rust: fix unsound `OwningDirstateMap`

As per the previous patch, `OwningDirstateMap` is unsound. Self-referential
structs are difficult to implement correctly in Rust since the compiler is
free to move structs around as much as it wants to. They are also very rarely
needed in practice, so the state-of-the-art on how they should be done within
the Rust rules is still a bit new.

The crate `ouroboros` is an attempt at providing a safe way (in the Rust sense)
of declaring self-referential structs. It is getting a lot attention and was
improved very quickly when soundness issues were found in the past: rather than
relying on our own (limited) review circle, we might as well use the de-facto
common crate to fix this problem. This will give us a much better chance of
finding issues should any new ones be discovered as well as the benefit of
fewer `unsafe` APIs of our own.

I was starting to think about how I would present a safe API to the old struct
but soon realized that the callback-based approach was already done in
`ouroboros`, along with a lot more care towards refusing incorrect structs.

In short: we don't return a mutable reference to the `DirstateMap` anymore, we
expect users of its API to pass a `FnOnce` that takes the map as an argument.
This allows our `OwningDirstateMap` to control the input and output lifetimes
of the code that modifies it to prevent such issues.

Changing to `ouroboros` meant changing every API with it, but it is relatively
low churn in the end. It correctly identified the example buggy modification of
`copy_map_insert` outlined in the previous patch as violating the borrow rules.

Differential Revision: https://phab.mercurial-scm.org/D12429

rust/Cargo.lock

@@ -3,6 +3,12 b''
 version = 3
 
 [[package]]
+name = "Inflector"
+version = "0.11.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "fe438c63458706e03479442743baae6c88256498e6431708f6dfc520a26515d3"
+
+[[package]]
 name = "adler"
 version = "0.2.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
@@ -18,6 +24,12 b' dependencies = ['
 ]
 
 [[package]]
+name = "aliasable"
+version = "0.1.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "250f629c0161ad8107cf89319e990051fae62832fd343083bea452d93e2205fd"
+
+[[package]]
 name = "ansi_term"
 version = "0.11.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
@@ -407,6 +419,7 b' dependencies = ['
  "log",
  "memmap2",
  "micro-timer",
+ "ouroboros",
  "pretty_assertions",
  "rand 0.8.4",
  "rand_distr",
@@ -415,7 +428,6 b' dependencies = ['
  "regex",
  "same-file",
  "sha-1",
- "stable_deref_trait",
  "tempfile",
  "twox-hash",
  "zstd",
@@ -623,6 +635,30 b' source = "registry+https://github.com/ru'
 checksum = "624a8340c38c1b80fd549087862da4ba43e08858af025b236e509b6649fc13d5"
 
 [[package]]
+name = "ouroboros"
+version = "0.15.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9f31a3b678685b150cba82b702dcdc5e155893f63610cf388d30cd988d4ca2bf"
+dependencies = [
+ "aliasable",
+ "ouroboros_macro",
+ "stable_deref_trait",
+]
+
+[[package]]
+name = "ouroboros_macro"
+version = "0.15.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "084fd65d5dd8b3772edccb5ffd1e4b7eba43897ecd0f9401e330e8c542959408"
+dependencies = [
+ "Inflector",
+ "proc-macro-error",
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
 name = "output_vt100"
 version = "0.1.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
@@ -662,6 +698,30 b' dependencies = ['
 ]
 
 [[package]]
+name = "proc-macro-error"
+version = "1.0.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "da25490ff9892aab3fcf7c36f08cfb902dd3e71ca0f9f9517bea02a73a5ce38c"
+dependencies = [
+ "proc-macro-error-attr",
+ "proc-macro2",
+ "quote",
+ "syn",
+ "version_check",
+]
+
+[[package]]
+name = "proc-macro-error-attr"
+version = "1.0.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a1be40180e52ecc98ad80b184934baf3d0d29f979574e439af5a55274b35f869"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "version_check",
+]
+
+[[package]]
 name = "proc-macro2"
 version = "1.0.24"
 source = "registry+https://github.com/rust-lang/crates.io-index"

rust/hg-core/Cargo.toml

@@ -18,6 +18,7 b' im-rc = "15.0.*"'
 itertools = "0.9"
 lazy_static = "1.4.0"
 libc = "0.2"
+ouroboros = "0.15.0"
 rand = "0.8.4"
 rand_pcg = "0.3.1"
 rand_distr = "0.4.2"
@@ -26,7 +27,6 b' regex = "1.3.9"'
 sha-1 = "0.9.6"
 twox-hash = "1.5.0"
 same-file = "1.0.6"
-stable_deref_trait = "1.2.0"
 tempfile = "3.1.0"
 crossbeam-channel = "0.4"
 micro-timer = "0.3.0"

rust/hg-core/src/dirstate/status.rs

@@ -136,8 +136,6 b' pub enum StatusError {'
     DirstateV2ParseError(DirstateV2ParseError),
 }
 
