Re: [pbs-devel] [PATCH v3 pxar 13/58] format: add pxar format version entry

["Fabian Grünbichler" <f.gruenbichler@proxmox.com>]

On March 28, 2024 1:36 pm, Christian Ebner wrote:
> Adds an additional entry type at the start of each pxar archive
> signaling the encoding format version. If not present, the default
> version 1 is assumed.
> 
> This allows to early on detect the pxar encoding version, allowing tools
> to switch mode or bail on non compatible encoder/decoder functionality.
> 
> Signed-off-by: Christian Ebner <c.ebner@proxmox.com>
> ---
> changes since version 2:
> - not present in previous version
> 
>  examples/mk-format-hashes.rs |  5 +++++
>  src/decoder/mod.rs           | 29 ++++++++++++++++++++++++++--
>  src/encoder/mod.rs           | 37 +++++++++++++++++++++++++++++++++---
>  src/format/mod.rs            | 11 +++++++++++
>  src/lib.rs                   |  3 +++
>  5 files changed, 80 insertions(+), 5 deletions(-)
> 
> diff --git a/examples/mk-format-hashes.rs b/examples/mk-format-hashes.rs
> index 35cff99..e5d69b1 100644
> --- a/examples/mk-format-hashes.rs
> +++ b/examples/mk-format-hashes.rs
> @@ -1,6 +1,11 @@
>  use pxar::format::hash_filename;
>  
>  const CONSTANTS: &[(&str, &str, &str)] = &[
> +    (
> +        "Pxar format version entry, fallback to version 1 if not present",
> +        "PXAR_FORMAT_VERSION",
> +        "__PROXMOX_FORMAT_VERSION__",
> +    ),
>      (
>          "Beginning of an entry (current version).",
>          "PXAR_ENTRY",
> diff --git a/src/decoder/mod.rs b/src/decoder/mod.rs
> index 00d9abf..5b2fafb 100644
> --- a/src/decoder/mod.rs
> +++ b/src/decoder/mod.rs
> @@ -17,7 +17,7 @@ use std::task::{Context, Poll};
>  
>  use endian_trait::Endian;
>  
> -use crate::format::{self, Header};
> +use crate::format::{self, FormatVersion, Header};
>  use crate::util::{self, io_err_other};
>  use crate::{Entry, EntryKind, Metadata};
>  
> @@ -164,6 +164,8 @@ pub(crate) struct DecoderImpl<T> {
>      /// The random access code uses decoders for sub-ranges which may not end in a `PAYLOAD` for
>      /// entries like FIFOs or sockets, so there we explicitly allow an item to terminate with EOF.
>      eof_after_entry: bool,
> +    /// The format version as determined by the format version header
> +    version: format::FormatVersion,
>  }
>  
>  enum State {
> @@ -242,6 +244,7 @@ impl<I: SeqRead> DecoderImpl<I> {
>              payload_input,
>              payload_consumed,
>              eof_after_entry,
> +            version: FormatVersion::default(),
>          };
>  
>          // this.read_next_entry().await?;
> @@ -258,7 +261,16 @@ impl<I: SeqRead> DecoderImpl<I> {
>          loop {
>              match self.state {
>                  State::Eof => return Ok(None),
> -                State::Begin => return self.read_next_entry().await.map(Some),
> +                State::Begin => {
> +                    let entry = self.read_next_entry().await.map(Some);
> +                    if let Ok(Some(ref entry)) = entry {
> +                        if let EntryKind::Version(version) = entry.kind() {
> +                            self.version = version.clone();
> +                            return self.read_next_entry().await.map(Some);
> +                        }
> +                    }
> +                    return entry;

a bit unsure here, if we want to enforce the order, wouldn't it be more
clean to transition to a new state here rather than adding more nested
ifs over time? ;)

