format/encoder/decoder: new pxar entry type Prelude

Introduces a new pxar format entry type `Prelude` and the associated
encoder and decoder methods.
A prelude starts with header marker `PXAR_PRELUDE` followed by raw
byte content, used to store additional metadata associated with the
pxar archive, e.g. command line arguments passed on archive creation.

The prelude's content has no fixed encoding format but is stored as
an raw, arbitrary byte slice. A prelude entry is encoded right after
a pxar format version entry, both being encoded in the metadata
archive in case of an archive with dedicated payload output.

The prelude is not backwards compatible to pxar format version 1.

Signed-off-by: Christian Ebner <c.ebner@proxmox.com>

examples/mk-format-hashes.rs

@@ -16,6 +16,7 @@ const CONSTANTS: &[(&str, &str, &str)] = &[
         "PXAR_ENTRY_V1",
         "__PROXMOX_FORMAT_ENTRY__",
     ),
+    ("", "PXAR_PRELUDE", "__PROXMOX_FORMAT_PRELUDE__"),
     ("", "PXAR_FILENAME", "__PROXMOX_FORMAT_FILENAME__"),
     ("", "PXAR_SYMLINK", "__PROXMOX_FORMAT_SYMLINK__"),
     ("", "PXAR_DEVICE", "__PROXMOX_FORMAT_DEVICE__"),

src/accessor/mod.rs

@@ -322,6 +322,12 @@ impl<T: Clone + ReadAt> AccessorImpl<T> {
                 .next()
                 .await
                 .ok_or_else(|| io_format_err!("unexpected EOF while decoding directory entry"))??;
+
+            if let EntryKind::Prelude(_) = entry.kind() {
+                entry = decoder.next().await.ok_or_else(|| {
+                    io_format_err!("unexpected EOF while decoding directory entry")
+                })??;
+            }
         }
 
         Ok(FileEntryImpl {
@@ -559,6 +565,12 @@ impl<T: Clone + ReadAt> DirectoryImpl<T> {
                 .next()
                 .await
                 .ok_or_else(|| io_format_err!("unexpected EOF while decoding directory entry"))??;
+
+            if let EntryKind::Prelude(_) = entry.kind() {
+                entry = decoder.next().await.ok_or_else(|| {
+                    io_format_err!("unexpected EOF while decoding directory entry")
+                })??;
+            }
         }
 
         Ok((entry, decoder))

src/decoder/mod.rs

@@ -176,6 +176,7 @@ pub(crate) struct DecoderImpl<T> {
 #[derive(Clone, PartialEq)]
 enum State {
     Begin,
+    Prelude,
     Root,
     Default,
     InPayload {
@@ -264,10 +265,25 @@ impl<I: SeqRead> DecoderImpl<I> {
                 State::Eof => return Ok(None),
                 State::Begin => {
                     let entry = self.read_next_entry().await.map(Some);
+                    // If the first entry is of kind Version, next must be Prelude or Directory
                     if let Ok(Some(ref entry)) = entry {
                         if let EntryKind::Version(version) = entry.kind() {
                             self.version = version.clone();
-                            self.state = State::Root;
+                            self.state = State::Prelude;
+                        }
+                    }
+                    return entry;
+                }
+                State::Prelude => {
+                    let entry = self.read_next_entry().await.map(Some);
+                    if let Ok(Some(ref entry)) = entry {
+                        match entry.kind() {
+                            EntryKind::Prelude(_) => self.state = State::Root,
+                            EntryKind::Directory => self.state = State::InDirectory,
+                            _ => io_bail!(
+                                "expected directory or prelude entry, got entry kind {:?}",
+                                entry.kind()
+                            ),
                         }
                     }
                     return entry;
@@ -433,6 +449,14 @@ impl<I: SeqRead> DecoderImpl<I> {
             self.current_header = header;
             self.entry.kind = EntryKind::Version(self.read_format_version().await?);
 
+            Ok(Some(self.entry.take()))
+        } else if header.htype == format::PXAR_PRELUDE {
+            if previous_state != State::Prelude {
+                io_bail!("Got format version entry at unexpected position");
+            }
+            self.current_header = header;
+            self.entry.kind = EntryKind::Prelude(self.read_prelude().await?);
+
             Ok(Some(self.entry.take()))
         } else if header.htype == format::PXAR_ENTRY || header.htype == format::PXAR_ENTRY_V1 {
             if header.htype == format::PXAR_ENTRY {
@@ -797,6 +821,11 @@ impl<I: SeqRead> DecoderImpl<I> {
         let version: u64 = seq_read_entry(self.input.archive_mut()).await?;
         FormatVersion::deserialize(version)
     }
+
+    async fn read_prelude(&mut self) -> io::Result<format::Prelude> {
+        let data = self.read_entry_as_bytes().await?;
+        Ok(format::Prelude { data })
+    }
 }
 