-pub type StatusResult<T> = Result<T, StatusError>;
-
 impl fmt::Display for StatusError {
     fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
         match self {

rust/hg-core/src/dirstate_tree/dirstate_map.rs

@@ -725,10 +725,11 b' where'
 
 impl OwningDirstateMap {
     pub fn clear(&mut self) {
-        let map = self.get_map_mut();
-        map.root = Default::default();
-        map.nodes_with_entry_count = 0;
-        map.nodes_with_copy_source_count = 0;
+        self.with_dmap_mut(|map| {
+            map.root = Default::default();
+            map.nodes_with_entry_count = 0;
+            map.nodes_with_copy_source_count = 0;
+        });
     }
 
     pub fn set_entry(
@@ -736,9 +737,10 b' impl OwningDirstateMap {'
         filename: &HgPath,
         entry: DirstateEntry,
     ) -> Result<(), DirstateV2ParseError> {
-        let map = self.get_map_mut();
-        map.get_or_insert(&filename)?.data = NodeData::Entry(entry);
-        Ok(())
+        self.with_dmap_mut(|map| {
+            map.get_or_insert(&filename)?.data = NodeData::Entry(entry);
+            Ok(())
+        })
     }
 
     pub fn add_file(
@@ -747,8 +749,9 b' impl OwningDirstateMap {'
         entry: DirstateEntry,
     ) -> Result<(), DirstateError> {
         let old_state = self.get(filename)?.map(|e| e.state());
-        let map = self.get_map_mut();
-        Ok(map.add_or_remove_file(filename, old_state, entry)?)
+        self.with_dmap_mut(|map| {
+            Ok(map.add_or_remove_file(filename, old_state, entry)?)
+        })
     }
 
     pub fn remove_file(
@@ -779,9 +782,10 b' impl OwningDirstateMap {'
         if size == 0 {
             self.copy_map_remove(filename)?;
         }
-        let map = self.get_map_mut();
-        let entry = DirstateEntry::new_removed(size);
-        Ok(map.add_or_remove_file(filename, old_state, entry)?)
+        self.with_dmap_mut(|map| {
+            let entry = DirstateEntry::new_removed(size);
+            Ok(map.add_or_remove_file(filename, old_state, entry)?)
+        })
     }
 
     pub fn drop_entry_and_copy_source(
@@ -791,7 +795,6 b' impl OwningDirstateMap {'
         let was_tracked = self
             .get(filename)?
             .map_or(false, |e| e.state().is_tracked());
-        let map = self.get_map_mut();
         struct Dropped {
             was_tracked: bool,
             had_entry: bool,
@@ -878,52 +881,56 b' impl OwningDirstateMap {'
             Ok(Some((dropped, remove)))
         }
 
-        if let Some((dropped, _removed)) = recur(
-            map.on_disk,
-            &mut map.unreachable_bytes,
-            &mut map.root,
-            filename,
-        )? {
-            if dropped.had_entry {
-                map.nodes_with_entry_count -= 1
+        self.with_dmap_mut(|map| {
+            if let Some((dropped, _removed)) = recur(
+                map.on_disk,
+                &mut map.unreachable_bytes,
+                &mut map.root,
+                filename,
+            )? {
+                if dropped.had_entry {
+                    map.nodes_with_entry_count -= 1
+                }
+                if dropped.had_copy_source {
+                    map.nodes_with_copy_source_count -= 1
+                }
+            } else {
+                debug_assert!(!was_tracked);
             }
-            if dropped.had_copy_source {
-                map.nodes_with_copy_source_count -= 1
-            }
-        } else {
-            debug_assert!(!was_tracked);
-        }
-        Ok(())
+            Ok(())
+        })
     }
 
     pub fn has_tracked_dir(
         &mut self,
         directory: &HgPath,
     ) -> Result<bool, DirstateError> {
-        let map = self.get_map_mut();
-        if let Some(node) = map.get_node(directory)? {
-            // A node without a `DirstateEntry` was created to hold child
-            // nodes, and is therefore a directory.
-            let state = node.state()?;
-            Ok(state.is_none() && node.tracked_descendants_count() > 0)
-        } else {
-            Ok(false)
-        }
+        self.with_dmap_mut(|map| {
+            if let Some(node) = map.get_node(directory)? {
+                // A node without a `DirstateEntry` was created to hold child
+                // nodes, and is therefore a directory.
+                let state = node.state()?;
+                Ok(state.is_none() && node.tracked_descendants_count() > 0)
+            } else {
+                Ok(false)
+            }
+        })
     }
 
     pub fn has_dir(
         &mut self,
         directory: &HgPath,
     ) -> Result<bool, DirstateError> {
-        let map = self.get_map_mut();
-        if let Some(node) = map.get_node(directory)? {
-            // A node without a `DirstateEntry` was created to hold child
-            // nodes, and is therefore a directory.
-            let state = node.state()?;
-            Ok(state.is_none() && node.descendants_with_entry_count() > 0)
-        } else {
-            Ok(false)
-        }
+        self.with_dmap_mut(|map| {
+            if let Some(node) = map.get_node(directory)? {
+                // A node without a `DirstateEntry` was created to hold child
+                // nodes, and is therefore a directory.
+                let state = node.state()?;
+                Ok(state.is_none() && node.descendants_with_entry_count() > 0)
+            } else {
+                Ok(false)
+            }
+        })
     }
 
