test_helpers::tmpdir;
+
+#[test]
+/// Test that `get_path_canonical` and `get_path_fallback` return the exact same path.
+fn canonicalize_fallback() {
+    let t = tmpdir();
+    let fname = t.join("hello.txt");
+    // This test may break if run in an environment that requires the fallback.
+    // So skip it if not in CI.
+    if env::var_os("CI").is_none() && canonicalize(&fname).is_err() {
+        return;
+    }
+    let f = File::create(fname).unwrap();
+    let canonical = get_path_canonical(f.as_raw_handle()).unwrap();
+    let fallback = get_path_fallback(f.as_raw_handle()).unwrap();
+    assert_eq!(canonical, fallback);
+}

library/std/src/sys/pal/windows/api.rs

@@ -364,3 +364,42 @@ pub macro unicode_str {
         )
     }
 }
+
+/// Returns a list of enabled drive letters.
+///
+/// This is a wrapper around [`GetLogicalDrives`].
+/// Each letter is returned as an ascii byte.
+///
+/// [`GetLogicalDrives`]: (https://learn.microsoft.com/en-us/windows/win32/api/fileapi/nf-fileapi-getlogicaldrives)
+pub fn get_logical_drives() -> impl Iterator<Item = u8> {
+    // SAFETY: `GetLogicalDrives` only returns information.
+    let drives = unsafe { c::GetLogicalDrives() };
+    (b'A'..=b'Z').filter(move |letter| drives >> (letter - b'A') & 1 == 1)
+}
+
+/// Get the NT path a device name points to.
+///
+/// # Safety
+///
+/// `device_name` must be null-terminated.
+// FIXME: Use a null-terminated wide string type to assert validity, similar to CStr.
+// Then this function can be safe.
+pub unsafe fn query_dos_device<'a>(
+    device_name: &[u16],
+    buffer: &'a mut [u16],
+) -> Option<&'a [u16]> {
+    let device_ptr = device_name.as_ptr();
+    let buffer_ptr = buffer.as_mut_ptr();
+    let buffer_len = buffer.len().try_into().ok()?;
+    // SAFETY: `device_ptr` points to a null-terminated u16 string.
+    // `buffer_ptr` is writeable up to buffer_len u16s.
+    let result = unsafe { c::QueryDosDeviceW(device_ptr, buffer_ptr, buffer_len) } as usize;
+    if result > 0 {
+        // QueryDosDeviceW returns a list of null-terminated strings where the list itself is also null-terminated
+        // In the case where you pass a device name (which we always) it only returns one string.
+        // Therefore to get the string we trim off both the list null termination and the string null termination.
+        Some(buffer[..result].trim_suffix(&[0, 0]))
+    } else {
+        None
+    }
+}

library/std/src/sys/pal/windows/c/bindings.txt

@@ -2181,6 +2181,7 @@ GETFINALPATHNAMEBYHANDLE_FLAGS
 GetFinalPathNameByHandleW
 GetFullPathNameW
 GetLastError
+GetLogicalDrives
 GetModuleFileNameW
 GetModuleHandleA
 GetModuleHandleExW
@@ -2354,6 +2355,7 @@ PROFILE_KERNEL
 PROFILE_SERVER
 PROFILE_USER
 PROGRESS_CONTINUE
+QueryDosDeviceW
 QueryPerformanceCounter
 QueryPerformanceFrequency
 READ_CONTROL
@@ -2508,6 +2510,7 @@ UpdateProcThreadAttribute
 VOLUME_NAME_DOS
 VOLUME_NAME_GUID
 VOLUME_NAME_NONE
+VOLUME_NAME_NT
 WAIT_ABANDONED
 WAIT_ABANDONED_0
 WAIT_FAILED

