dirstate-v2: Drop cached read_dir results after .hgignore changes

Soon we’ll want the status algorithm to be able to skip `std::fs::read_dir` in
more cases, notabling when listing unknown files but not ignored files.

When ignore patterns change (which we detect by their hash, added to the
dirstate-v2 format in a previous changeset), a formerly-ignored file could
become unknown without changing its parent directory’s modification time.
Therefore we remove any directory mtime from the dirstate, effictively
invalidating the existing caches.

Differential Revision: https://phab.mercurial-scm.org/D10907

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

@@ -1,1117 +1,1130 b''
 use bytes_cast::BytesCast;
 use micro_timer::timed;
 use std::borrow::Cow;
 use std::convert::TryInto;
 use std::path::PathBuf;
 
 use super::on_disk;
 use super::on_disk::DirstateV2ParseError;
 use super::path_with_basename::WithBasename;
 use crate::dirstate::parsers::pack_entry;
 use crate::dirstate::parsers::packed_entry_size;
 use crate::dirstate::parsers::parse_dirstate_entries;
 use crate::dirstate::parsers::Timestamp;
 use crate::matchers::Matcher;
 use crate::utils::hg_path::{HgPath, HgPathBuf};
 use crate::CopyMapIter;
 use crate::DirstateEntry;
 use crate::DirstateError;
 use crate::DirstateParents;
 use crate::DirstateStatus;
 use crate::EntryState;
 use crate::FastHashMap;
 use crate::PatternFileWarning;
 use crate::StateMapIter;
 use crate::StatusError;
 use crate::StatusOptions;
 
 pub struct DirstateMap<'on_disk> {
     /// Contents of the `.hg/dirstate` file
     pub(super) on_disk: &'on_disk [u8],
 
     pub(super) root: ChildNodes<'on_disk>,
 
     /// Number of nodes anywhere in the tree that have `.entry.is_some()`.
     pub(super) nodes_with_entry_count: u32,
 
     /// Number of nodes anywhere in the tree that have
     /// `.copy_source.is_some()`.
     pub(super) nodes_with_copy_source_count: u32,
 
     /// See on_disk::Header
     pub(super) ignore_patterns_hash: on_disk::IgnorePatternsHash,
 }
 
 /// Using a plain `HgPathBuf` of the full path from the repository root as a
 /// map key would also work: all paths in a given map have the same parent
 /// path, so comparing full paths gives the same result as comparing base
 /// names. However `HashMap` would waste time always re-hashing the same
 /// string prefix.
 pub(super) type NodeKey<'on_disk> = WithBasename<Cow<'on_disk, HgPath>>;
 
 /// Similar to `&'tree Cow<'on_disk, HgPath>`, but can also be returned
 /// for on-disk nodes that don’t actually have a `Cow` to borrow.
 pub(super) enum BorrowedPath<'tree, 'on_disk> {
     InMemory(&'tree HgPathBuf),
     OnDisk(&'on_disk HgPath),
 }
 
 pub(super) enum ChildNodes<'on_disk> {
     InMemory(FastHashMap<NodeKey<'on_disk>, Node<'on_disk>>),
     OnDisk(&'on_disk [on_disk::Node]),
 }
 
 pub(super) enum ChildNodesRef<'tree, 'on_disk> {
     InMemory(&'tree FastHashMap<NodeKey<'on_disk>, Node<'on_disk>>),
     OnDisk(&'on_disk [on_disk::Node]),
 }
 
 pub(super) enum NodeRef<'tree, 'on_disk> {
     InMemory(&'tree NodeKey<'on_disk>, &'tree Node<'on_disk>),
     OnDisk(&'on_disk on_disk::Node),
 }
 
 impl<'tree, 'on_disk> BorrowedPath<'tree, 'on_disk> {
     pub fn detach_from_tree(&self) -> Cow<'on_disk, HgPath> {
         match *self {
             BorrowedPath::InMemory(in_memory) => Cow::Owned(in_memory.clone()),
             BorrowedPath::OnDisk(on_disk) => Cow::Borrowed(on_disk),
         }
     }
 }
 
 impl<'tree, 'on_disk> std::ops::Deref for BorrowedPath<'tree, 'on_disk> {
     type Target = HgPath;
 
     fn deref(&self) -> &HgPath {
         match *self {
             BorrowedPath::InMemory(in_memory) => in_memory,
             BorrowedPath::OnDisk(on_disk) => on_disk,
         }
     }
 }
 
 impl Default for ChildNodes<'_> {
     fn default() -> Self {
         ChildNodes::InMemory(Default::default())
     }
 }
 
 impl<'on_disk> ChildNodes<'on_disk> {
     pub(super) fn as_ref<'tree>(
         &'tree self,
     ) -> ChildNodesRef<'tree, 'on_disk> {
         match self {
             ChildNodes::InMemory(nodes) => ChildNodesRef::InMemory(nodes),
             ChildNodes::OnDisk(nodes) => ChildNodesRef::OnDisk(nodes),
         }
     }
 
     pub(super) fn is_empty(&self) -> bool {
         match self {
             ChildNodes::InMemory(nodes) => nodes.is_empty(),
             ChildNodes::OnDisk(nodes) => nodes.is_empty(),
         }
     }
 
     pub(super) fn make_mut(
         &mut self,
         on_disk: &'on_disk [u8],
     ) -> Result<
         &mut FastHashMap<NodeKey<'on_disk>, Node<'on_disk>>,
         DirstateV2ParseError,
     > {
         match self {
             ChildNodes::InMemory(nodes) => Ok(nodes),
             ChildNodes::OnDisk(nodes) => {
                 let nodes = nodes
                     .iter()
                     .map(|node| {
                         Ok((
                             node.path(on_disk)?,
                             node.to_in_memory_node(on_disk)?,
                         ))
                     })
                     .collect::<Result<_, _>>()?;
                 *self = ChildNodes::InMemory(nodes);
                 match self {
                     ChildNodes::InMemory(nodes) => Ok(nodes),
                     ChildNodes::OnDisk(_) => unreachable!(),
                 }
             }
         }
     }
 }
 
 impl<'tree, 'on_disk> ChildNodesRef<'tree, 'on_disk> {
     pub(super) fn get(
         &self,
         base_name: &HgPath,
         on_disk: &'on_disk [u8],
     ) -> Result<Option<NodeRef<'tree, 'on_disk>>, DirstateV2ParseError> {
         match self {
             ChildNodesRef::InMemory(nodes) => Ok(nodes
                 .get_key_value(base_name)
                 .map(|(k, v)| NodeRef::InMemory(k, v))),
             ChildNodesRef::OnDisk(nodes) => {
                 let mut parse_result = Ok(());
                 let search_result = nodes.binary_search_by(|node| {
                     match node.base_name(on_disk) {
                         Ok(node_base_name) => node_base_name.cmp(base_name),
                         Err(e) => {
                             parse_result = Err(e);
                             // Dummy comparison result, `search_result` won’t
                             // be used since `parse_result` is an error
                             std::cmp::Ordering::Equal
                         }
                     }
                 });
                 parse_result.map(|()| {
                     search_result.ok().map(|i| NodeRef::OnDisk(&nodes[i]))
                 })
             }
         }
     }
 
     /// Iterate in undefined order
     pub(super) fn iter(
         &self,
     ) -> impl Iterator<Item = NodeRef<'tree, 'on_disk>> {
         match self {
             ChildNodesRef::InMemory(nodes) => itertools::Either::Left(
                 nodes.iter().map(|(k, v)| NodeRef::InMemory(k, v)),
             ),
             ChildNodesRef::OnDisk(nodes) => {
                 itertools::Either::Right(nodes.iter().map(NodeRef::OnDisk))
             }
         }
     }
 