     #[timed]
@@ -975,16 +982,29 b' impl OwningDirstateMap {'
         on_disk::write(map, can_append)
     }
 
-    pub fn status<'a>(
-        &'a mut self,
-        matcher: &'a (dyn Matcher + Sync),
+    /// `callback` allows the caller to process and do something with the
+    /// results of the status. This is needed to do so efficiently (i.e.
+    /// without cloning the `DirstateStatus` object with its paths) because
+    /// we need to borrow from `Self`.
+    pub fn with_status<R>(
+        &mut self,
+        matcher: &(dyn Matcher + Sync),
         root_dir: PathBuf,
         ignore_files: Vec<PathBuf>,
         options: StatusOptions,
-    ) -> Result<(DirstateStatus<'a>, Vec<PatternFileWarning>), StatusError>
-    {
-        let map = self.get_map_mut();
-        super::status::status(map, matcher, root_dir, ignore_files, options)
+        callback: impl for<'r> FnOnce(
+            Result<(DirstateStatus<'r>, Vec<PatternFileWarning>), StatusError>,
+        ) -> R,
+    ) -> R {
+        self.with_dmap_mut(|map| {
+            callback(super::status::status(
+                map,
+                matcher,
+                root_dir,
+                ignore_files,
+                options,
+            ))
+        })
     }
 
     pub fn copy_map_len(&self) -> usize {
@@ -1032,22 +1052,23 b' impl OwningDirstateMap {'
         &mut self,
         key: &HgPath,
     ) -> Result<Option<HgPathBuf>, DirstateV2ParseError> {
-        let map = self.get_map_mut();
-        let count = &mut map.nodes_with_copy_source_count;
-        let unreachable_bytes = &mut map.unreachable_bytes;
-        Ok(DirstateMap::get_node_mut(
-            map.on_disk,
-            unreachable_bytes,
-            &mut map.root,
-            key,
-        )?
-        .and_then(|node| {
-            if let Some(source) = &node.copy_source {
-                *count -= 1;
-                DirstateMap::count_dropped_path(unreachable_bytes, source);
-            }
-            node.copy_source.take().map(Cow::into_owned)
-        }))
+        self.with_dmap_mut(|map| {
+            let count = &mut map.nodes_with_copy_source_count;
+            let unreachable_bytes = &mut map.unreachable_bytes;
+            Ok(DirstateMap::get_node_mut(
+                map.on_disk,
+                unreachable_bytes,
+                &mut map.root,
+                key,
+            )?
+            .and_then(|node| {
+                if let Some(source) = &node.copy_source {
+                    *count -= 1;
+                    DirstateMap::count_dropped_path(unreachable_bytes, source);
+                }
+                node.copy_source.take().map(Cow::into_owned)
+            }))
+        })
     }
 
     pub fn copy_map_insert(
@@ -1055,19 +1076,20 b' impl OwningDirstateMap {'
         key: HgPathBuf,
         value: HgPathBuf,
     ) -> Result<Option<HgPathBuf>, DirstateV2ParseError> {
-        let map = self.get_map_mut();
-        let node = DirstateMap::get_or_insert_node(
-            map.on_disk,
-            &mut map.unreachable_bytes,
-            &mut map.root,
-            &key,
-            WithBasename::to_cow_owned,
-            |_ancestor| {},
-        )?;
-        if node.copy_source.is_none() {
-            map.nodes_with_copy_source_count += 1
-        }
-        Ok(node.copy_source.replace(value.into()).map(Cow::into_owned))
+        self.with_dmap_mut(|map| {
+            let node = DirstateMap::get_or_insert_node(
+                map.on_disk,
+                &mut map.unreachable_bytes,
+                &mut map.root,
+                &key,
+                WithBasename::to_cow_owned,
+                |_ancestor| {},
+            )?;
+            if node.copy_source.is_none() {
+                map.nodes_with_copy_source_count += 1
+            }
+            Ok(node.copy_source.replace(value.into()).map(Cow::into_owned))
+        })
     }
 
     pub fn len(&self) -> usize {
@@ -1115,7 +1137,7 b' impl OwningDirstateMap {'
         >,
         DirstateError,
     > {
-        let map = self.get_map_mut();
+        let map = self.get_map();
         let on_disk = map.on_disk;
         Ok(Box::new(filter_map_results(
             map.iter_nodes(),

rust/hg-core/src/dirstate_tree/owning.rs

@@ -1,142 +1,89 b''
+use crate::{DirstateError, DirstateParents};
+
 use super::dirstate_map::DirstateMap;
-use stable_deref_trait::StableDeref;
 use std::ops::Deref;
 