library/std/src/sys/pal/windows/c/windows_sys.rs

@@ -54,6 +54,7 @@ windows_link::link!("kernel32.dll" "system" fn GetFileType(hfile : HANDLE) -> FI
 windows_link::link!("kernel32.dll" "system" fn GetFinalPathNameByHandleW(hfile : HANDLE, lpszfilepath : PWSTR, cchfilepath : u32, dwflags : GETFINALPATHNAMEBYHANDLE_FLAGS) -> u32);
 windows_link::link!("kernel32.dll" "system" fn GetFullPathNameW(lpfilename : PCWSTR, nbufferlength : u32, lpbuffer : PWSTR, lpfilepart : *mut PWSTR) -> u32);
 windows_link::link!("kernel32.dll" "system" fn GetLastError() -> WIN32_ERROR);
+windows_link::link!("kernel32.dll" "system" fn GetLogicalDrives() -> u32);
 windows_link::link!("kernel32.dll" "system" fn GetModuleFileNameW(hmodule : HMODULE, lpfilename : PWSTR, nsize : u32) -> u32);
 windows_link::link!("kernel32.dll" "system" fn GetModuleHandleA(lpmodulename : PCSTR) -> HMODULE);
 windows_link::link!("kernel32.dll" "system" fn GetModuleHandleExW(dwflags : u32, lpmodulename : PCWSTR, phmodule : *mut HMODULE) -> BOOL);
@@ -83,6 +84,7 @@ windows_link::link!("ntdll.dll" "system" fn NtReadFile(filehandle : HANDLE, even
 windows_link::link!("ntdll.dll" "system" fn NtSetInformationFile(filehandle : HANDLE, iostatusblock : *mut IO_STATUS_BLOCK, fileinformation : *const core::ffi::c_void, length : u32, fileinformationclass : FILE_INFORMATION_CLASS) -> NTSTATUS);
 windows_link::link!("ntdll.dll" "system" fn NtWriteFile(filehandle : HANDLE, event : HANDLE, apcroutine : PIO_APC_ROUTINE, apccontext : *const core::ffi::c_void, iostatusblock : *mut IO_STATUS_BLOCK, buffer : *const core::ffi::c_void, length : u32, byteoffset : *const i64, key : *const u32) -> NTSTATUS);
 windows_link::link!("advapi32.dll" "system" fn OpenProcessToken(processhandle : HANDLE, desiredaccess : TOKEN_ACCESS_MASK, tokenhandle : *mut HANDLE) -> BOOL);
+windows_link::link!("kernel32.dll" "system" fn QueryDosDeviceW(lpdevicename : PCWSTR, lptargetpath : PWSTR, ucchmax : u32) -> u32);
 windows_link::link!("kernel32.dll" "system" fn QueryPerformanceCounter(lpperformancecount : *mut i64) -> BOOL);
 windows_link::link!("kernel32.dll" "system" fn QueryPerformanceFrequency(lpfrequency : *mut i64) -> BOOL);
 windows_link::link!("kernel32.dll" "system" fn ReadConsoleW(hconsoleinput : HANDLE, lpbuffer : *mut core::ffi::c_void, nnumberofcharstoread : u32, lpnumberofcharsread : *mut u32, pinputcontrol : *const CONSOLE_READCONSOLE_CONTROL) -> BOOL);
@@ -3411,6 +3413,7 @@ impl Default for UNICODE_STRING {
 pub const VOLUME_NAME_DOS: GETFINALPATHNAMEBYHANDLE_FLAGS = 0u32;
 pub const VOLUME_NAME_GUID: GETFINALPATHNAMEBYHANDLE_FLAGS = 1u32;
 pub const VOLUME_NAME_NONE: GETFINALPATHNAMEBYHANDLE_FLAGS = 4u32;
+pub const VOLUME_NAME_NT: GETFINALPATHNAMEBYHANDLE_FLAGS = 2u32;
 pub const WAIT_ABANDONED: WAIT_EVENT = 128u32;
 pub const WAIT_ABANDONED_0: WAIT_EVENT = 128u32;
 pub type WAIT_EVENT = u32;

src/tools/generate-windows-sys/src/main.rs

@@ -33,7 +33,7 @@ fn main() -> Result<(), Box<dyn Error>> {
 
     let mut f = std::fs::File::options().append(true).open("windows_sys.rs")?;
     f.write_all(ARM32_SHIM.as_bytes())?;
-    writeln!(&mut f, "// ignore-tidy-filelength")?;
+    writeln!(&mut f, "// ignore-tidy-file-filelength")?;
 
     Ok(())
 }