1 | //! This is a densely packed error representation which is used on targets with |
2 | //! 64-bit pointers. |
3 | //! |
4 | //! (Note that `bitpacked` vs `unpacked` here has no relationship to |
5 | //! `#[repr(packed)]`, it just refers to attempting to use any available bits in |
6 | //! a more clever manner than `rustc`'s default layout algorithm would). |
7 | //! |
8 | //! Conceptually, it stores the same data as the "unpacked" equivalent we use on |
9 | //! other targets. Specifically, you can imagine it as an optimized version of |
10 | //! the following enum (which is roughly equivalent to what's stored by |
11 | //! `repr_unpacked::Repr`, e.g. `super::ErrorData<Box<Custom>>`): |
12 | //! |
13 | //! ```ignore (exposition-only) |
14 | //! enum ErrorData { |
15 | //! Os(i32), |
16 | //! Simple(ErrorKind), |
17 | //! SimpleMessage(&'static SimpleMessage), |
18 | //! Custom(Box<Custom>), |
19 | //! } |
20 | //! ``` |
21 | //! |
22 | //! However, it packs this data into a 64bit non-zero value. |
23 | //! |
24 | //! This optimization not only allows `io::Error` to occupy a single pointer, |
25 | //! but improves `io::Result` as well, especially for situations like |
26 | //! `io::Result<()>` (which is now 64 bits) or `io::Result<u64>` (which is now |
27 | //! 128 bits), which are quite common. |
28 | //! |
29 | //! # Layout |
30 | //! Tagged values are 64 bits, with the 2 least significant bits used for the |
31 | //! tag. This means there are 4 "variants": |
32 | //! |
33 | //! - **Tag 0b00**: The first variant is equivalent to |
34 | //! `ErrorData::SimpleMessage`, and holds a `&'static SimpleMessage` directly. |
35 | //! |
36 | //! `SimpleMessage` has an alignment >= 4 (which is requested with |
37 | //! `#[repr(align)]` and checked statically at the bottom of this file), which |
38 | //! means every `&'static SimpleMessage` should have the both tag bits as 0, |
39 | //! meaning its tagged and untagged representation are equivalent. |
40 | //! |
41 | //! This means we can skip tagging it, which is necessary as this variant can |
42 | //! be constructed from a `const fn`, which probably cannot tag pointers (or |
43 | //! at least it would be difficult). |
44 | //! |
45 | //! - **Tag 0b01**: The other pointer variant holds the data for |
46 | //! `ErrorData::Custom` and the remaining 62 bits are used to store a |
47 | //! `Box<Custom>`. `Custom` also has alignment >= 4, so the bottom two bits |
48 | //! are free to use for the tag. |
49 | //! |
50 | //! The only important thing to note is that `ptr::wrapping_add` and |
51 | //! `ptr::wrapping_sub` are used to tag the pointer, rather than bitwise |
52 | //! operations. This should preserve the pointer's provenance, which would |
53 | //! otherwise be lost. |
54 | //! |
55 | //! - **Tag 0b10**: Holds the data for `ErrorData::Os(i32)`. We store the `i32` |
56 | //! in the pointer's most significant 32 bits, and don't use the bits `2..32` |
57 | //! for anything. Using the top 32 bits is just to let us easily recover the |
58 | //! `i32` code with the correct sign. |
59 | //! |
60 | //! - **Tag 0b11**: Holds the data for `ErrorData::Simple(ErrorKind)`. This |
61 | //! stores the `ErrorKind` in the top 32 bits as well, although it doesn't |
62 | //! occupy nearly that many. Most of the bits are unused here, but it's not |
63 | //! like we need them for anything else yet. |
64 | //! |
65 | //! # Use of `NonNull<()>` |
66 | //! |
67 | //! Everything is stored in a `NonNull<()>`, which is odd, but actually serves a |
68 | //! purpose. |
69 | //! |
70 | //! Conceptually you might think of this more like: |
71 | //! |