-/*
-// /!\ This is unsound and can cause use after free. It will be fixed in the
-// next patch
-
-// If we change `value` from its current use of `HgPathBuf` to `&HgPath`,
-// nothing here tells that `value` will outlive `OwningDirstateMap`
-pub fn copy_map_insert<'a,'owned>(
-    &'owned mut self,
-    key: &HgPath,
-    value: &'a HgPath,
-) -> Result<Option<HgPathBuf>, DirstateV2ParseError> {
-    // `'local` is smaller than `'a` here
-    let map: &'local mut DirstateMap<'local> = self.get_map_mut();
-    let node: &'local mut Node<'local> = DirstateMap::get_or_insert_node(
-        map.on_disk,
-        &mut map.unreachable_bytes,
-        &mut map.root,
-        &key,
-        WithBasename::to_cow_owned,
-        |_ancestor| {},
-    )?;
-    if node.copy_source.is_none() {
-        map.nodes_with_copy_source_count += 1
-    }
-    Ok(node.copy_source.replace(value.into()).map(Cow::into_owned))
-    // and right here ----------^^^^^^^^^^^^
-    // we are storing `&'a HgPath` in `Node<'local>` which is possible
-    // because to the compiler, `'a` is longer than ``local`.
-    // It is wrong because nothing proves that `&'a HgPath` will outlive `self`.
-}
-
-// All of this is caused by the wrong cast of the DirstateMap pointer that
-// fakes the lifetime of `DirstateMap` and ensures the compiler that it lives
-// as long as `on_disk`, which is only true for its immutable data.
-// This will be fixed in the next commit.
-*/
+use ouroboros::self_referencing;
 
 /// Keep a `DirstateMap<'on_disk>` next to the `on_disk` buffer that it
 /// borrows.
-///
-/// This is similar to [`OwningRef`] which is more limited because it
-/// represents exactly one `&T` reference next to the value it borrows, as
-/// opposed to a struct that may contain an arbitrary number of references in
-/// arbitrarily-nested data structures.
-///
-/// [`OwningRef`]: https://docs.rs/owning_ref/0.4.1/owning_ref/struct.OwningRef.html
+#[self_referencing]
 pub struct OwningDirstateMap {
-    /// Owned handle to a bytes buffer with a stable address.
-    ///
-    /// See <https://docs.rs/owning_ref/0.4.1/owning_ref/trait.StableAddress.html>.
     on_disk: Box<dyn Deref<Target = [u8]> + Send>,
-
-    /// Pointer for `Box<DirstateMap<'on_disk>>`, typed-erased because the
-    /// language cannot represent a lifetime referencing a sibling field.
-    /// This is not quite a self-referencial struct (moving this struct is not
-    /// a problem as it doesn’t change the address of the bytes buffer owned
-    /// by `on_disk`) but touches similar borrow-checker limitations.
-    ptr: *mut (),
+    #[borrows(on_disk)]
+    #[covariant]
+    map: DirstateMap<'this>,
 }
 
 impl OwningDirstateMap {
     pub fn new_empty<OnDisk>(on_disk: OnDisk) -> Self
     where
-        OnDisk: Deref<Target = [u8]> + StableDeref + Send + 'static,
+        OnDisk: Deref<Target = [u8]> + Send + 'static,
     {
         let on_disk = Box::new(on_disk);
-        let bytes: &'_ [u8] = &on_disk;
-        let map = DirstateMap::empty(bytes);
 
-        // Like in `bytes` above, this `'_` lifetime parameter borrows from
-        // the bytes buffer owned by `on_disk`.
-        let ptr: *mut DirstateMap<'_> = Box::into_raw(Box::new(map));
-
-        // Erase the pointed type entirely in order to erase the lifetime.
-        let ptr: *mut () = ptr.cast();
-
-        Self { on_disk, ptr }
+        OwningDirstateMapBuilder {
+            on_disk,
+            map_builder: |bytes| DirstateMap::empty(&bytes),
+        }
+        .build()
     }
 
-    pub fn get_pair_mut<'a>(
-        &'a mut self,
-    ) -> (&'a [u8], &'a mut DirstateMap<'a>) {
-        // SAFETY: We cast the type-erased pointer back to the same type it had
-        // in `new`, except with a different lifetime parameter. This time we
-        // connect the lifetime to that of `self`. This cast is valid because
-        // `self` owns the same `on_disk` whose buffer `DirstateMap`
-        // references. That buffer has a stable memory address because our
-        // `Self::new_empty` counstructor requires `StableDeref`.
-        let ptr: *mut DirstateMap<'a> = self.ptr.cast();
-        // SAFETY: we dereference that pointer, connecting the lifetime of the
-        // new `&mut` to that of `self`. This is valid because the
-        // raw pointer is to a boxed value, and `self` owns that box.
-        (&self.on_disk, unsafe { &mut *ptr })
-    }
+    pub fn new_v1<OnDisk>(
+        on_disk: OnDisk,
+    ) -> Result<(Self, DirstateParents), DirstateError>
+    where
+        OnDisk: Deref<Target = [u8]> + Send + 'static,
+    {
+        let on_disk = Box::new(on_disk);
+        let mut parents = DirstateParents::NULL;
 
-    pub fn get_map_mut<'a>(&'a mut self) -> &'a mut DirstateMap<'a> {
-        self.get_pair_mut().1
+        Ok((
+            OwningDirstateMapTryBuilder {
+                on_disk,
+                map_builder: |bytes| {
+                    DirstateMap::new_v1(&bytes).map(|(dmap, p)| {
+                        parents = p.unwrap_or(DirstateParents::NULL);
+                        dmap
+                    })
+                },
+            }
+            .try_build()?,
+            parents,
+        ))
     }
 