     /// Iterate in parallel in undefined order
     pub(super) fn par_iter(
         &self,
     ) -> impl rayon::iter::ParallelIterator<Item = NodeRef<'tree, 'on_disk>>
     {
         use rayon::prelude::*;
         match self {
             ChildNodesRef::InMemory(nodes) => rayon::iter::Either::Left(
                 nodes.par_iter().map(|(k, v)| NodeRef::InMemory(k, v)),
             ),
             ChildNodesRef::OnDisk(nodes) => rayon::iter::Either::Right(
                 nodes.par_iter().map(NodeRef::OnDisk),
             ),
         }
     }
 
     pub(super) fn sorted(&self) -> Vec<NodeRef<'tree, 'on_disk>> {
         match self {
             ChildNodesRef::InMemory(nodes) => {
                 let mut vec: Vec<_> = nodes
                     .iter()
                     .map(|(k, v)| NodeRef::InMemory(k, v))
                     .collect();
                 fn sort_key<'a>(node: &'a NodeRef) -> &'a HgPath {
                     match node {
                         NodeRef::InMemory(path, _node) => path.base_name(),
                         NodeRef::OnDisk(_) => unreachable!(),
                     }
                 }
                 // `sort_unstable_by_key` doesn’t allow keys borrowing from the
                 // value: https://github.com/rust-lang/rust/issues/34162
                 vec.sort_unstable_by(|a, b| sort_key(a).cmp(sort_key(b)));
                 vec
             }
             ChildNodesRef::OnDisk(nodes) => {
                 // Nodes on disk are already sorted
                 nodes.iter().map(NodeRef::OnDisk).collect()
             }
         }
     }
 }
 
 impl<'tree, 'on_disk> NodeRef<'tree, 'on_disk> {
     pub(super) fn full_path(
         &self,
         on_disk: &'on_disk [u8],
     ) -> Result<&'tree HgPath, DirstateV2ParseError> {
         match self {
             NodeRef::InMemory(path, _node) => Ok(path.full_path()),
             NodeRef::OnDisk(node) => node.full_path(on_disk),
         }
     }
 
     /// Returns a `BorrowedPath`, which can be turned into a `Cow<'on_disk,
     /// HgPath>` detached from `'tree`
     pub(super) fn full_path_borrowed(
         &self,
         on_disk: &'on_disk [u8],
     ) -> Result<BorrowedPath<'tree, 'on_disk>, DirstateV2ParseError> {
         match self {
             NodeRef::InMemory(path, _node) => match path.full_path() {
                 Cow::Borrowed(on_disk) => Ok(BorrowedPath::OnDisk(on_disk)),
                 Cow::Owned(in_memory) => Ok(BorrowedPath::InMemory(in_memory)),
             },
             NodeRef::OnDisk(node) => {
                 Ok(BorrowedPath::OnDisk(node.full_path(on_disk)?))
             }
         }
     }
 
     pub(super) fn base_name(
         &self,
         on_disk: &'on_disk [u8],
     ) -> Result<&'tree HgPath, DirstateV2ParseError> {
         match self {
             NodeRef::InMemory(path, _node) => Ok(path.base_name()),
             NodeRef::OnDisk(node) => node.base_name(on_disk),
         }
     }
 
     pub(super) fn children(
         &self,
         on_disk: &'on_disk [u8],
     ) -> Result<ChildNodesRef<'tree, 'on_disk>, DirstateV2ParseError> {
         match self {
             NodeRef::InMemory(_path, node) => Ok(node.children.as_ref()),
             NodeRef::OnDisk(node) => {
                 Ok(ChildNodesRef::OnDisk(node.children(on_disk)?))
             }
         }
     }
 
     pub(super) fn has_copy_source(&self) -> bool {
         match self {
             NodeRef::InMemory(_path, node) => node.copy_source.is_some(),
             NodeRef::OnDisk(node) => node.has_copy_source(),
         }
     }
 
     pub(super) fn copy_source(
         &self,
         on_disk: &'on_disk [u8],
     ) -> Result<Option<&'tree HgPath>, DirstateV2ParseError> {
         match self {
             NodeRef::InMemory(_path, node) => {
                 Ok(node.copy_source.as_ref().map(|s| &**s))
             }
             NodeRef::OnDisk(node) => node.copy_source(on_disk),
         }
     }
 
     pub(super) fn entry(
         &self,
     ) -> Result<Option<DirstateEntry>, DirstateV2ParseError> {
         match self {
             NodeRef::InMemory(_path, node) => {
                 Ok(node.data.as_entry().copied())
             }
             NodeRef::OnDisk(node) => node.entry(),
         }
     }
 
     pub(super) fn state(
         &self,
     ) -> Result<Option<EntryState>, DirstateV2ParseError> {
         match self {
             NodeRef::InMemory(_path, node) => {
                 Ok(node.data.as_entry().map(|entry| entry.state))
             }
             NodeRef::OnDisk(node) => node.state(),
         }
     }
 
     pub(super) fn cached_directory_mtime(
         &self,
     ) -> Option<&'tree on_disk::Timestamp> {
         match self {
             NodeRef::InMemory(_path, node) => match &node.data {
                 NodeData::CachedDirectory { mtime } => Some(mtime),
                 _ => None,
             },
             NodeRef::OnDisk(node) => node.cached_directory_mtime(),
         }
     }
 
     pub(super) fn tracked_descendants_count(&self) -> u32 {
         match self {
             NodeRef::InMemory(_path, node) => node.tracked_descendants_count,
             NodeRef::OnDisk(node) => node.tracked_descendants_count.get(),
         }
     }
 }
 
 /// Represents a file or a directory
 #[derive(Default)]
 pub(super) struct Node<'on_disk> {
     pub(super) data: NodeData,
 
     pub(super) copy_source: Option<Cow<'on_disk, HgPath>>,
 
     pub(super) children: ChildNodes<'on_disk>,
 
     /// How many (non-inclusive) descendants of this node are tracked files
     pub(super) tracked_descendants_count: u32,
 }
 
 pub(super) enum NodeData {
     Entry(DirstateEntry),
     CachedDirectory { mtime: on_disk::Timestamp },
     None,
 }
 
 impl Default for NodeData {
     fn default() -> Self {
         NodeData::None
     }
 }
 
 impl NodeData {
     fn has_entry(&self) -> bool {
         match self {
             NodeData::Entry(_) => true,
             _ => false,
         }
     }
 
     fn as_entry(&self) -> Option<&DirstateEntry> {
         match self {
             NodeData::Entry(entry) => Some(entry),
             _ => None,
         }
     }
 }
 
 impl<'on_disk> DirstateMap<'on_disk> {
     pub(super) fn empty(on_disk: &'on_disk [u8]) -> Self {
         Self {
             on_disk,
             root: ChildNodes::default(),
             nodes_with_entry_count: 0,
             nodes_with_copy_source_count: 0,
             ignore_patterns_hash: [0; on_disk::IGNORE_PATTERNS_HASH_LEN],
         }
     }
 
     #[timed]
     pub fn new_v2(
         on_disk: &'on_disk [u8],
     ) -> Result<(Self, Option<DirstateParents>), DirstateError> {
         Ok(on_disk::read(on_disk)?)
     }
 
     #[timed]
     pub fn new_v1(
         on_disk: &'on_disk [u8],
     ) -> Result<(Self, Option<DirstateParents>), DirstateError> {
         let mut map = Self::empty(on_disk);
         if map.on_disk.is_empty() {
             return Ok((map, None));
         }
 
         let parents = parse_dirstate_entries(
             map.on_disk,
             |path, entry, copy_source| {
                 let tracked = entry.state.is_tracked();
                 let node = Self::get_or_insert_node(
                     map.on_disk,
                     &mut map.root,
                     path,
                     WithBasename::to_cow_borrowed,
                     |ancestor| {
                         if tracked {
                             ancestor.tracked_descendants_count += 1
                         }
                     },
                 )?;
                 assert!(
                     !node.data.has_entry(),
                     "duplicate dirstate entry in read"
                 );
                 assert!(
                     node.copy_source.is_none(),
                     "duplicate dirstate entry in read"
                 );
                 node.data = NodeData::Entry(*entry);
                 node.copy_source = copy_source.map(Cow::Borrowed);
                 map.nodes_with_entry_count += 1;
                 if copy_source.is_some() {
                     map.nodes_with_copy_source_count += 1
                 }
                 Ok(())
             },
         )?;
         let parents = Some(parents.clone());
 