72 | //! ```ignore (exposition-only) |
73 | //! union Repr { |
74 | //! // holds integer (Simple/Os) variants, and |
75 | //! // provides access to the tag bits. |
76 | //! bits: NonZero<u64>, |
77 | //! // Tag is 0, so this is stored untagged. |
78 | //! msg: &'static SimpleMessage, |
79 | //! // Tagged (offset) `Box<Custom>` pointer. |
80 | //! tagged_custom: NonNull<()>, |
81 | //! } |
82 | //! ``` |
83 | //! |
84 | //! But there are a few problems with this: |
85 | //! |
86 | //! 1. Union access is equivalent to a transmute, so this representation would |
87 | //! require we transmute between integers and pointers in at least one |
88 | //! direction, which may be UB (and even if not, it is likely harder for a |
89 | //! compiler to reason about than explicit ptr->int operations). |
90 | //! |
91 | //! 2. Even if all fields of a union have a niche, the union itself doesn't, |
92 | //! although this may change in the future. This would make things like |
93 | //! `io::Result<()>` and `io::Result<usize>` larger, which defeats part of |
94 | //! the motivation of this bitpacking. |
95 | //! |
96 | //! Storing everything in a `NonZero<usize>` (or some other integer) would be a |
97 | //! bit more traditional for pointer tagging, but it would lose provenance |
98 | //! information, couldn't be constructed from a `const fn`, and would probably |
99 | //! run into other issues as well. |
100 | //! |
101 | //! The `NonNull<()>` seems like the only alternative, even if it's fairly odd |
102 | //! to use a pointer type to store something that may hold an integer, some of |
103 | //! the time. |
104 | |
105 | use core::marker::PhantomData; |
106 | use core::num::NonZeroUsize; |
107 | use core::ptr::NonNull; |
108 | |
109 | use super::{Custom, ErrorData, ErrorKind, RawOsError, SimpleMessage}; |
110 | |
111 | // The 2 least-significant bits are used as tag. |
112 | const TAG_MASK: usize = 0b11; |
113 | const TAG_SIMPLE_MESSAGE: usize = 0b00; |
114 | const TAG_CUSTOM: usize = 0b01; |
115 | const TAG_OS: usize = 0b10; |
116 | const TAG_SIMPLE: usize = 0b11; |
117 | |
118 | /// The internal representation. |
119 | /// |
120 | /// See the module docs for more, this is just a way to hack in a check that we |
121 | /// indeed are not unwind-safe. |
122 | /// |
123 | /// ```compile_fail,E0277 |
124 | /// fn is_unwind_safe<T: core::panic::UnwindSafe>() {} |
125 | /// is_unwind_safe::<std::io::Error>(); |
126 | /// ``` |
127 | #[repr (transparent)] |
128 | #[rustc_insignificant_dtor ] |
129 | pub(super) struct Repr(NonNull<()>, PhantomData<ErrorData<Box<Custom>>>); |
130 | |
131 | // All the types `Repr` stores internally are Send + Sync, and so is it. |
132 | unsafe impl Send for Repr {} |
133 | unsafe impl Sync for Repr {} |
134 | |
135 | impl Repr { |
136 | pub(super) fn new(dat: ErrorData<Box<Custom>>) -> Self { |
137 | match dat { |
138 | ErrorData::Os(code) => Self::new_os(code), |
139 | ErrorData::Simple(kind) => Self::new_simple(kind), |
140 | ErrorData::SimpleMessage(simple_message) => Self::new_simple_message(simple_message), |
141 | ErrorData::Custom(b) => Self::new_custom(b), |
142 | } |
143 | } |
144 | |
145 | pub(super) fn new_custom(b: Box<Custom>) -> Self { |
146 | let p = Box::into_raw(b).cast::<u8>(); |
147 | // Should only be possible if an allocator handed out a pointer with |
148 | // wrong alignment. |
149 | debug_assert_eq!(p.addr() & TAG_MASK, 0); |
150 | // Note: We know `TAG_CUSTOM <= size_of::<Custom>()` (static_assert at |
151 | // end of file), and both the start and end of the expression must be |
152 | // valid without address space wraparound due to `Box`'s semantics. |
153 | // |
