From 0157d0643f4f0a550399b84c1f35f9561abae609 Mon Sep 17 00:00:00 2001
From: Ben Kimock <kimockb@gmail.com>
Date: Sat, 10 Feb 2024 17:15:15 -0500
Subject: [PATCH] Hash the mtime and size of every file in the sysroot

---
 Cargo.lock | 51 +++++++++++++++++++++++++++++++++++++++++++++++++++
 Cargo.toml |  1 +
 src/lib.rs | 33 ++++++++++++++++++++++++++++-----
 3 files changed, 80 insertions(+), 5 deletions(-)

diff --git a/Cargo.lock b/Cargo.lock
index a84104e..203ed51 100644
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -70,6 +70,7 @@ dependencies = [
  "anyhow",
  "rustc_version",
  "tempfile",
+ "walkdir",
 ]
 
 [[package]]
@@ -94,6 +95,15 @@ dependencies = [
  "windows-sys",
 ]
 
+[[package]]
+name = "same-file"
+version = "1.0.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "93fc1dc3aaa9bfed95e02e6eadabb4baf7e3078b0bd1b4d7b6b0b68378900502"
+dependencies = [
+ "winapi-util",
+]
+
 [[package]]
 name = "semver"
 version = "1.0.21"
@@ -113,6 +123,47 @@ dependencies = [
  "windows-sys",
 ]
 
+[[package]]
+name = "walkdir"
+version = "2.4.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d71d857dc86794ca4c280d616f7da00d2dbfd8cd788846559a6813e6aa4b54ee"
+dependencies = [
+ "same-file",
+ "winapi-util",
+]
+
+[[package]]
+name = "winapi"
+version = "0.3.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5c839a674fcd7a98952e593242ea400abe93992746761e38641405d28b00f419"
+dependencies = [
+ "winapi-i686-pc-windows-gnu",
+ "winapi-x86_64-pc-windows-gnu",
+]
+
+[[package]]
+name = "winapi-i686-pc-windows-gnu"
+version = "0.4.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ac3b87c63620426dd9b991e5ce0329eff545bccbbb34f3be09ff6fb6ab51b7b6"
+
+[[package]]
+name = "winapi-util"
+version = "0.1.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f29e6f9198ba0d26b4c9f07dbe6f9ed633e1f3d5b8b414090084349e46a52596"
+dependencies = [
+ "winapi",
+]
+
+[[package]]
+name = "winapi-x86_64-pc-windows-gnu"
+version = "0.4.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "712e227841d057c1ee1cd2fb22fa7e5a5461ae8e48fa2ca79ec42cfc1931183f"
+
 [[package]]
 name = "windows-sys"
 version = "0.52.0"
diff --git a/Cargo.toml b/Cargo.toml
index 9d1f58c..d88c29e 100644
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -12,3 +12,4 @@ description = "Build a rustc sysroot with custom flags"
 tempfile = "3"
 rustc_version = "0.4"
 anyhow = "1.0"
+walkdir = "2.4"
diff --git a/src/lib.rs b/src/lib.rs
index a01e323..252d654 100644
--- a/src/lib.rs
+++ b/src/lib.rs
@@ -15,6 +15,7 @@ use std::process::Command;
 
 use anyhow::{bail, Context, Result};
 use tempfile::TempDir;
+use walkdir::WalkDir;
 
 /// Returns where the given rustc stores its sysroot source code.
 pub fn rustc_sysroot_src(mut rustc: Command) -> Result<PathBuf> {
@@ -84,6 +85,29 @@ fn make_writeable(p: &Path) -> Result<()> {
     Ok(())
 }
 
+/// Hash the metadata and size of every file in a directory, recursively.
+pub fn hash_recursive(path: &Path, hasher: &mut DefaultHasher) -> Result<()> {
+    // We sort the entries to ensure a stable hash.
+    for entry in WalkDir::new(path)
+        .follow_links(true)
+        .sort_by_file_name()
+        .into_iter()
+    {
+        let entry = entry?;
+        // WalkDir yields the directories as well, and File::open will succeed on them. The
+        // reliable way to distinguish directories here is to check explicitly.
+        if entry.file_type().is_dir() {
+            continue;
+        }
+        let meta = entry.metadata()?;
+        // Hashing the mtime and file size should catch basically all mutations,
+        // and is faster than hashing the file contents.
+        meta.modified()?.hash(hasher);
+        meta.len().hash(hasher);
+    }
+    Ok(())
+}
+
 /// The build mode to use for this sysroot.
 #[derive(Copy, Clone, Debug, PartialEq, Eq, Hash)]
 pub enum BuildMode {
@@ -220,18 +244,17 @@ impl SysrootBuilder {
         &self,
         src_dir: &Path,
         rustc_version: &rustc_version::VersionMeta,
-    ) -> u64 {
+    ) -> Result<u64> {
         let mut hasher = DefaultHasher::new();
 
-        // For now, we just hash in the information we have in `self`.
-        // Ideally we'd recursively hash the entire folder but that sounds slow?
         src_dir.hash(&mut hasher);
+        hash_recursive(src_dir, &mut hasher)?;
         self.config.hash(&mut hasher);
         self.mode.hash(&mut hasher);
         self.rustflags.hash(&mut hasher);
         rustc_version.hash(&mut hasher);
 
-        hasher.finish()
+        Ok(hasher.finish())
     }
 
     fn sysroot_read_hash(&self) -> Option<u64> {
@@ -372,7 +395,7 @@ path = "lib.rs"
         }
 
         // Check if we even need to do anything.
-        let cur_hash = self.sysroot_compute_hash(src_dir, &rustc_version);
+        let cur_hash = self.sysroot_compute_hash(src_dir, &rustc_version)?;
         if self.sysroot_read_hash() == Some(cur_hash) {
             // Already done!
             return Ok(());