         Ok((map, parents))
     }
 
     fn get_node<'tree>(
         &'tree self,
         path: &HgPath,
     ) -> Result<Option<NodeRef<'tree, 'on_disk>>, DirstateV2ParseError> {
         let mut children = self.root.as_ref();
         let mut components = path.components();
         let mut component =
             components.next().expect("expected at least one components");
         loop {
             if let Some(child) = children.get(component, self.on_disk)? {
                 if let Some(next_component) = components.next() {
                     component = next_component;
                     children = child.children(self.on_disk)?;
                 } else {
                     return Ok(Some(child));
                 }
             } else {
                 return Ok(None);
             }
         }
     }
 
     /// Returns a mutable reference to the node at `path` if it exists
     ///
     /// This takes `root` instead of `&mut self` so that callers can mutate
     /// other fields while the returned borrow is still valid
     fn get_node_mut<'tree>(
         on_disk: &'on_disk [u8],
         root: &'tree mut ChildNodes<'on_disk>,
         path: &HgPath,
     ) -> Result<Option<&'tree mut Node<'on_disk>>, DirstateV2ParseError> {
         let mut children = root;
         let mut components = path.components();
         let mut component =
             components.next().expect("expected at least one components");
         loop {
             if let Some(child) = children.make_mut(on_disk)?.get_mut(component)
             {
                 if let Some(next_component) = components.next() {
                     component = next_component;
                     children = &mut child.children;
                 } else {
                     return Ok(Some(child));
                 }
             } else {
                 return Ok(None);
             }
         }
     }
 
+    pub(super) fn get_or_insert<'tree, 'path>(
+        &'tree mut self,
+        path: &HgPath,
+    ) -> Result<&'tree mut Node<'on_disk>, DirstateV2ParseError> {
+        Self::get_or_insert_node(
+            self.on_disk,
+            &mut self.root,
+            path,
+            WithBasename::to_cow_owned,
+            |_| {},
+        )
+    }
+
     pub(super) fn get_or_insert_node<'tree, 'path>(
         on_disk: &'on_disk [u8],
         root: &'tree mut ChildNodes<'on_disk>,
         path: &'path HgPath,
         to_cow: impl Fn(
             WithBasename<&'path HgPath>,
         ) -> WithBasename<Cow<'on_disk, HgPath>>,
         mut each_ancestor: impl FnMut(&mut Node),
     ) -> Result<&'tree mut Node<'on_disk>, DirstateV2ParseError> {
         let mut child_nodes = root;
         let mut inclusive_ancestor_paths =
             WithBasename::inclusive_ancestors_of(path);
         let mut ancestor_path = inclusive_ancestor_paths
             .next()
             .expect("expected at least one inclusive ancestor");
         loop {
             // TODO: can we avoid allocating an owned key in cases where the
             // map already contains that key, without introducing double
             // lookup?
             let child_node = child_nodes
                 .make_mut(on_disk)?
                 .entry(to_cow(ancestor_path))
                 .or_default();
             if let Some(next) = inclusive_ancestor_paths.next() {
                 each_ancestor(child_node);
                 ancestor_path = next;
                 child_nodes = &mut child_node.children;
             } else {
                 return Ok(child_node);
             }
         }
     }
 
     fn add_or_remove_file(
         &mut self,
         path: &HgPath,
         old_state: EntryState,
         new_entry: DirstateEntry,
     ) -> Result<(), DirstateV2ParseError> {
         let tracked_count_increment =
             match (old_state.is_tracked(), new_entry.state.is_tracked()) {
                 (false, true) => 1,
                 (true, false) => -1,
                 _ => 0,
             };
 
         let node = Self::get_or_insert_node(
             self.on_disk,
             &mut self.root,
             path,
             WithBasename::to_cow_owned,
             |ancestor| {
                 // We can’t use `+= increment` because the counter is unsigned,
                 // and we want debug builds to detect accidental underflow
                 // through zero
                 match tracked_count_increment {
                     1 => ancestor.tracked_descendants_count += 1,
                     -1 => ancestor.tracked_descendants_count -= 1,
                     _ => {}
                 }
             },
         )?;
         if !node.data.has_entry() {
             self.nodes_with_entry_count += 1
         }
         node.data = NodeData::Entry(new_entry);
         Ok(())
     }
 
     fn iter_nodes<'tree>(
         &'tree self,
     ) -> impl Iterator<
         Item = Result<NodeRef<'tree, 'on_disk>, DirstateV2ParseError>,
     > + 'tree {
         // Depth first tree traversal.
         //
         // If we could afford internal iteration and recursion,
         // this would look like:
         //
         // ```
         // fn traverse_children(
         //     children: &ChildNodes,
         //     each: &mut impl FnMut(&Node),
         // ) {
         //     for child in children.values() {
         //         traverse_children(&child.children, each);
         //         each(child);
         //     }
         // }
         // ```
         //
         // However we want an external iterator and therefore can’t use the
         // call stack. Use an explicit stack instead:
         let mut stack = Vec::new();
         let mut iter = self.root.as_ref().iter();
         std::iter::from_fn(move || {
             while let Some(child_node) = iter.next() {
                 let children = match child_node.children(self.on_disk) {
                     Ok(children) => children,
                     Err(error) => return Some(Err(error)),
                 };
                 // Pseudo-recursion
                 let new_iter = children.iter();
                 let old_iter = std::mem::replace(&mut iter, new_iter);
                 stack.push((child_node, old_iter));
             }
             // Found the end of a `children.iter()` iterator.
             if let Some((child_node, next_iter)) = stack.pop() {
                 // "Return" from pseudo-recursion by restoring state from the
                 // explicit stack
                 iter = next_iter;
 
                 Some(Ok(child_node))
             } else {
                 // Reached the bottom of the stack, we’re done
                 None
             }
         })
     }
 
     fn clear_known_ambiguous_mtimes(
         &mut self,
         paths: &[impl AsRef<HgPath>],
     ) -> Result<(), DirstateV2ParseError> {
         for path in paths {
             if let Some(node) = Self::get_node_mut(
                 self.on_disk,
                 &mut self.root,
                 path.as_ref(),
             )? {
                 if let NodeData::Entry(entry) = &mut node.data {
                     entry.clear_mtime();
                 }
             }
         }
         Ok(())
     }
 
     /// Return a faillilble iterator of full paths of nodes that have an
     /// `entry` for which the given `predicate` returns true.
     ///
     /// Fallibility means that each iterator item is a `Result`, which may
     /// indicate a parse error of the on-disk dirstate-v2 format. Such errors
     /// should only happen if Mercurial is buggy or a repository is corrupted.
     fn filter_full_paths<'tree>(
         &'tree self,
         predicate: impl Fn(&DirstateEntry) -> bool + 'tree,
     ) -> impl Iterator<Item = Result<&HgPath, DirstateV2ParseError>> + 'tree
     {
         filter_map_results(self.iter_nodes(), move |node| {
             if let Some(entry) = node.entry()? {
                 if predicate(&entry) {
                     return Ok(Some(node.full_path(self.on_disk)?));
                 }
             }
             Ok(None)
         })
     }
 }
 