154 | // This means it would be correct to implement this using `ptr::add` |
155 | // (rather than `ptr::wrapping_add`), but it's unclear this would give |
156 | // any benefit, so we just use `wrapping_add` instead. |
157 | let tagged = p.wrapping_add(TAG_CUSTOM).cast::<()>(); |
158 | // Safety: `TAG_CUSTOM + p` is the same as `TAG_CUSTOM | p`, |
159 | // because `p`'s alignment means it isn't allowed to have any of the |
160 | // `TAG_BITS` set (you can verify that addition and bitwise-or are the |
161 | // same when the operands have no bits in common using a truth table). |
162 | // |
163 | // Then, `TAG_CUSTOM | p` is not zero, as that would require |
164 | // `TAG_CUSTOM` and `p` both be zero, and neither is (as `p` came from a |
165 | // box, and `TAG_CUSTOM` just... isn't zero -- it's `0b01`). Therefore, |
166 | // `TAG_CUSTOM + p` isn't zero and so `tagged` can't be, and the |
167 | // `new_unchecked` is safe. |
168 | let res = Self(unsafe { NonNull::new_unchecked(tagged) }, PhantomData); |
169 | // quickly smoke-check we encoded the right thing (This generally will |
170 | // only run in std's tests, unless the user uses -Zbuild-std) |
171 | debug_assert!(matches!(res.data(), ErrorData::Custom(_)), "repr(custom) encoding failed" ); |
172 | res |
173 | } |
174 | |
175 | #[inline ] |
176 | pub(super) fn new_os(code: RawOsError) -> Self { |
177 | let utagged = ((code as usize) << 32) | TAG_OS; |
178 | // Safety: `TAG_OS` is not zero, so the result of the `|` is not 0. |
179 | let res = Self( |
180 | NonNull::without_provenance(unsafe { NonZeroUsize::new_unchecked(utagged) }), |
181 | PhantomData, |
182 | ); |
183 | // quickly smoke-check we encoded the right thing (This generally will |
184 | // only run in std's tests, unless the user uses -Zbuild-std) |
185 | debug_assert!( |
186 | matches!(res.data(), ErrorData::Os(c) if c == code), |
187 | "repr(os) encoding failed for {code}" |
188 | ); |
189 | res |
190 | } |
191 | |
192 | #[inline ] |
193 | pub(super) fn new_simple(kind: ErrorKind) -> Self { |
194 | let utagged = ((kind as usize) << 32) | TAG_SIMPLE; |
195 | // Safety: `TAG_SIMPLE` is not zero, so the result of the `|` is not 0. |
196 | let res = Self( |
197 | NonNull::without_provenance(unsafe { NonZeroUsize::new_unchecked(utagged) }), |
198 | PhantomData, |
199 | ); |
200 | // quickly smoke-check we encoded the right thing (This generally will |
201 | // only run in std's tests, unless the user uses -Zbuild-std) |
202 | debug_assert!( |
203 | matches!(res.data(), ErrorData::Simple(k) if k == kind), |
204 | "repr(simple) encoding failed {:?}" , |
205 | kind, |
206 | ); |
207 | res |
208 | } |
209 | |
210 | #[inline ] |
211 | pub(super) const fn new_simple_message(m: &'static SimpleMessage) -> Self { |
212 | // Safety: References are never null. |
213 | Self(unsafe { NonNull::new_unchecked(m as *const _ as *mut ()) }, PhantomData) |
214 | } |
215 | |
216 | #[inline ] |
217 | pub(super) fn data(&self) -> ErrorData<&Custom> { |
218 | // Safety: We're a Repr, decode_repr is fine. |
219 | unsafe { decode_repr(self.0, |c| &*c) } |
220 | } |
221 | |
222 | #[inline ] |
223 | pub(super) fn data_mut(&mut self) -> ErrorData<&mut Custom> { |
224 | // Safety: We're a Repr, decode_repr is fine. |
225 | unsafe { decode_repr(self.0, |c| &mut *c) } |
226 | } |
227 | |
228 | #[inline ] |
229 | pub(super) fn into_data(self) -> ErrorData<Box<Custom>> { |
230 | let this = core::mem::ManuallyDrop::new(self); |
231 | // Safety: We're a Repr, decode_repr is fine. The `Box::from_raw` is |
232 | // safe because we prevent double-drop using `ManuallyDrop`. |
233 | unsafe { decode_repr(this.0, |p| Box::from_raw(p)) } |