> +                }
>                  State::Default => {
>                      // we completely finished an entry, so now we're going "up" in the directory
>                      // hierarchy and parse the next PXAR_FILENAME or the PXAR_GOODBYE:
> @@ -412,6 +424,11 @@ impl<I: SeqRead> DecoderImpl<I> {
>              self.entry.metadata = Metadata::default();
>              self.entry.kind = EntryKind::Hardlink(self.read_hardlink().await?);
>  
> +            Ok(Some(self.entry.take()))
> +        } else if header.htype == format::PXAR_FORMAT_VERSION {
> +            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_ENTRY || header.htype == format::PXAR_ENTRY_V1 {
>              if header.htype == format::PXAR_ENTRY {
> @@ -777,6 +794,14 @@ impl<I: SeqRead> DecoderImpl<I> {
>  
>          seq_read_entry(&mut self.input).await
>      }
> +
> +    async fn read_format_version(&mut self) -> io::Result<format::FormatVersion> {
> +        match seq_read_entry(&mut self.input).await? {
> +            1u64 => Ok(format::FormatVersion::Version1),

this should never happen though, right?

> +            2u64 => Ok(format::FormatVersion::Version2),

also this (cted below)

> +            _ => io_bail!("unexpected pxar format version"),

this should maybe include the value? ;)

> +        }
> +    }
>  }
>  
>  /// Reader for file contents inside a pxar archive.
> diff --git a/src/encoder/mod.rs b/src/encoder/mod.rs
> index 88c0ed5..9270153 100644
> --- a/src/encoder/mod.rs
> +++ b/src/encoder/mod.rs
> @@ -17,7 +17,7 @@ use endian_trait::Endian;
>  
>  use crate::binary_tree_array;
>  use crate::decoder::{self, SeqRead};
> -use crate::format::{self, GoodbyeItem, PayloadRef};
> +use crate::format::{self, FormatVersion, GoodbyeItem, PayloadRef};
>  use crate::Metadata;
>  
>  pub mod aio;
> @@ -307,6 +307,8 @@ pub(crate) struct EncoderImpl<'a, T: SeqWrite + 'a> {
>      /// Since only the "current" entry can be actively writing files, we share the file copy
>      /// buffer.
>      file_copy_buffer: Arc<Mutex<Vec<u8>>>,
> +    /// Pxar format version to encode
> +    version: format::FormatVersion,
>  }
>  
>  impl<'a, T: SeqWrite + 'a> EncoderImpl<'a, T> {
> @@ -320,11 +322,14 @@ impl<'a, T: SeqWrite + 'a> EncoderImpl<'a, T> {
>          }
>  
>          let mut state = EncoderState::default();
> -        if let Some(payload_output) = payload_output.as_mut() {
> +        let version = if let Some(payload_output) = payload_output.as_mut() {
>              let header = format::Header::with_content_size(format::PXAR_PAYLOAD_START_MARKER, 0);
>              header.check_header_size()?;
>              seq_write_struct(payload_output, header, &mut state.payload_write_position).await?;
> -        }
> +            format::FormatVersion::Version2
> +        } else {
> +            format::FormatVersion::default()

shouldn't this be Version1 instead of default()? they are the same
*now*, but that might not be the case forever?

> +        };
>  
>          let mut this = Self {
>              output,
> @@ -334,8 +339,10 @@ impl<'a, T: SeqWrite + 'a> EncoderImpl<'a, T> {
>              file_copy_buffer: Arc::new(Mutex::new(unsafe {
>                  crate::util::vec_new_uninitialized(1024 * 1024)
>              })),
> +            version,
>          };
>  
> +        this.encode_format_version().await?;
>          this.encode_metadata(metadata).await?;
>          let state = this.state_mut()?;
>          state.files_offset = state.position();
> @@ -522,6 +529,10 @@ impl<'a, T: SeqWrite + 'a> EncoderImpl<'a, T> {
>          file_size: u64,
>          payload_offset: PayloadOffset,
>      ) -> io::Result<()> {
> +        if self.version == FormatVersion::Version1 {
> +            io_bail!("payload references not supported pxar format version 1");
> +        }
> +
>          if self.payload_output.as_mut().is_none() {
>              io_bail!("unable to add payload reference");
>          }
> @@ -729,6 +740,26 @@ impl<'a, T: SeqWrite + 'a> EncoderImpl<'a, T> {
>          Ok(())
>      }
>  
> +    async fn encode_format_version(&mut self) -> io::Result<()> {
> +		let version_bytes = match self.version {
> +			format::FormatVersion::Version1 => return Ok(()),
> +			format::FormatVersion::Version2 => 2u64.to_le_bytes(),