-    pub fn get_map<'a>(&'a self) -> &'a DirstateMap<'a> {
-        // SAFETY: same reasoning as in `get_pair_mut` above.
-        let ptr: *mut DirstateMap<'a> = self.ptr.cast();
-        unsafe { &*ptr }
+    pub fn new_v2<OnDisk>(
+        on_disk: OnDisk,
+        data_size: usize,
+        metadata: &[u8],
+    ) -> Result<Self, DirstateError>
+    where
+        OnDisk: Deref<Target = [u8]> + Send + 'static,
+    {
+        let on_disk = Box::new(on_disk);
+
+        OwningDirstateMapTryBuilder {
+            on_disk,
+            map_builder: |bytes| {
+                DirstateMap::new_v2(&bytes, data_size, metadata)
+            },
+        }
+        .try_build()
     }
 
-    pub fn on_disk<'a>(&'a self) -> &'a [u8] {
-        &self.on_disk
+    pub fn with_dmap_mut<R>(
+        &mut self,
+        f: impl FnOnce(&mut DirstateMap) -> R,
+    ) -> R {
+        self.with_map_mut(f)
+    }
+
+    pub fn get_map(&self) -> &DirstateMap {
+        self.borrow_map()
+    }
+
+    pub fn on_disk(&self) -> &[u8] {
+        self.borrow_on_disk()
     }
 }
-
-impl Drop for OwningDirstateMap {
-    fn drop(&mut self) {
-        // Silence a "field is never read" warning, and demonstrate that this
-        // value is still alive.
-        let _: &Box<dyn Deref<Target = [u8]> + Send> = &self.on_disk;
-        // SAFETY: this cast is the same as in `get_mut`, and is valid for the
-        // same reason. `self.on_disk` still exists at this point, drop glue
-        // will drop it implicitly after this `drop` method returns.
-        let ptr: *mut DirstateMap<'_> = self.ptr.cast();
-        // SAFETY: `Box::from_raw` takes ownership of the box away from `self`.
-        // This is fine because drop glue does nothing for `*mut ()` and we’re
-        // in `drop`, so `get` and `get_mut` cannot be called again.
-        unsafe { drop(Box::from_raw(ptr)) }
-    }
-}
-
-fn _static_assert_is_send<T: Send>() {}
-
-fn _static_assert_fields_are_send() {
-    _static_assert_is_send::<Box<DirstateMap<'_>>>();
-}
-
-// SAFETY: we don’t get this impl implicitly because `*mut (): !Send` because
-// thread-safety of raw pointers is unknown in the general case. However this
-// particular raw pointer represents a `Box<DirstateMap<'on_disk>>` that we
-// own. Since that `Box` is `Send` as shown in above, it is sound to mark
-// this struct as `Send` too.
-unsafe impl Send for OwningDirstateMap {}

rust/hg-core/src/dirstate_tree/status.rs

@@ -40,13 +40,14 b' use std::time::SystemTime;'
 /// exists in one of the two trees, depending on information requested by
 /// `options` we may need to traverse the remaining subtree.
 #[timed]
-pub fn status<'tree, 'on_disk: 'tree>(
-    dmap: &'tree mut DirstateMap<'on_disk>,
+pub fn status<'dirstate>(
+    dmap: &'dirstate mut DirstateMap,
     matcher: &(dyn Matcher + Sync),
     root_dir: PathBuf,
     ignore_files: Vec<PathBuf>,
     options: StatusOptions,
-) -> Result<(DirstateStatus<'on_disk>, Vec<PatternFileWarning>), StatusError> {
+) -> Result<(DirstateStatus<'dirstate>, Vec<PatternFileWarning>), StatusError>
+{
     // Force the global rayon threadpool to not exceed 16 concurrent threads.
     // This is a stop-gap measure until we figure out why using more than 16
     // threads makes `status` slower for each additional thread.

rust/hg-core/src/repo.rs

@@ -1,7 +1,6 b''
 use crate::changelog::Changelog;
 use crate::config::{Config, ConfigError, ConfigParseError};
 use crate::dirstate::DirstateParents;
-use crate::dirstate_tree::dirstate_map::DirstateMap;
 use crate::dirstate_tree::on_disk::Docket as DirstateDocket;
 use crate::dirstate_tree::owning::OwningDirstateMap;
 use crate::errors::HgResultExt;
@@ -340,25 +339,19 b' impl Repo {'
                 .set(Some(docket.uuid.to_owned()));
             let data_size = docket.data_size();
             let metadata = docket.tree_metadata();
-            let mut map = if let Some(data_mmap) = self
+            if let Some(data_mmap) = self
                 .hg_vfs()
                 .mmap_open(docket.data_filename())
                 .io_not_found_as_none()?
             {
-                OwningDirstateMap::new_empty(data_mmap)
+                OwningDirstateMap::new_v2(data_mmap, data_size, metadata)
             } else {
-                OwningDirstateMap::new_empty(Vec::new())
-            };
-            let (on_disk, placeholder) = map.get_pair_mut();
-            *placeholder = DirstateMap::new_v2(on_disk, data_size, metadata)?;
-            Ok(map)
+                OwningDirstateMap::new_v2(Vec::new(), data_size, metadata)
+            }
         } else {
-            let mut map = OwningDirstateMap::new_empty(dirstate_file_contents);
-            let (on_disk, placeholder) = map.get_pair_mut();
-            let (inner, parents) = DirstateMap::new_v1(on_disk)?;
-            self.dirstate_parents
-                .set(parents.unwrap_or(DirstateParents::NULL));
-            *placeholder = inner;
+            let (map, parents) =
+                OwningDirstateMap::new_v1(dirstate_file_contents)?;
+            self.dirstate_parents.set(parents);
             Ok(map)
         }
     }