 /// Like `Iterator::filter_map`, but over a fallible iterator of `Result`s.
 ///
 /// The callback is only called for incoming `Ok` values. Errors are passed
 /// through as-is. In order to let it use the `?` operator the callback is
 /// expected to return a `Result` of `Option`, instead of an `Option` of
 /// `Result`.
 fn filter_map_results<'a, I, F, A, B, E>(
     iter: I,
     f: F,
 ) -> impl Iterator<Item = Result<B, E>> + 'a
 where
     I: Iterator<Item = Result<A, E>> + 'a,
     F: Fn(A) -> Result<Option<B>, E> + 'a,
 {
     iter.filter_map(move |result| match result {
         Ok(node) => f(node).transpose(),
         Err(e) => Some(Err(e)),
     })
 }
 
 impl<'on_disk> super::dispatch::DirstateMapMethods for DirstateMap<'on_disk> {
     fn clear(&mut self) {
         self.root = Default::default();
         self.nodes_with_entry_count = 0;
         self.nodes_with_copy_source_count = 0;
     }
 
     fn add_file(
         &mut self,
         filename: &HgPath,
         old_state: EntryState,
         entry: DirstateEntry,
     ) -> Result<(), DirstateError> {
         Ok(self.add_or_remove_file(filename, old_state, entry)?)
     }
 
     fn remove_file(
         &mut self,
         filename: &HgPath,
         old_state: EntryState,
         size: i32,
     ) -> Result<(), DirstateError> {
         let entry = DirstateEntry {
             state: EntryState::Removed,
             mode: 0,
             size,
             mtime: 0,
         };
         Ok(self.add_or_remove_file(filename, old_state, entry)?)
     }
 
     fn drop_file(
         &mut self,
         filename: &HgPath,
         old_state: EntryState,
     ) -> Result<bool, DirstateError> {
         struct Dropped {
             was_tracked: bool,
             had_entry: bool,
             had_copy_source: bool,
         }
 
         /// If this returns `Ok(Some((dropped, removed)))`, then
         ///
         /// * `dropped` is about the leaf node that was at `filename`
         /// * `removed` is whether this particular level of recursion just
         ///   removed a node in `nodes`.
         fn recur<'on_disk>(
             on_disk: &'on_disk [u8],
             nodes: &mut ChildNodes<'on_disk>,
             path: &HgPath,
         ) -> Result<Option<(Dropped, bool)>, DirstateV2ParseError> {
             let (first_path_component, rest_of_path) =
                 path.split_first_component();
             let node = if let Some(node) =
                 nodes.make_mut(on_disk)?.get_mut(first_path_component)
             {
                 node
             } else {
                 return Ok(None);
             };
             let dropped;
             if let Some(rest) = rest_of_path {
                 if let Some((d, removed)) =
                     recur(on_disk, &mut node.children, rest)?
                 {
                     dropped = d;
                     if dropped.was_tracked {
                         node.tracked_descendants_count -= 1;
                     }
 
                     // Directory caches must be invalidated when removing a
                     // child node
                     if removed {
                         if let NodeData::CachedDirectory { .. } = &node.data {
                             node.data = NodeData::None
                         }
                     }
                 } else {
                     return Ok(None);
                 }
             } else {
                 let had_entry = node.data.has_entry();
                 if had_entry {
                     node.data = NodeData::None
                 }
                 dropped = Dropped {
                     was_tracked: node
                         .data
                         .as_entry()
                         .map_or(false, |entry| entry.state.is_tracked()),
                     had_entry,
                     had_copy_source: node.copy_source.take().is_some(),
                 };
             }
             // After recursion, for both leaf (rest_of_path is None) nodes and
             // parent nodes, remove a node if it just became empty.
             let remove = !node.data.has_entry()
                 && node.copy_source.is_none()
                 && node.children.is_empty();
             if remove {
                 nodes.make_mut(on_disk)?.remove(first_path_component);
             }
             Ok(Some((dropped, remove)))
         }
 
         if let Some((dropped, _removed)) =
             recur(self.on_disk, &mut self.root, filename)?
         {
             if dropped.had_entry {
                 self.nodes_with_entry_count -= 1
             }
             if dropped.had_copy_source {
                 self.nodes_with_copy_source_count -= 1
             }
             Ok(dropped.had_entry)
         } else {
             debug_assert!(!old_state.is_tracked());
             Ok(false)
         }
     }
 
     fn clear_ambiguous_times(
         &mut self,
         filenames: Vec<HgPathBuf>,
         now: i32,
     ) -> Result<(), DirstateV2ParseError> {
         for filename in filenames {
             if let Some(node) =
                 Self::get_node_mut(self.on_disk, &mut self.root, &filename)?
             {
                 if let NodeData::Entry(entry) = &mut node.data {
                     entry.clear_ambiguous_mtime(now);
                 }
             }
         }
         Ok(())
     }
 
     fn non_normal_entries_contains(
         &mut self,
         key: &HgPath,
     ) -> Result<bool, DirstateV2ParseError> {
         Ok(if let Some(node) = self.get_node(key)? {
             node.entry()?.map_or(false, |entry| entry.is_non_normal())
         } else {
             false
         })
     }
 
     fn non_normal_entries_remove(&mut self, _key: &HgPath) {
         // Do nothing, this `DirstateMap` does not have a separate "non normal
         // entries" set that need to be kept up to date
     }
 
     fn non_normal_or_other_parent_paths(
         &mut self,
     ) -> Box<dyn Iterator<Item = Result<&HgPath, DirstateV2ParseError>> + '_>
     {
         Box::new(self.filter_full_paths(|entry| {
             entry.is_non_normal() || entry.is_from_other_parent()
         }))
     }
 
     fn set_non_normal_other_parent_entries(&mut self, _force: bool) {
         // Do nothing, this `DirstateMap` does not have a separate "non normal
         // entries" and "from other parent" sets that need to be recomputed
     }
 
     fn iter_non_normal_paths(
         &mut self,
     ) -> Box<
         dyn Iterator<Item = Result<&HgPath, DirstateV2ParseError>> + Send + '_,
     > {
         self.iter_non_normal_paths_panic()
     }
 
     fn iter_non_normal_paths_panic(
         &self,
     ) -> Box<
         dyn Iterator<Item = Result<&HgPath, DirstateV2ParseError>> + Send + '_,
     > {
         Box::new(self.filter_full_paths(|entry| entry.is_non_normal()))
     }
 
     fn iter_other_parent_paths(
         &mut self,
     ) -> Box<
         dyn Iterator<Item = Result<&HgPath, DirstateV2ParseError>> + Send + '_,
     > {
         Box::new(self.filter_full_paths(|entry| entry.is_from_other_parent()))
     }
 
     fn has_tracked_dir(
         &mut self,
         directory: &HgPath,
     ) -> Result<bool, DirstateError> {
         if let Some(node) = self.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)
         }
     }
 
     fn has_dir(&mut self, directory: &HgPath) -> Result<bool, DirstateError> {
         if let Some(node) = self.get_node(directory)? {
             // A node without a `DirstateEntry` was created to hold child
             // nodes, and is therefore a directory.
             Ok(node.state()?.is_none())
         } else {
             Ok(false)
         }
     }
 
     #[timed]
     fn pack_v1(
         &mut self,
         parents: DirstateParents,
         now: Timestamp,
     ) -> Result<Vec<u8>, DirstateError> {
         let now: i32 = now.0.try_into().expect("time overflow");
         let mut ambiguous_mtimes = Vec::new();
         // Optizimation (to be measured?): pre-compute size to avoid `Vec`
         // reallocations
         let mut size = parents.as_bytes().len();
         for node in self.iter_nodes() {
             let node = node?;
             if let Some(entry) = node.entry()? {
                 size += packed_entry_size(
                     node.full_path(self.on_disk)?,
                     node.copy_source(self.on_disk)?,
                 );
                 if entry.mtime_is_ambiguous(now) {
                     ambiguous_mtimes.push(
                         node.full_path_borrowed(self.on_disk)?
                             .detach_from_tree(),
                     )
                 }
             }
         }
         self.clear_known_ambiguous_mtimes(&ambiguous_mtimes)?;
 
         let mut packed = Vec::with_capacity(size);
         packed.extend(parents.as_bytes());
 
         for node in self.iter_nodes() {
             let node = node?;
             if let Some(entry) = node.entry()? {
                 pack_entry(
                     node.full_path(self.on_disk)?,
                     &entry,
                     node.copy_source(self.on_disk)?,
                     &mut packed,
                 );
             }
         }
         Ok(packed)
     }
 