 /// Reader for file contents inside a pxar archive.

src/encoder/aio.rs

@@ -24,8 +24,14 @@ impl<'a, T: tokio::io::AsyncWrite + 'a> Encoder<'a, TokioWriter<T>> {
     pub async fn from_tokio(
         output: PxarVariant<T, T>,
         metadata: &Metadata,
+        prelude: Option<&[u8]>,
     ) -> io::Result<Encoder<'a, TokioWriter<T>>> {
-        Encoder::new(output.wrap(|output| TokioWriter::new(output)), metadata).await
+        Encoder::new(
+            output.wrap(|output| TokioWriter::new(output)),
+            metadata,
+            prelude,
+        )
+        .await
     }
 }
 
@@ -41,6 +47,7 @@ impl<'a> Encoder<'a, TokioWriter<tokio::fs::File>> {
                 tokio::fs::File::create(path.as_ref()).await?,
             )),
             metadata,
+            None,
         )
         .await
     }
@@ -48,10 +55,14 @@ impl<'a> Encoder<'a, TokioWriter<tokio::fs::File>> {
 
 impl<'a, T: SeqWrite + 'a> Encoder<'a, T> {
     /// Create an asynchronous encoder for an output implementing our internal write interface.
-    pub async fn new(output: PxarVariant<T, T>, metadata: &Metadata) -> io::Result<Encoder<'a, T>> {
+    pub async fn new(
+        output: PxarVariant<T, T>,
+        metadata: &Metadata,
+        prelude: Option<&[u8]>,
+    ) -> io::Result<Encoder<'a, T>> {
         let output = output.wrap_multi(|output| output.into(), |payload_output| payload_output);
         Ok(Self {
-            inner: encoder::EncoderImpl::new(output, metadata).await?,
+            inner: encoder::EncoderImpl::new(output, metadata, prelude).await?,
         })
     }
 
@@ -326,6 +337,7 @@ mod test {
             let mut encoder = Encoder::new(
                 crate::PxarVariant::Unified(DummyOutput),
                 &Metadata::dir_builder(0o700).build(),
+                None,
             )
             .await
             .unwrap();

src/encoder/mod.rs

@@ -346,6 +346,7 @@ impl<'a, T: SeqWrite + 'a> EncoderImpl<'a, T> {
     pub async fn new(
         mut output: PxarVariant<EncoderOutput<'a, T>, T>,
         metadata: &Metadata,
+        prelude: Option<&[u8]>,
     ) -> io::Result<EncoderImpl<'a, T>> {
         if !metadata.is_dir() {
             io_bail!("directory metadata must contain the directory mode flag");
@@ -372,6 +373,9 @@ impl<'a, T: SeqWrite + 'a> EncoderImpl<'a, T> {
         };
 
         this.encode_format_version().await?;
+        if let Some(prelude) = prelude {
+            this.encode_prelude(prelude).await?;
+        }
         this.encode_metadata(metadata).await?;
         let state = this.state_mut()?;
         state.files_offset = state.position();
@@ -773,6 +777,28 @@ impl<'a, T: SeqWrite + 'a> EncoderImpl<'a, T> {
         Ok(())
     }
 
+    async fn encode_prelude(&mut self, prelude: &[u8]) -> io::Result<()> {
+        if self.version == FormatVersion::Version1 {
+            io_bail!("encoding prelude not supported in format version 1");
+        }
+
+        let (mut output, state) = self.output_state()?;
+        if state.write_position != (size_of::<u64>() + size_of::<format::Header>()) as u64 {
+            io_bail!(
+                "prelude must be encoded following the version header, current position {}",
+                state.write_position,
+            );
+        }
+
+        seq_write_pxar_entry(
+            output.archive_mut(),
+            format::PXAR_PRELUDE,
+            prelude,
+            &mut state.write_position,
+        )
+        .await
+    }
+
     async fn encode_format_version(&mut self) -> io::Result<()> {
         if let Some(version_bytes) = self.version.serialize() {
             let (mut output, state) = self.output_state()?;

src/encoder/sync.rs

@@ -28,7 +28,11 @@ impl<'a, T: io::Write + 'a> Encoder<'a, StandardWriter<T>> {
     /// Encode a `pxar` archive into a regular `std::io::Write` output.
     #[inline]
     pub fn from_std(output: T, metadata: &Metadata) -> io::Result<Encoder<'a, StandardWriter<T>>> {
-        Encoder::new(PxarVariant::Unified(StandardWriter::new(output)), metadata)
+        Encoder::new(
+            PxarVariant::Unified(StandardWriter::new(output)),
+            metadata,
+            None,
+        )
     }
 }
 