234 | } |
235 | } |
236 | |
237 | impl Drop for Repr { |
238 | #[inline ] |
239 | fn drop(&mut self) { |
240 | // Safety: We're a Repr, decode_repr is fine. The `Box::from_raw` is |
241 | // safe because we're being dropped. |
242 | unsafe { |
243 | let _ = decode_repr(self.0, |p: *mut Custom| Box::<Custom>::from_raw(p)); |
244 | } |
245 | } |
246 | } |
247 | |
248 | // Shared helper to decode a `Repr`'s internal pointer into an ErrorData. |
249 | // |
250 | // Safety: `ptr`'s bits should be encoded as described in the document at the |
251 | // top (it should `some_repr.0`) |
252 | #[inline ] |
253 | unsafe fn decode_repr<C, F>(ptr: NonNull<()>, make_custom: F) -> ErrorData<C> |
254 | where |
255 | F: FnOnce(*mut Custom) -> C, |
256 | { |
257 | let bits = ptr.as_ptr().addr(); |
258 | match bits & TAG_MASK { |
259 | TAG_OS => { |
260 | let code = ((bits as i64) >> 32) as RawOsError; |
261 | ErrorData::Os(code) |
262 | } |
263 | TAG_SIMPLE => { |
264 | let kind_bits = (bits >> 32) as u32; |
265 | let kind = kind_from_prim(kind_bits).unwrap_or_else(|| { |
266 | debug_assert!(false, "Invalid io::error::Repr bits: `Repr( {:#018x})`" , bits); |
267 | // This means the `ptr` passed in was not valid, which violates |
268 | // the unsafe contract of `decode_repr`. |
269 | // |
270 | // Using this rather than unwrap meaningfully improves the code |
271 | // for callers which only care about one variant (usually |
272 | // `Custom`) |
273 | unsafe { core::hint::unreachable_unchecked() }; |
274 | }); |
275 | ErrorData::Simple(kind) |
276 | } |
277 | TAG_SIMPLE_MESSAGE => { |
278 | // SAFETY: per tag |
279 | unsafe { ErrorData::SimpleMessage(&*ptr.cast::<SimpleMessage>().as_ptr()) } |
280 | } |
281 | TAG_CUSTOM => { |
282 | // It would be correct for us to use `ptr::byte_sub` here (see the |
283 | // comment above the `wrapping_add` call in `new_custom` for why), |
284 | // but it isn't clear that it makes a difference, so we don't. |
285 | let custom = ptr.as_ptr().wrapping_byte_sub(TAG_CUSTOM).cast::<Custom>(); |
286 | ErrorData::Custom(make_custom(custom)) |
287 | } |
288 | _ => { |
289 | // Can't happen, and compiler can tell |
290 | unreachable!(); |
291 | } |
292 | } |
293 | } |
294 | |
295 | // This compiles to the same code as the check+transmute, but doesn't require |
296 | // unsafe, or to hard-code max ErrorKind or its size in a way the compiler |
297 | // couldn't verify. |
298 | #[inline ] |
299 | fn kind_from_prim(ek: u32) -> Option<ErrorKind> { |
300 | macro_rules! from_prim { |
301 | ($prim:expr => $Enum:ident { $($Variant:ident),* $(,)? }) => {{ |
302 | // Force a compile error if the list gets out of date. |
303 | const _: fn(e: $Enum) = |e: $Enum| match e { |
304 | $($Enum::$Variant => ()),* |
305 | }; |
306 | match $prim { |
307 | $(v if v == ($Enum::$Variant as _) => Some($Enum::$Variant),)* |
308 | _ => None, |
309 | } |
310 | }} |
311 | } |
312 | from_prim!(ek => ErrorKind { |
313 | NotFound, |
314 | PermissionDenied, |
315 | ConnectionRefused, |
316 | ConnectionReset, |
317 | HostUnreachable, |
318 | NetworkUnreachable, |
319 | ConnectionAborted, |
320 | NotConnected, |
321 | AddrInUse, |
322 | AddrNotAvailable, |
323 | NetworkDown, |
324 | BrokenPipe, |
325 | AlreadyExists, |
326 | WouldBlock, |
327 | NotADirectory, |
328 | IsADirectory, |
329 | DirectoryNotEmpty, |
330 | ReadOnlyFilesystem, |
331 | FilesystemLoop, |
332 | StaleNetworkFileHandle, |
333 | InvalidInput, |
334 | InvalidData, |
335 | TimedOut, |
336 | WriteZero, |
337 | StorageFull, |
338 | NotSeekable, |
339 | QuotaExceeded, |
340 | FileTooLarge, |
341 | ResourceBusy, |