     #[timed]
     fn pack_v2(
         &mut self,
         parents: DirstateParents,
         now: Timestamp,
     ) -> Result<Vec<u8>, DirstateError> {
         // TODO: how do we want to handle this in 2038?
         let now: i32 = now.0.try_into().expect("time overflow");
         let mut paths = Vec::new();
         for node in self.iter_nodes() {
             let node = node?;
             if let Some(entry) = node.entry()? {
                 if entry.mtime_is_ambiguous(now) {
                     paths.push(
                         node.full_path_borrowed(self.on_disk)?
                             .detach_from_tree(),
                     )
                 }
             }
         }
         // Borrow of `self` ends here since we collect cloned paths
 
         self.clear_known_ambiguous_mtimes(&paths)?;
 
         on_disk::write(self, parents)
     }
 
     fn set_all_dirs(&mut self) -> Result<(), DirstateError> {
         // Do nothing, this `DirstateMap` does not a separate `all_dirs` that
         // needs to be recomputed
         Ok(())
     }
 
     fn set_dirs(&mut self) -> Result<(), DirstateError> {
         // Do nothing, this `DirstateMap` does not a separate `dirs` that needs
         // to be recomputed
         Ok(())
     }
 
     fn status<'a>(
         &'a mut self,
         matcher: &'a (dyn Matcher + Sync),
         root_dir: PathBuf,
         ignore_files: Vec<PathBuf>,
         options: StatusOptions,
     ) -> Result<(DirstateStatus<'a>, Vec<PatternFileWarning>), StatusError>
     {
         super::status::status(self, matcher, root_dir, ignore_files, options)
     }
 
     fn copy_map_len(&self) -> usize {
         self.nodes_with_copy_source_count as usize
     }
 
     fn copy_map_iter(&self) -> CopyMapIter<'_> {
         Box::new(filter_map_results(self.iter_nodes(), move |node| {
             Ok(if let Some(source) = node.copy_source(self.on_disk)? {
                 Some((node.full_path(self.on_disk)?, source))
             } else {
                 None
             })
         }))
     }
 
     fn copy_map_contains_key(
         &self,
         key: &HgPath,
     ) -> Result<bool, DirstateV2ParseError> {
         Ok(if let Some(node) = self.get_node(key)? {
             node.has_copy_source()
         } else {
             false
         })
     }
 
     fn copy_map_get(
         &self,
         key: &HgPath,
     ) -> Result<Option<&HgPath>, DirstateV2ParseError> {
         if let Some(node) = self.get_node(key)? {
             if let Some(source) = node.copy_source(self.on_disk)? {
                 return Ok(Some(source));
             }
         }
         Ok(None)
     }
 
     fn copy_map_remove(
         &mut self,
         key: &HgPath,
     ) -> Result<Option<HgPathBuf>, DirstateV2ParseError> {
         let count = &mut self.nodes_with_copy_source_count;
         Ok(
             Self::get_node_mut(self.on_disk, &mut self.root, key)?.and_then(
                 |node| {
                     if node.copy_source.is_some() {
                         *count -= 1
                     }
                     node.copy_source.take().map(Cow::into_owned)
                 },
             ),
         )
     }
 
     fn copy_map_insert(
         &mut self,
         key: HgPathBuf,
         value: HgPathBuf,
     ) -> Result<Option<HgPathBuf>, DirstateV2ParseError> {
         let node = Self::get_or_insert_node(
             self.on_disk,
             &mut self.root,
             &key,
             WithBasename::to_cow_owned,
             |_ancestor| {},
         )?;
         if node.copy_source.is_none() {
             self.nodes_with_copy_source_count += 1
         }
         Ok(node.copy_source.replace(value.into()).map(Cow::into_owned))
     }
 
     fn len(&self) -> usize {
         self.nodes_with_entry_count as usize
     }
 
     fn contains_key(
         &self,
         key: &HgPath,
     ) -> Result<bool, DirstateV2ParseError> {
         Ok(self.get(key)?.is_some())
     }
 
     fn get(
         &self,
         key: &HgPath,
     ) -> Result<Option<DirstateEntry>, DirstateV2ParseError> {
         Ok(if let Some(node) = self.get_node(key)? {
             node.entry()?
         } else {
             None
         })
     }
 
     fn iter(&self) -> StateMapIter<'_> {
         Box::new(filter_map_results(self.iter_nodes(), move |node| {
             Ok(if let Some(entry) = node.entry()? {
                 Some((node.full_path(self.on_disk)?, entry))
             } else {
                 None
             })
         }))
     }
 
     fn iter_directories(
         &self,
     ) -> Box<
         dyn Iterator<
                 Item = Result<
                     (&HgPath, Option<Timestamp>),
                     DirstateV2ParseError,
                 >,
             > + Send
             + '_,
     > {
         Box::new(filter_map_results(self.iter_nodes(), move |node| {
             Ok(if node.state()?.is_none() {
                 Some((
                     node.full_path(self.on_disk)?,
                     node.cached_directory_mtime()
                         .map(|mtime| Timestamp(mtime.seconds())),
                 ))
             } else {
                 None
             })
         }))
     }
 }

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

@@ -1,705 +1,728 b''
 use crate::dirstate::status::IgnoreFnType;
 use crate::dirstate_tree::dirstate_map::BorrowedPath;
 use crate::dirstate_tree::dirstate_map::ChildNodesRef;
 use crate::dirstate_tree::dirstate_map::DirstateMap;
 use crate::dirstate_tree::dirstate_map::NodeData;
 use crate::dirstate_tree::dirstate_map::NodeRef;
 use crate::dirstate_tree::on_disk::DirstateV2ParseError;
 use crate::dirstate_tree::on_disk::Timestamp;
-use crate::dirstate_tree::path_with_basename::WithBasename;
 use crate::matchers::get_ignore_function;
 use crate::matchers::Matcher;
 use crate::utils::files::get_bytes_from_os_string;
 use crate::utils::files::get_path_from_bytes;
 use crate::utils::hg_path::HgPath;
 use crate::BadMatch;
 use crate::DirstateStatus;
 use crate::EntryState;
 use crate::HgPathBuf;
 use crate::PatternFileWarning;
 use crate::StatusError;
 use crate::StatusOptions;
 use micro_timer::timed;
 use rayon::prelude::*;
 use sha1::{Digest, Sha1};
 use std::borrow::Cow;
 use std::io;
 use std::path::Path;
 use std::path::PathBuf;
 use std::sync::Mutex;
 use std::time::SystemTime;
 