rust/hg-cpython/src/dirstate/dirstate_map.rs

@@ -23,7 +23,6 b' use crate::{'
 };
 use hg::{
     dirstate::StateMapIter,
-    dirstate_tree::dirstate_map::DirstateMap as TreeDirstateMap,
     dirstate_tree::on_disk::DirstateV2ParseError,
     dirstate_tree::owning::OwningDirstateMap,
     revlog::Node,
@@ -53,18 +52,12 b' py_class!(pub class DirstateMap |py| {'
         on_disk: PyBytes,
     ) -> PyResult<PyObject> {
         let on_disk = PyBytesDeref::new(py, on_disk);
-        let mut map = OwningDirstateMap::new_empty(on_disk);
-        let (on_disk, map_placeholder) = map.get_pair_mut();
-
-        let (actual_map, parents) = TreeDirstateMap::new_v1(on_disk)
+        let (map, parents) = OwningDirstateMap::new_v1(on_disk)
             .map_err(|e| dirstate_error(py, e))?;
-        *map_placeholder = actual_map;
         let map = Self::create_instance(py, map)?;
-        let parents = parents.map(|p| {
-            let p1 = PyBytes::new(py, p.p1.as_bytes());
-            let p2 = PyBytes::new(py, p.p2.as_bytes());
-            (p1, p2)
-        });
+        let p1 = PyBytes::new(py, parents.p1.as_bytes());
+        let p2 = PyBytes::new(py, parents.p2.as_bytes());
+        let parents = (p1, p2);
         Ok((map, parents).to_py_object(py).into_object())
     }
 
@@ -79,9 +72,7 b' py_class!(pub class DirstateMap |py| {'
             PyErr::new::<exc::OSError, _>(py, format!("Dirstate error: {:?}", e))
         };
         let on_disk = PyBytesDeref::new(py, on_disk);
-        let mut map = OwningDirstateMap::new_empty(on_disk);
-        let (on_disk, map_placeholder) = map.get_pair_mut();
-        *map_placeholder = TreeDirstateMap::new_v2(
+        let map = OwningDirstateMap::new_v2(
             on_disk, data_size, tree_metadata.data(py),
         ).map_err(dirstate_error)?;
         let map = Self::create_instance(py, map)?;

rust/hg-cpython/src/dirstate/status.rs

@@ -127,25 +127,29 b' pub fn status_wrapper('
     // The caller may call `copymap.items()` separately
     let list_copies = false;
 
+    let after_status = |res: Result<(DirstateStatus<'_>, _), StatusError>| {
+        let (status_res, warnings) =
+            res.map_err(|e| handle_fallback(py, e))?;
+        build_response(py, status_res, warnings)
+    };
+
     match matcher.get_type(py).name(py).borrow() {
         "alwaysmatcher" => {
             let matcher = AlwaysMatcher;
-            let (status_res, warnings) = dmap
-                .status(
-                    &matcher,
-                    root_dir.to_path_buf(),
-                    ignore_files,
-                    StatusOptions {
-                        check_exec,
-                        list_clean,
-                        list_ignored,
-                        list_unknown,
-                        list_copies,
-                        collect_traversed_dirs,
-                    },
-                )
-                .map_err(|e| handle_fallback(py, e))?;
-            build_response(py, status_res, warnings)
+            dmap.with_status(
+                &matcher,
+                root_dir.to_path_buf(),
+                ignore_files,
+                StatusOptions {
+                    check_exec,
+                    list_clean,
+                    list_ignored,
+                    list_unknown,
+                    list_copies,
+                    collect_traversed_dirs,
+                },
+                after_status,
+            )
         }
         "exactmatcher" => {
             let files = matcher.call_method(
@@ -167,22 +171,20 b' pub fn status_wrapper('
             let files = files?;
             let matcher = FileMatcher::new(files.as_ref())
                 .map_err(|e| PyErr::new::<ValueError, _>(py, e.to_string()))?;
-            let (status_res, warnings) = dmap
-                .status(
-                    &matcher,
-                    root_dir.to_path_buf(),
-                    ignore_files,
-                    StatusOptions {
-                        check_exec,
-                        list_clean,
-                        list_ignored,
-                        list_unknown,
-                        list_copies,
-                        collect_traversed_dirs,
-                    },
-                )
-                .map_err(|e| handle_fallback(py, e))?;
-            build_response(py, status_res, warnings)
+            dmap.with_status(
+                &matcher,
+                root_dir.to_path_buf(),
+                ignore_files,
+                StatusOptions {
+                    check_exec,
+                    list_clean,
+                    list_ignored,
+                    list_unknown,
+                    list_copies,
+                    collect_traversed_dirs,
+                },
+                after_status,
+            )
         }
         "includematcher" => {
             // Get the patterns from Python even though most of them are
@@ -219,23 +221,20 b' pub fn status_wrapper('
             let matcher = IncludeMatcher::new(ignore_patterns)
                 .map_err(|e| handle_fallback(py, e.into()))?;
 