@@ -41,6 +45,7 @@ impl<'a> Encoder<'a, StandardWriter<std::fs::File>> {
         Encoder::new(
             PxarVariant::Unified(StandardWriter::new(std::fs::File::create(path.as_ref())?)),
             metadata,
+            None,
         )
     }
 }
@@ -52,11 +57,15 @@ impl<'a, T: SeqWrite + 'a> Encoder<'a, T> {
     /// not allowed to use the `Waker`, as this will cause a `panic!`.
     // Optionally attach a dedicated writer to redirect the payloads of regular files to a separate
     // output.
-    pub fn new(output: PxarVariant<T, T>, metadata: &Metadata) -> io::Result<Self> {
+    pub fn new(
+        output: PxarVariant<T, T>,
+        metadata: &Metadata,
+        prelude: Option<&[u8]>,
+    ) -> io::Result<Self> {
         let output = output.wrap_multi(|output| output.into(), |payload_output| payload_output);
 
         Ok(Self {
-            inner: poll_result_once(encoder::EncoderImpl::new(output, metadata))?,
+            inner: poll_result_once(encoder::EncoderImpl::new(output, metadata, prelude))?,
         })
     }
 

src/format/mod.rs

@@ -87,6 +87,7 @@ pub const PXAR_FORMAT_VERSION: u64 = 0x730f6c75df16a40d;
 pub const PXAR_ENTRY: u64 = 0xd5956474e588acef;
 /// Previous version of the entry struct
 pub const PXAR_ENTRY_V1: u64 = 0x11da850a1c1cceff;
+pub const PXAR_PRELUDE: u64 = 0xe309d79d9f7b771b;
 pub const PXAR_FILENAME: u64 = 0x16701121063917b3;
 pub const PXAR_SYMLINK: u64 = 0x27f971e7dbf5dc5f;
 pub const PXAR_DEVICE: u64 = 0x9fc9e906586d5ce9;
@@ -147,6 +148,7 @@ impl Header {
     #[inline]
     pub fn max_content_size(&self) -> u64 {
         match self.htype {
+            PXAR_PRELUDE => u64::MAX - (size_of::<Self>() as u64),
             // + null-termination
             PXAR_FILENAME => crate::util::MAX_FILENAME_LEN + 1,
             // + null-termination
@@ -190,6 +192,7 @@ impl Display for Header {
     fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
         let readable = match self.htype {
             PXAR_FORMAT_VERSION => "FORMAT_VERSION",
+            PXAR_PRELUDE => "PRELUDE",
             PXAR_FILENAME => "FILENAME",
             PXAR_SYMLINK => "SYMLINK",
             PXAR_HARDLINK => "HARDLINK",
@@ -712,6 +715,29 @@ impl Device {
     }
 }
 
+#[derive(Clone, Debug)]
+pub struct Prelude {
+    pub data: Vec<u8>,
+}
+
+impl Prelude {
+    pub fn as_os_str(&self) -> &OsStr {
+        self.as_ref()
+    }
+}
+
+impl AsRef<[u8]> for Prelude {
+    fn as_ref(&self) -> &[u8] {
+        &self.data
+    }
+}
+
+impl AsRef<OsStr> for Prelude {
+    fn as_ref(&self) -> &OsStr {
+        OsStr::from_bytes(&self.data[..self.data.len().max(1) - 1])
+    }
+}
+
 #[cfg(all(test, target_os = "linux"))]
 #[test]
 fn test_linux_devices() {

src/lib.rs

@@ -345,6 +345,9 @@ pub enum EntryKind {
     /// Pxar file format version
     Version(format::FormatVersion),
 
+    /// Pxar prelude blob
+    Prelude(format::Prelude),
+
     /// Symbolic links.
     Symlink(format::Symlink),
 

tests/simple/fs.rs

@@ -230,6 +230,7 @@ impl Entry {
                 };
             match item.kind() {
                 PxarEntryKind::Version(_) => continue,
+                PxarEntryKind::Prelude(_) => continue,
                 PxarEntryKind::GoodbyeTable => break,
                 PxarEntryKind::File { size, .. } => {
                     let mut data = Vec::new();