 /// Returns the status of the working directory compared to its parent
 /// changeset.
 ///
 /// This algorithm is based on traversing the filesystem tree (`fs` in function
 /// and variable names) and dirstate tree at the same time. The core of this
 /// traversal is the recursive `traverse_fs_directory_and_dirstate` function
 /// and its use of `itertools::merge_join_by`. When reaching a path that only
 /// 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>,
     matcher: &(dyn Matcher + Sync),
     root_dir: PathBuf,
     ignore_files: Vec<PathBuf>,
     options: StatusOptions,
 ) -> Result<(DirstateStatus<'on_disk>, Vec<PatternFileWarning>), StatusError> {
     let (ignore_fn, warnings, patterns_changed): (IgnoreFnType, _, _) =
         if options.list_ignored || options.list_unknown {
             let mut hasher = Sha1::new();
             let (ignore_fn, warnings) = get_ignore_function(
                 ignore_files,
                 &root_dir,
                 &mut |pattern_bytes| hasher.update(pattern_bytes),
             )?;
             let new_hash = *hasher.finalize().as_ref();
             let changed = new_hash != dmap.ignore_patterns_hash;
             dmap.ignore_patterns_hash = new_hash;
             (ignore_fn, warnings, Some(changed))
         } else {
             (Box::new(|&_| true), vec![], None)
         };
 
     let common = StatusCommon {
         dmap,
         options,
         matcher,
         ignore_fn,
         outcome: Default::default(),
         ignore_patterns_have_changed: patterns_changed,
         new_cachable_directories: Default::default(),
+        outated_cached_directories: Default::default(),
         filesystem_time_at_status_start: filesystem_now(&root_dir).ok(),
     };
     let is_at_repo_root = true;
     let hg_path = &BorrowedPath::OnDisk(HgPath::new(""));
     let has_ignored_ancestor = false;
     let root_cached_mtime = None;
     let root_dir_metadata = None;
     // If the path we have for the repository root is a symlink, do follow it.
     // (As opposed to symlinks within the working directory which are not
     // followed, using `std::fs::symlink_metadata`.)
     common.traverse_fs_directory_and_dirstate(
         has_ignored_ancestor,
         dmap.root.as_ref(),
         hg_path,
         &root_dir,
         root_dir_metadata,
         root_cached_mtime,
         is_at_repo_root,
     )?;
     let mut outcome = common.outcome.into_inner().unwrap();
     let new_cachable = common.new_cachable_directories.into_inner().unwrap();
+    let outdated = common.outated_cached_directories.into_inner().unwrap();
 
     outcome.dirty = common.ignore_patterns_have_changed == Some(true)
+        || !outdated.is_empty()
         || !new_cachable.is_empty();
 
+    // Remove outdated mtimes before adding new mtimes, in case a given
+    // directory is both
+    for path in &outdated {
+        let node = dmap.get_or_insert(path)?;
+        if let NodeData::CachedDirectory { .. } = &node.data {
+            node.data = NodeData::None
+        }
+    }
     for (path, mtime) in &new_cachable {
-        let node = DirstateMap::get_or_insert_node(
-            dmap.on_disk,
-            &mut dmap.root,
-            path,
-            WithBasename::to_cow_owned,
-            |_| {},
-        )?;
+        let node = dmap.get_or_insert(path)?;
         match &node.data {
             NodeData::Entry(_) => {} // Don’t overwrite an entry
             NodeData::CachedDirectory { .. } | NodeData::None => {
                 node.data = NodeData::CachedDirectory { mtime: *mtime }
             }
         }
     }
 
     Ok((outcome, warnings))
 }
 
 /// Bag of random things needed by various parts of the algorithm. Reduces the
 /// number of parameters passed to functions.
 struct StatusCommon<'a, 'tree, 'on_disk: 'tree> {
     dmap: &'tree DirstateMap<'on_disk>,
     options: StatusOptions,
     matcher: &'a (dyn Matcher + Sync),
     ignore_fn: IgnoreFnType<'a>,
     outcome: Mutex<DirstateStatus<'on_disk>>,
     new_cachable_directories: Mutex<Vec<(Cow<'on_disk, HgPath>, Timestamp)>>,
+    outated_cached_directories: Mutex<Vec<Cow<'on_disk, HgPath>>>,
 
     /// Whether ignore files like `.hgignore` have changed since the previous
     /// time a `status()` call wrote their hash to the dirstate. `None` means
     /// we don’t know as this run doesn’t list either ignored or uknown files
     /// and therefore isn’t reading `.hgignore`.
     ignore_patterns_have_changed: Option<bool>,
 
     /// The current time at the start of the `status()` algorithm, as measured
     /// and possibly truncated by the filesystem.
     filesystem_time_at_status_start: Option<SystemTime>,
 }
 
 impl<'a, 'tree, 'on_disk> StatusCommon<'a, 'tree, 'on_disk> {
     fn read_dir(
         &self,
         hg_path: &HgPath,
         fs_path: &Path,
         is_at_repo_root: bool,
     ) -> Result<Vec<DirEntry>, ()> {
         DirEntry::read_dir(fs_path, is_at_repo_root)
             .map_err(|error| self.io_error(error, hg_path))
     }
 
     fn io_error(&self, error: std::io::Error, hg_path: &HgPath) {
         let errno = error.raw_os_error().expect("expected real OS error");
         self.outcome
             .lock()
             .unwrap()
             .bad
             .push((hg_path.to_owned().into(), BadMatch::OsError(errno)))
     }
 
+    fn check_for_outdated_directory_cache(
+        &self,
+        dirstate_node: &NodeRef<'tree, 'on_disk>,
+    ) -> Result<(), DirstateV2ParseError> {
+        if self.ignore_patterns_have_changed == Some(true)
+            && dirstate_node.cached_directory_mtime().is_some()
+        {
+            self.outated_cached_directories.lock().unwrap().push(
+                dirstate_node
+                    .full_path_borrowed(self.dmap.on_disk)?
+                    .detach_from_tree(),
+            )
+        }
+        Ok(())
+    }
+
     /// If this returns true, we can get accurate results by only using
     /// `symlink_metadata` for child nodes that exist in the dirstate and don’t
     /// need to call `read_dir`.
     fn can_skip_fs_readdir(
         &self,
         directory_metadata: Option<&std::fs::Metadata>,
         cached_directory_mtime: Option<&Timestamp>,
     ) -> bool {
         if !self.options.list_unknown && !self.options.list_ignored {
             // All states that we care about listing have corresponding
             // dirstate entries.
             // This happens for example with `hg status -mard`.
             return true;
         }
         if let Some(cached_mtime) = cached_directory_mtime {
             // The dirstate contains a cached mtime for this directory, set by
             // a previous run of the `status` algorithm which found this
             // directory eligible for `read_dir` caching.
             if let Some(meta) = directory_metadata {
                 if let Ok(current_mtime) = meta.modified() {
                     if current_mtime == cached_mtime.into() {
                         // The mtime of that directory has not changed since
                         // then, which means that the
                         // results of `read_dir` should also
                         // be unchanged.
                         return true;
                     }
                 }
             }
         }
         false
     }
 
     /// Returns whether the filesystem directory was found to have any entry
     /// that does not have a corresponding dirstate tree node.
     fn traverse_fs_directory_and_dirstate(
         &self,
         has_ignored_ancestor: bool,
         dirstate_nodes: ChildNodesRef<'tree, 'on_disk>,
         directory_hg_path: &BorrowedPath<'tree, 'on_disk>,
         directory_fs_path: &Path,
         directory_metadata: Option<&std::fs::Metadata>,
         cached_directory_mtime: Option<&Timestamp>,
         is_at_repo_root: bool,
     ) -> Result<bool, DirstateV2ParseError> {
         if self.can_skip_fs_readdir(directory_metadata, cached_directory_mtime)
         {
             dirstate_nodes
                 .par_iter()
                 .map(|dirstate_node| {
                     let fs_path = directory_fs_path.join(get_path_from_bytes(
                         dirstate_node.base_name(self.dmap.on_disk)?.as_bytes(),
                     ));
                     match std::fs::symlink_metadata(&fs_path) {
                         Ok(fs_metadata) => self.traverse_fs_and_dirstate(
                             &fs_path,
                             &fs_metadata,
                             dirstate_node,
                             has_ignored_ancestor,
                         ),
                         Err(e) if e.kind() == std::io::ErrorKind::NotFound => {
                             self.traverse_dirstate_only(dirstate_node)
                         }
                         Err(error) => {
                             let hg_path =
                                 dirstate_node.full_path(self.dmap.on_disk)?;
                             Ok(self.io_error(error, hg_path))
                         }
                     }
                 })
                 .collect::<Result<_, _>>()?;
 