-            let (status_res, warnings) = dmap
-                .status(
-                    &matcher,
-                    root_dir.to_path_buf(),
-                    ignore_files,
-                    StatusOptions {
-                        check_exec,
-                        list_clean,
-                        list_ignored,
-                        list_unknown,
-                        list_copies,
-                        collect_traversed_dirs,
-                    },
-                )
-                .map_err(|e| handle_fallback(py, e))?;
-
-            build_response(py, status_res, warnings)
+            dmap.with_status(
+                &matcher,
+                root_dir.to_path_buf(),
+                ignore_files,
+                StatusOptions {
+                    check_exec,
+                    list_clean,
+                    list_ignored,
+                    list_unknown,
+                    list_copies,
+                    collect_traversed_dirs,
+                },
+                after_status,
+            )
         }
         e => Err(PyErr::new::<ValueError, _>(
             py,

rust/rhg/src/commands/status.rs

@@ -25,6 +25,9 b' use hg::utils::files::get_bytes_from_os_'
 use hg::utils::files::get_bytes_from_path;
 use hg::utils::files::get_path_from_bytes;
 use hg::utils::hg_path::{hg_path_to_path_buf, HgPath};
+use hg::DirstateStatus;
+use hg::PatternFileWarning;
+use hg::StatusError;
 use hg::StatusOptions;
 use log::info;
 use std::io;
@@ -230,117 +233,132 b' pub fn run(invocation: &crate::CliInvoca'
         list_copies,
         collect_traversed_dirs: false,
     };
-    let (mut ds_status, pattern_warnings) = dmap.status(
-        &AlwaysMatcher,
-        repo.working_directory_path().to_owned(),
-        ignore_files(repo, config),
-        options,
-    )?;
-    for warning in pattern_warnings {
-        match warning {
-            hg::PatternFileWarning::InvalidSyntax(path, syntax) => ui
-                .write_stderr(&format_bytes!(
-                    b"{}: ignoring invalid syntax '{}'\n",
-                    get_bytes_from_path(path),
-                    &*syntax
-                ))?,
-            hg::PatternFileWarning::NoSuchFile(path) => {
-                let path = if let Ok(relative) =
-                    path.strip_prefix(repo.working_directory_path())
-                {
-                    relative
-                } else {
-                    &*path
-                };
-                ui.write_stderr(&format_bytes!(
-                    b"skipping unreadable pattern file '{}': \
-                      No such file or directory\n",
-                    get_bytes_from_path(path),
-                ))?
+
+    type StatusResult<'a> =
+        Result<(DirstateStatus<'a>, Vec<PatternFileWarning>), StatusError>;
+
+    let after_status = |res: StatusResult| -> Result<_, CommandError> {
+        let (mut ds_status, pattern_warnings) = res?;
+        for warning in pattern_warnings {
+            match warning {
+                hg::PatternFileWarning::InvalidSyntax(path, syntax) => ui
+                    .write_stderr(&format_bytes!(
+                        b"{}: ignoring invalid syntax '{}'\n",
+                        get_bytes_from_path(path),
+                        &*syntax
+                    ))?,
+                hg::PatternFileWarning::NoSuchFile(path) => {
+                    let path = if let Ok(relative) =
+                        path.strip_prefix(repo.working_directory_path())
+                    {
+                        relative
+                    } else {
+                        &*path
+                    };
+                    ui.write_stderr(&format_bytes!(
+                        b"skipping unreadable pattern file '{}': \
+                          No such file or directory\n",
+                        get_bytes_from_path(path),
+                    ))?
+                }
             }
         }
-    }
 