(cted from above) and this here should maybe go together?

> +		};
> +
> +        let (output, state) = self.output_state()?;
> +		if state.write_position != 0 {
> +			io_bail!("pxar format version must be encoded at the beginning of an archive");

should this also be enforced while decoding?

should we also encode a/the version of the payload archive?

> +		}
> +
> +        seq_write_pxar_entry(
> +            output,
> +            format::PXAR_FORMAT_VERSION,
> +            &version_bytes,
> +            &mut state.write_position,
> +        )
> +        .await
> +    }
> +
>      async fn encode_metadata(&mut self, metadata: &Metadata) -> io::Result<()> {
>          let (output, state) = self.output_state()?;
>          seq_write_pxar_struct_entry(
> diff --git a/src/format/mod.rs b/src/format/mod.rs
> index a672d19..2bf33c9 100644
> --- a/src/format/mod.rs
> +++ b/src/format/mod.rs
> @@ -6,6 +6,7 @@
>  //! item data.
>  //!
>  //! An archive contains items in the following order:
> +//!  * `FORMAT_VERSION`     -- (optional for v1), version of encoding format
>  //!  * `ENTRY`              -- containing general stat() data and related bits
>  //!   * `XATTR`             -- one extended attribute
>  //!   * ...                 -- more of these when there are multiple defined
> @@ -80,6 +81,8 @@ pub mod mode {
>  }
>  
>  // Generated by `cargo run --example mk-format-hashes`
> +/// Pxar format version entry, fallback to version 1 if not present
> +pub const PXAR_FORMAT_VERSION: u64 = 0x730f6c75df16a40d;
>  /// Beginning of an entry (current version).
>  pub const PXAR_ENTRY: u64 = 0xd5956474e588acef;
>  /// Previous version of the entry struct
> @@ -186,6 +189,7 @@ impl Header {
>  impl Display for Header {
>      fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
>          let readable = match self.htype {
> +            PXAR_FORMAT_VERSION => "FORMAT_VERSION",
>              PXAR_FILENAME => "FILENAME",
>              PXAR_SYMLINK => "SYMLINK",
>              PXAR_HARDLINK => "HARDLINK",
> @@ -551,6 +555,13 @@ impl From<&std::fs::Metadata> for Stat {
>      }
>  }
>  
> +#[derive(Clone, Debug, Default, PartialEq)]
> +pub enum FormatVersion {
> +    #[default]
> +    Version1,
> +    Version2,
> +}
> +
>  #[derive(Clone, Debug)]
>  pub struct Filename {
>      pub name: Vec<u8>,
> diff --git a/src/lib.rs b/src/lib.rs
> index ef81a85..a87b5ac 100644
> --- a/src/lib.rs
> +++ b/src/lib.rs
> @@ -342,6 +342,9 @@ impl Acl {
>  /// Identifies whether the entry is a file, symlink, directory, etc.
>  #[derive(Clone, Debug)]
>  pub enum EntryKind {
> +    /// Pxar file format version
> +    Version(format::FormatVersion),
> +
>      /// Symbolic links.
>      Symlink(format::Symlink),
>  
> -- 
> 2.39.2
> 
> 
> 
> _______________________________________________
> pbs-devel mailing list
> pbs-devel@lists.proxmox.com
> https://lists.proxmox.com/cgi-bin/mailman/listinfo/pbs-devel
> 
> 
>