342 | ExecutableFileBusy, |
343 | Deadlock, |
344 | CrossesDevices, |
345 | TooManyLinks, |
346 | InvalidFilename, |
347 | ArgumentListTooLong, |
348 | Interrupted, |
349 | Other, |
350 | UnexpectedEof, |
351 | Unsupported, |
352 | OutOfMemory, |
353 | InProgress, |
354 | Uncategorized, |
355 | }) |
356 | } |
357 | |
358 | // Some static checking to alert us if a change breaks any of the assumptions |
359 | // that our encoding relies on for correctness and soundness. (Some of these are |
360 | // a bit overly thorough/cautious, admittedly) |
361 | // |
362 | // If any of these are hit on a platform that std supports, we should likely |
363 | // just use `repr_unpacked.rs` there instead (unless the fix is easy). |
364 | macro_rules! static_assert { |
365 | ($condition:expr) => { |
366 | const _: () = assert!($condition); |
367 | }; |
368 | (@usize_eq: $lhs:expr, $rhs:expr) => { |
369 | const _: [(); $lhs] = [(); $rhs]; |
370 | }; |
371 | } |
372 | |
373 | // The bitpacking we use requires pointers be exactly 64 bits. |
374 | static_assert!(@usize_eq: size_of::<NonNull<()>>(), 8); |
375 | |
376 | // We also require pointers and usize be the same size. |
377 | static_assert!(@usize_eq: size_of::<NonNull<()>>(), size_of::<usize>()); |
378 | |
379 | // `Custom` and `SimpleMessage` need to be thin pointers. |
380 | static_assert!(@usize_eq: size_of::<&'static SimpleMessage>(), 8); |
381 | static_assert!(@usize_eq: size_of::<Box<Custom>>(), 8); |
382 | |
383 | static_assert!((TAG_MASK + 1).is_power_of_two()); |
384 | // And they must have sufficient alignment. |
385 | static_assert!(align_of::<SimpleMessage>() >= TAG_MASK + 1); |
386 | static_assert!(align_of::<Custom>() >= TAG_MASK + 1); |
387 | |
388 | static_assert!(@usize_eq: TAG_MASK & TAG_SIMPLE_MESSAGE, TAG_SIMPLE_MESSAGE); |
389 | static_assert!(@usize_eq: TAG_MASK & TAG_CUSTOM, TAG_CUSTOM); |
390 | static_assert!(@usize_eq: TAG_MASK & TAG_OS, TAG_OS); |
391 | static_assert!(@usize_eq: TAG_MASK & TAG_SIMPLE, TAG_SIMPLE); |
392 | |
393 | // This is obviously true (`TAG_CUSTOM` is `0b01`), but in `Repr::new_custom` we |
394 | // offset a pointer by this value, and expect it to both be within the same |
395 | // object, and to not wrap around the address space. See the comment in that |
396 | // function for further details. |
397 | // |
398 | // Actually, at the moment we use `ptr::wrapping_add`, not `ptr::add`, so this |
399 | // check isn't needed for that one, although the assertion that we don't |
400 | // actually wrap around in that wrapping_add does simplify the safety reasoning |
401 | // elsewhere considerably. |
402 | static_assert!(size_of::<Custom>() >= TAG_CUSTOM); |
403 | |
404 | // These two store a payload which is allowed to be zero, so they must be |
405 | // non-zero to preserve the `NonNull`'s range invariant. |
406 | static_assert!(TAG_OS != 0); |
407 | static_assert!(TAG_SIMPLE != 0); |
408 | // We can't tag `SimpleMessage`s, the tag must be 0. |
409 | static_assert!(@usize_eq: TAG_SIMPLE_MESSAGE, 0); |
410 | |
411 | // Check that the point of all of this still holds. |
412 | // |
413 | // We'd check against `io::Error`, but *technically* it's allowed to vary, |
414 | // as it's not `#[repr(transparent)]`/`#[repr(C)]`. We could add that, but |
415 | // the `#[repr()]` would show up in rustdoc, which might be seen as a stable |
416 | // commitment. |
417 | static_assert!(@usize_eq: size_of::<Repr>(), 8); |
418 | static_assert!(@usize_eq: size_of::<Option<Repr>>(), 8); |
419 | static_assert!(@usize_eq: size_of::<Result<(), Repr>>(), 8); |
420 | static_assert!(@usize_eq: size_of::<Result<usize, Repr>>(), 16); |
421 | |