             // Conservatively don’t let the caller assume that there aren’t
             // any, since we don’t know.
             let directory_has_any_fs_only_entry = true;
 
             return Ok(directory_has_any_fs_only_entry);
         }
 
         let mut fs_entries = if let Ok(entries) = self.read_dir(
             directory_hg_path,
             directory_fs_path,
             is_at_repo_root,
         ) {
             entries
         } else {
             // Treat an unreadable directory (typically because of insufficient
             // permissions) like an empty directory. `self.read_dir` has
             // already called `self.io_error` so a warning will be emitted.
             Vec::new()
         };
 
         // `merge_join_by` requires both its input iterators to be sorted:
 
         let dirstate_nodes = dirstate_nodes.sorted();
         // `sort_unstable_by_key` doesn’t allow keys borrowing from the value:
         // https://github.com/rust-lang/rust/issues/34162
         fs_entries.sort_unstable_by(|e1, e2| e1.base_name.cmp(&e2.base_name));
 
         // Propagate here any error that would happen inside the comparison
         // callback below
         for dirstate_node in &dirstate_nodes {
             dirstate_node.base_name(self.dmap.on_disk)?;
         }
         itertools::merge_join_by(
             dirstate_nodes,
             &fs_entries,
             |dirstate_node, fs_entry| {
                 // This `unwrap` never panics because we already propagated
                 // those errors above
                 dirstate_node
                     .base_name(self.dmap.on_disk)
                     .unwrap()
                     .cmp(&fs_entry.base_name)
             },
         )
         .par_bridge()
         .map(|pair| {
             use itertools::EitherOrBoth::*;
             let is_fs_only = pair.is_right();
             match pair {
                 Both(dirstate_node, fs_entry) => self
                     .traverse_fs_and_dirstate(
                         &fs_entry.full_path,
                         &fs_entry.metadata,
                         dirstate_node,
                         has_ignored_ancestor,
                     )?,
                 Left(dirstate_node) => {
                     self.traverse_dirstate_only(dirstate_node)?
                 }
                 Right(fs_entry) => self.traverse_fs_only(
                     has_ignored_ancestor,
                     directory_hg_path,
                     fs_entry,
                 ),
             }
             Ok(is_fs_only)
         })
         .try_reduce(|| false, |a, b| Ok(a || b))
     }
 
     fn traverse_fs_and_dirstate(
         &self,
         fs_path: &Path,
         fs_metadata: &std::fs::Metadata,
         dirstate_node: NodeRef<'tree, 'on_disk>,
         has_ignored_ancestor: bool,
     ) -> Result<(), DirstateV2ParseError> {
+        self.check_for_outdated_directory_cache(&dirstate_node)?;
         let hg_path = &dirstate_node.full_path_borrowed(self.dmap.on_disk)?;
         let file_type = fs_metadata.file_type();
         let file_or_symlink = file_type.is_file() || file_type.is_symlink();
         if !file_or_symlink {
             // If we previously had a file here, it was removed (with
             // `hg rm` or similar) or deleted before it could be
             // replaced by a directory or something else.
             self.mark_removed_or_deleted_if_file(
                 &hg_path,
                 dirstate_node.state()?,
             );
         }
         if file_type.is_dir() {
             if self.options.collect_traversed_dirs {
                 self.outcome
                     .lock()
                     .unwrap()
                     .traversed
                     .push(hg_path.detach_from_tree())
             }
             let is_ignored = has_ignored_ancestor || (self.ignore_fn)(hg_path);
             let is_at_repo_root = false;
             let directory_has_any_fs_only_entry = self
                 .traverse_fs_directory_and_dirstate(
                     is_ignored,
                     dirstate_node.children(self.dmap.on_disk)?,
                     hg_path,
                     fs_path,
                     Some(fs_metadata),
                     dirstate_node.cached_directory_mtime(),
                     is_at_repo_root,
                 )?;
             self.maybe_save_directory_mtime(
                 directory_has_any_fs_only_entry,
                 fs_metadata,
                 dirstate_node,
             )?
         } else {
             if file_or_symlink && self.matcher.matches(hg_path) {
                 if let Some(state) = dirstate_node.state()? {
                     match state {
                         EntryState::Added => self
                             .outcome
                             .lock()
                             .unwrap()
                             .added
                             .push(hg_path.detach_from_tree()),
                         EntryState::Removed => self
                             .outcome
                             .lock()
                             .unwrap()
                             .removed
                             .push(hg_path.detach_from_tree()),
                         EntryState::Merged => self
                             .outcome
                             .lock()
                             .unwrap()
                             .modified
                             .push(hg_path.detach_from_tree()),
                         EntryState::Normal => self
                             .handle_normal_file(&dirstate_node, fs_metadata)?,
                         // This variant is not used in DirstateMap
                         // nodes
                         EntryState::Unknown => unreachable!(),
                     }
                 } else {
                     // `node.entry.is_none()` indicates a "directory"
                     // node, but the filesystem has a file
                     self.mark_unknown_or_ignored(has_ignored_ancestor, hg_path)
                 }
             }
 
             for child_node in dirstate_node.children(self.dmap.on_disk)?.iter()
             {
                 self.traverse_dirstate_only(child_node)?
             }
         }
         Ok(())
     }
 
     fn maybe_save_directory_mtime(
         &self,
         directory_has_any_fs_only_entry: bool,
         directory_metadata: &std::fs::Metadata,
         dirstate_node: NodeRef<'tree, 'on_disk>,
     ) -> Result<(), DirstateV2ParseError> {
         if !directory_has_any_fs_only_entry {
             // All filesystem directory entries from `read_dir` have a
             // corresponding node in the dirstate, so we can reconstitute the
             // names of those entries without calling `read_dir` again.
             if let (Some(status_start), Ok(directory_mtime)) = (
                 &self.filesystem_time_at_status_start,
                 directory_metadata.modified(),
             ) {
                 // Although the Rust standard library’s `SystemTime` type
                 // has nanosecond precision, the times reported for a
                 // directory’s (or file’s) modified time may have lower
                 // resolution based on the filesystem (for example ext3
                 // only stores integer seconds), kernel (see
                 // https://stackoverflow.com/a/14393315/1162888), etc.
                 if &directory_mtime >= status_start {
                     // The directory was modified too recently, don’t cache its
                     // `read_dir` results.
                     //
                     // A timeline like this is possible:
                     //
                     // 1. A change to this directory (direct child was
                     //    added or removed) cause its mtime to be set
                     //    (possibly truncated) to `directory_mtime`
                     // 2. This `status` algorithm calls `read_dir`
                     // 3. An other change is made to the same directory is
                     //    made so that calling `read_dir` agin would give
                     //    different results, but soon enough after 1. that
                     //    the mtime stays the same
                     //
                     // On a system where the time resolution poor, this
                     // scenario is not unlikely if all three steps are caused
                     // by the same script.
                 } else {
                     // We’ve observed (through `status_start`) that time has
                     // “progressed” since `directory_mtime`, so any further
                     // change to this directory is extremely likely to cause a
                     // different mtime.
                     //
                     // Having the same mtime again is not entirely impossible
                     // since the system clock is not monotonous. It could jump
                     // backward to some point before `directory_mtime`, then a
                     // directory change could potentially happen during exactly
                     // the wrong tick.
                     //
                     // We deem this scenario (unlike the previous one) to be
                     // unlikely enough in practice.
                     let timestamp = directory_mtime.into();
                     let cached = dirstate_node.cached_directory_mtime();
                     if cached != Some(&timestamp) {
                         let hg_path = dirstate_node
                             .full_path_borrowed(self.dmap.on_disk)?
                             .detach_from_tree();
                         self.new_cachable_directories
                             .lock()
                             .unwrap()
                             .push((hg_path, timestamp))
                     }
                 }
             }
         }
         Ok(())
     }
 