-    for (path, error) in ds_status.bad {
-        let error = match error {
-            hg::BadMatch::OsError(code) => {
-                std::io::Error::from_raw_os_error(code).to_string()
-            }
-            hg::BadMatch::BadType(ty) => {
-                format!("unsupported file type (type is {})", ty)
-            }
-        };
-        ui.write_stderr(&format_bytes!(
-            b"{}: {}\n",
-            path.as_bytes(),
-            error.as_bytes()
-        ))?
-    }
-    if !ds_status.unsure.is_empty() {
-        info!(
-            "Files to be rechecked by retrieval from filelog: {:?}",
-            ds_status.unsure.iter().map(|s| &s.path).collect::<Vec<_>>()
-        );
-    }
-    let mut fixup = Vec::new();
-    if !ds_status.unsure.is_empty()
-        && (display_states.modified || display_states.clean)
-    {
-        let p1 = repo.dirstate_parents()?.p1;
-        let manifest = repo.manifest_for_node(p1).map_err(|e| {
-            CommandError::from((e, &*format!("{:x}", p1.short())))
-        })?;
-        for to_check in ds_status.unsure {
-            if unsure_is_modified(repo, &manifest, &to_check.path)? {
-                if display_states.modified {
-                    ds_status.modified.push(to_check);
+        for (path, error) in ds_status.bad {
+            let error = match error {
+                hg::BadMatch::OsError(code) => {
+                    std::io::Error::from_raw_os_error(code).to_string()
+                }
+                hg::BadMatch::BadType(ty) => {
+                    format!("unsupported file type (type is {})", ty)
                 }
-            } else {
-                if display_states.clean {
-                    ds_status.clean.push(to_check.clone());
+            };
+            ui.write_stderr(&format_bytes!(
+                b"{}: {}\n",
+                path.as_bytes(),
+                error.as_bytes()
+            ))?
+        }
+        if !ds_status.unsure.is_empty() {
+            info!(
+                "Files to be rechecked by retrieval from filelog: {:?}",
+                ds_status.unsure.iter().map(|s| &s.path).collect::<Vec<_>>()
+            );
+        }
+        let mut fixup = Vec::new();
+        if !ds_status.unsure.is_empty()
+            && (display_states.modified || display_states.clean)
+        {
+            let p1 = repo.dirstate_parents()?.p1;
+            let manifest = repo.manifest_for_node(p1).map_err(|e| {
+                CommandError::from((e, &*format!("{:x}", p1.short())))
+            })?;
+            for to_check in ds_status.unsure {
+                if unsure_is_modified(repo, &manifest, &to_check.path)? {
+                    if display_states.modified {
+                        ds_status.modified.push(to_check);
+                    }
+                } else {
+                    if display_states.clean {
+                        ds_status.clean.push(to_check.clone());
+                    }
+                    fixup.push(to_check.path.into_owned())
                 }
-                fixup.push(to_check.path.into_owned())
             }
         }
-    }
-    let relative_paths = (!ui.plain(None))
-        && config
-            .get_option(b"commands", b"status.relative")?
-            .unwrap_or(config.get_bool(b"ui", b"relative-paths")?);
-    let output = DisplayStatusPaths {
-        ui,
-        no_status,
-        relativize: if relative_paths {
-            Some(RelativizePaths::new(repo)?)
-        } else {
-            None
-        },
+        let relative_paths = (!ui.plain(None))
+            && config
+                .get_option(b"commands", b"status.relative")?
+                .unwrap_or(config.get_bool(b"ui", b"relative-paths")?);
+        let output = DisplayStatusPaths {
+            ui,
+            no_status,
+            relativize: if relative_paths {
+                Some(RelativizePaths::new(repo)?)
+            } else {
+                None
+            },
+        };
+        if display_states.modified {
+            output.display(b"M ", "status.modified", ds_status.modified)?;
+        }
+        if display_states.added {
+            output.display(b"A ", "status.added", ds_status.added)?;
+        }
+        if display_states.removed {
+            output.display(b"R ", "status.removed", ds_status.removed)?;
+        }
+        if display_states.deleted {
+            output.display(b"! ", "status.deleted", ds_status.deleted)?;
+        }
+        if display_states.unknown {
+            output.display(b"? ", "status.unknown", ds_status.unknown)?;
+        }
+        if display_states.ignored {
+            output.display(b"I ", "status.ignored", ds_status.ignored)?;
+        }
+        if display_states.clean {
+            output.display(b"C ", "status.clean", ds_status.clean)?;
+        }
+
+        let dirstate_write_needed = ds_status.dirty;
+        let filesystem_time_at_status_start =
+            ds_status.filesystem_time_at_status_start;
+
+        Ok((
+            fixup,
+            dirstate_write_needed,
+            filesystem_time_at_status_start,
+        ))
     };
-    if display_states.modified {
-        output.display(b"M ", "status.modified", ds_status.modified)?;
-    }
-    if display_states.added {
-        output.display(b"A ", "status.added", ds_status.added)?;
-    }
-    if display_states.removed {
-        output.display(b"R ", "status.removed", ds_status.removed)?;
-    }
-    if display_states.deleted {
-        output.display(b"! ", "status.deleted", ds_status.deleted)?;
-    }
-    if display_states.unknown {
-        output.display(b"? ", "status.unknown", ds_status.unknown)?;
-    }
-    if display_states.ignored {
-        output.display(b"I ", "status.ignored", ds_status.ignored)?;
-    }
-    if display_states.clean {
-        output.display(b"C ", "status.clean", ds_status.clean)?;
-    }
-
-    let mut dirstate_write_needed = ds_status.dirty;
-    let filesystem_time_at_status_start =
-        ds_status.filesystem_time_at_status_start;
+    let (fixup, mut dirstate_write_needed, filesystem_time_at_status_start) =
+        dmap.with_status(
+            &AlwaysMatcher,
+            repo.working_directory_path().to_owned(),
+            ignore_files(repo, config),
+            options,
+            after_status,
+        )?;
 
     if (fixup.is_empty() || filesystem_time_at_status_start.is_none())
         && !dirstate_write_needed