     /// A file with `EntryState::Normal` in the dirstate was found in the
     /// filesystem
     fn handle_normal_file(
         &self,
         dirstate_node: &NodeRef<'tree, 'on_disk>,
         fs_metadata: &std::fs::Metadata,
     ) -> Result<(), DirstateV2ParseError> {
         // Keep the low 31 bits
         fn truncate_u64(value: u64) -> i32 {
             (value & 0x7FFF_FFFF) as i32
         }
         fn truncate_i64(value: i64) -> i32 {
             (value & 0x7FFF_FFFF) as i32
         }
 
         let entry = dirstate_node
             .entry()?
             .expect("handle_normal_file called with entry-less node");
         let hg_path = &dirstate_node.full_path_borrowed(self.dmap.on_disk)?;
         let mode_changed =
             || self.options.check_exec && entry.mode_changed(fs_metadata);
         let size_changed = entry.size != truncate_u64(fs_metadata.len());
         if entry.size >= 0
             && size_changed
             && fs_metadata.file_type().is_symlink()
         {
             // issue6456: Size returned may be longer due to encryption
             // on EXT-4 fscrypt. TODO maybe only do it on EXT4?
             self.outcome
                 .lock()
                 .unwrap()
                 .unsure
                 .push(hg_path.detach_from_tree())
         } else if dirstate_node.has_copy_source()
             || entry.is_from_other_parent()
             || (entry.size >= 0 && (size_changed || mode_changed()))
         {
             self.outcome
                 .lock()
                 .unwrap()
                 .modified
                 .push(hg_path.detach_from_tree())
         } else {
             let mtime = mtime_seconds(fs_metadata);
             if truncate_i64(mtime) != entry.mtime
                 || mtime == self.options.last_normal_time
             {
                 self.outcome
                     .lock()
                     .unwrap()
                     .unsure
                     .push(hg_path.detach_from_tree())
             } else if self.options.list_clean {
                 self.outcome
                     .lock()
                     .unwrap()
                     .clean
                     .push(hg_path.detach_from_tree())
             }
         }
         Ok(())
     }
 
     /// A node in the dirstate tree has no corresponding filesystem entry
     fn traverse_dirstate_only(
         &self,
         dirstate_node: NodeRef<'tree, 'on_disk>,
     ) -> Result<(), DirstateV2ParseError> {
+        self.check_for_outdated_directory_cache(&dirstate_node)?;
         self.mark_removed_or_deleted_if_file(
             &dirstate_node.full_path_borrowed(self.dmap.on_disk)?,
             dirstate_node.state()?,
         );
         dirstate_node
             .children(self.dmap.on_disk)?
             .par_iter()
             .map(|child_node| self.traverse_dirstate_only(child_node))
             .collect()
     }
 
     /// A node in the dirstate tree has no corresponding *file* on the
     /// filesystem
     ///
     /// Does nothing on a "directory" node
     fn mark_removed_or_deleted_if_file(
         &self,
         hg_path: &BorrowedPath<'tree, 'on_disk>,
         dirstate_node_state: Option<EntryState>,
     ) {
         if let Some(state) = dirstate_node_state {
             if self.matcher.matches(hg_path) {
                 if let EntryState::Removed = state {
                     self.outcome
                         .lock()
                         .unwrap()
                         .removed
                         .push(hg_path.detach_from_tree())
                 } else {
                     self.outcome
                         .lock()
                         .unwrap()
                         .deleted
                         .push(hg_path.detach_from_tree())
                 }
             }
         }
     }
 
     /// Something in the filesystem has no corresponding dirstate node
     fn traverse_fs_only(
         &self,
         has_ignored_ancestor: bool,
         directory_hg_path: &HgPath,
         fs_entry: &DirEntry,
     ) {
         let hg_path = directory_hg_path.join(&fs_entry.base_name);
         let file_type = fs_entry.metadata.file_type();
         let file_or_symlink = file_type.is_file() || file_type.is_symlink();
         if file_type.is_dir() {
             let is_ignored =
                 has_ignored_ancestor || (self.ignore_fn)(&hg_path);
             let traverse_children = if is_ignored {
                 // Descendants of an ignored directory are all ignored
                 self.options.list_ignored
             } else {
                 // Descendants of an unknown directory may be either unknown or
                 // ignored
                 self.options.list_unknown || self.options.list_ignored
             };
             if traverse_children {
                 let is_at_repo_root = false;
                 if let Ok(children_fs_entries) = self.read_dir(
                     &hg_path,
                     &fs_entry.full_path,
                     is_at_repo_root,
                 ) {
                     children_fs_entries.par_iter().for_each(|child_fs_entry| {
                         self.traverse_fs_only(
                             is_ignored,
                             &hg_path,
                             child_fs_entry,
                         )
                     })
                 }
             }
             if self.options.collect_traversed_dirs {
                 self.outcome.lock().unwrap().traversed.push(hg_path.into())
             }
         } else if file_or_symlink && self.matcher.matches(&hg_path) {
             self.mark_unknown_or_ignored(
                 has_ignored_ancestor,
                 &BorrowedPath::InMemory(&hg_path),
             )
         }
     }
 
     fn mark_unknown_or_ignored(
         &self,
         has_ignored_ancestor: bool,
         hg_path: &BorrowedPath<'_, 'on_disk>,
     ) {
         let is_ignored = has_ignored_ancestor || (self.ignore_fn)(&hg_path);
         if is_ignored {
             if self.options.list_ignored {
                 self.outcome
                     .lock()
                     .unwrap()
                     .ignored
                     .push(hg_path.detach_from_tree())
             }
         } else {
             if self.options.list_unknown {
                 self.outcome
                     .lock()
                     .unwrap()
                     .unknown
                     .push(hg_path.detach_from_tree())
             }
         }
     }
 }
 
 #[cfg(unix)] // TODO
 fn mtime_seconds(metadata: &std::fs::Metadata) -> i64 {
     // Going through `Metadata::modified()` would be portable, but would take
     // care to construct a `SystemTime` value with sub-second precision just
     // for us to throw that away here.
     use std::os::unix::fs::MetadataExt;
     metadata.mtime()
 }
 
 struct DirEntry {
     base_name: HgPathBuf,
     full_path: PathBuf,
     metadata: std::fs::Metadata,
 }
 
 impl DirEntry {
     /// Returns **unsorted** entries in the given directory, with name and
     /// metadata.
     ///
     /// If a `.hg` sub-directory is encountered:
     ///
     /// * At the repository root, ignore that sub-directory
     /// * Elsewhere, we’re listing the content of a sub-repo. Return an empty
     ///   list instead.
     fn read_dir(path: &Path, is_at_repo_root: bool) -> io::Result<Vec<Self>> {
         let mut results = Vec::new();
         for entry in path.read_dir()? {
             let entry = entry?;
             let metadata = entry.metadata()?;
             let name = get_bytes_from_os_string(entry.file_name());
             // FIXME don't do this when cached
             if name == b".hg" {
                 if is_at_repo_root {
                     // Skip the repo’s own .hg (might be a symlink)
                     continue;
                 } else if metadata.is_dir() {
                     // A .hg sub-directory at another location means a subrepo,
                     // skip it entirely.
                     return Ok(Vec::new());
                 }
             }
             results.push(DirEntry {
                 base_name: name.into(),
                 full_path: entry.path(),
                 metadata,
             })
         }
         Ok(results)
     }
 }
 
 /// Return the `mtime` of a temporary file newly-created in the `.hg` directory
 /// of the give repository.
 ///
 /// This is similar to `SystemTime::now()`, with the result truncated to the
 /// same time resolution as other files’ modification times. Using `.hg`
 /// instead of the system’s default temporary directory (such as `/tmp`) makes
 /// it more likely the temporary file is in the same disk partition as contents
 /// of the working directory, which can matter since different filesystems may
 /// store timestamps with different resolutions.
 ///
 /// This may fail, typically if we lack write permissions. In that case we
 /// should continue the `status()` algoritm anyway and consider the current
 /// date/time to be unknown.
 fn filesystem_now(repo_root: &Path) -> Result<SystemTime, io::Error> {
     tempfile::tempfile_in(repo_root.join(".hg"))?
         .metadata()?
         .modified()
 }